Computational Intelligence and Neuroscience · 2021 · 14 citations · 9 references
ComputingComputer EngineeringComputer ScienceMachine LearningOptimizationSoftware EngineeringDeep LearningDefect DetectionEvolutionary ComputationEvolutionary OptimizationLoss FunctionOptimization For Machine LearningDefect PredictionHyperparameter OptimizationOptimization AlgorithmsParticle Swarm OptimizationSoftware Fault PredictionWolf Algorithm
In order to improve software quality and testing efficiency, this paper implements the prediction of software defects based on deep learning. According to the respective advantages and disadvantages of the particle swarm algorithm and the wolf swarm algorithm, the two algorithms are mixed to realize the complementary advantages of the algorithms. At the same time, the hybrid algorithm is used in the search of model hyperparameter optimization, the loss function of the model is used as the fitness function, and the collaborative search ability of the swarm intelligence population is used to find the global optimal solution in multiple local solution spaces. Through the analysis of the experimental results of six data sets, compared with the traditional hyperparameter optimization method and a single swarm intelligence algorithm, the model using the hybrid algorithm has higher and better indicators. And, under the processing of the autoencoder, the performance of the model has been further improved.
9
Radu‐Emil Precup, Radu‐Codruţ David, Raul‐Cristian Roman et al. · International Journal of Systems Science · 2021 · 137 citations · Full text
Engineering, Mechanical Engineering, Mechatronics Engineering +17
Qing Wang · Journal of Software · 2008 · 53 citations