Wireless applications have been growing rapidly in the past years, leading to the problem of spectrum scarcity. Cognitive radio network (CRN) is an emerging technology which can provide a promising solution to resolve this spectrum scarcity problem in wireless communication. However, the security concerns in cognitive radio (CR) is an unavoidable issue, since it introduces significant new classes of threats due to its unique characteristics and functioning techniques and also has received more attention by the researchers recently. In this paper, we provide a brief overview of CRN technology and analyse its associated security vulnerabilities and discuss a number of available solutions for countering those threats. We identify the security threats based on the targeted open system interconnection (OSI) layer and classified those into traditional wireless threats and CRN specific threats. The paper will also focus on Byzantine attack or spectrum sensing data falsification (SSDF) attack, which is a common CRN specific threat and reviewed the distinguished proposed techniques by research community to detect and isolation of such attack. Finally, a road-map for future research is addressed.

The computational intelligence approach using Neural Network (NN) has been known to be very useful in predicting software reliability. Software reliability plays a key role in software quality. In order to improve accuracy and consistency of software reliability prediction, we propose the applicability of Feed Forward Back-Propagation Network (FFBPN) as a model to predict software reliability. The model has been applied on data sets collected across several standard software projects during system testing phase with fault removal. Unlike most connectionist models, our model attempt to compute average error (AE), the root mean square error (RMSE), normalized root mean square error (NRMSE), mean absolute error (MAE) simultaneously. A comparative study among the proposed feed-forward neural network with some traditional parametric software reliability growth model’s performance is carried out. The results indicated in this work suggest that FFBPN model exhibit an accurate and consistent behavior in reliability prediction.

Fuzzy Logic (FL) together with Recurrent Neural Network (RNN) is used to predict the software reliability. Fuzzy Min-Max algorithm is used to optimize the number of the kgaussian nodes in the hidden layer and delayed input neurons. The optimized recurrent neural network is used to dynamically reconfigure in real-time as actual software failure. In this work, an enhanced fuzzy min-max algorithm together with recurrent neural network based machine learning technique is explored and a comparative analysis is performed for the modeling of reliability prediction in software systems. The model has been applied on data sets collected across several standard software projects during system testing phase with fault removal. The performance of our proposed approach has been tested using distributed system application failure data set.

Recurrent Neural Network (RNN) has been known to be very useful in predicting software reliability. In this paper, we propose a model that explores the applicability of Recurrent Neural Network with Back-propagation Through Time (RNNBPTT) learning to predict software reliability. The model has been applied on data sets collected across several standard software projects during system testing phase. Though the procedure is relatively complicated, the results depicted in this work suggest that RNN exhibits an accurate and consistent behavior in reliability prediction.

Recurrent Neural Network (RNN) has been known to be very useful in predicting software reliability. A number of parametric models and reliability growth models, have been proposed, but developing a model that can predict reliability in all types of data sets, in any environment, and at any phase of software development is still a challenge. In this paper, we propose a model that explores the applicability of Recurrent Neural Network with Back- propagation Through Time (RNNBPTT) learning rule to predict software reliability. The detailed procedure of reliability prediction using recurrent neural networks is explained. The model has been applied on data sets collected across several standard software projects during system testing phase with fault removal. Though the procedure is relatively complicated, the results depicted in this work suggest that Fully Recurrent Neural Networks (FRNN) exhibits an accurate and consistent behavior in reliability prediction.

The objective of this paper is to predict software reliability using non-parametric neural network of computational intelligence (CI). The study uses data sets containing failure history such as number of failures, failure time interval etc. In this paper, we explore the applicability of feed-forward neural network with back-propagation training as a reliability growth model for software reliability prediction. The prediction result is compared with that of traditional parametric software reliability growth models. The results described in the proposed model exhibits an accurate and consistent behavior in reliability prediction. The experimental results demonstrate that the proposed model provides a significant difference respect to accuracy and consistency.

Computational Intelligence has been known to be very useful in predicting software reliability. In this paper, two kinds of investigations are performed. First, we provide a systematic review of Software Reliability Prediction studies with consideration of various metrics, methods and CI techniques (including fuzzy logic, neural networks, genetic algorithms). Second, reliability prediction and data collection with the help of various available tools are discussed. The overall idea of this paper is to present, analyze, investigate, compare and discuss software reliability prediction with various CI techniques and tools and their advantages and disadvantages.