Band 32, Heft 1

The efficiency of distribution networks is hugely affected by active and reactive power flows in distribution electric power systems. Currently, distributed generators (DGs) of energy are extensively applied to minimize power loss and improve voltage deviancies on power distribution systems. The best position and volume of DGs produce better power outcomes. This work prepares a new hybrid SSA–GWO metaheuristic optimization algorithm that combines the salp swarm algorithm (SSA) and the gray wolf optimizer (GWO) algorithm. The SSA–GWO algorithm ensures generating the best size and site of one and multi-DGs on the radial distribution network to decrease real power losses (RPL) (kW) on lines and resolve voltage deviancies. Our novel algorithm is executed on IEEE 123-bus radial distribution test systems. The results confirm the success of the suggested hybrid SSA–GWO algorithm compared with implementing the SSA and GWO individually. Through the proposed SSA–GWO algorithm, the study decreases the RPL and improves the voltage profile on distribution networks with multiple DGs units.

With the rapid growth of informatics systems’ technology in this modern age, the Internet of Things (IoT) has become more valuable and vital to everyday life in many ways. IoT applications are now more popular than they used to be due to the availability of many gadgets that work as IoT enablers, including smartwatches, smartphones, security cameras, and smart sensors. However, the insecure nature of IoT devices has led to several difficulties, one of which is distributed denial-of-service (DDoS) attacks. IoT systems have several security limitations due to their disreputability characteristics, like dynamic communication between IoT devices. The dynamic communications resulted from the limited resources of these devices, such as their data storage and processing units. Recently, many attempts have been made to develop intelligent models to protect IoT networks against DDoS attacks. The main ongoing research issue is developing a model capable of protecting the network from DDoS attacks that is sensitive to various classes of DDoS and can recognize legitimate traffic to avoid false alarms. Subsequently, this study proposes combining three deep learning algorithms, namely recurrent neural network (RNN), long short-term memory (LSTM)-RNN, and convolutional neural network (CNN), to build a bidirectional CNN-BiLSTM DDoS detection model. The RNN, CNN, LSTM, and CNN-BiLSTM are implemented and tested to determine the most effective model against DDoS attacks that can accurately detect and distinguish DDoS from legitimate traffic. The intrusion detection evaluation dataset (CICIDS2017) is used to provide more realistic detection. The CICIDS2017 dataset includes benign and up-to-date examples of typical attacks, closely matching real-world data of Packet Capture. The four models are tested and assessed using Confusion Metrix against four commonly used criteria: accuracy, precision, recall, and F -measure. The performance of the models is quite effective as they obtain an accuracy rate of around 99.00%, except for the CNN model, which achieves an accuracy of 98.82%. The CNN-BiLSTM achieves the best accuracy of 99.76% and precision of 98.90%.

Knowledge reduction of information systems is one of the most important parts of rough set theory in real-world applications. Based on the connections between the rough set theory and the theory of topology, a kind of topological reduction of incomplete information systems is discussed. In this study, the topological reduction of incomplete information systems is characterized by belief and plausibility functions from evidence theory. First, we present that a topological space induced by a pair of approximation operators in an incomplete information system is pseudo-discrete, which deduces a partition. Then, the topological reduction is characterized by the belief and plausibility function values of the sets in the partition. A topological reduction algorithm for computing the topological reducts in incomplete information systems is also proposed based on evidence theory, and its efficiency is examined by an example. Moreover, relationships among the concepts of topological reduct, classical reduct, belief reduct, and plausibility reduct of an incomplete information system are presented.

In the case of magnetic resonance imaging (MRI) imaging, image processing is crucial. In the medical industry, MRI images are commonly used to analyze and diagnose tumor growth in the body. A number of successful brain tumor identification and classification procedures have been developed by various experts. Existing approaches face a number of obstacles, including detection time, accuracy, and tumor size. Early detection of brain tumors improves options for treatment and patient survival rates. Manually segmenting brain tumors from a significant number of MRI data for brain tumor diagnosis is a tough and time-consuming task. Automatic image segmentation of brain tumors is required. The objective of this study is to evaluate the degree of accuracy and simplify the medical picture segmentation procedure used to identify the type of brain tumor from MRI results. Additionally, this work suggests a novel method for identifying brain malignancies utilizing the Bagging Ensemble with K-Nearest Neighbor (BKNN) in order to raise the KNN’s accuracy and quality rate. For image segmentation, a U-Net architecture is utilized first, followed by a bagging-based k-NN prediction algorithm for classification. The goal of employing U-Net is to improve the accuracy and uniformity of parameter distribution in the layers. Each decision tree is fitted on a little different training dataset during classification, and the bagged decision trees are effective since each tree has minor differences and generates slightly different skilled predictions. The overall classification accuracy was up to 97.7 percent, confirming the efficiency of the suggested strategy for distinguishing normal and pathological tissues from brain MR images; this is greater than the methods that are already in use.

Collaborative filtering recommender system (CFRS) plays a vital role in today’s e-commerce industry. CFRSs collect ratings from the users and predict recommendations for the targeted product. Conventionally, CFRS uses the user-product ratings to make recommendations. Often these user-product ratings are biased. The higher ratings are called push ratings (PRs) and the lower ratings are called nuke ratings (NRs). PRs and NRs are injected by factitious users with an intention either to aggravate or degrade the recommendations of a product. Hence, it is necessary to investigate PRs or NRs and discard them. In this work, opinion mining approach is applied on textual reviews that are given by users for a product to detect the PRs and NRs. The work also examines the effect of PRs and NRs on the performance of CFRS by evaluating various measures such as precision, recall, F -measure and accuracy.

In order to better improve the teaching quality of university teachers, an effective method should be adopted for evaluation and analysis. This work studied the machine learning algorithms and selected the support vector machine (SVM) algorithm to evaluate teaching quality. First, the principles of selecting evaluation indexes were briefly introduced, and 16 evaluation indexes were selected from different aspects. Then, the SVM algorithm was used for evaluation. A genetic algorithm (GA)-SVM algorithm was designed and experimentally analyzed. It was found that the training time and testing time of the GA-SVM algorithm were 23.21 and 7.25 ms, both of which were shorter than the SVM algorithm. In the evaluation of teaching quality, the evaluation value of the GA-SVM algorithm was closer to the actual value, indicating that the evaluation result was more accurate. The average accuracy of the GA-SVM algorithm was 11.64% higher than that of the SVM algorithm (98.36 vs 86.72%). The experimental results verify that the GA-SVM algorithm can have a good application in evaluating and analyzing teaching quality in universities with its advantages in efficiency and accuracy.

The continuous development of information communication technology facilitates the conventional grid in transforming into an automated modern system. Internet-of-Things solutions are used along with the evolving services of end-users to the electricity service provider for smart grid applications. In terms of various devices and machine integration, adequate authentication is the key to an accurate source and destination in advanced metering infrastructure (AMI). Various protocols are deployed to lead the identification between two parties, which require high computation time and communicational bit operations for system development. Therefore, Kerberos-based authentication protocols were designed in this study with the assistance of elliptic curve cryptography to manage the mutual authentication between two parties and reduce the time and bit operations. The protocols were evaluated in a widely adopted tool, AVISPA, which builds an understanding of the proposed protocol and ensures mutual authentication without unauthorized knowledge. In addition, upon comparing security and performance assessments to the current schemes, it was found that the protocol in this study required less time and bits to transmit information. Consequently, it effectively provides multiple security features making it suitable for resource constraint smart meters in AMI.

The accurate recognition of speech is beneficial to the fields of machine translation and intelligent human–computer interaction. After briefly introducing speech recognition algorithms, this study proposed to recognize speech with a recurrent neural network (RNN) and adopted the connectionist temporal classification (CTC) algorithm to align input speech sequences and output text sequences forcibly. Simulation experiments compared the RNN-CTC algorithm with the Gaussian mixture model–hidden Markov model and convolutional neural network-CTC algorithms. The results demonstrated that the more training samples the speech recognition algorithm had, the higher the recognition accuracy of the trained algorithm was, but the training time consumption increased gradually; the more samples a trained speech recognition algorithm had to test, the lower the recognition accuracy and the longer the testing time. The proposed RNN-CTC speech recognition algorithm always had the highest accuracy and the lowest training and testing time among the three algorithms when the number of training and testing samples was the same.

Identifying the writer of a handwritten document has remained an interesting pattern classification problem for document examiners, forensic experts, and paleographers. While mature identification systems have been developed for handwriting in contemporary documents, the problem remains challenging from the viewpoint of historical manuscripts. Design and development of expert systems that can identify the writer of a questioned manuscript or retrieve samples belonging to a given writer can greatly help the paleographers in their practices. In this context, the current study exploits the textural information in handwriting to characterize writer from historical documents. More specifically, we employ oBIF(oriented Basic Image Features) and hinge features and introduce a novel moment-based matching method to compare the feature vectors extracted from writing samples. Classification is based on minimization of a similarity criterion using the proposed moment distance. A comprehensive series of experiments using the International Conference on Document Analysis and Recognition 2017 historical writer identification dataset reported promising results and validated the ideas put forward in this study.

Deaf-mute people have much potential to contribute to society. However, communication between deaf-mutes and non-deaf-mutes is a problem that isolates deaf-mutes from society and prevents them from interacting with others. In this study, an information technology intervention, intelligent gloves (IG), a prototype of a two-way communication glove, was developed to facilitate communication between deaf-mutes and non-deaf-mutes. IG consists of a pair of gloves, flex sensors, an Arduino nano, a screen with a built-in microphone, a speaker, and an SD card module. To facilitate communication from the deaf-mutes to the non-deaf-mutes, the flex sensors sense the hand gestures and connected wires, and then transmit the hand movement signals to the Arduino nano where they are translated into words and sentences. The output is displayed on a small screen attached to the gloves, and it is also issued as voice from the speakers attached to the gloves. For communication from the non-deaf-mutes to the deaf-mute, the built-in microphone in the screen senses the voice, which is then transmitted to the Arduino nano to translate it to sentences and sign language, which are displayed on the screen using a 3D avatar. A unit testing of IG has shown that it performed as expected without errors. In addition, IG was tested on ten participants, and it has been shown to be both usable and accepted by the target users.

The essential part of existing reinforcement learning algorithms that use Gaussian process regression involves a complicated online Gaussian process regression algorithm. Our study proposes online and mini-batch Gaussian process regression algorithms that are easier to implement and faster to estimate for reinforcement learning. In our algorithm, the Gaussian process regression updates the value function through only the computation of two equations, which we then use to construct reinforcement learning algorithms. Our numerical experiments show that the proposed algorithm works as well as those from previous studies.

With the development of artificial intelligence, people begin to pay attention to the protection of sensitive information and data. Therefore, a homomorphic encryption framework based on effective integer vector is proposed and applied to deep learning to protect the privacy of users in binary convolutional neural network model. The conclusion shows that the model can achieve high accuracy. The training is 93.75% in MNIST dataset and 89.24% in original dataset. Because of the confidentiality of data, the training accuracy of the training set is only 86.77%. After increasing the training period, the accuracy began to converge to about 300 cycles, and finally reached about 86.39%. In addition, after taking the absolute value of the elements in the encryption matrix, the training accuracy of the model is 88.79%, and the test accuracy is 85.12%. The improved model is also compared with the traditional model. This model can reduce the storage consumption in the model calculation process, effectively improve the calculation speed, and have little impact on the accuracy. Specifically, the speed of the improved model is 58 times that of the traditional CNN model, and the storage consumption is 1/32 of that of the traditional CNN model. Therefore, homomorphic encryption can be applied to information encryption under the background of big data, and the privacy of the neural network can be realized.

Translation of long sentences in English is a complex problem in machine translation. This work briefly introduced the basic framework of intelligent machine translation algorithm and improved the long short-term memory (LSTM)-based intelligent machine translation algorithm by introducing the long sentence segmentation module and reordering module. Simulation experiments were conducted using the public corpus and the local corpus containing self-collected linguistic data. The improved algorithm was compared with machine translation algorithms based on a recurrent neural network and LSTM. The results suggested that the LSTM-based machine translation algorithm added with the long sentence segmentation module and reordering module effectively segmented long sentences and translated long English sentences more accurately, and the translation was more grammatically correct.

Named entity recognition (NER) is the localization and classification of entities with specific meanings in text data, usually used for applications such as relation extraction, question answering, etc. Chinese is a language with Chinese characters as the basic unit, but a Chinese named entity is normally a word containing several characters, so both the relationships between words and those between characters play an important role in Chinese NER. At present, a large number of studies have demonstrated that reasonable word information can effectively improve deep learning models for Chinese NER. Besides, graph convolution can help deep learning models perform better for sequence labeling. Therefore, in this article, we combine word information and graph convolution and propose our Lattice-Transformer-Graph (LTG) deep learning model for Chinese NER. The proposed model pays more attention to additional word information through position-attention, and therefore can learn relationships between characters by using lattice-transformer. Moreover, the adapted graph convolutional layer enables the model to learn both richer character relationships and word relationships and hence helps to recognize Chinese named entities better. Our experiments show that compared with 12 other state-of-the-art models, LTG achieves the best results on the public datasets of Microsoft Research Asia, Resume, and WeiboNER, with the F 1 score of 95.89%, 96.81%, and 72.32%, respectively.

At present, low-cost Red Green Blue Depth (RGB-D) sensors are mainly used in indoor robot environment perception, but the depth information obtained by RGB-D cameras has problems such as poor accuracy and high noise, and the generated 3D color point cloud map has low accuracy. In order to solve these problems, this article proposes a vision sensor-based point cloud map generation algorithm for robot indoor navigation. The aim is to obtain a more accurate point cloud map through visual SLAM and Kalman filtering visual-inertial navigation attitude fusion algorithm. The results show that in the positioning speed test data of the fusion algorithm in this study, the average time-consuming of camera tracking is 23.4 ms, which can meet the processing speed requirement of 42 frames per second. The yaw angle error of the fusion algorithm is the smallest, and the ATE test values of the algorithm are smaller than those of the Inertial measurement unit and Simultaneous-Localization-and-Mapping algorithms. This research algorithm can make the mapping process more stable and robust. It can use visual sensors to make more accurate route planning, and this algorithm improves the indoor positioning accuracy of the robot. In addition, the research algorithm can also obtain a dense point cloud map in real time, which provides a more comprehensive idea for the research of robot indoor navigation point cloud map generation.

An intrusion detection system plays an essential role in system security by discovering and preventing malicious activities. Over the past few years, several research projects on host-based intrusion detection systems (HIDSs) have been carried out utilizing the Australian Defense Force Academy Linux Dataset (ADFA-LD). These HIDS have also been subjected to various algorithm analyses to enhance their detection capability for high accuracy and low false alarms. However, less attention is paid to the actual implementation of real-time HIDS. Our principal objective in this study is to create a performant real-time HIDS. We propose a new model, “Better Similarity Algorithm for Host-based Intrusion Detection System” (BSA-HIDS), using the same dataset ADFA-LD. The proposed model uses three classifications to represent the attack folder according to certain criteria, the entire system call sequence is used. Furthermore, this work uses textual distance and compares five algorithms like Levenshtein, Jaro–Winkler, Jaccard, Hamming, and Dice coefficient, to classify the system call trace as attack or non-attack based on the notions of interclass decoupling and intra-class coupling. The model can detect zero-day attacks because of the threshold definition. The experimental results show a good detection performance in real-time for Levenshtein/Jaro–Winkler algorithms, 99–94% in detection rate, 2–5% in false alarm rate, and 3,300–720 s in running time, respectively.

A good AI algorithm can make accurate predictions and provide reasonable explanations for the field in which it is applied. However, the application of deep models makes the black box problem, i.e., the lack of interpretability of a model, more prominent. In particular, when there are multiple features in an application domain and complex interactions between these features, it is difficult for a deep model to intuitively explain its prediction results. Moreover, in practical applications, multiorder feature interactions are ubiquitous. To break the interpretation limitations of deep models, we argue that a multiorder linearly separable deep model can be divided into different orders to explain its prediction results. Inspired by the interpretability advantage of tree models, we design a feature representation mechanism that can consistently represent the features of both trees and deep models. Based on the consistent representation, we propose a multiorder feature-tracking strategy to provide a prediction-oriented multiorder explanation for a linearly separable deep model. In experiments, we have empirically verified the effectiveness of our approach in two binary classification application scenarios: education and marketing. Experimental results show that our model can intuitively represent complex relationships between features through diversified multiorder explanations.

With the rapid development of the information age, the traditional data center network management can no longer meet the rapid expansion of network data traffic needs. Therefore, the research uses the biological ant colony foraging behavior to find the optimal path of network traffic scheduling, and introduces pheromone and heuristic functions to improve the convergence and stability of the algorithm. In order to find the light load path more accurately, the strategy redefines the heuristic function according to the number of large streams on the link and the real-time load. At the same time, in order to reduce the delay, the strategy defines the optimal path determination rule according to the path delay and real-time load. The experiments show that under the link load balancing strategy based on ant colony algorithm, the link utilization ratio is 4.6% higher than that of ECMP, while the traffic delay is reduced, and the delay deviation fluctuates within ±2 ms. The proposed network data transmission scheduling strategy can better solve the problems in traffic scheduling, and effectively improve network throughput and traffic transmission quality.

Privacy is the main concern in cyberspace because, every single click of a user on Internet is recognized and analyzed for different purposes like credit card purchase records, healthcare records, business, personalized shopping store experience to the user, deciding marketing strategy, and the list goes on. Here, the user’s personal information is considered a risk process. Though data mining applications focus on statistically useful patterns and not on the personal data of individuals, there is a threat of unrestricted access to individual records. Also, it is necessary to maintain the secrecy of data while retaining the accuracy of data classification and quality as well. For real-time applications, the data analytics carried out should be time efficient. Here, the proposed Convolution-based Privacy Preserving Algorithm (C-PPA) transforms the input into lower dimensions while preserving privacy which leads to better mining accuracy. The proposed algorithm is evaluated over different privacy-preserving metrics like accuracy, precision, recall, and F 1-measure. Simulations carried out show that the average increment in the accuracy of C-PPA is 14.15 for Convolutional Neural Network (CNN) classifier when compared with results without C-PPA. Overlap-add C-PPA is proposed for parallel processing which is based on overlap-add convolution. It shows an average accuracy increment of 12.49 for CNN. The analytics show that the algorithm benefits regarding privacy preservation, data utility, and performance. Since the algorithm works on lowering the dimensions of data, the communication cost over the Internet is also reduced.

In multimedia correspondence, steganography schemes are commonly applied. To reduce storage capacity, multimedia files, including images, are always compressed. Most steganographic video schemes are, therefore, not compression tolerant. In the frame sequences, the video includes extra hidden space. Artificial intelligence (AI) creates a digital world of real-time information for athletes, sponsors, and broadcasters. AI is reshaping business, and although it has already produced a significant impact on other sectors, the sports industry is the newest and most receptive one. Human-centered AI for web applications has substantially influenced audience participation, strategic plan execution, and other aspects of the sports industry that have traditionally relied heavily on statistics. Thus, this study presents the motion vector steganography of sports training video integrating with the artificial bee colony algorithm (MVS-ABC). The motion vector stenography detects the hidden information from the motion vectors in the sports training video bitstreams. Artificial bee colony (ABC) algorithm optimizes the block assignment to inject a hidden message into a host video, in which the block assignment is considered a combinatorial optimization problem. The experimental analysis evaluates the data embedding performance using steganographic technology compared with existing embedding technologies, using the ABC algorithm compared with other genetic algorithms. The findings show that the proposed model can give the highest performance in terms of embedding capacity and the least error rate of video steganography compared with the existing models.

Remote sensing image technology to the ground has important guiding significance in disaster assessment and emergency rescue deployment. In order to realize the fast automatic registration of multi-sensor remote sensing images, the remote sensing image block registration idea is introduced, and the image reconstruction is processed by using the conjugate gradient descent (CGD) method. The scale-invariant feature transformation (SIFT) algorithm is improved and optimized by combining the function-fitting method. By this way, it can improve the registration accuracy and efficiency of multi-sensor remote sensing images. The results show that the average peak signal-to-noise ratio of the image processed by the CGD method is 25.428. The average root mean square value is 17.442. The average image processing time is 6.093 s. These indicators are better than the passive filter algorithm and the gradient descent method. The average accuracy of image registration of the improved SIFT registration method is 96.37%, and the average image registration time is 2.14 s. These indicators are significantly better than the traditional SIFT algorithm and speeded-up robust features algorithm. It is proved that the improved SIFT registration method can effectively improve the accuracy and operation efficiency of multi-sensor remote sensing image registration methods. The improved SIFT registration method effectively solves the problems of low accuracy and long time consumption of traditional multi-sensor remote sensing image fast registration methods. While maintaining high registration accuracy, it improves the image registration speed and provides technical support for a rapid disaster assessment after major disasters such as earthquakes and floods. And it has an important value for the development of the efficient post-disaster rescue deployment.

As an important identity authentication method, speaker verification (SV) has been widely used in many domains, e.g., mobile financials. At the same time, the existing SV systems are insecure under replay spoofing attacks. Toward a more secure and stable SV system, this article proposes a replay attack detection system based on deformable convolutional neural networks (DCNNs) and a time–frequency double-channel attention model. In DCNN, the positions of elements in the convolutional kernel are not fixed. Instead, they are modified by some trainable variable to help the model extract more useful local information from input spectrograms. Meanwhile, a time–frequency domino double-channel attention model is adopted to extract more effective distinctive features to collect valuable information for distinguishing genuine and replay speeches. Experimental results on ASVspoof 2019 dataset show that the proposed model can detect replay attacks accurately.

In recent years, there have been several calls by practitioners of machine learning to provide more guidelines on how to use its methods and techniques. For example, the current literature on resampling methods is confusing and sometimes contradictory; worse, there are sometimes no practical guidelines offered at all. To address this shortcoming, a simulation study was conducted that evaluated ridge regression models fitted on five real-world datasets. The study compared the performance of four resampling methods, namely, Monte Carlo resampling, bootstrap, k -fold cross-validation, and repeated k -fold cross-validation. The goal was to find the best-fitting λ (regularization) parameter that would minimize mean squared error, by using nine variations of these resampling methods. For each of the nine resampling variations, 1,000 runs were performed to see how often a good fit, average fit, and poor fit λ value would be chosen. The resampling method that chose good fit values the greatest number of times was deemed the best method. Based on the results of the investigation, three general recommendations are made: (1) repeated k -fold cross-validation is the best method to select as a general-purpose resampling method; (2) k = 10 folds is a good choice in k -fold cross-validation; (3) Monte Carlo and bootstrap are underperformers, so they are not recommended as general-purpose resampling methods. At the same time, no resampling method was found to be uniformly better than the others.

Due to the diversity and complexity of data information, traditional data fusion methods cannot effectively fuse multidimensional data, which affects the effective application of data. To achieve accurate and efficient fusion of multidimensional data, this experiment used back propagation (BP) neural network and fireworks algorithm (FWA) to establish the FWA–BP multidimensional data processing model, and a case study of PM 2.5 concentration prediction was carried out by using the model. In the PM 2.5 concentration prediction results, the trend between the FWA–BP prediction curve and the real curve was basically consistent, and the prediction deviation was less than 10. The average mean absolute error and root mean square error of FWA–BP network model in different samples were 3.7 and 4.3%, respectively. The correlation coefficient R value of FWA–BP network model was 0.963, which is higher than other network models. The results showed that FWA–BP network model could continuously optimize when predicting PM 2.5 concentration, so as to avoid falling into local optimum prematurely. At the same time, the prediction accuracy is better with the improvement in the correlation coefficient between real and predicted value, which means, in computer technology of multisensor data fusion, this method can be applied better.

This study based on the standard differential evolution (DE) algorithm was carried out to address the issues of control parameter imprinting, mutation process, and crossover process in the standard DE algorithm as well as the issue of multidimensional circuit testing optimization. A rotation control vector was introduced to expand the search range in the poor strategy to the circumference range of the individual and the parent target individual, and a rotation crossover operator and a binomial poor operator were combined. Finally, an improved adaptive DE algorithm based on a multi-angle search rotation crossover strategy was obtained. The research will improve the DE algorithm to optimize the testing of multidimensional circuits. It can be noted that the improved average precision value is 0.9919 when comparing the precision recall curves of the DE algorithm before and after the change, demonstrating a significant improvement in accuracy and stability. The fitness difference of the 30-dimensional problem is discovered to be between 0.25 × 10 3 and 0.5 × 10 3 by comparing the box graphs of the 30-dimensional problem with that of the 50-dimensional problem. On the 50-dimensional problem, when calculating the F4–F10 function, the fitness difference of the improved DE algorithm is 0.2 × 10 4 –0.4 × 10 4 . In summary, the improved DE algorithm proposed in this study compensates for the shortcomings of traditional algorithms in complex problem calculations and has also achieved significant optimization results in multidimensional circuit testing.

Image data play important role in various real-time online and offline applications. Biomedical field has adopted the imaging system to detect, diagnose, and prevent several types of diseases and abnormalities. The biomedical imaging data contain huge information which requires huge storage space. Moreover, currently telemedicine and IoT based remote health monitoring systems are widely developed where data is transmitted from one place to another. Transmission of this type of huge data consumes more bandwidth. Along with this, during this transmission, the attackers can attack the communication channel and obtain the important and secret information. Hence, biomedical image compression and encryption are considered the solution to deal with these issues. Several techniques have been presented but achieving desired performance for combined module is a challenging task. Hence, in this work, a novel combined approach for image compression and encryption is developed. First, image compression scheme using wavelet transform is presented and later a cryptography scheme is presented using confusion and diffusion schemes. The outcome of the proposed approach is compared with various existing techniques. The experimental analysis shows that the proposed approach achieves better performance in terms of autocorrelation, histogram, information entropy, PSNR, MSE, and SSIM.

Environmental landscaping is known to build, plan, and manage landscapes that consider the ecology of a site and produce gardens that benefit both people and the rest of the ecosystem. Landscaping and the environment are combined in landscape design planning to provide holistic answers to complex issues. Seeding native species and eradicating alien species are just a few ways humans influence the region’s ecosystem. Landscape architecture is the design of landscapes, urban areas, or gardens and their modification. It comprises the construction of urban and rural landscapes via coordinating the creation and management of open spaces and economics, finding a job, and working within a confined project budget. There was a lot of discussion about global warming and water shortages. There is a lot of hope to be found even in the face of seemingly insurmountable obstacles. AI is becoming more significant in many urban landscape planning and design elements with the advent of web 4.0 and Human-Centred computing. It created a virtual reality-based landscape to create deep neural networks (DNNs) to make deep learning (DL) more user-friendly and efficient. Users may only manipulate physical items in this environment to manually construct neural networks. These setups are automatically converted into a model, and the real-time testing set is reported and aware of the DNN models that users are producing. This research presents a novel strategy for combining DL-DNN with landscape architecture, providing a long-term solution to the problem of environmental pollution. Carbon dioxide levels are constantly checked when green plants are in and around the house. Plants, on either hand, remove toxins from the air, making it easier to maintain a healthy environment. Human-centered Artificial Intelligence-based web 4.0 may be used to assess and evaluate the data model. The study findings can be sent back into the design process for further modification and optimization.

In wireless communication technology, wireless sensor networks usually need to collect and process information in very harsh environment. Therefore, accurate positioning of sensors becomes the key to wireless communication technology. In this study, Davidon–Fletcher–Powell (DFP) algorithm was combined with particle swarm optimization (PSO) to reduce the influence of distance estimation error on positioning accuracy by using the characteristics of PSO iterative optimization. From the experimental results, among the average precision (AP) values of DFP, PSO, and PSO-DFP algorithms, the AP value of PSO-DFP was 0.9972. In the analysis of node positioning error, the maximum node positioning error of PSO-DFP was only about 21 mm. The results showed that the PSO-DFP algorithm had better performance, and the average positioning error of the algorithm was inversely proportional to the proportion of anchor nodes, node communication radius, and node density. In conclusion, the wireless sensor node location algorithm combined with PSO-DFP has a better location effect and higher stability than the traditional location algorithm.

Increasing the efficiency of an enterprise largely depends on the productivity of its employees, which must be properly assessed and the correct assessment of the contribution of each employee is important. In this regard, this article is devoted to a study conducted by the authors on the development of a digital employee rating system (DERES). The study was conducted on the basis of machine learning technologies and modern assessment methods that will allow companies to evaluate the performance of their departments, analyze the competencies of the employees and predict the rating of employees in the future. The authors developed a 360-degree employee rating model and a rating prediction model using regression machine learning algorithms. The article also analyzed the results obtained using the employee evaluation model, which showed that the performance of the tested employees is reduced due to remote work. Using DERES, a rating analysis of a real business company was carried out with recommendations for improving the efficiency of employees. An analysis of the forecasting results obtained using the rating prediction model developed by the authors showed that personal development and relationship are key parameters in predicting the future rating of employees. In addition, the authors provide a detailed description of the developed DERES information system, main components, and architecture.

Aiming at the problem that users’ check-in interest preferences in social networks have complex time dependences, which leads to inaccurate point-of-interest (POI) recommendations, a location-based POI recommendation model using deep learning for social network big data is proposed. First, the original data are fed into an embedding layer of the model for dense vector representation and to obtain the user’s check-in sequence (UCS) and space-time interval information. Then, the UCS and spatiotemporal interval information are sent into a bidirectional long-term memory model for detailed analysis, where the UCS and location sequence representation are updated using a self-attention mechanism. Finally, candidate POIs are compared with the user’s preferences, and a POI sequence with three consecutive recommended locations is generated. The experimental analysis shows that the model performs best when the Huber loss function is used and the number of training iterations is set to 200. In the Foursquare dataset, Recall@20 and NDCG@20 reach 0.418 and 0.143, and in the Gowalla dataset, the corresponding values are 0.387 and 0.148.

Deep learning (DL) has revolutionized advanced digital picture processing, enabling significant advancements in computer vision (CV). However, it is important to note that older CV techniques, developed prior to the emergence of DL, still hold value and relevance. Particularly in the realm of more complex, three-dimensional (3D) data such as video and 3D models, CV and multimedia retrieval remain at the forefront of technological advancements. We provide critical insights into the progress made in developing higher-dimensional qualities through the application of DL, and also discuss the advantages and strategies employed in DL. With the widespread use of 3D sensor data and 3D modeling, the analysis and representation of the world in three dimensions have become commonplace. This progress has been facilitated by the development of additional sensors, driven by advancements in areas such as 3D gaming and self-driving vehicles. These advancements have enabled researchers to create feature description models that surpass traditional two-dimensional approaches. This study reveals the current state of advanced digital picture processing, highlighting the role of DL in pushing the boundaries of CV and multimedia retrieval in handling complex, 3D data.

With the advent of the Internet of Things (IoT) era, the application of intelligent devices in the network is becoming more and more extensive, and the monitoring technology is gradually developing towards the direction of intelligence and digitization. As a hot topic in the field of computer vision, face recognition faces problems such as low level of intelligence and long processing time. Therefore, under the technical support of the IoTs, the research uses internet protocol cameras to collect face information, improves the principal component analysis (PCA), poses a PLV algorithm, and then applies it to the face recognition system for remote monitoring. The outcomes demonstrate that in the Olivetti Research Laboratory face database, the accuracy of PLV is relatively stable, and the highest and lowest are 98 and 94%, respectively. In Yale testing, the accuracy of this algorithm is 12% higher than that of PCA algorithm; In the database of Georgia Institute of Technology (GT), the PLV algorithm requires a time range of 0.2–0.3 seconds and has high operational efficiency. In the selected remote monitoring face database, the accuracy of the method is stable at more than 90%, with the highest being 98%, indicating that it can effectively improve the accuracy of face recognition and provide a reference technical means for further optimization of the remote monitoring system.

In this study, we proposed a fast line-structured light stripe center extraction algorithm based on an improved barycenter algorithm to address the problem that the conventional strip center extraction algorithm cannot meet the requirements of a structured light 3D measurement system in terms of speed and accuracy. First, the algorithm performs pretreatment of the structured light image and obtains the approximate position of the stripe center through skeleton extraction. Next, the normal direction of each pixel on the skeleton is solved using the gray gradient method. Then, the weighted gray center of the gravity method is used to solve the stripe center coordinates along the normal direction. Finally, a smooth strip centerline is fitted using the least squares method. The experimental results show that the improved algorithm achieved significant improvement in speed, sub-pixel level accuracy, and a good structured light stripe center extraction effect, as well as the repeated measurement accuracy of the improved algorithm is within 0.01 mm, and the algorithm has good repeatability.

Anomaly detection is a fundamental problem in data science and is one of the highly studied topics in machine learning. This problem has been addressed in different contexts and domains. This article investigates anomalous data within time series data in the maritime sector. Since there is no annotated dataset for this purpose, in this study, we apply an unsupervised approach. Our method benefits from the unsupervised learning feature of autoencoders. We utilize the reconstruction error as a signal for anomaly detection. For this purpose, we estimate the probability density function of the reconstruction error and find different levels of abnormality based on statistical attributes of the density of error. Our results demonstrate the effectiveness of this approach for localizing irregular patterns in the trajectory of vessel movements.

Maintaining the content quality on social media Q&A platforms is pivotal for user attraction and retention. Automating post quality assessment offers benefits such as reduced moderator workload, amplified community impact, enhanced expert user recognition, and importance to expert feedback. While existing approaches for post quality mainly employ binary classification, they often lack optimal feature selection. Our research introduces an automated system that categorizes features into textual, readability, format, and community dimensions. This system integrates 20 features belonging to the aforementioned categories, with a hybrid convolutional neural network–long short-term memory deep learning model for multi-class classification. Evaluation against baseline models and state-of-the-art methods demonstrates our system’s superiority, achieving a remarkable 21–23% accuracy enhancement. Furthermore, our system produced better results in terms of other metrics such as precision, recall, and F 1 score.

In modern society, the scientific symbiotic relationship of aesthetic community space is crucial for the development of cities. This article aimed to explore the symbiotic relationship between aesthetic community space and science, and analyze this relationship based on the k-means clustering algorithm. The article analyzed the spatial characteristics of different types of aesthetic communities, as well as the commonalities and differences between aesthetic communities and science, including the complementary relationship between the two. The k-means clustering algorithm is integrated to classify community spatial features, thereby analyzing and optimizing the relationship between the two. The experiment selected a sample of an aesthetic community and divided it into three different types of spatial features: architectural area, landscape greening area, and other activity areas. This article also compared the clustering results of the k-means algorithm with the k-means algorithm based on three-dimensional grid space. The results showed that the k-means algorithm optimized by the principle of three-dimensional grid space had stronger clustering performance. In the experiment, four different types of clustering algorithms and multiple evaluation indicators were also selected for testing. The data showed that in the clustering of spatial features in building areas, the k-means average clustering error score was controlled at around 13–14 under different missing ratios; the minimum average clustering error score of the characteristic data of the landscape greening area was 12.1. The average clustering error score in spatial feature clustering of other activity areas reached a minimum value of 23.5 when the missing ratio was 10%, which was lower than other algorithms. The overall experimental results indicate that the fused k-means clustering algorithm can effectively partition the aesthetic community space and optimize scientific symbiotic relationships.

In order to better solve the shortcomings of the k -means clustering method and density peaks clustering (DPC) method in agricultural image segmentation, this work proposes a method to divide points in a high-dimensional space, and a clustering method is obtained to divide crops and soil. In the process of assigning points in the DPC method, if a point is divided incorrectly, a series of points may be assigned to a cluster that is not related to it. In response to this problem, this study uses the decision graph to select the centroids, and uses Gaussian kernel to map the data to the high-dimensional space, each centroid searches for the most relevant points in the high-dimensional space until a temporary boundary point is found to stop the first assignment strategy, and then the points that are not clustered are assigned to the correct cluster to complete the clustering. The experimental results show that the proposed method has a better clustering effect through experiments on multiple artificial datasets and UCI datasets, compared with other clustering methods, and finally applied to plant image segmentation.

Biomedical event extraction is applied to biomedical texts to obtain a list of events within the biomedical domain. The best GENIA biomedical event extraction research uses sequence labeling techniques with a joint approach, softmax decoder for event trigger identification, and the BioBERT v1.1 encoder. However, this event extraction model has three drawbacks: tasks are carried out independently, it does not provide special handling of multi-label event trigger labels, and it uses an encoder with vocabulary from non-biomedical domains. We propose to use the pipeline approach to provide forward information sigmoid to address multi-label event trigger labels and alternative BERT encoders with vocabulary from the biomedical domain. The experiment showed that the performance of the biomedical event extraction model increased after changing the encoder, which had been built using a biomedical-specific domain vocabulary. Changing the encoder to SciBERT while still using the joint approach and softmax decoder increased the precision by 4.22 points (reaching 69.88) and resulted in an F 1-score of 58.48.

This study proposes an emotional analysis method of consumer comment text based on Bidirectional Encoder Representations from Transformers (BERT) and hierarchical attention. First, using the BERT pre-training model, the left and right contextual information is fused to enhance the semantic representation of words and generate dynamic word vectors containing contextual semantics. Second, the bidirectional long short-term memory network is used to obtain the sequence feature matrix, and the sentence representation and the text representation are obtained using the two-layer long short-term memory. Finally, the local attention mechanism and the global attention mechanism are introduced into the sentence representation layer and the text representation layer, respectively, and the text emotion of consumer comments is classified by softmax. Experiments show that the accuracy of the proposed method in Laptop data set is 93.01% and that in Restaurant data set is 92.45%. Therefore, the performance of the proposed method in the emotional analysis of consumer comment text is significantly better than that of the comparison method.

The development of contemporary college English teaching methods and practice should respect the subjective will of college students; fully tap their wisdom and potential; constantly innovate college English teaching methods, teaching practice activities, classroom teaching, and teaching evaluation models; create a good teaching atmosphere; and establish the concept of developmental evaluation. Through the innovation of teaching methods, college students’ actual language communication ability is cultivated, the teaching objectives and teaching methods of college English reading are innovated, and interactive, body language, role play, situational teaching, communicative teaching, and other teaching methods are used. The College English teaching quality evaluation is a classical multiple attribute decision making (MADM). In this article, the triangular Pythagorean fuzzy sets (TPFSs) are introduced, and the MADM problem is investigated under TPFSs. Based on the traditional dual generalized weighted Bonferroni mean operator and power average operator, the triangular Pythagorean fuzzy dual generalized power Bonferroni mean (TPFDGPBM) operator is proposed. Accordingly, the TPFDGPBM operator is employed to construct the triangular Pythagorean fuzzy MADM method. Finally, a numerical example for College English teaching quality evaluation is constructed to verify the TPFDGPBM technique.

In 2019, lung disease severely affected human health and was later renamed coronavirus disease 2019 (COVID-2019). Since then, several research methods have been proposed, such as reverse transcription polymerase chain reaction (RT-PCR), and disease identification through chest X-rays and computed tomography (CT) scans, to help the healthcare sector. RT-PCR was time-consuming when more patients were present, and a CT scan was costly. Several deep-learning (DL) methods were used to identify diseases using computer-aided tools. Among those convolutional neural networks (CNNs), the state of the art was adopted in the machinery to predict cancer. However, there is a lack of explainability (XAI) in how CNN predicts the disease. In this article, we construct XAI ensembles with Local Interpretation Model Agnostic Explanation(LIME), Grad CAM, and a Saliency map. It provides a visual explanation for a DL prognostic model that predicts COVID-19 respiratory infection in patients. Our quantitative experimental results have shown that ensemble XAI with an accuracy of 98.85%, although individual LIME has scored an accuracy of 99.62% on test data, is more reliable since it is the combination of models.

Vision is the main sensory organ for human beings to contact and understand the objective world. The results of various statistical data show that more than 60% of all ways for human beings to obtain external information are through the visual system. Vision is of great significance for human beings to obtain all kinds of information needed for survival, which is the most important sense of human beings. The rapid growth of computer technology, image processing, pattern recognition, and other disciplines have been widely applied. Traditional image processing algorithms have some limitations when dealing with complex images. To solve these problems, some scholars have proposed various new methods. Most of these methods are based on statistical models or artificial neural networks. Although they meet the requirements of modern computer vision systems for feature extraction algorithms with high accuracy, high speed, and low complexity, these algorithms still have many shortcomings. For example, many researchers have used different methods for feature extraction and segmentation to get better segmentation results. Scale-invariant feature transform (SIFT) is a description used in the field of image processing. This description has scale invariance and can detect key points in the image. It is a local feature descriptor. A sparse coding algorithm is an unsupervised learning method, which is used to find a set of “super complete” basis vectors to represent sample data more efficiently. Therefore, combining SIFT and sparse coding, this article proposed an image feature extraction algorithm based on visual information to extract image features. The results showed that the feature extraction time of X algorithm for different targets was within 0.5 s when the other conditions were the same. The feature matching time was within 1 s, and the correct matching rate was more than 90%. The feature extraction time of Y algorithm for different targets was within 2 s. The feature matching time was within 3 s, and the correct matching rate was between 80 and 90%, indicating that the recognition effect of X algorithm was better than that of Y algorithm. It indicates the positive relationship between visual information and image feature extraction algorithm.

The utility of DNA sequencing in diagnosing and prognosis of diseases is vital for assessing the risk of genetic disorders, particularly for asymptomatic individuals with a genetic predisposition. Such diagnostic approaches are integral in guiding health and lifestyle decisions and preparing families with the necessary foreknowledge to anticipate potential genetic abnormalities. The present study explores implementing a define-by-run deep learning (DL) model optimized using the Tree-structured Parzen estimator algorithm to enhance the precision of genetic diagnostic tools. Unlike conventional models, the define-by-run model bolsters accuracy through dynamic adaptation to data during the learning process and iterative optimization of critical hyperparameters, such as layer count, neuron count per layer, learning rate, and batch size. Utilizing a diverse dataset comprising DNA sequences from two distinct groups: patients diagnosed with breast cancer and a control group of healthy individuals. The model showcased remarkable performance, with accuracy, precision, recall, F 1-score, and area under the curve metrics reaching 0.871, 0.872, 0.871, 0.872, and 0.95, respectively, outperforming previous models. These findings underscore the significant potential of DL techniques in amplifying the accuracy of disease diagnosis and prognosis through DNA sequencing, indicating substantial advancements in personalized medicine and genetic counseling. Collectively, the findings of this investigation suggest that DL presents transformative potential in the landscape of genetic disorder diagnosis and management.

The recognition and classification of English accents have high practical value in areas such as security management and information retrieval. This study introduced two English accent features, filter bank (FBank) and Mel-frequency cepstral coefficient (MFCC), based on deep learning techniques. It then combined convolutional neural network (CNN), gated recurrent unit, and an attention mechanism to design a 1D CNN-BiGRU-Attention model for English accent recognition and classification. Experimental tests were conducted on the VoxForge dataset. The results showed that compared to MFCC, FBank performed better in English accent recognition and classification, and 70FBank achieved the highest F 1 value. Among the recurrent neural network, long short-term memory, and other models, the BiGRU model had the best performance. The average F 1 value of the 1D CNN-BiGRU-attention model was the highest, reaching 85.52%, and all the F 1 values were above 80% for different accents, indicating that the addition of the attention mechanism effectively improved the model’s recognition and classification effectiveness. The results prove the reliability of the method proposed in this article for English accent recognition and classification, making it suitable for practical application and promotion.

The Internet of medical things (IoMT) is a modern technology that is increasingly being used to provide good healthcare services. As IoMT devices are vulnerable to cyberattacks, healthcare centers and patients face privacy and security challenges. A safe IoMT environment has been used by combining blockchain (BC) technology with artificial intelligence (AI). However, the services of the systems are costly and suffer from security and privacy problems. This study aims to summarize previous research in the IoMT and discusses the roles of AI, BC, and cybersecurity in the IoMT, as well as the problems, opportunities, and directions of research in this field based on a comprehensive literature review. This review describes the integration schemes of AI, BC, and cybersecurity technologies, which can support the development of new systems based on a decentralized approach, especially in healthcare applications. This study also identifies the strengths and weaknesses of these technologies, as well as the datasets they use.

In recent years, smart contract technology has garnered significant attention due to its ability to address trust issues that traditional technologies have long struggled with. However, like any evolving technology, smart contracts are not immune to vulnerabilities, and some remain underexplored, often eluding detection by existing vulnerability assessment tools. In this article, we have performed a systematic literature review of all the scientific research and papers conducted between 2016 and 2021. The main objective of this work is to identify what vulnerabilities and smart contract technologies have not been well studied. In addition, we list all the datasets used by previous researchers that can help researchers in building more efficient machine-learning models in the future. In addition, comparisons are drawn among the smart contract analysis tools by considering various features. Finally, various future directions are also discussed in the field of smart contracts that can help researchers to set the direction for future research in this domain.

Content-based image retrieval (CBIR) is a technique used to retrieve image from an image database. However, the CBIR process suffers from less accuracy to retrieve many images from an extensive image database and prove the privacy of images. The aim of this article is to address the issues of accuracy utilizing deep learning techniques such as the CNN method. Also, it provides the necessary privacy for images using fully homomorphic encryption methods by Cheon–Kim–Kim–Song (CKKS). The system has been proposed, namely RCNN_CKKS, which includes two parts. The first part (offline processing) extracts automated high-level features based on a flatting layer in a convolutional neural network (CNN) and then stores these features in a new dataset. In the second part (online processing), the client sends the encrypted image to the server, which depends on the CNN model trained to extract features of the sent image. Next, the extracted features are compared with the stored features using a Hamming distance method to retrieve all similar images. Finally, the server encrypts all retrieved images and sends them to the client. Deep-learning results on plain images were 97.87% for classification and 98.94% for retriever images. At the same time, the NIST test was used to check the security of CKKS when applied to Canadian Institute for Advanced Research (CIFAR-10) dataset. Through these results, researchers conclude that deep learning is an effective method for image retrieval and that a CKKS method is appropriate for image privacy protection.

The feature selection (FS) process has an essential effect in solving many problems such as prediction, regression, and classification to get the optimal solution. For solving classification problems, selecting the most relevant features of a dataset leads to better classification accuracy with low training time. In this work, a hybrid binary crow search algorithm (BCSA) based quasi-oppositional (QO) method is proposed as an FS method based on wrapper mode to solve a classification problem. The QO method was employed in tuning the value of flight length in the BCSA which is controlling the ability of the crows to find the optimal solution. To evaluate the performance of the proposed method, four benchmark datasets have been used which are human intestinal absorption, HDAC8 inhibitory activity (IC50), P-glycoproteins, and antimicrobial. Accordingly, the experimental results are discussed and compared against other standard algorithms based on the accuracy rate, the average number of selected features, and running time. The results have proven the robustness of the proposed method relied on the high obtained value of accuracy (84.93–95.92%), G -mean (0.853–0.971%), and average selected features (4.36–11.8) with a relatively low computational time. Moreover, to investigate the effectiveness of the proposed method, Friedman test was used which declared that the performance supremacy of the proposed BCSA-QO with four datasets was very evident against BCSA and CSA by selecting the minimum relevant features and producing the highest accuracy classification rate. The obtained results verify the usefulness of the proposed method (BCSA-QO) in the FS with classification in terms of high classification accuracy, a small number of selected features, and low computational time.

Data mining’s primary clustering method has several uses, including gene analysis. A set of unlabeled data is divided into clusters using data features in a clustering study, which is an unsupervised learning problem. Data in a cluster are more comparable to one another than to those in other groups. However, the number of clusters has a direct impact on how well the K -means algorithm performs. In order to find the best solutions for these real-world optimization issues, it is necessary to use techniques that properly explore the search spaces. In this research, an enhancement of K -means clustering is proposed by applying an equilibrium optimization approach. The suggested approach adjusts the number of clusters while simultaneously choosing the best attributes to find the optimal answer. The findings establish the usefulness of the suggested method in comparison to existing algorithms in terms of intra-cluster distances and Rand index based on five datasets. Through the results shown and a comparison of the proposed method with the rest of the traditional methods, it was found that the proposal is better in terms of the internal dimension of the elements within the same cluster, as well as the Rand index. In conclusion, the suggested technique can be successfully employed for data clustering and can offer significant support.

Crime is a threat to any nation’s security administration and jurisdiction. Therefore, crime analysis becomes increasingly important because it assigns the time and place based on the collected spatial and temporal data. However, old techniques, such as paperwork, investigative judges, and statistical analysis, are not efficient enough to predict the accurate time and location where the crime had taken place. But when machine learning and data mining methods were deployed in crime analysis, crime analysis and predication accuracy increased dramatically. In this study, various types of criminal analysis and prediction using several machine learning and data mining techniques, based on the percentage of an accuracy measure of the previous work, are surveyed and introduced, with the aim of producing a concise review of using these algorithms in crime prediction. It is expected that this review study will be helpful for presenting such techniques to crime researchers in addition to supporting future research to develop these techniques for crime analysis by presenting some crime definition, prediction systems challenges and classifications with a comparative study. It was proved though literature, that supervised learning approaches were used in more studies for crime prediction than other approaches, and Logistic Regression is the most powerful method in predicting crime.

The problem addressed in this study is the limitations of previous works that considered electrocardiogram (ECG) classification as a multiclass problem, despite many abnormalities being diagnosed simultaneously in real life, making it a multilabel classification problem. The aim of the study is to test the effectiveness of deep learning (DL)-based methods (Inception, MobileNet, LeNet, AlexNet, VGG16, and ResNet50) using three large 12-lead ECG datasets to overcome this limitation. The define-by-run technique is used to build the most efficient DL model using the tree-structured Parzen estimator (TPE) algorithm. Results show that the proposed methods achieve high accuracy and precision in classifying ECG abnormalities for large datasets, with the best results being 97.89% accuracy and 90.83% precision for the Ningbo dataset, classifying 42 classes for the Inception model; 96.53% accuracy and 85.67% precision for the PTB-XL dataset, classifying 24 classes for the Alex net model; and 95.02% accuracy and 70.71% precision for the Georgia dataset, classifying 23 classes for the Alex net model. The best results achieved for the optimum model that was proposed by the define-by-run technique were 97.33% accuracy and 97.71% precision for the Ningbo dataset, classifying 42 classes; 96.60% accuracy and 83.66% precision for the PTB-XL dataset, classifying 24 classes; and 94.32% accuracy and 66.97% precision for the Georgia dataset, classifying 23 classes. The proposed DL-based methods using the TPE algorithm provide accurate results for multilabel classification of ECG abnormalities, improving the diagnostic accuracy of heart conditions.

The supply and storage of drugs are critical components of the medical industry and distribution. The shelf life of most medications is predetermined. When medicines are supplied in large quantities it is exceeding actual need, and long-term drug storage results. If demand is lower than necessary, this has an impact on consumer happiness and medicine marketing. Therefore, it is necessary to find a way to predict the actual quantity required for the organization’s needs to avoid material spoilage and storage problems. A mathematical prediction model is required to assist any management in achieving the required availability of medicines for customers and safe storage of medicines. Artificial intelligence applications and predictive modeling have used machine learning (ML) and deep learning algorithms to build prediction models. This model allows for the optimization of inventory levels, thus reducing costs and potentially increasing sales. Various measures, such as mean squared error, mean absolute squared error, root mean squared error, and others, are used to evaluate the prediction model. This study aims to review ML and deep learning approaches of forecasting to obtain the highest accuracy in the process of forecasting future demand for pharmaceuticals. Because of the lack of data, they could not use complex models for prediction. Even when there is a long history of accessible demand data, these problems still exist because the old data may not be very useful when it changes the market climate.

Wireless sensor networks (WSNs) require accurate localization of sensor nodes for various applications. In this article, we propose the distance vector hop localization method (DVHLM) to address the node dislocation issue in real-time networks. The proposed method combines trilateration and Particle Swarm Optimization techniques to estimate the location of unknown or dislocated nodes. Our methodology includes four steps: coordinate calculation, distance calculation, unknown node position estimation, and estimation correction. To evaluate the proposed method, we conducted simulation experiments and compared its performance with state-of-the-art methods in terms of localization accuracy with known nodes, dislocated nodes, and shadowing effects. Our results demonstrate that DVHLM outperforms the existing methods and achieves better localization accuracy with reduced error. This article provides a valuable contribution to the field of WSNs by proposing a new method with a detailed methodology and superior performance.

Training, sports equipment, and facilities are the main aspects of sports advancement. Countries are investing heavily in the training of athletes, especially in table tennis. Athletes require basic equipment for exercises, but most athletes cannot afford the high cost; hence, the necessity for developing a low-cost automated system has increased. To enhance the quality of the athletes’ training, the proposed research focuses on using the enormous developments in artificial intelligence by developing an automated training system that can maintain the training duration and intensity whenever necessary. In this research, an intelligent controller has been designed to simulate training patterns of table tennis. The intelligent controller will control the system that sends the table tennis balls’ intensity, speed, and duration. The system will detect the hand sign that has been previously assigned to different speeds using an image detection method and will work accordingly by accelerating the speed using pulse width modulation techniques. Simply showing the athletes’ hand sign to the system will trigger the artificial intelligent camera to identify it, sending the tennis ball at the assigned speed. The artificial intelligence of the proposed device showed promising results in detecting hand signs with minimum errors in training sessions and intensity. The image detection accuracy collected from the intelligent controller during training was 90.05%. Furthermore, the proposed system has a minimal material cost and can be easily installed and used.

Protecting big data from attacks on large organizations is essential because of how vital such data are to organizations and individuals. Moreover, such data can be put at risk when attackers gain unauthorized access to information and use it in illegal ways. One of the most common such attacks is the structured query language injection attack (SQLIA). This attack is a vulnerability attack that allows attackers to illegally access a database quickly and easily by manipulating structured query language (SQL) queries, especially when dealing with a big data environment. To address these risks, this study aims to build an approach that acts as a middle protection layer between the client and database server layers and reduces the time consumed to classify the SQL payload sent from the user layer. The proposed method involves training a model by using a machine learning (ML) technique for logistic regression with the Spark ML library that handles big data. An experiment was conducted using the SQLI dataset. Results show that the proposed approach achieved an accuracy of 99.04, a precision of 98.87, a recall of 99.89, and an F -score of 99.04. The time taken to identify and prevent SQLIA is 0.05 s. Our approach can protect the data by using the middle layer. Moreover, using the Spark ML library with ML algorithms gives better accuracy and shortens the time required to determine the type of request sent from the user layer.

Problem Recognizing written languages using symbols written in cuneiform is a tough endeavor due to the lack of information and the challenge of the process of tokenization. The Cuneiform Language Identification (CLI) dataset attempts to understand seven cuneiform languages and dialects, including Sumerian and six dialects of the Akkadian language: Old Babylonian, Middle Babylonian Peripheral, Standard Babylonian, Neo-Babylonian, Late Babylonian, and Neo-Assyrian. However, this dataset suffers from the problem of imbalanced categories. Aim Therefore, this article aims to build a system capable of distinguishing between several cuneiform languages and solving the problem of unbalanced categories in the CLI dataset. Methods Oversampling technique was used to balance the dataset, and the performance of machine learning algorithms such as Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF), and deep learning such as deep neural networks (DNNs) using the unigram feature extraction method was investigated. Results The proposed method using machine learning algorithms (SVM, KNN, DT, and RF) on a balanced dataset obtained an accuracy of 88.15, 88.14, 94.13, and 95.46%, respectively, while the DNN model got an accuracy of 93%. This proves improved performance compared to related works. Conclusion This proves the improvement of classifiers when working on a balanced dataset. The use of unigram features also showed an improvement in the performance of the classifier as it reduced the size of the data and accelerated the processing process.

Waste classification is the issue of sorting rubbish into valuable categories for efficient waste management. Problems arise from issues such as individual ignorance or inactivity and more overt issues like pollution in the environment, lack of resources, or a malfunctioning system. Education, established behaviors, an improved infrastructure, technology, and legislative incentives to promote effective trash sorting and management are all necessary for a solution to be implemented. For solid waste management and recycling efforts to be successful, waste materials must be sorted appropriately. This study evaluates the effectiveness of several deep learning (DL) models for the challenge of waste material classification. The focus will be on finding the best DL technique for solid waste classification. This study extensively compares several DL architectures (Resnet50, GoogleNet, InceptionV3, and Xception). Images of various types of trash are amassed and cleaned up to form a dataset. Accuracy, precision, recall, and F 1 score are only a few measures used to assess the performance of the many DL models trained and tested on this dataset. ResNet50 showed impressive performance in waste material classification, with 95% accuracy, 95.4% precision, 95% recall, and 94.8% in the F 1 score, with only two incorrect categories in the glass class. All classes are correctly classified with an F 1 score of 100% due to Inception V3’s remarkable accuracy, precision, recall, and F 1 score. Xception’s classification accuracy was excellent (100%), with a few difficulties in the glass and trash categories. With a good 90.78% precision, 100% recall, and 89.81% F 1 score, GoogleNet performed admirably. This study highlights the significance of using models based on DL for categorizing trash. The results open the way for enhanced trash sorting and recycling operations, contributing to an economically and ecologically friendly future.

Paternity testing using a deoxyribose nucleic acid (DNA) profile is an essential branch of forensic science, and DNA short tandem repeat (STR) is usually used for this purpose. Nowadays, in third-world countries, conventional kinship analysis techniques used in forensic investigations result in inadequate accuracy measurements, especially when dealing with large human STR datasets; they compare human profiles manually so that the number of samples is limited due to the required human efforts and time consumption. By utilizing automation made possible by AI, forensic investigations are conducted more efficiently, saving both time conception and cost. In this article, we propose a new algorithm for predicting paternity based on the 15-loci STR-DNA datasets using a deep neural network (DNN), where comparisons among many human profiles are held regardless of the limitation of the number of samples. For the purpose of paternity testing, familial data are artificially created based on the real data of individual Iraqi people from Al-Najaf province. Such action helps to overcome the shortage of Iraqi data due to restricted policies and the secrecy of familial datasets. About 53,530 datasets are used in the proposed DNN model for the purpose of training and testing. The Keras library based on Python is used to implement and test the proposed system, as well as the confusion matrix and receiver operating characteristic curve for system evaluation. The system shows excellent accuracy of 99.6% in paternity tests, which is the highest accuracy compared to the existing works. This system shows a good attempt at testing paternity based on a technique of artificial intelligence.

Addressing the complex problem of 6D pose estimation from single RGB images is essential for robotics, augmented reality, and autonomous driving applications. The aim of this study is to overcome limitations in handling scenes with high object occlusion and clutter. We introduce an attention-driven end-to-end model that builds upon existing methods employing pixel-wise unit vectors and voting for object keypoints. Integrating attention mechanisms allows the model to focus computational resources on salient features, enhancing accuracy. Experimental results using the LINEMOD benchmark dataset demonstrate an accuracy rate of 99.73%, outperforming state-of-the-art approaches. The model also exhibits strong generalization capabilities, achieving an average accuracy of 97.36% on objects not included in the dataset. This work concludes that the attention mechanism significantly elevates the performance and robustness of 6D pose estimation, particularly in challenging environments, and opens new avenues for real-world applications.

This study investigates the impact of innovation and digitalization on the quality of higher education at Tashkent State Technical University (TSTU) in Uzbekistan. Using a mixed-methods approach, data were collected through a well-structured questionnaire from 300 participants, including students, faculty members, and administrative staff. The results demonstrate a strong positive perception among respondents regarding the influence of digital technologies on educational quality, with 83% acknowledging their positive impact. In addition, 72% reported having access to beneficial digital resources, while 68% perceived TSTU as an innovative institution. The study concludes that digital technologies play a significant role in enhancing the quality of higher education at TSTU, promoting a dynamic learning environment and improved student engagement.

Problem The frequency of liver cancer is rising worldwide, and it is a common, deadly condition. For successful treatment and patient survival, early and precise diagnosis is essential. The automated classification of liver cancer using medical imaging data has shown potential outcome when employing machine and deep learning (DL) approaches. To train deep neural networks, it is still quite difficult to obtain a large and diverse dataset, especially in the medical field. Aim This article classifies liver tumors and identifies whether they are malignant, benign tumor, or normal liver. Methods This study mainly focuses on computed tomography scans from the Radiology Institute in Baghdad Medical City, Iraq, and provides a novel transfer learning (TL) approach for the categorization of liver cancer using medical images. Our findings show that the TL-based model performs better at classifying data, as in our method, high-level characteristics from liver images are extracted using pre-trained convolutional neural networks compared to conventional techniques and DL models that do not use TL. Results The proposed method using models of TL technology (VGG-16, ResNet-50, and MobileNetV2) successfully achieves high accuracy, sensitivity, and specificity in identifying liver cancer, making it an important tool for radiologists and other healthcare professionals. The experiment results show that the diagnostic accuracy in the VGG-16 model is up to 99%, ResNet-50 model 100%, and 99% total classification accuracy was attained with the MobileNetV2 model. Conclusion This proves the improvement of models when working on a small dataset. The use of new layers also showed an improvement in the performance of the classifiers, which accelerated the process.

Biometric recognition is essential for identifying people in security, surveillance, and mobile device authentication. Iris recognition (IR) biometrics is exact because it uses unique iris patterns to identify individuals. Iris segmentation, which isolates the iris from the rest of the ocular image, determines iris identification accuracy. The main problem is concerned with selecting the best deep learning (DL) algorithm to classify and estimate biometric iris biometric iris. This study proposed a comprehensive review of DL-based methods to improve biometric iris segmentation and recognition. It also evaluates reliability, specificity, memory, and F -score. It was reviewed with iris image analysis, edge detection, and classification literature. DL improves iris segmentation and identification in biometric authentication, especially when combined with additional biometric modalities like fingerprint fusion. Besides, that DL in iris detection requires large training datasets and is challenging to use with noisy or low-quality photos. In addition, it examines DL for iris segmentation and identification efforts to improve biometric application understanding. It also suggests ways to improve precision and reliability. DL may be used in biometric identification; however, further study is needed to overcome current limits and improve IR processes.

Real-time object detection is an integral part of internet of things (IoT) application, which is an important research field of computer vision. Existing lightweight algorithms cannot handle target occlusions well in target detection tasks in indoor narrow scenes, resulting in a large number of missed detections and misclassifications. To this end, an accurate real-time multi-scale detection method that integrates density-based spatial clustering of applications with noise (DBSCAN) clustering algorithm and the improved You Only Look Once (YOLO)-v4-tiny network is proposed. First, by improving the neck network of the YOLOv4-tiny model, the detailed information of the shallow network is utilized to boost the average precision of the model to identify dense small objects, and the Cross mini-Batch Normalization strategy is adopted to improve the accuracy of statistical information. Second, the DBSCAN clustering algorithm is fused with the modified network to achieve better clustering effects. Finally, Mosaic data enrichment technique is adopted during model training process to improve the capability of the model to recognize occluded targets. Experimental results show that compared to the original YOLOv4-tiny algorithm, the mAP values of the improved algorithm on the self-construct dataset are significantly improved, and the processing speed can well meet the requirements of real-time applications on embedded devices. The performance of the proposed model on public datasets PASCAL VOC07 and PASCAL VOC12 is also better than that of other advanced lightweight algorithms, and the detection ability for occluded objects is significantly improved, which meets the requirements of mobile terminals for real-time detection in crowded indoor environments.

Factors like rising work costs and the imminent transformation and upgrading of manufacturing industries are driving the rapid development of the industrial robotics market. In this study, by analyzing the structure of the transport arm and China Fusion Engineering Test Reactor and performing mathematical modeling, a feasible solution for the robot can be obtained using the dynamic ant colony optimization algorithm and grayscale values. However, for multiple degree of freedom robots, due to a large number of joints, the pure use of joint angle restrictions cannot avoid their own mutual interference. The design of the transport arm robot’s own collision algorithm is shown, which focuses on each linkage as a rod wrapped by a cylinder. The experiment shows that the relationship between the integrated center of mass and the whole machine center of mass can get the action area of the whole machine center of mass of the robot, according to which the relationship between the radius of the catch circle and time of the projection area of the whole machine center of mass of the robot in the horizontal plane can be obtained. The maximum outer circle radius r com = 267.977 mm {r}_{\text{com}}=267.977\hspace{.25em}\text{mm} , according to the stability criterion r ssa > r con {r}_{\text{ssa}}\gt {r}_{\text{con}} , can be obtained, so the stability analysis of the gait switching process can be judged to be correct and effective.

In order to realize online detection and control of network viruses in robots, the authors propose a data mining-based anti-virus solution for smart robots. First, using internet of things (IoT) intrusion prevention system design method based on network intrusion signal detection and feedforward modulation filtering design, the overall design description and function analysis are carried out, and then the intrusion signal detection algorithm is designed, and finally, the hardware design and software development for a breach protection solution for the IoT are completed, and the integrated design of the system is realized. The findings demonstrated that based on the mean value of 10,000 tests, the IoT’s average packet loss rate is 0. Conclusion: This system has high accuracy, good performance, and strong compatibility and friendliness.

With the wide popularization of Internet of Things (IoT) technology, the design and implementation of intelligent speech equipment have attracted more and more researchers’ attention. Speech recognition is one of the core technologies to control intelligent mechanical equipment. An industrial IoT sensor-based broadcast speech recognition and control system is presented to address the issue of integrating a broadcast speech recognition and control system with an IoT sensor for smart cities. In this work, a design approach for creating an intelligent voice control system for the Robot operating system (ROS) is provided. The speech recognition control program for the ROS is created using the Baidu intelligent voice software development kit, and the experiment is run on a particular robot platform. ROS makes use of communication modules to implement network connections between various system modules, mostly via topic-based asynchronous data transmission. A point-to-point network structure serves as the communication channel for the many operations that make up the ROS. The hardware component is mostly made up of the main controller’s motor driving module, a power module, a WiFi module, a Bluetooth module, a laser ranging module, etc. According to the experimental findings, the control system can identify the gathered sound signals, translate them into control instructions, and then direct the robot platform to carry out the necessary actions in accordance with the control instructions. Over 95% of speech is recognized. The control system has a high recognition rate and is simple to use, which is what most industrial controls require. It has significant implications for the advancement of control technology and may significantly increase production and life efficiency.

Industrialization has advanced quickly, bringing intelligent production and manufacturing into people’s daily lives, but it has also created a number of issues with the ability of intelligent control systems for industrial robots. As a result, a study has been conducted on the use of multi-source data fusion methods in the mechanical industry. First, the research analyzes and discusses the existing research at home and abroad. Then, a robot intelligent control system based on multi-source fusion method is proposed, which combines multi-source data fusion with principal component analysis to better fuse data of multiple control periods; In the process, the experimental results are dynamically evaluated, and the performance of the proposed method is compared with other fusion methods. The results of the study showed that the confidence values and recognition correctness of the intelligent control system under the proposed method were superior compared to the Yu, Murphy, and Deng methods. Applying the method to the comparison of real-time and historical data values, it is found that the predicted data under the proposed method fits better with the actual data values, and the fit can be as high as 0.9945. The dynamic evaluation analysis of single and multi-factor in the simulation stage demonstrates that the control ability in the training samples of 0–100 is often better than the actual results, and the best evaluation results may be obtained at the sample size of 50 per batch. The aforementioned findings demonstrated that the multi-data fusion method that was suggested had a high degree of viability and accuracy for the intelligent control system of industrial robots and could offer a fresh line of enquiry for the advancement and development of the mechanical industrialization field.

The current technology of foundation pit deformation measurement is inefficient, and its accuracy is not ideal. Therefore, an intelligent prediction model of foundation pit deformation based on back propagation neural network (BPNN) is proposed to predict the foundation pit deformation intelligently, with high accuracy and efficiency, so as to improve the safety of the project. Firstly, to address the shortcomings of BPNNs, which rely on the initial parameter settings and tend to fall into local optimum and unstable performance, this study adopts the modified particle swarm optimization (MPSO) to optimise the parameters of BPNNs and constructs a pit deformation prediction model based on the MPSO–BP algorithm to achieve predictive measurements of pit deformation. After training and testing the data samples, the results show that the prediction accuracy of the MPSO–BP pit deformation prediction model is 99.76%, which is 2.25% higher than that of the particle swarm optimization–back propagation (PSO–BP) pit deformation prediction model and 3.01% higher than that of the BP pit deformation prediction model. The aforementioned results show that the MPSO–BP pit deformation prediction model proposed in this study can effectively predict the pit deformation variables of construction projects and provide data support for the protective measures of the staff, which is helpful for the cause of construction projects in China.

In the era of big data, data information has exploded, and all walks of life are impacted by big data. The arrival of big data provides the possibility for the realization of intelligent financial analysis of enterprises. At present, most enterprises’ financial analysis and decision-making based on the analysis results are mainly based on human resources, with poor automation and obvious problems in efficiency and error. In order to help the senior management of enterprises to conduct scientific and effective management, the study uses big data web crawler technology and ETL technology to process data and build an intelligent financial decision support system integrating big data together with Internet plus platform. J Group in S Province is taken as an example to study the effect before and after the application of intelligent financial decision support system. The results show that the crawler technology can monitor the basic data and the big data in the industry in real time, and improve the accuracy of decision-making. Through the intelligent financial decision support system which integrates big data, the core indexes such as profit, net asset return, and accounts receivable of the enterprises can be clearly displayed. The system can query the causes of financial changes hidden behind the financial data. Through the intelligent financial decision support system, it is found that the asset liability ratio, current assets growth rate, operating income growth rate, and financial expenses of J Group are 55.27, 10.38, 20.28%, and 1,974 million RMB, respectively. The growth rate of real sales income of J Group is 0.63%, which is 31.27% less than the excellent value of the industry 31.90%. After adopting the intelligent financial decision support system, the monthly financial statements of the enterprises increase significantly, and the monthly report analysis time decreases. The maximum number of financial statements received by the Group per month is 332, and the processing time at this time is only 2 h. According to the results, it can be seen that the intelligent financial decision support system integrating big data as the research result can effectively improve the financial management level of enterprises, improve the usefulness of financial decision-making, and make practical contributions to the field of corporate financial decision-making.

The nonlinear system is difficult to achieve the desired effect by using traditional proportional integral derivative (PID) or linear controller. First, this study presents an improved lazy learning algorithm based on k-vector nearest neighbors, which not only considers the matching of input and output data, but also considers the consistency of the model. Based on the optimization index of an additional penalty function, the optimal solution of the lazy learning is obtained by the iterative least-square method. Second, based on the improved lazy learning, an adaptive PID control algorithm is proposed. Finally, the control effect under the condition of complete data and incomplete data is compared by simulation experiment.

In order to improve the shortcomings of the traditional monitoring equipment that is difficult to measure the daily physical parameters of the elderly and improve the accuracy of parameter measurement, this article designs wearable devices through the Internet of Things technology and virtual reality technology. With this device, four daily physical parameters of the elderly, such as exercise heart rate, blood pressure, plantar health, and sleep function, are measured. The feasibility of the measurement method and equipment is verified by experiments. The experimental results showed that the accuracy of the measurement method based on the reflective photoplethysmography signal was high, with the mean and difference values of the subjects’ heart rate basically lying around 0 BPM and in good agreement between the estimated heart rate and the reference value. In the blood pressure measurements, the correlation coefficient between the P r s {P}_{rs} estimate and the reference value was 0.81. The estimation accuracy of the device used in the article was high, with the highest correlation coefficient of 0.96 ± 0.02 for subjects’ heart rate at rest, and its estimation error rate was 0.02 ± 0.01. The P n t h {P}_{{n}th} value for subject B8 exceeded the threshold of 0.5 before subject B21, and subject B8 had more severe symptoms, which was consistent with the actual situation. The wearable device was able to identify the subject’s eye features and provide appropriate videos to help subjects with poor sleep quality to fall asleep. The article provides a method and device that facilitates healthcare professionals to make real-time enquiries and receive user health advice.

Anti-jamming cyclic frequency feature extraction is an important link in identifying communication interference signals, which is of great significance for eliminating electronic communication interference factors and improving the security of electronic communication environment. However, when the traditional feature extraction technology faces a large number of data samples, the processing capacity is low, and it cannot solve the multi-classification problems. For this type of problem, a method of electronic communication signal anti-jamming cyclic frequency feature extraction based on particle swarm optimization-support vector machines (PSO-SVM) algorithm is proposed. First, the SVM signal feature extraction model is proposed, and then the particle swarm optimization (PSO) algorithm is used. Optimize the kernel function parameter settings of SVM to raise the classifying quality of the SVM model. Finally, the function of the PSO-SVM signal feature extraction model is tested. The results verify that the PSO-SVM model begins to converge after 60 iterations, and the loss value remains at about 0.2, which is 0.2 lower than that of the SVM technique. The exactitude of signal feature extraction is 90.4%, and the recognition effect of binary phase shift keying signal is the best. The complete rate of signal feature extraction is 85%. This shows that the PSO-SVM model enhances the sensitivity of the anti-jamming cyclic frequency feature, improves the accuracy of the anti-jamming cyclic frequency feature recognition, reduces the running process, reduces the time cost, and greatly increases the performance of the SVM method. The good model performance also improves the application value of the method in the field of electronic communication.

With the need of social and economic development, the audit method is also continuously reformed and improved. Traditional audit methods have defects of comprehensively considering various risk factors, and cannot meet the needs of enterprise financial work. To improve the effectiveness of audit work and meet the financial needs of enterprises, a solution for intelligent auditing of enterprise finance is proposed, including intelligent analysis of accounting vouchers and of audit reports. Then, Bi-directional Long Short-Term Memory (BiLSTM) neural network is used to classify the audit problems under three text feature extraction methods. The test results show that the accuracy, recall rate, and F 1 value of the COWORDS-IOM algorithm in the aggregate clustering of accounting vouchers are 85.12, 83.28, and 84.85%, respectively, which are better than the self-organizing map algorithm before the improvement. The accuracy rate, recall rate, and F 1 value of Word2vec TF-IDF LDA-BiLSTM model for intelligent analysis of audit reports are 87.43, 87.88, and 87.66%, respectively. This shows that the proposed method has good performance in accounting voucher clustering and intelligent analysis of audit reports, which can provide guidance for the development of enterprise financial intelligence software to a certain extent.

The existing predictive control strategy has comprehensive prior knowledge of the controlled process, requires weak continuity of the search space for parameter optimization, and its application is limited to some extent. Therefore, improved research on the fuzzy fractional proportional integral differential (PID) predictive control algorithm is proposed. First, the control principle of PID predictive control equipment is proposed. According to this principle, the structure of the PID predictive control equipment adaptive fuzzy PID energy-saving controller is constructed. Through the PID energy-saving control parameter setting principle and fuzzy control rules, the adaptive fuzzy PID energy-saving control of PID predictive control equipment is realized. Finally, the fractional order PID predictive transfer function model is constructed to improve the predictive control algorithm based on PID optimization technology. The experimental results show that the accuracy and efficiency of the designed algorithm can get the best performance index, and its stability, overshoot, time, and control accuracy are basically unchanged. In the small area temperature control, the disturbance interference is small, the anti-disturbance ability is good, and it has strong robustness.

Image segmentation is one of the important tasks of computer vision and computer image processing, and the purpose of image segmentation is to achieve the extraction and recognition of the target image region. The classical Mumford–Shah (MSh) image segmentation model is used to achieve the segmentation of images. With the goal to get the best segmentation effect on images by minimizing the MSh energy generalization function, a level set strategy is developed, and a model with global information infinite curve evolution is utilized. However, considering the low efficiency of this model for processing level set curves and the general quality of image segmentation. A multi-layer threshold search scheme is proposed to achieve rapid convergence of the target image level set curve. The experimental results showed that the multi-level thresholding image segmentation algorithm based on the MSh model can significantly improve the segmentation effect of images and reduce the segmentation time. The suggested MSK method outperforms the MPO algorithm, SSA algorithm, and EMO algorithm in the picture segmentation convergence time test, respectively, in terms of runtime efficiency by 356, 289, and 71%. Additionally, it performs superbly in both threshold searches and picture quality tests. The research topic has significant reference value for the study of contemporary computer vision imaging technologies.

With the rapid expansion in plant disease detection, there has been a progressive increase in the demand for more accurate systems. In this work, we propose a new method combining color information, edge information, and textural information to identify diseases in 14 different plants. A novel 3-branch architecture is proposed containing the color information branch, an edge information branch, and a textural information branch extracting the textural information with the help of the central difference convolution network (CDCN). ResNet-18 was chosen as the base architecture of the deep neural network (DNN). Unlike the traditional DNNs, the weights adjust automatically during the training phase and provide the best of all the ratios. The experiments were performed to determine individual and combinational features’ contribution to the classification process. Experimental results of the PlantVillage database with 38 classes show that the proposed method has higher accuracy, i.e., 99.23%, than the existing feature fusion methods for plant disease identification.

In this work, a technique is proposed to identify the diseases that occur in plants. The system is based on a combination of residual network and attention learning. The work focuses on disease identification from the images of four different plant types by analyzing leaf images of the plants. A total of four datasets are used for the work. The system incorporates attention-aware features computed by the Residual Attention Network (Res-ATTEN). The base of the network is ResNet-18 architecture. Integrating attention learning in the residual network helps improve the system's overall accuracy. Various residual attention units are combined to create a single architecture. Unlike the traditional attention network architectures, which focus only on a single type of attention, the system uses a mixed type of attention learning, i.e., a combination of spatial and channel attention. Our technique achieves state-of-the-art performance with the highest accuracy of 99%. The results show that the proposed system has performed well for both purposes and notably outperformed the traditional systems.

The finest resource for consumers to evaluate products is online product reviews, and finding such reviews that are accurate and helpful can be difficult. These reviews may sometimes be corrupted, biased, contradictory, or lacking in detail. This opens the door for customer-focused review analysis methods. A method called “Multi-Domain Keyword Extraction using Word Vectors” aims to streamline the customer experience by giving them reviews from several websites together with in-depth assessments of the evaluations. Using the specific model number of the product, inputs are continuously grabbed from different e-commerce websites. Aspects and key phrases in the reviews are properly identified using machine learning, and the average sentiment for each keyword is calculated using context-based sentiment analysis. To precisely discover the keywords in massive texts, word embedding data will be analyzed by machine learning techniques. A unique methodology developed to locate trustworthy reviews considers several criteria that determine what makes a review credible. The experiments on real-time data sets showed better results compared to the existing traditional models.

In this research, a novel real time approach has been proposed for detection and analysis of Covid19 using chest X-ray images based on a non-iterative deterministic classifier, kernel extreme learning machine (KELM), and a pretrained network ResNet50. The information extraction capability of deep learning and non-iterative deterministic training nature of KELM has been incorporated in the proposed novel fusion model. The binary classification is carried out with a non-iterative deterministic learning based classifier, KELM. Our proposed approach is able to minimize the average testing error up to 2.76 on first dataset, and up to 0.79 on the second one, demonstrating its effectiveness after experimental confirmation. A comparative analysis of the approach with other existing state-of-the-art methods is also presented in this research and the classification performance confirm the advantages and superiority of our novel approach called RES-KELM algorithm.

The objective of this study is to supply an overview of research work based on video-based networks and tiny object identification. The identification of tiny items and video objects, as well as research on current technologies, are discussed first. The detection, loss function, and optimization techniques are classified and described in the form of a comparison table. These comparison tables are designed to help you identify differences in research utility, accuracy, and calculations. Finally, it highlights some future trends in video and small object detection (people, cars, animals, etc.), loss functions, and optimization techniques for solving new problems.