The Influence of Deep Learning Algorithms Factors in Software Fault Prediction

Abstract

The discovery of software faults at early stages plays an important role in improving software quality; reduce the costs, time, and effort that should be spent on software development. Machine learning (ML) have been widely used in the software faults prediction (SFP), ML algorithms provide varying results in terms of predicting software fault. Deep learning achieves remarkable performance in various areas such as computer vision, natural language processing, speech recognition, and other fields. In this study, two deep learning algorithms are studied, Multi-layer perceptron's (MLPs) and Convolutional Neural Network (CNN) to address the factors that might have an influence on the performance of both algorithms. The experiment results show how modifying parameters is directly affecting the resulting improvement, these parameters are manipulated until the optimal number for each of them is reached. Moreover, the experiments show that the effect of modifying parameters had an important role in prediction performance, which reached a high rate in comparison with the traditional ML algorithm. To validate our assumptions, the experiments are conducted on four common NASA datasets. The result shows how the addressed factors might increase or decrease the fault detection rate measurement. The improvement rate was as follows up to 43.5% for PC1, 8% for KC1, 18% for KC2 and 76.5% for CM1.

MLPNN‐RF: Software fault prediction based on robust weight based optimization and Jacobian adaptive neural network

“…The study 14 It has been found that the proposed system outperformed existing system by showing high accuracy percentage of 99.01%. Thus the proposed MLP has shown high accuracy in classifying the SFP which reveal its efficiency than the traditional methods.…”

“…TA B L E 1 Comparative analysis of the proposed and existing methods 14 The proposed system is compared with the existing methods with respect to error rate and it is shown in Table 2. The existing methods such as RF, LR, CART, and MLP are considered.…”

“…in terms of accuracy Comparative analysis in terms of accuracy TA B L E 2 Comparative analysis of the proposed and existing methods14 in terms of error rate Comparative analysis in terms of various performance metrics…”

Survey of Supervised Learning for Medical Image Processing

“…19 . These factors include the number of samples [ 89 ], the number of layers [ 89 , 103 ], the number of classes [ 25 ], the image modality and quality [ 104 ], and the hyperparameters values [ 85 , 103 ]. For instance, AlexNet achieved the highest sensitivity and specificity of 100% in the binary classification of a brain tumor in MRI images [ 6 ].…”

Software fault prediction using Whale algorithm with genetics algorithm

“…Fault prediction techniques are developed to minimize time and cost in maintenance and testing phases in the software development lifecycle and to develop a safe and efficient system. Machine learning and deep learning are commonly used in predicting software faults and utilized in diverse research fields 8‐14 . One of the techniques that are used for optimization and prediction is called Genetics algorithm, and it is defined by Reference 15 as “a problem‐solving algorithm that uses genetics as a model of problem‐solving, also It's a search technique to find approximate solutions to optimization and search problems”.…”