Hybrid support vector machine and K‐nearest neighbor‐based software testing for educational assistant

An improved group search optimizer with operation of quantum-behaved swarm and its application

Chapter 1 Introduction of swarm intelligent algorithms.- Chapter 2 Application of particle swarm optimization algorithm to engineering structures.- Chapter 3 Optimum design of structures with heuristic particle swarm optimization algorithm .-Chapter 4 Optimum design of structures with group search optimizer algorithm .-Chapter 5 Improvements and applications of group search optimizer in structural optimal design .-Chapter 6 Optimum design of structures with quick group search optimization algorithm .-Chapter 7 Group search optimizer and its applications on multi-objective structural optimal design .-Chapter 8 Prospecting swarm intelligent algorithms.

In this paper, a new optimization algorithm is presented for coordinated design of a conventional power system stabilizer (CPSS) and a unified power flow controller (UPFC) that are connected to a single-machine infinite-bus (SMIB) power system. First, this coordinated design problem is converted into an optimization problem. Then, the group search optimization (GSO) algorithm is used to solve it. The proposed algorithm is tested under various operating conditions and its effectiveness is proved by simulation results.

Accurate damping of inter-area and intra area oscillations are very much critical in the stability of electric power system. Power system stabilizer (PSS) is mainly used as auxiliary controllers to damp out the low frequency oscillations in the area of electric power system. The tuning of Conventional Power System Stabilizer (CPSS) for a nonlinear power system should be robust such that overall system stability can be improved under several operating points. Today's scenario, various populations based heuristic algorithms are available to minimize the effect of stability problem by properly tuning the parameters of CPSS. In this paper presents a new heuristic population based optimization technique named as Group Search Optimization (GSO) algorithm to tune the PSS parameters for a multi-machine system for different operating conditions. The importance of the GSO algorithm is evaluated and compared for damping the system oscillations during small and large disturbances, and their robustness is illustrated using the transient signal analysis.

Group search optimizer (GSO) which is an effective evolutionary algorithm has been successfully applied in many applications. However, the purely stochastic resampling or selection mechanism in GSO leads to long computing time and premature convergence. In this paper, we propose a diversity-guided group search optimizer (DGSO) with opposition-based learning (OBL) to overcome these limitations. Opposition-based learning is utilized to accelerate the convergence rate of GSO, while the diversity guidance (DG) is used to increase the diversity of population. When compared with the standard GSO, a novel operator using OBL and DG is developed for the population initialization as well as the generation jumping. A comprehensive set of 19 complex benchmark functions is used for experiment verification and is compared to the original GSO algorithm. Numerical experiments show that the proposed DGSO leads to better performance in comparison with the standard GSO in the convergence rate and the solution accuracy.

To overcome the prematurity of Group Search Optimizer( GSO) and improve its convergence speed, a producer pre-selection mechanism based self-adaptive group search optimizer( PSAGSO) algorithm was proposed. Firstly, the reverse mutation operator and pre-selection mechanism were employed to generate a new producer by producer-scrounger model to guide the search directions of scrounger and effectively maintain the diversity of population. Secondly, a self-adaptive method based on linear decreasing weight was adopted to adjust the proportion of rangers, which is to improve individual vigor of the population and benefit to escape from local optima. Experiments were conducted on a set of 12 benchmark functions. For 30-dimensional function optimization, the test data obtained by the PSAGSO algorithm was better than that in the literature( HE S, WU Q H, SAUNDERS J R. Group search optimizer: an optimization algorithm inspired by animal searching behavior.IEEE Transactions on Evolutionary Computation, 2009, 13( 5) : 973- 990). For 300-dimensional numerical optimization problems, the PSAGSO algorithm exhibited better performance. The experimental result demonstrates that the PSAGSO algorithm improves the group search optimizer, and to some extent it improves the algorithm convergence speed and accuracy.

This article presents a scheme using singular value decomposition (SVD) combined group search optimizer (GSO) algorithm to estimate the parameters of low frequency oscillation (LFO) in power grids. Firstly, Mathematical morphology (MM) is adopted as a preprocessing method. Secondly, SVD is applied to identify the number of modes in a LFO event. Finally, parameters of each mode are identified and determined by GSO. In order to demonstrate the accuracy and efficiency of the scheme proposed in this article, three simulation cases are implemented, which use predefined parameters, real-time digital system and wide-area measurement signal data collected from North American SynchroPhasor Initiative, respectively. The analysis results indicate that the proposed scheme can be applied in real-time monitoring environment on digital signal processor platform within short computation time, even in heavy noisy environment.

Watermarking is defined as about hiding any valuable information set in the particular digital media by itself through modifying the particular graphic contents. In our proposed method, the process of watermarking is performed from video data. In this work group search optimization is used to determine the position, selection for watermarking. The proposed framework includes the following stages particularly, frame conversion, preprocessing, watermark image selection, watermarking position selection and inverse watermarking. Initially, the input video is segregated into a number of frames. Then in preprocessing, both the input and the original image are resized and the original image is transformed by discrete wavelet transform. Then the secret data to be embedded is selected and replaced in the watermark position determined through the Group Search Optimization (GSO) Algorithm. Finally, inverse watermarking is performed to retrieve the secret data. The proposed technique is implemented in the working platform of MATLAB which shows improved results by using GSO as compared to without GSO method.

We propose a diversity-guided group search optimizer-based approach for solving the location management problem in mobile computing. The location management problem, which is to find the optimal network configurations of management under the mobile computing environment, is considered here as an optimization problem. The proposed diversity-guided group search optimizer algorithm is realized with the aid of diversity operator, which helps alleviate the premature convergence problem of group search optimizer algorithm, a successful optimization algorithm inspired by the animal behavior. To address the location management problem, diversity-guided group search optimizer algorithm is exploited to optimize network configurations of management by minimizing the sum of location update cost and location paging cost. Experimental results illustrate the effectiveness of the proposed approach.

Most bug assignment approaches utilize text classification and information retrieval techniques.These approaches use the textual contents of bug reports to build recommendation models.The textual contents of bug reports are usually of high dimension and noisy source of information.These approaches suffer from low accuracy and high computational needs.In this paper, we investigate whether using categorical fields of bug reports, such as component to which the bug belongs, are appropriate to represent bug reports instead of textual description.We build a classification model by utilizing the categorical features, as a representation, for the bug report.The experimental evaluation is conducted using three projects namely NetBeans, Freedesktop, and Firefox.We compared this approach with two machine learning based bug assignment approaches.The evaluation shows that using the textual contents of bug reports is important.In addition, it shows that the categorical features can improve the classification accuracy.

E-learning is a response to the new educational needs of society and an important development in information and communication technologies because it represents the future of the teaching and learning processes. However, this trend presents many challenges, such as the processing of online forums which generate a huge number of messages with an unordered structure and a great variety of topics. These forums provide an excellent platform for learning and connecting students of a subject but the difficulty of following and searching the vast volume of information that they generate may be counterproductive. The main goal of this paper is to review the approaches and techniques related to online courses in order to present a set of learning analytics techniques and a general architecture that solve the main challenges found in the state of the art by managing them in a more efficient way: 1) efficient tracking and monitoring of forums generated; 2) design of effective search mechanisms for questions and answers in the forums; and 3) extraction of relevant key performance indicators with the objective of carrying out an efficient management of online forums. In our proposal, natural language processing, clustering, information retrieval, question answering, and data mining techniques will be used.

In software testing and maintenance activities, the observed faults and bugs are reported in bug report managing systems (BRMS) for further analysis and repair. According to the information provided by bug reports, developers need to find out the location of these faults and fix them. However, bug locating usually involves intensively browsing back and forth through bug reports and software code and thus incurs unpredictable cost of labor and time. Hence, establishing a robust model to efficiently and effectively locate and track faults is crucial to facilitate software testing and maintenance. In our observation, some related bug locations are tightly associated with the implicit links among source files. In this paper, we present an implicit social network model using PageRank to establish a social network graph with the extracted links. When a new bug report arrives, the prediction model provides users with likely bug locations according to the implicit social network graph constructed from the co-cited source files. The proposed approach has been implemented in real-world software archives and can effectively predict correct bug locations.

Various evolving approaches have been extensively applied to evolve densely connected communities in complex networks. However these techniques have been primarily single objective optimization techniques, which optimize only a specific feature of the network missing on other important features. Multiobjective optimization techniques can overcome this drawback by simultaneously optimizing multiple features of a network. This paper proposes MGSO, a multiobjective variant of Group Search Optimization (GSO) algorithm to globally search and evolve densely connected communities. It uses inherent animal food searching behavior of GSO to simultaneously optimize two negatively correlated objective functions and overcomes the drawbacks of single objective based CD algorithms. The algorithm reduces random initializations which results in fast convergence. It was applied on 6 real world and 33 synthetic network datasets and results were compared with varied state of the art community detection algorithms. The results established show the efficacy of MGSO to find accurate community structures.

Users can use bug tracking systems (BTS) such as Bugzilla, JIRA, and GitHub to report defects they detect while using or testing the software applications. Bugzilla has specified the bug's information such as bug ID, description, product, classification, component, platform, operating system, bug status, resolution, priority, and severity. The severity assigned to the bug report is conducted manually. So, it takes some considerable time to assign the severity manually, and also it is a tedious task. In this research, we used a deep learning-based technique to develop the prediction model for severity. Our proposed approach is based on the convolutional neural network (CNN) for severity prediction of the bug reports. First, we pre-process the textual content in bug reports using natural language processing (NLP) approaches. Then we extract the features from the textual context (short description) using the Bag-of-Words feature extraction method. Finally, we train a CNN-based classifier to severity prediction based on its input. Then our result is compared with the Support Vector Machine (SVM) and Temporal Convolutional Network (TCN) to find a better model for severity prediction. The final results show that the proposed approach based on the CNN classifier performs better than the other approaches, and it shows an 81% accuracy while others have low accuracy, like 61% and 48% for SVM and TCN, respectively. The proposed model's performance was evaluated using the Bugzilla dataset, which included over 25,000 bug reports. The accuracy, precision, recall, and F1-Score are used to measure the performance.

A Supervised Bug Report Classification with Incorporate and Textual field Knowledge