Trustworthiness is an important indicator for service selection and recommendation in the cloud environment. However, predicting the trust rate of a cloud service based on its multifaceted quality of services (QoSs) is not an easy task due to the complicated and non-linear relations between service's QoS values and the final trust rate of the service. According to the existing studies, the adoption of intelligent technique is a rational way to attack this problem. Neural network (NN) has been validated as an effective way to predict the trust rate of the service. However, the parameter setting of NN, which plays an important role in its prediction performance, has not been properly addressed yet. In the paper, particle swarm optimization (PSO) is introduced to enhance NN by optimizing its initial settings. In the proposed hybrid prediction algorithm named PSO-NN, PSO is used to search the appropriate parameters for NN so as to realize accurate trust prediction of cloud services. In order to investigate the effectiveness of PSO-NN, extensive experiments are performed based on public QoS data set, as well as in-depth comparison analysis. The results show that our proposed approach has better performance than basic classification methods in most cases, and significantly outperforms the basic NN in the terms of prediction precision. In addition, PSO-NN demonstrates better stability than the basic NN.

Random testing (RT) is considered important owing to the popularity of fuzzing techniques. Yet, its effectiveness has been questioned because it disregards the property that failures are usually conglomerated. Adaptive random testing (ART) has been developed to spread the test cases more evenly. A set of candidate test cases is first generated randomly. Then, the candidate farthest from the executed test cases is selected as the next test case. However, this process is time-consuming, especially for object-oriented programs. In order to improve the efficiency, a forgetting strategy may be added, taking into account only part of the executed test cases. Of course, the failure detection capability is compromised. In this paper, we propose a new approach that improves the efficiency of object-oriented program testing through K-means clustering. Frequency transform and improved wavelet transform are adopted to better determine the dissimilarity of test cases. Two measures, namely, the wavelet transform (WT) metric and the trisection frequency conversion (TFC) metric, are proposed. Based on the metrics, we develop two algorithms called WClustering-ART and TFClustering-ART. Experimental studies and statistical analysis have been conducted to evaluate the F-measure and the Fm-time of our approach. The results show that both algorithms demonstrate better effectiveness and efficiency than RT and object-oriented ART algorithms with forgetting.