One of the most informative measures for feature extraction (FE) is mutual information (MI). In terms of MI, the optimal FE creates new features that jointly have the largest dependency on the target class. However, obtaining an accurate estimate of a high-dimensional MI as well as optimizing with respect to it is not always easy, especially when only small training sets are available. In this paper, we propose an efficient tree-based method for FE in which at each step a new feature is created by selecting and linearly combining two features such that the MI between the new feature and the class is maximized. Both the selection of the features to be combined and the estimation of the coefficients of the linear transform rely on estimating 2-D MIs. The estimation of the latter is computationally very efficient and robust. The effectiveness of our method is evaluated on several real-world data sets. The results show that the classification accuracy obtained by the proposed method is higher than that achieved by other FE methods.
The software is often responsible for controlling the behavior of mechanical and electrical components, as well as interactions among these components in cyber-physical systems (CPS). The risks in CPS systems could result in losing tools, features, performance and even life. Therefore, safety analysis for software in these systems is a highly critical and serious issue. In general, safety and reliability approaches play a major role in a risk management process in CPS. In this paper, after reviewing the major techniques of software reliability and safety in CPS, an software fault tree analysis (SFTA)-based approach is presented for analysis of operational use-cases (UC) in a CPS system. In our approach, the events related to use-cases are extracted, and the related SFTA is then obtained using the proposed algorithm. Moreover, a semi-automatic method is presented in this paper to produce software failure mode and effects analysis (SFMEA) from SFTA. The results of our approach are applicable for software safety analysis in a real CPS system, including the control system of Iranian National Observatory telescope. Assessment of the suggested method is performed through numerous safety/reliability criteria and the qualitative/quantitative analysis based on these criteria.
Software often controls the behavior of mechanical and electrical systems, as well as interactions among their components in cyberphysical systems (CPS). The risks in CPS systems could result in losing tools, features, performance, and even life. Therefore, safety analysis for software in these systems is a highly critical and serious issue. The use of reliability block diagram is a method for checking the safety and reliability of systems. A reliability block diagram is a diagrammatic method for showing how component reliability contributes to the success or failure of a complex system. In this paper, a method for generating RBDs is presented analysis and demonstration of this method capability to evaluation of a software safety by use-case analysis, use-case diagram review, and use-case specification. Then, a Fuzzy VIKOR-based FMEA is used for further evaluation due to the presence of uncertain data. Finally, it is applied to a real CPS.
Numerous methods have been introduced to predict the reliability of software. In general, these methods can be divided into two main categories, namely parametric (e.g. software reliability growth models) and non-parametric (e.g. neural networks). Both approaches have been successfully implemented in software testing applications over the past four decades. Since most software reliability prediction data are available in the form of time series, deep recurrent network models (e.g. RNN, LSTM, NARX, and LSTM Encoder-Decoder networks) are considered as powerful tools to be employed in reliability-related problems. However, the problem of overfitting is a major concern when using deep neural networks for software reliability applications. To address this issue, we propose the use of dropout; therefore, this study utilizes a deep learning model based on LSTM Encoder-Decoder Dropout to predict the number of faults in software and assess software reliability. Experimental results show that the proposed model has better prediction performance compared with other RNN-based models.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.