The sparse data of Web services Quality of Service (QoS) which is invoked by service users in Web service recommendation may lead to low recommendation quality. In order to solve the problem, a collaborative filtering based Web service Recommendation algorithm for User Group (WRUG) was proposed. Firstly, personalized similar user group was constructed for each service user according to user similarity matrix. Secondly, instead of the group, the center of similar user group was employed to compute the user group similarity matrix. Finally, Web service recommendation equation with user group was defined and missing QoS values of Web service were predicted for target user. And a dataset was used for experiments which included 1.97 million real-world Web QoS invocation records. Compared with Traditional Collaborative Filtering algorithm (TCF) and Collaborative Filtering recommendation algorithm Based on User Group Influence (CFBUGI), the mean absolute error of the proposed WRUG was decreased by 28.9% and 4.57% respectively, and the coverage rate of WRUG was increased by 110% and 22.5% separately. The experimental results show that the proposed WRUG can not only achieve better prediction accuracy of Web service recommendation system, but also noticeably enhance the percentage of valuable predicted QoS values under the same experimental settings.

Aiming at the shortage of current mobile Wireless Sensor Network (WSN) localization, a localization algorithm based on improved flooding broadcast mechanism and particle filtering was proposed. For a given unknown node, firstly, by the improved flooding broadcast mechanism, the effective average hop distance of an unknown node from its closest anchor node was used to calculate the distances to its all neighbor nodes. Then a differential error correction scheme was devised to reduce the measurement error accumulated over multiple hops for the average hop distance. Secondly, the particle filter and the virtual anchor node were used to narrow the prediction area, and more effective particle prediction area was obtained so as to further decrease the estimation error of the position of unknown node. The simulation results show that compared with DV-Hop, Monte Carlo Baggio (MCB) and Range-based Monte Carlo Localization (MCL) algorithms, the proposed positioning algorithm can effectively inhibit the broadcast redundancy and reduce the message overhead related to the node localization, and can achieve higher-accuracy positioning performance with lower communication cost.

The access request for computer network has the characteristics of real-time and dynamic change. In order to detect network intrusion in real time and be adapted to the dynamic change of network access data, a real-time detection framework for network intrusion was proposed based on data stream. First of all, misuse detection model and anomaly detection model were combined. A knowledge base was established by the initial clustering which was made up of normal patterns and abnormal patterns. Secondly, the similarity between network access data and normal pattern and abnormal pattern was measured using the dissimilarity between data point and data cluster, and the legitimacy of network access data was determined. Finally, when network access data stream evolved, the knowledge base was updated by reclustering to reflect the state of network access. Experiments on intrusion detection dataset KDDCup99 show that, when initial clustering samples are 10000, clustering samples in buffer are 10000, adjustment coefficient is 0.9, the proposed framework achieves a recall rate of 91.92% and a false positive rate of 0.58%. It approaches the result of the traditional non-real-time detection model, but the whole process of learning and detection only scans network access data once. With the introduction of knowledge base update mechanism, the proposed framework is more advantageous in the real-time performance and adaptability of intrusion detection.