International Journal of Intelligent Engineering and Systems

7

Authors: Hongbing Zhu, Chengdong Pu, Jinguang Gu

Particle swarm optimization (PSO) is a swarm intelligence algorithm, has been successfully applied to many engineering optimization problems and shown its high search speed in these applications. However, as the dimension and the number of local optima of optimization problems increase, PSO and most existing improved PSO algorithms such as, the standard particle swarm optimization (SPSO) and the Gaussian particle swarm optimization (GPSO), are easily trapped in local optima. In this paper we proposed a novel algorithm based on SPSO called Euclidean particle swarm optimization (EPSO) which has greatly improved the ability of escaping from local optima. To confirm the effectiveness of EPSO, we have employed five benchmark functions to examine it, and compared it with SPSO and GPSO. The experiments results showed that EPSO is significantly better than SPSO and GPSO, especially obvious in higher-dimension problems. As one of tis application, we applied EPSO to the structure prediction of toy model both on artificial and real protein sequences. Predicting the structure of protein through its sequence of amino acids is a complex and challenging problem in computational biology. Though toy model is one of the simplest and effective models, it is still extremely difficult to predict its structure as the increase of amino acids. The experimental results demonstrated that EPSO was efficient in protein structure prediction problem in toy model.

10

Authors: Sang Haifeng, Chen Yu, Chen Zhong

Compared with several methods of extraction from static background of video, and for the limitations of these methods, a new type of method is put forward for updating background extraction. In this method background weight is thought as a standard of reliability to evaluation background by introducing a new parameter value and its variation, and is anticipated to maintain or upgrade the numerical size control background. For each frame image of two judges, the image elements will be classified, and the variation of background weights will be produced separately, control weight by weight change background. The experimental results show that this method has the advantages of simple principle, fast operation, updates faster and anti-interference ability of the foreground, and can be adapted to different circumstances in background extraction through adjusting the setting parameter.

9

Authors: Yuto Takeda, Yasuo Musashi, Kenichi Sugitani, Toshiyuki Moriyama

We statistically investigated the total ANY resource record (RR) based DNS query request packet traffic from the Internet to the top domain DNS server in a university campus network from January 1st, 2011 to December 31st, 2012. The obtained results are: (1) we found a significant increase in the inbound ANY RR based DNS query request traffic at November 28th, 2011. (2) In the DNS query request packet traffic, we observed only a query keyword of the campus domain name. (3) We found a correlation between the total inbound DNS query request packet traffic and the DNS query request packet traffic including the query keyword. (4) We also carried out the loading test sending ANY, A, and PTR RRs based unique DNS queries to a test DNS server, however, we observed no difference among the vmstat parameters based on the queries, and the load value was only 0.10-0.20. These results indicate that the ANY RR based DNS request packet traffic is quite strange. Therefore, we should pay much attention to the ANY RR based DNS query request traffic including the single domain name.