In this paper, we propose a context-awareness based personalized recommender system in the pervasive application space. The recommender system comprises the personalized recommender engine and the distributed context management framework. With a hybrid approach, the personalized recommender engine combines those contexts into the decisions on recommendations to get more comprehensive recommendation effectiveness. In contrast with existing middleware of context-awareness, the recommender system has an ability of user-centric recommendation. At the end of this paper, an emphasis is put on the metrics of the effectiveness of the recommender system.

In order to improve the accuracy of the image segmentation in video surveillance sequences and to overcome the limits of the traditional clustering algorithms that can not accurately model the image data sets which Contains noise data, the paper presents an automatic and accurate video image segmentation algorithm, according to the spatial properties, which uses the Gaussian mixture models to segment the image. But the expectation-maximization algorithm is very sensitive to initial values, and easy to fall into local optimums, so the paper presents a differential evolution-based parameters estimation for Gaussian mixture models. The experiment result shows that the segmentation accuracy has been improved greatly than by the traditional segmentation algorithms.