Cai Qingling

A Minimalist Mutual Authentication Protocol for RFID System & BAN Logic Analysis

This paper proposes a new security protocol with satisfying the lightweight requirements of the security of RFID system - A Minimalist Mutual Authentication Protocol for RFID System Based on EPC C1G2 Standard. The scheme makes sufficiently use of the limited resources of RFID system to encrypt, decrypt and implement mutual authentication between readers and tags, Then the paper gives qualitative analysis against various security attacks and BAN logic analysis of the security of the protocol. The results demonstrate that the protocol can effectively solve the security problem of RFID system based on C1G2 standard.

Application of arti cial bee colony optimization algorithm in complex blind separation source

Aiming at the key technologies of number estimation and ordered recovery of complex-valued signals, a method of complex blind source separation with an unknown number of sources based on artificial bee colony optimization was proposed. Firstly, we introduced an algorithm based on cross validation technology to estimate number of sources. Then, the optimally extracted vectors were determined through maximizing absolute value of kurtosis by using artificial bee colony optimization, so as to separate complex-valued signals one by one. The simulation results show that the proposed method can achieve the blind separation for source signals of any distribution in decreasing order of absolute kurtosis, and compared to other conventional algorithms, this method has preferable estimating performancee. In addition, we considered the underdetermined complex blind source separation problem of instantaneous mixtures based on kurtosis. The cost function of the extracted vector in the underdetermined mixed case was constructed by exploiting the statistics properties of complex-valued source signals, and then artificial bee colony optimization algorithm was used to maximize the function to determine the optimally extracted vectors. The underdetermined complex blind source separation was achieved through many times of extracting. The simulation result of blind separation of different types of signals validates the feasibility of the proposed method.

Activity Recognition in Smart Homes

In recent years, activity recognition in smart homes is an active research area. It is an important problem of Human Computer Interaction (HCI), and has many applications in HCI, such as assistive living and healthcare. Recognition of users’ common behaviors allows an environment to provide personalized service. Unlike activity recognition in computer vision which uses cameras, it studies activities by embedded sensors in smart homes. In this paper, we propose a method to extract latent features from sensor data by Beta Process Hidden Markov Model (BP-HMM). The contributions of our method are twofold: 1, we extend BP-HMM by dependent Beta process, and integrate state constraints of sensors into the sampling process of BP-HMM. 2, we extract latent features automatically by our dependent BP-HMM, and train a structural support vector machine (SVM) by these features in a supervised way for activity recognition. To evaluate the proposed method, we performed experiments on the real-world smart home datasets. Our results suggest that extracting latent features from sensor data leads to good performance for activity recognition.

Recognizing human actions by two-level Beta process hidden Markov model

We propose a method for human action recognition using latent topic models. There are two main differences between our method and previous latent topic models used for recognition problems. First, our model is trained in a supervised way, and we propose a two-level Beta process hidden Markov model which automatically identifies latent topics of action in video sequences. Second, we use the human skeleton to refine the spatial–temporal interest points that are extracted from video sequences. Because latent topics are derived from these interest points, the refined interest points can improve the precision of action recognition. Experimental results using the publicly available “Weizmann”, “KTH”, “UCF sport action”, “Hollywood2”, and “HMDB51” datasets demonstrate that our method outperforms other state-of-the-art methods.