LS-SVM's no-reference video quality assessment model under the Internet of things

The Internet of things, including Internet technology, including wired and wireless networks. The purpose of QOS-QOE energy saving optimization model for wireless sensor networks is to define and study the QOS-QOE energy saving optimization modeling problem of WSN networks. The main content is the research object of QOS-QOE wireless sensor network. The main research method is to find such key problems in QOS-QOE modeling of wireless sensor network, usually the objective function is the key issue, mainly uses the ant colony algorithm, genetic algorithm, SVM+PCA and LS-SVM and LIBSVM artificial neural network method. The four key technologies of the Internet are widely used, and these four technologies are mainly RFID, WSN, M2M, two kinds of integration. RFID can be implemented using MATLAB, NS2, and JAVA, and WSN can be implemented using NS2, and M2M can be developed using JAVA. In this paper, we investigate on the QOE and packet loss rate of the network because QOE is important in the network and packet loss rate is the key point in many papers. In order to have a better evaluate of video quality which through the network transmission, build NS2+MyEvalvid simulation platform, extract features, using Least squares support vector machine method to establish no-reference video quality assessment model considering the network packet loss. The experimental results show that, LS-SVM's training speed is fast, the model is more accurate than the other models.