Over the past few decades, researchers in software engineering (SE) have focused on testing, analyzing, repairing, and generating programs automatically and effectively. Today, combining neural networks and traditional software engineering techniques has major potential to benefit software quality and productivity. Regarding the development of neural networks, deep learning (DL) and convolution neural networks (CNNs) have been widely adopted by software applications for making decisions or providing suggestions. Considering life-critical DL-based applications, there is a need to correct the wrong decisions made by DL systems immediately. Therefore, we propose a novel fault-correction framework for alleviating potential misclassification issues of DL systems called the Outlier Modification for DL Systems (OMDLS). Our experiment results with two public datasets using different scales and label numbers to show that modifying the outliers based on the misclassification pairs can improve accuracy by up to 2.12% without retraining the model and modifying the inference immediately.

In the popularity of the Internet, users can find a variety of services on the Internet to meet their needs; but whether the stability of software service is a problem for users. Similarly, service providers seek to continuously update service to provide a better user experience. In this paper, we proposed four QoS prediction architectures that can consider more factors and variables than past methods. We compared the prediction performance of our proposed models with the regression model, the convolutional neural network (CNN), and the recurrent neural network (RNN). Four real datasets are used and experimental results show that considering multiple variables are better than single variable as inputs in our models. The Single method performed better than past methods using a single time series. Moreover, in four datasets multi-factor method predicted better than single factor method. Each model took different average training time in different datasets. Some methods took less time but does not have good performance. We used a CNN and RNN to converge more quickly than long short-term memory (LSTM) and gated recurrent unit (GRU), and to also achieve good prediction performance.