342 Hits in 13.1 sec

Research on Software Multiple Fault Localization Method Based on Machine Learning

Meng Gao, Pengyu Li, Congcong Chen, Yunsong Jiang, Yansong Wang
2018 MATEC Web of Conferences  
Despite the research of neural network and decision tree has made some progress in software multiple fault localization, there is still a lack of systematic research on various algorithms of machine learning  ...  Then, a software multiple fault localization research framework based on machine learning is proposed.  ...  based on integrated learning and BP neural network perform well in software multiple fault localization.  ... 
doi:10.1051/matecconf/201823201060 fatcat:bqj662y6fjgd5ny2bz6hkp67bm


2009 International journal of software engineering and knowledge engineering  
Our results suggest that a BP neural network-based fault localization method is effective in locating program faults.  ...  We first train a BP neural network with the coverage data (statement coverage in our case) and the execution result (success or failure) collected from executing a program, and then we use the trained  ...  Acknowledgments The authors wish to thank Yan Shi of the Software Technology Advanced Research (STAR) Lab at the University of Texas at Dallas for her comments while this paper was still a work in progress  ... 
doi:10.1142/s021819400900426x fatcat:ixsclahdwbhu7ayfz7nka32ere

Software Fault Localization [chapter]

W. Eric Wong, Vidroha Debroy
2010 Encyclopedia of Software Engineering  
[25] propose a fault localization technique based on a back-propagation (BP) neural network, which is one of the most popular neural network models in practice.  ...  The statement coverage of each test case, and the corresponding execution result, are used to train a BP neural network.  ... 
doi:10.1081/e-ese-120044231 fatcat:zpue4k7zkjaz3f5lcunhhvheu4

Effective Software Fault Localization Using an RBF Neural Network

W. Eric Wong, Vidroha Debroy, Richard Golden, Xiaofeng Xu, Bhavani Thuraisingham
2012 IEEE Transactions on Reliability  
Index Terms-Fault location, radial basis function neural networks, software debugging.  ...  We propose the application of a modified radial basis function neural network in the context of software fault localization, to assist programmers in locating bugs effectively.  ...  In this paper, we propose to use an RBF neural network-based fault localization technique because RBF networks have several advantages over BP networks, including a faster learning rate, and a resistance  ... 
doi:10.1109/tr.2011.2172031 fatcat:2lhth4dxcnfcpix773equi6l4y

A Survey on Software Fault Localization

W. Eric Wong, Ruizhi Gao, Yihao Li, Rui Abreu, Franz Wotawa
2016 IEEE Transactions on Software Engineering  
Software fault localization is one of the (if not the) most expensive, tedious and time consuming activities in program debugging.  ...  In this article we provide an overview of several such methods and discuss some of the key issues and concerns that are relevant to fault localization.  ...  ACKNOWLEDGMENT The authors wish to thank Andy Restrepo of the Software Technology Advanced Research (STAR) Lab at the University of Texas at Dallas for his valuable comments in helping us preparing this  ... 
doi:10.1109/tse.2016.2521368 fatcat:ruma7ykuv5bhfftwr35m7375y4

Nature inspired optimization and its application to engineering

Janmenjoy Nayak, Bighnaraj Naik, Asit Kumar Das, Danilo Pelusi
2021 Evolutionary Intelligence  
fault localization using BP neural network based on function and branch coverage, a novel stacked sparse denoising autoencoder for mammography restoration to visual interpretation of breast lesion, ensemble  ...  Prioritization using Firefly Algorithm, accurate localization of sensor nodes in underwater sensor networks using a Doppler shift and modified genetic algorithm based localization technique, Differential  ...  1 Department of Computer Science and Engineering, Aditya  ... 
doi:10.1007/s12065-021-00586-x fatcat:6msdidy4wjdgdhpypi2hxlxjam

Fault Localization for Java Programs using Probabilistic Program Dependence Graph [article]

A. Askarunisa, T. Manju, B. Giri Babu
2012 arXiv   pre-print
The PPDG is based on the established framework of probabilistic graphical models. This work presents algorithms for constructing PPDGs and applying fault localization.  ...  In the proposed method Model Based Fault Localization Technique is used, which is called Probabilistic Program Dependence Graph .  ...  [21] propose a fault localization technique based on a back-propagation (BP) neural network, which is one of the most popular neural network models in practice.  ... 
arXiv:1201.3985v1 fatcat:ykqhx3je5zdx7gtr7lwmbjre7m

Realization Path of the Social Development of Meteorological Services Based on Intelligent Data Analysis

Fang Guo, Yufang Feng, Han Xiao, Shalli Rani
2022 Wireless Communications and Mobile Computing  
services for users based on this information.  ...  This paper mainly uses a simulation experiment method, investigation method, and statistical method to conduct in-depth research on the social development of meteorological services.  ...  The PSO algorithm is used to optimize the weights and thresholds of the BP neural network, and an intelligent prediction model based on PSO-BPNN is established.  ... 
doi:10.1155/2022/8904136 fatcat:b2ypibechvd2vjzzr5nccc2zim

An Inspired Machine-Learning Algorithm with a Hybrid Whale Optimization for Power Transformer PHM

Wei Zhang, Xiaohui Yang, Yeheng Deng, Anyi Li
2020 Energies  
In particular, to enhance the robustness of the model, we adopt a modified differential evolution whale optimization algorithm (MDE-WOA) to optimize the probabilistic neural network (PNN), namely, the  ...  The model uses intelligent sensors to obtain dissolved gas analysis (DGA) data for fault diagnosis of the power transformer system, so as to compress the complexity of features (gas types) in the power  ...  methods to the power transformer fault detection model based on DGA dataset, such as fuzzy theory [15] , support vector machine (SVM) [16] , and artificial neural network (ANN) [17] [18] [19] [20] .  ... 
doi:10.3390/en13123143 fatcat:qwuh543scbedrft75k4j7rhfsq

Applying Neural Network Approach with Imperialist Competitive Algorithm for Software Reliability Prediction

Shirin Noekhah, Naomie Binti Salim, Nor Hawaniah Zakaria
2017 Kurdistan Journal of Applied Research  
The proposed model has solved some of the problems of existing methods such as convergence problem and demanding on huge number of data. This model can be used in complicated software systems.  ...  To overcome the problem of dependency to human power and time limitation for software reliability prediction, researchers consider soft computing approaches such as Neural Network and Fuzzy Logic.  ...  [4] based on using neural networks, and their results showed the effectiveness of their approach compared with analytical models.  ... 
doi:10.24017/science.2017.3.5 fatcat:usns7aks6jca3o56ho3xcdwzji

Dissolved Gas Analysis Principle-Based Intelligent Approaches to Fault Diagnosis and Decision Making for Large Oil-Immersed Power Transformers: A Survey

Lefeng Cheng, Tao Yu
2018 Energies  
intelligent approaches applied in fault diagnosis and decision making for large oil-immersed power transformers based on dissolved gas analysis (DGA), including expert system (EPS), artificial neural  ...  into a local optimum.  ...  between the local searching and global searching of the BP neural network, thus avoiding it falling into a local optimum.  ... 
doi:10.3390/en11040913 fatcat:5abufqmt7rcrlkquxncgxame2m

Protection coordination in distribution systems with and without distributed energy resources- a review

Manohar Singh
2017 Protection and Control of Modern Power Systems  
/non-functional.  ...  Distributed energy resources connected distribution networks become interconnected in nature and protection coordination schemes, which are designed for unidirectional flow of fault currents become ineffective  ...  A method based on the branches of the network was also reported in [22] for determining the minimum BPS.  ... 
doi:10.1186/s41601-017-0061-1 fatcat:jufmvsyiwnfivgh5uihlavlfiq

Automatic Programming Methodologies for Electronic Hardware Fault Monitoring

Ajith Abraham, Crina Grosan
2006 Journal of universal computer science (Online)  
Empirical results are compared with artificial neural networks trained using backpropagation algorithm and classification and regression trees.  ...  For on-line prediction, validated stressor vectors may be obtained by direct measurements or sensors, which after pre-processing and standardization are fed into the GP models.  ...  Authors would like to thank the anonymous referees for the technical suggestions and remarks which helped to improve the contents and the quality of presentation.  ... 
doi:10.3217/jucs-012-04-0408 dblp:journals/jucs/AbrahamG06 fatcat:5k4bueg76fap3eltfjnqrpx4xe

Soft Computing for diagnostics in equipment service

2001 Artificial intelligence for engineering design, analysis and manufacturing  
We present methods and tools from the Soft Computing domain, which is used within the diagnostics and prognostics framework to accommodate imprecision of real systems.  ...  Soft Computing (SC) is an association of computing methodologies that includes as its principal members fuzzy, neural, evolutionary, and probabilistic computing.  ...  in particular neural networks) give us a supervised learning algorithm that perform fine-granule local optimization.  ... 
doi:10.1017/s0890060401154028 fatcat:f254znza55c3tajt6hexudvehy

Hybrid soft computing systems: industrial and commercial applications

P.P. Bonissone, Yu-To Chen, K. Goebel, P.S. Khedkar
1999 Proceedings of the IEEE  
We illustrate some combinations of hybrid SC systems, such as fuzzy logic controllers (FLCs) tuned by neural networks (NNs) and evolutionary computing (EC), NNs tuned by EC or FLCs, and EC controlled by  ...  We present a collection of methods and tools that can be used to perform diagnostics, estimation, and control.  ...  For instance, AIGEN used a fuzzy model with local gradient search, but one could also use a pure neural network trained by an evolutionary algorithm.  ... 
doi:10.1109/5.784245 fatcat:ntpjdm3exbgudlxqi62ikvsvuu
« Previous Showing results 1 — 15 out of 342 results