Band 27, Heft 3

The progress of databases in fields such as medical, business, education, marketing, etc., is colossal because of the developments in information technology. Knowledge discovery from such concealed bulk databases is a tedious task. For this, data mining is one of the promising solutions and clustering is one of its applications. The clustering process groups the data objects related to each other in a similar cluster and diverse objects in another cluster. The literature presents many clustering algorithms for data clustering. Optimisation-based clustering algorithm is one of the recently developed algorithms for the clustering process to discover the optimal cluster based on the objective function. In our previous method, direct operative fractional lion optimisation algorithm was proposed for data clustering. In this paper, we designed a new clustering algorithm called adaptive decisive operative fractional lion (ADOFL) optimisation algorithm based on multi-kernel function. Moreover, a new fitness function called multi-kernel WL index is proposed for the selection of the best centroid point for clustering. The experimentation of the proposed ADOFL algorithm is carried out over two benchmarked datasets, Iris and Wine. The performance of the proposed ADOFL algorithm is validated over existing clustering algorithms such as particle swarm clustering (PSC) algorithm, modified PSC algorithm, lion algorithm, fractional lion algorithm, and DOFL. The result shows that the maximum clustering accuracy of 79.51 is obtained by the proposed method in data clustering.

With the ever-increasing need for concealing messages within cover media like image, video, and audio, numerous attempts have been developed for steganography. Most of the steganographic techniques perform their embedding operation on the cover image without selecting a better location. The right selection of location for embedding the information can lead to high imperceptibility and robustness. Accordingly, in this paper, we develop a new cost function for estimating the cost of every pixel to identify the good location to embed the message data. The proposed cost estimation procedure utilizes multiple parameters like wavelet coefficient, edge transformation, and pixel intensity. The proposed cost matrix is then utilized to embed the message data into the cover media using an embedding integer. The proposed steganographic technique is experimented with two magnetic resonance brain images, and the results are analyzed with the peak-to-peak signal-to-noise ratio (PSNR) and mean square error. The robustness analysis ensured that the proposed steganographic technique outperforms the existing methods by reaching the maximum PSNR of 72.74 dB.

DNA sequence mining is essential in the study of the structure and function of the DNA sequence. A few exploration works have been published in the literature concerning sequence mining in information mining task. Similarly, in our past paper, an effective sequence mining was performed on a DNA database utilizing constraint measures and group search optimization (GSO). In that study, GSO calculation was utilized to optimize the sequence extraction process from a given DNA database. However, it is apparent that, occasionally, such an arbitrary seeking system does not accompany the optimal solution in the given time. To overcome the problem, we proposed in this work multiple constraints with hybrid firefly and GSO (HFGSO) algorithm. The complete DNA sequence mining process comprised the following three modules: (i) applying prefix span algorithm; (ii) calculating the length, width, and regular expression (RE) constraints; and (iii) optimal mining via HFGSO. First, we apply the concept of prefix span, which detects the frequent DNA sequence pattern using a prefix tree. Based on this prefix tree, length, width, and RE constraints are applied to handle restrictions. Finally, we adopt the HFGSO algorithm for the completeness of the mining result. The experimentation is carried out on the standard DNA sequence dataset, and the evaluation with DNA sequence dataset and the results show that our approach is better than the existing approach.

This paper presents a new method of detecting vehicles by using a simple and effective algorithm. The features of a vehicle are the most important aspects in detection of vehicles. The corner points are considered for the proposed algorithm. A large number of points are densely packed within the area of a vehicle, and the points are calculated by using the Harris corner detector. Making use of the fact that they are densely packed, grouping of these points is carried out. This grouping indicates that the group of corners belongs to each vehicle, and such groupings play a vital role in the algorithm. Once grouping is done, the next step is to eliminate the background noise. The Lucas-Kande algorithm is used to track the extracted corner points. Each corner point of the vehicle is tracked to make the output stable and reliable. The proposed algorithm is new, detect vehicles in multiple conditions, and also works for complex environments.

This paper presents a fast and efficient method for load flow analysis of radial distribution networks. Here, an adaptive algorithm is proposed to analyze the load flow problem of distribution systems. An adaptive algorithm is the combination of backward/forward (BW/FW) sweep and cuckoo search (CS) algorithms. In the proposed method, the optimum load flow analysis of the radial distribution system is attained, while optimizing the voltage and current computation of the BW/FW sweep algorithm. Now, by the CS, the output voltage of the BW/FW sweep algorithm is compared with the standard voltage and optimized. From the optimized voltage and current, load flow parameters like power loss and real and reactive power flow are assessed. The proposed method is implemented using the MATLAB platform and tested into the IEEE 33 bus radial distribution system. The effectiveness of the proposed technique is determined by comparing with the BW/FW algorithm and genetic algorithm-based BW/FW algorithm.

The significance of researches in modeling of boiler design and its optimization is high for saving energy and minimizing emissions. Modeling the boiler plant with all demands is rather challenging. A lot of techniques are reported in the literature for enhancing the boiler efficiency. The neural network scheme has been proved for the boiler design, and it provides a framework for the non-linear system models. In this paper, a hybrid of artificial neural network and firefly algorithm is proposed. The proposed modeling technique is simulated in MATLAB, and the experimentation is carried out extensively. The performance of the proposed modeling technique is demonstrated using type I and II error functions, followed by performing higher statistical measures such as error deviation and correlation analysis. Comparative analysis is made to substantiate the superiority of the proposed modeling technique.

Software project effort estimation is one of the important aspects of software engineering. Researchers in this area are still striving hard to come out with the best predictive model that has befallen as a greatest challenge. In this work, the effort estimation for small-scale visualization projects all rendered on engineering, general science, and other allied areas developed by 60 postgraduate students in a supervised academic setting is modeled by three approaches, namely, linear regression, quadratic regression, and neural network. Seven unique parameters, namely, number of lines of code (LOC), new and change code (N&C), reuse code (R), cumulative grade point average (CGPA), cyclomatic complexity (CC), algorithmic complexity (AC), and function points (FP), which are considered to be influential in software development effort, are elicited along with actual effort. The three models are compared with respect to their prediction accuracy via the magnitude of error relative to the estimate (MER) for each project and also its mean MER (MMER) in all the projects in both the verification and validation phases. Evaluations of the models have shown MMER of 0.002, 0.006, and 0.009 during verification and 0.006, 0.002, and 0.002 during validation for the multiple linear regression, nonlinear regression, and neural network models, respectively. Thus, the marginal differences in the error estimates have indicated that the three models can be alternatively used for effort computation specific to visualization projects. Results have also suggested that parameters such as LOC, N&C, R, CC, and AC have a direct influence on effort prediction, whereas CGPA has an inverse relationship. FP seems to be neutral as far as visualization projects are concerned.

In this paper, an adaptive neuro fuzzy interference system (ANFIS) is proposed for eliminating voltage harmonics present in the multilevel inverter. It is achieved by reducing the total harmonic distortion (THD) present in the multilevel inverter output voltage. Here, the voltage variation of the multilevel inverter is determined from the actual load voltage and the reference voltage. The voltage variations at different time intervals have been applied to the ANFIS. According to the voltage variations, the switching angles can be generated from the interference system. These switching angles can make the multilevel inverter output voltage with reduced THD. The proposed technique is implemented in the MATLAB/simulink working platform. The effectiveness of the proposed method is evaluated by the multilevel inverter output voltage without controller and with neuro fuzzy controller (NFC).

Fighter aircraft recognition is important in military applications to make strategic decisions. The complexity lies in correctly identifying the unknown aircraft irrespective of its orientations. The work reported here is a research initiative in this regard. The database used here was obtained by using rapid prototyped physical models of four classes of fighter aircraft: P51 Mustang, G1-Fokker, MiG25-F, and Mirage 2000. The image database was divided into the training set and test set. Two feature sets, Feature Set1 (FS1) and FS2, were extracted for the images. FS1 consisted of 15 general features and FS2 consisted of 14 invariant moment features. Four multilayered feedforward backpropagation neural networks were designed and trained optimally with the normalized feature sets. The neural networks were configured to classify the test aircraft image. An overall accuracy of recognition of 91% and a response time of 3 s were achieved for the developed automatic fighter aircraft model image recognition system.

The feature selection process can be considered a problem of global combinatorial optimization in machine learning, which reduces the irrelevant, noisy, and non-contributing features, resulting in acceptable classification accuracy. Harmony search algorithm (HSA) is an evolutionary algorithm that is applied to various optimization problems such as scheduling, text summarization, water distribution networks, vehicle routing, etc. This paper presents a hybrid approach based on support vector machine and HSA for wrapper feature subset selection. This approach is used to select an optimized set of features from an initial set of features obtained by applying Modified log-Gabor filters on prepartitioned rectangular blocks of handwritten document images written in either of 12 official Indic scripts. The assessment justifies the need of feature selection for handwritten script identification where local and global features are computed without knowing the exact importance of features. The proposed approach is also compared with four well-known evolutionary algorithms, namely genetic algorithm, particle swarm optimization, tabu search, ant colony optimization, and two statistical feature dimensionality reduction techniques, namely greedy attribute search and principal component analysis. The acquired results show that the optimal set of features selected using HSA gives better accuracy in handwritten script recognition.

In modern software development processes, software effort estimation plays a crucial role. The success or failure of projects depends greatly on the accuracy of effort estimation and schedule results. Many studies focused on proposing novel models to enhance the accuracy of predicted results; however, the question of accurate estimation of effort has been a challenging issue with regards to researchers and practitioners, especially when it comes to projects using agile methodologies. This study aims at introducing a novel formula based on team velocity and story point factors. The parameters of this formula are then optimized by employing swarm optimization algorithms. We also propose an improved algorithm combining the advantages of the artificial bee colony and particle swarm optimization algorithms. The experimental results indicated that our approaches outperformed methods in other studies in terms of the accuracy of predicted results.