Band 14, Heft 1

Aerial photo target detection in remote sensing utilizes high-resolution aerial images, along with computer vision techniques, to identify and pinpoint specific objects. To tackle imprecise detection caused by the random arrangement of objects, a two-stage model named anchor-free orientation detection, based on an anchor-free rotating frame, has been introduced. This model aims to deliver encouraging outcomes in the analysis of high-resolution aerial photos. Initially, the model adopts faster Region with CNN feature (faster R-CNN) as a foundational framework. Eliminating the anchor configuration and introducing supplementary angle parameters accommodates the identification of rotating frame objects. Subsequently, it integrates the spatial attention module to seize global semantic information and establish an approximate detection frame with certainty. Additionally, the channel attention module extracts critical features from the semantic data within the predicted frame. Ultimately, the faster R-CNN detection head is employed to refine, leading to enhanced model outcomes and further bolstered regression and classification precision. After validation, the accuracy of the model detection reaches 88.15 and 77.18% on the publicly accessible aerial remote sensing datasets HRSC2016 and DOTA, respectively, which is better than other advanced rotating frame object detection methods.

In the rumor detection based on crowd intelligence, the crowd behavior is constructed as a graph model or probability mode. The detection of rumors is achieved through the collaborative utilization of data and knowledge. Aiming at the problems of insufficient feature extraction ability and data redundancy of current rumor detection methods based on deep learning model, a social network rumor detection method based on bidirectional gated recurrent unit (Bi-GRU) and double self-attention (DSA) mechanism is suggested. First, a combination of application program interface and third-party crawler approach is used to obtain microblogging data from publicly available fake microblogging information pages, including both rumor and non-rumor information. Second, Bi-GRU is used to capture the tendency of medium- and long-term dependence of data and is flexible enough to deal with variable length input. Finally, the DSA mechanism is introduced to help reduce the redundant information in the dataset, thereby enhancing the model’s efficacy. The results of the experiments indicate that the proposed method outperforms existing advanced methods by at least 0.114, 0.108, 0.064, and 0.085 in terms of accuracy, precision, recall, and F 1-scores, respectively. Therefore, the proposed method can significantly enhance the ability of social network rumor detection.

Mobile edge computing (MEC) paradigm has emerged to improve the quality of service & experience of applications deployed in close proximity to end-users. Due to their restricted computational and communication resources, MEC nodes can provide access to a portion of the entire set of services and data gathered. Therefore, there are several obstacles to their management. Keeping track of all the services offered by the MEC nodes is challenging, particularly if their demand rates change over time. Received tasks (such as, analytics queries, classification tasks, and model learning) require services to be invoked in real MEC use-case scenarios, e.g., smart cities. It is not unusual for a node to lack the necessary services or part of them. Undeniably, not all the requested services may be locally available; thus, MEC nodes must deal with the timely and appropriate choice of whether to carry out a service replication ( pull action ) or tasks offloading ( push action ) to peer nodes in a MEC environment. In this study, we contribute with a novel time-optimized mechanism based on the optimal stopping theory, which is built on the cost-based decreasing service demand rates evidenced in various service management situations. Our mechanism tries to optimally solve the decision-making dilemma between pull and push action. The experimental findings of our mechanism and its comparative assessment with other methods found in the literature showcase the achieved optimal decisions with respect to certain cost-based objective functions over dynamic service demand rates.

Communication network security situation analysis prevents unauthorized users from accessing and stealing sensitive information. Network security analysis aims to monitor, discover, and eradicate security flaws by carefully examining the network’s architecture, data, and traffic to ensure safety. In time series data mining analysis by cyber terrorism, specialists must pay attention to cyber security, which involves identifying the elements contributing to long-term trends or systemic patterns via pattern-matching algorithms and other types of inferential processing on large datasets. The challenging characteristics of communication network security situation analysis are data loss, security breaches, hacking, and viruses. Hence, in this research, attention mechanism-based convolutional neural network-enabled practical byzantine fault tolerant (AMBCNN-PBFT) has been designed to improve communication network security situation analysis in time series data mining. AMBCNN-PBFT helps to increase communication network security usage and support the expansion during the evaluation system by optimizing the time series data mining. AMBCNN-PBFT effectively predicts the rise in the communication network, associated with faster times series benefits data mining approach. The study concludes that the AMBCNN-PBFT efficiently indicates and validates the communication network security in time series data mining during the evaluation system. The experimental analysis of AMBCNN-PBFT outperforms the data mining time series in terms of accuracy, efficiency, performance, and prediction.

To improve the effectiveness of the construction of teacher morality in colleges and universities, this article employs the performance evaluation model of education informatization to construct an evaluation system for the construction of teacher morality in colleges and universities. The evaluation of the construction effect of teacher morality is carried out through intelligent data analysis, and the significant error is used as the parameter of the teacher’s morality to make estimations. Moreover, a binary variable is introduced to judge whether the data have a significant error. Mixed integer linear and nonlinear programming methods are employed to detect significant errors. In addition, the idea of synchronizing teachers’ moral data is added. The effectiveness of the proposed method is verified by a simulation study using MATLAB 2017. The results show that it is necessary to establish and improve the talent flow mechanism that conforms to the requirements to promote the rational flow of teachers.

In recent years, sports events have continuously attracted people’s attention, and people’s enthusiasm and participation in sports have been rising. The sports + tourism model can meet people’s travel needs and enjoy sports-related entertainment and experiences. With the expansion of sports tourism, people have a new understanding of sports + tourism. Sports tourism based on the current strategic background of national fitness is an emerging industry, and it has had a certain degree of development prospects before this. This article explores traditional sports tourism with national characteristics under the blessing of the wireless sensor network. This exploration discusses and explores the development and construction of local sports + tourism in terms of literature and logical analysis. The experimental results of this article show that most consumers are not satisfied with the construction of sports tourism network information, and they are the least satisfied with key information coverage, e-commerce, and security systems. It shows that in these aspects, the construction of sports tourism informatization is relatively lagging, and it is in urgent need of improvement and improvement.

In distributed computing environments, the collaboration of nodes for predictive analytics at the network edge plays a crucial role in supporting real-time services. When a node’s service becomes unavailable for various reasons (e.g., service updates, node maintenance, or even node failure), the rest of the available nodes connot efficiently replace its service due to different data and predictive models (e.g., machine learning [ML] models). To address this, we propose decision-making strategies rooted in the statistical signatures of nodes’ data. Specifically, these signatures refer to the unique patterns and behaviors within each node’s data that can be leveraged to predict the suitability of potential surrogate nodes. Recognizing and acting on these statistical nuances ensures a more targeted and efficient response to node failures. Such strategies aim to identify surrogate nodes capable of substituting for failing nodes’ services by building enhanced predictive models. Our resilient framework helps to guide the task requests from failing nodes to the most appropriate surrogate nodes. In this case, the surrogate nodes can use their enhanced models, which can produce equivalent and satisfactory results for the requested tasks. We provide experimental evaluations and comparative assessments with baseline approaches over real datasets. Our results showcase the capability of our framework to maintain the overall performance of predictive analytics under nodes’ failures in edge computing environments.

To improve the classification effect of music genres in the digital music era, the article employs deep-learning algorithms to improve the performance of the classification of music genres. An auxiliary (estimated) model is constructed to estimate the amount of unmeasured data in the dual-rate system to enhance the recognition effect of music features. Moreover, a dual-rate output error model to identify such impacts is proposed to eliminate the impact of corrupt data caused by the estimation, which eventually leads to the further improvement of the proposed model called dual-rate multi-innovation forgetting gradient algorithm based on the auxiliary model. In addition, the article employs linear time-varying forgetting factors to improve the stability of the system, advances the recognition effect of music features through enhancement processing, and combines a deep-learning algorithm to construct a classification system of music genres. The result shows that the classification of the music genre system based on a deep-learning algorithm has a good music genre classification effect.

Foreground segmentation (FS) plays a fundamental and important role in computer vision, but it remains a challenging task in dynamic backgrounds. The supervised method has achieved good results, but the generalization ability needs to be improved. To address this challenge and improve the performance of FS in dynamic scenarios, a simple yet effective method has been proposed that leverages superpixel features and a one-dimensional convolution neural network (1D-CNN) named SPF-CNN. SPF-CNN involves several steps. First, the coined Iterated Robust CUR (IRCUR) is utilized to obtain candidate foregrounds for an image sequence. Simultaneously, the image sequence is segmented using simple linear iterative clustering. Next, the proposed feature extraction approach is applied to the candidate matrix region corresponding to the superpixel block. Finally, the 1D-CNN is trained using the obtained superpixel features. Experimental results demonstrate the effectiveness of SPF-CNN, which also exhibits strong generalization capabilities. The average F 1-score reaches 0.83.

Let α \alpha be a set of n n elements and δ \delta be a nonnegative integer. A δ \delta -partition of α \alpha is a set of pairwise disjoint nonempty subsets of α \alpha such that the union of the subsets is equal to α \alpha and every subset has a size greater than δ \delta . We formulate an algorithm for computing all δ \delta -partitions of a given n n -element set and show that the algorithm runs in O ( n ) {\mathcal{O}}\left(n) space and O ( n ) {\mathcal{O}}\left(n) delay time between any two successive outputs of δ \delta -partitions of the given set. An application of the notion of δ \delta -partitions is illustrated in the following scheduling problem. Suppose a factory has n n machines and m ≤ n m\le n jobs to complete daily. Every job can be accomplished by operating at least δ + 1 \delta +1 machines. A machine cannot work on multiple jobs simultaneously. According to a utilization policy of the factory’s management, no machine is allowed to be idle, so all machines should be running on some job. Find a daily schedule of the factory’s machines satisfying all the mentioned constraints. Let α \alpha be the set of the factory’s machines. Then, an α \alpha ’s δ \delta -partition with m m subsets is a legal schedule if every subset (in the δ \delta -partition) includes exclusively δ + 1 \delta +1 or more machines that run on the same job.

The emergence of emergencies has impacted China’s politics, economy, and other aspects to varying degrees, seriously threatening social stability, economic development, and people’s happiness. The emergency management platform plays an important role in the handling of emergencies. The establishment of the emergency management platform can help leaders make correct decisions and reduce the impact of emergencies on the safety of people’s lives and property. However, some problems are gradually exposed in the process of establishing the emergency management platform. How to make it play its role better has become an important goal of platform informatization. With the advent of the big data era, big data technology has become a new way of information construction of emergency management platforms. This article mainly discussed the information construction of the emergency management platform. This article proposed to use big data technology to carry out the information construction of the emergency management platform and use the time series data mining algorithm based on the Artificial Neural Network to achieve the prediction function of the platform. The experimental results in this article showed that the prediction rate was 98.0% when the emergencies of the input platform were 50 and 99.0% when the emergencies of the input platform were 300. It can be seen that the emergency management platform designed in this article has a high ability to predict emergencies, so that emergency management measures can be taken in advance to reduce the occurrence of emergencies.

With the continuous improvement of China’s current technology level, the Internet of Things (IoT) technology is also increasingly widely used in various fields. IoT is a network composed of electronic components, software, sensors, etc. With the development of IoT technology, users’ demand for remote control equipment is increasingly urgent. In this article, the genetic algorithm–backpropagation neural network (GA–BPNN) algorithm was deeply studied by combining genetic algorithm (GA) and backpropagation neural network (BPNN) algorithm, and its application in network security evaluation was discussed. This article mainly studied the security and remote control technology of computer network and applied it to intelligent agriculture. In the evaluation performance test of the GA–BPNN algorithm, the evaluation accuracy of GA, BPNN, and GA–BPNN under simple difficulty was 99.58, 99.15, and 99.92%, respectively, and the evaluation accuracy under difficulty was 96.72, 96.47, and 98.88%, respectively. This proved the effectiveness of the GA–BPNN algorithm. In addition, in the application of smart agriculture, through the experimental data and concentration change data, it can be seen that the use of air-driven CO 2 {\text{CO}}_{2} (carbon dioxide) for concentration replenishment can effectively adjust the requirements of crops on the concentration of CO 2 {\text{CO}}_{2} . Through the analysis of the system’s light compensation system, it was proved that the system has a good structure and remarkable light compensation effect; it can replenish light for crops in time, and the PLC control structure has good working performance. The correctness of the system design was proved.

Although online cloud classroom teaching has been popular, the current English teaching cloud classroom has the defects of low information utilization and low information acquisition accuracy. To improve the information utilization and accuracy in teaching, a Chinese and English text classification algorithm is proposed. The algorithm is based on an improved Chi-squared test feature selection (CHI) algorithm. The performance of CHI is optimized by adding parameters such as word frequency, document coverage, and coefficient of variation to the CHI algorithm. According to the experimental results, the proposed algorithm achieved a recall of up to 1.0 under the Chinese dataset. Its accuracy rate was 0.49 higher than traditional CHI. Under the English dataset, the MO of the proposed algorithm reached 0.9. The results indicate that the proposed algorithm has reliable classification ability for both English and Chinese texts and has the potential to be applied to the English language teaching cloud classroom.

The microservices architecture is widely used in modern businesses due to its ability to offer speed, efficiency, adaptability, autonomy, and usability. On the other hand, this architectural paradigm demands a well-designed infrastructure for optimal container and cluster utilization. Establishing version control and a solid continuous integration/continuous deployment (CI/CD) infrastructure becomes critical for accelerating software delivery to production and ensuring code alignment with best practices. This scientific investigation investigates the development of customized, specialized CI/CD procedures for software compliance, expanding its scope beyond traditional software delivery to include the complexities of design, testing, and server deployment. By integrating real-world examples from industry and reviewing crucial tools, the goal is to provide organizations with empirical information to navigate the difficulties of modern software development. The upcoming research seamlessly fits into the larger discussion, providing a deep understanding of sophisticated structures and their design. This interdisciplinary research combines the scientific principles governing microservices with the practical specifics of CI/CD methodologies, giving businesses a thorough understanding and practical insight into the tools needed to navigate the diverse landscape of modern software engineering. Among the main findings of this research is a suggestion for a new approach known as General repository compliance operations.

To improve the effect of corpus extraction in bilingual English–Chinese machine translation (ECMT), this article combines a machine learning algorithm with the ECMT corpus extraction method based on bilingual sentence pair coverage. Aiming at the propagation characteristics of medium- and short-range speeches, and employing multi-band speech waveforms in the troposphere, the actual requirements of remote machine translation are combined with the free-space, 1546, and the dual-path models, respectively, to analyze three typical air-to-ground wave propagation models. A simulation is conducted for both predictions and comparisons. In addition, a radio wave propagation model within the line of sight in the troposphere is established. The results suggest that the improved dual-path model is consistent with the propagation characteristics of radio waves in the troposphere. Moreover, the experiments show that the proposed ECMT corpus extraction method based on bilingual sentence pair coverage can play an important role in more accurate English–Chinese translations.

Multimedia teaching is a comprehensive teaching platform that integrates text, images, video, sound, animation, hyperlinks and other teaching methods, and plays an important role in teaching. This article mainly discussed the classification of courseware materials on the basis of data analysis and introduced the selection method of multimedia courseware materials. Data mining is one of the most commonly used classification methods in data analysis. In this article, the classification of material types was carried out based on the decision tree classification algorithm. This article took three middle schools in Z city as the research objects and objectively analyzed the application of multimedia courseware in literature and art courses. Through the questionnaire survey of teachers, it was found that 62.50% of the teachers chose “text-based, highlighting the key and difficult points of teaching.” Through the student questionnaires, it was found that there were differences in the students’ preference for materials. The most were animation and video, accounting for 59.00%; the least was text, accounting for 14.00%. This showed that students were more inclined to choose more intuitive and interesting content.

With the advancement of the concept of smart cities, research on urban and rural planning is also developing rapidly. How to make the spatial relationship description model in the context of smart cities more in line with the actual situation of urban development is still a problem to be solved. This article focuses on the spatial relationship description model and algorithm of urban and rural planning results in the context of smart cities, studies the impact of urban industrial structure under the action of the spatial relationship description model, and evaluates the impact of policy as well as the impact of smart city construction on urban green innovation efficiency. Its dynamic effects and urban heterogeneity are expanded and analyzed. The research results show that compared with the traditional ordinary least squares (OLS) technology, geographically weighted regression (GWR) has significantly improved the solution results of the model, the R value is reduced by 0.3–0.4, the residual sum of squares value is significantly reduced, and the Akaike information criterion value is significantly improved. For the same training samples and test data, compared with the OLS technology, the mean-squared error reduction rate of the prediction results obtained by the GWR technology basically reached more than 50%, especially in Experiment 4; it reached 57.9%, which shows a very obvious advantage in prediction accuracy. Smart city policies have a significant role in promoting green innovation efficiency in pilot areas, and over time, innovation efficiency has increased year by year, and the policy effects are particularly prominent in the eastern coastal areas with a good development foundation. Therefore, the construction of smart cities is based on the characteristics of the region, and it is necessary to seek a sustainable development path based on the conditions of the region.

Hardware testing has always been the core of hardware development, and improving the performance and efficiency of hardware testing is very important for hardware development. Because hardware quality management is insufficient, many large hardware tools were developed using manual workshop technology in the past and could hardly be maintained. This can lead to the cancellation of the project, causing major personnel and property losses. Improving hardware quality and ensuring security are very complex problems. Hardware testing is usually conducted through manual and automatic testing, and the limitations of manual testing are increasingly obvious. So hardware automatic testing technology has attracted people’s attention in recent years. It has become an important research direction in the field hardware testing and can overcome many problems of traditional testing methods. Strict test rules, based on standards and scores, provide a fully automated test process. With the continuous improvement of network technology, the functions and scope of hardware are constantly enriched and expanded. With the acceleration of hardware updates and development, this has brought a heavy burden to the previous hardware testing work. The purpose of this article was to study the application of machine learning technology in the field of hardware automatic testing and provide an appropriate theoretical basis for optimizing testing methods. This article introduced the research methods of hardware automatic testing technology, introduced three automatic testing framework models, and summarized the application of machine learning in hardware testing. It included hardware security and reliability analysis, hardware defect prediction, and source-based research. Then, this article studied the defect prediction model and machine learning algorithm and constructed a hardware defect prediction model based on machine learning based on the theory. First, the data were preprocessed, and then, the Stacking method was used to build a comprehensive prediction model, and four prediction results evaluation indicators were established. In the experiment part, the defect prediction results of the hardware automatic test model were studied. The results showed that the hardware defect prediction model based on machine learning had higher accuracy, recall rate, F _measure and area under curve. Compared with other models, the average accuracy of the hardware defect prediction model in this article was 0.092 higher, which was more suitable for automatic hardware testing and analysis.

At present, digital media art and environmental design industries are rising in various fields, making art design a popular major. In the era of artificial intelligence (AI), the establishment of public cloud Internet of things in universities and improving the security of design information will help the integration of digital media art and environmental art design, and improve the efficiency of digital media art and environmental design. This article first explains the principles and existing problems of virtual reality (VR) technology, digital media art, and environmental design, then uses AI algorithm to integrate digital media art and environmental design, and finally analyzes the impact of the integration of digital media art and environmental design based on VR technology. The results show that the satisfaction of the integration of digital media art and environmental design based on VR technology has increased by 8.77%. In addition, VR technology also improves the speed of integration of digital multimedia art and environmental design, as well as the added value and design quality of design works. In short, the use of VR technology can better promote the integration of digital multimedia art and environmental design.

This article investigates the effect of cybersecurity knowledge on the ability to detect malicious events in a network. We developed a simplified intrusion detection system (IDS) to simulate real-world scenarios and assess detection capabilities. The IDS features typical network intrusion characteristics, such as signature-based detection and anomaly detection, providing a realistic environment for participants. A cross-sectional study was conducted by recruiting 75 respondents who were from Al Neelain University, with novices observing ten distinct cyber-attack scenarios, including phishing, malware, and denial-of-service attacks. At the same time, experts examined three complex scenarios involving advanced persistent threats and zero-day exploits. Among these participants, 35 were considered novices (students) in cybersecurity, while 40 were security professionals from technical communities. The study procedure involved novices observing ten scenarios and completing a questionnaire assessing their detection accuracy, while experts observed three scenarios and filled out a similar questionnaire. The specific measures used to determine detection capabilities included the accuracy of identifying malicious events, the rate of false positives (mislabelling benign events as malicious), and the rate of false negatives (failing to identify malicious events). The findings of this study demonstrate that cybersecurity knowledge facilitates the accurate detection of malicious events and reduces mislabelling benign events as malicious. A deep understanding of a particular network is necessary for making precise detection decisions, which rely on cybersecurity knowledge. Experts exhibit the capability to differentiate different types of cyber-attacks. They accurately assess various network settings and determine the maliciousness of networking events with greater precision. In conclusion, this study highlights the importance of cybersecurity knowledge in detecting and differentiating cyber-attacks. The expertise of experts in network analysis and precise determination of malicious events emphasizes their significance. These findings have practical implications for enhancing attack detection capabilities.

Smooth operation of railway stations and yards is vital for the efficient functioning of the whole railway system. Being complex systems, their operation is extremely sensitive to various influences, which makes their management, especially at the operational level, very difficult. Efficient tools to aid the decision-making process of dispatchers of such stations are therefore needed. With an emphasis on increasing the effectiveness of decision support tools, we propose a simulation-based optimization algorithm. This algorithm extracts a dataset from a simulation model and then reduces it to a partial dataset to be able to use specific exact optimization method in operational management. The partial dataset is limited by certain time horizon. The applicability of the proposed algorithm has been verified on two distinct tasks, namely, personnel assignment and service task assignment in a maintenance depot, confirming the usability of the proposed approach.

To solve the problem of poor object detection effect caused by uneven light and high noise in underground mines, this study proposes a TTFNet (training-time-friendly network)-based object detection algorithm for underground mines. First, CenterNet and TTFNet algorithms are introduced, then pooling is introduced into CSPNet basic structure to design a lightweight feature extraction network, at the same time optimizing the feature fusion way in the original algorithm, optimizing residual shrinkage network structure, and introducing it into object detection task. Experiments were conducted on the established underground data set. The results show that compared with the original algorithm, our proposed algorithm can still maintain similar accuracy while significantly reducing model parameters; compared with other anchor-based detection algorithms, it has achieved similar overall performance.

Failure to wear a helmet correctly is a significant cause of injury or death in the construction industry and industrial production. Traditional supervision methods predominantly rely on manual oversight, incurring substantial costs and demonstrating inefficiencies. To address this pressing issue, the present work introduces an advanced intelligent detection technology based on deep learning algorithms, which leverages the YOLOv5 algorithm to train a dataset, enabling real-time assessment of correct helmet usage among personnel while promptly issuing warnings when deviations are detected. Simultaneously, to mitigate challenges related to object leakage and false detections in complex backgrounds, the model’s performance is further enhanced by optimizing Generalized Intersection over Union, Distance Intersection over Union, and Complete Intersection over Union loss functions and improving the Mosaic-9 data enhancement algorithm. Empirical results validate the system’s efficacy, with the optimized YOLOv5 algorithm achieving an impressive precision rate of 93.16% and a robust recall rate of 88.96%. These findings underscore the system’s ability to accurately identify instances of workers’ improper helmet usage. This enhanced YOLOv5-based intelligent detection technology provides a more efficient and accurate method for monitoring helmet compliance within the construction industry and industrial production, effectively addressing the limitations of traditional manual supervision and ensuring precision in complex operational contexts.

A network intrusion detection method that integrates improved spatiotemporal residual network and generative adversarial network (GAN) in a big data environment is proposed to address the issues of poor feature extraction and significant impact from data imbalance in most existing intrusion detection methods. First, GANs are used for wireless sensor network data resampling to generate new sample sets, thereby overcoming the impact of data imbalance. Then, an improved spatiotemporal residual network model is designed, in which the spatial and temporal features of the data are extracted and fused through multi-scale one-dimensional convolution modules and gated loop unit modules, and identity maps are added based on the idea of residual networks to avoid network degradation and other issues. Finally, the resampled samples are input into the improved spatiotemporal residual network model to output the intrusion detection results of the network. Based on the NSL-KDD, UNSW-NB15, and CICIDS2017 datasets, experimental analysis is conducted on the proposed method. The results showed that its accuracy on the three datasets is 99.62, 83.98, and 99.86%, respectively, which are superior to other comparative methods.

The use of decision trees and artificial neural networks (ANNs) in health-care research is widespread, as they enable health-care providers with the tools they need to make better medical decisions with their patients. ANNs specifically are extremely helpful in predictive research as they can provide investigators with knowledge about future trends and patterns. However, a major downside to ANNs is their lack of interpretability. Understandability of the model is important as it ensures the outcomes are true to the dataset’s original labels and are not impacted by algorithmic bias. In comparison, decision trees map out their entire process before providing the results, which leads to a higher level of trust in the model and the conclusions it supplies the investigators with. This is essential as many historical datasets lack equal and fair representation of all races and sexes, which might directly correlate to a lesser treatment given to females and individuals in minority groups. Here, we review existing work around the differences and connections between ANNs and decision trees with implications for research in health care.

The article deals with the solution of technical initial value problems. To solve such problems, an analytical or numerical approach is possible. The analytical approach can provide an accurate result; however, it is not available for all problems and it is not entirely suitable for calculation on a computer, due to the limited numerical accuracy. For this reason, the numerical approach is preferred. This approach uses ordinary differential equations to approximate the continuous behaviour of the real-world system. There are many known numerical methods for solving such equations, most of them limited in their accuracy, have a limited region of stability and can be quite slow to achieve the acceptable solution. The numerical method proposed in this article is based on the Taylor series and overcomes the biggest challenge, i.e. calculating higher derivatives. The aim of the article is therefore twofold: to introduce the method and show its properties, and to show its behaviour when solving problems composed of linear and nonlinear ordinary differential equations. Linear problems are modelled by partial differential equations and solved in parallel using the PETSc library. The parallel solution is demonstrated using the wave equation, which is transformed into the system of ordinary differential equations using the method of lines. The solution of nonlinear problems is introduced together with several optimisations that significantly increase the calculation speed. The improvements are demonstrated using several numerical examples that are solved using MATLAB software.