Recently, the Internet of Things （loT） has attracted more and more attention. Multimedia sensor network plays an important role in the IoT, and audio event detection in the multimedia sensor net- works is one of the...Recently, the Internet of Things （loT） has attracted more and more attention. Multimedia sensor network plays an important role in the IoT, and audio event detection in the multimedia sensor net- works is one of the most important applications for the Internet of Things. In practice, it is hard to get enough real-world samples to generate the classifi- ers for some special audio events （e.g., car-crash- ing in the smart traffic system）. In this paper, we introduce a TrAdaBoost-based method to solve the above problem. By using the proposed approach, we can train a strong classifier by using only a tiny amount of real-world data and a large number of more easily collected samples （e.g., collected from TV programs）, even when the real-world data is not sufficient to train a model alone. We deploy this ap- proach in a smart traffic system to evaluate its per- formance, and the experiment evaluations demonstrate that our method can achieve satisfying results.展开更多
Privacy is an important issue in electronic voting. The concept of ＇full privacy＇ in electronic voting was firstly proposed, not only the privacy of voters is concerned, but also the candidates＇. Privacy preserving...Privacy is an important issue in electronic voting. The concept of ＇full privacy＇ in electronic voting was firstly proposed, not only the privacy of voters is concerned, but also the candidates＇. Privacy preserving electronic election architecture without any trusted third party is presented and a general technique for k-out-of-m election based on distributed E1Gamal encryption and mix-match is also provided. The voters can compute the result by themselves without disclosing their will and the vote of the losing candidates. Moreover, whether the vote of winner candidate is more than a half can be verified directly. This scheme satisfies ＇vote and go＇ pattern and achieves full privacy. The correctness and security are also analyzed.展开更多
This paper presents a novel trust model based on multiple decision factor theory （MDFT） and a trust routing algorithm based on MDFT to exactly evaluate routing node trust and establish a trustworthy routing path. MD...This paper presents a novel trust model based on multiple decision factor theory （MDFT） and a trust routing algorithm based on MDFT to exactly evaluate routing node trust and establish a trustworthy routing path. MDFT integrates four dimensional trust decision factors including behavior, state, recommend and node liveness to realize an exactly finer-grained trust evaluation. On the basis of MDFT, a trust routing algorithm is presented and validated in open shortest path first （OSPF） protocol. Simulation resuRs show that the algorithm can reflect the routing node trust accurately and has better dynamic response ability. Under the circumstance of existing deceptive nodes, the algorithm has better anti-deception performance and higher attack node detection rate than conventional algorithm.展开更多
基金supported by the National Natural Science Foundation of China(No.60821001)the National Basic Research Program of China(No.2007CB311203)
文摘Recently, the Internet of Things （loT） has attracted more and more attention. Multimedia sensor network plays an important role in the IoT, and audio event detection in the multimedia sensor net- works is one of the most important applications for the Internet of Things. In practice, it is hard to get enough real-world samples to generate the classifi- ers for some special audio events （e.g., car-crash- ing in the smart traffic system）. In this paper, we introduce a TrAdaBoost-based method to solve the above problem. By using the proposed approach, we can train a strong classifier by using only a tiny amount of real-world data and a large number of more easily collected samples （e.g., collected from TV programs）, even when the real-world data is not sufficient to train a model alone. We deploy this ap- proach in a smart traffic system to evaluate its per- formance, and the experiment evaluations demonstrate that our method can achieve satisfying results.
基金supported by the National Natural Science Foundation of China (61121061)China High Technology Development Project (NDRC)
文摘Privacy is an important issue in electronic voting. The concept of ＇full privacy＇ in electronic voting was firstly proposed, not only the privacy of voters is concerned, but also the candidates＇. Privacy preserving electronic election architecture without any trusted third party is presented and a general technique for k-out-of-m election based on distributed E1Gamal encryption and mix-match is also provided. The voters can compute the result by themselves without disclosing their will and the vote of the losing candidates. Moreover, whether the vote of winner candidate is more than a half can be verified directly. This scheme satisfies ＇vote and go＇ pattern and achieves full privacy. The correctness and security are also analyzed.
基金supported by the National Natural Science Foundation of China (61121061, 61161140320)The National Key Technology R&D Program (2012BAH38B02)
文摘This paper presents a novel trust model based on multiple decision factor theory （MDFT） and a trust routing algorithm based on MDFT to exactly evaluate routing node trust and establish a trustworthy routing path. MDFT integrates four dimensional trust decision factors including behavior, state, recommend and node liveness to realize an exactly finer-grained trust evaluation. On the basis of MDFT, a trust routing algorithm is presented and validated in open shortest path first （OSPF） protocol. Simulation resuRs show that the algorithm can reflect the routing node trust accurately and has better dynamic response ability. Under the circumstance of existing deceptive nodes, the algorithm has better anti-deception performance and higher attack node detection rate than conventional algorithm.
