(ICICTA 2012)

The 2012 Fifth International Conference on Intelligent Computation Technology and Automation (ICICTA2012) aims to provide a high-level international forum for scientists, engineers, and educators to present the state of the art of intelligent computation technology and automation research and applications in diverse fields. The conference will feature plenary speeches given by renowned scholars and regular sessions with broad coverage. ICICTA 2012 was cosponsored by Intelligence Computation Technology and Automation Society, Hongkong and Changsha University of Science and Technology. It was held in Zhangjiajie, China, January 12–13, 2012. It has become an annual forum dedicated to the emerging and challenging topics in intelligent computation technology and automation. It is also expected that a synergy can be established between the academia and the industry, which will pave the way for further collaboration. Last year, ICICTA 2011 received about 2500 submissions from 14 countries and regions. All papers went through a rigorous peer review procedure and each paper received at least two review reports. On the basis of the review reports, the Program Committee finally selected about 800 highquality papers for presentation in ICICTA 2011 proceedings books. All accepted papers have been included in the proceedings of ICICTA2011 published by the IEEE computer society. Concurrency and computation plays an important role in computer and automation fields, and one of the main topics of ICICTA2012 (TOPIC A: Advanced Computation Theory and Application) really concerns the novel concurrent computation method and its application. ICICTA2012 organized this special issue to discuss the progress of the novel concurrent computation method and its application. Finally, we selected the 10 best papers recommended to Concurrency and Computation: Practice and Experience for special issue publication. Liu et al. [1] develop a layered classification method to detect malwares with a two-layer framework. The low-level-classifier is employed to identify whether the programs perform any malicious functions according to the API-calls of the programs; the up-level-classifier is applied to detect malwares according to the function identification. A hybrid structure — Type-Function — constituting of the classification results of low-level-classifier and up-level-classifier, is proposed to describe the malware. Zhao and Liang [2] study the intrinsic relationship between system throughput and fairness, and formulate a performance evaluation problem for packet scheduling algorithms in a wireless system. Through the use of nonlinear programming method, the performance evaluation framework for weighted-type packet scheduling algorithms can be established. Yang et al. [3] propose a nonintrusive packet layer model for quality assessment of voice over IP. Through a simple analysis on the packet headers of the bitstream, the information about the bit-rate and lost status is obtained for each frame. Tang et al. [4] propose an access rule transition matrix to model the access behavior of RRM, and apply it into the continuous-time Markov chain model. It is proved that the proposed model is equivalent to the original models assuming the random access strategy by simulation. Zhang and Yang [5] describe a vehicle positioning solution in urban environment with the aid of vehicle-to-vehicle network, which utilizes the existing roadside sensors of Vehicle-to-Vehicle (V2V) network. The designed localization scheme is based on angle of arrival measurements. Wan et al. [6] present an efficient method for bitstream extraction for scalable video based on simulated annealing. Following the same spirit as annealing, the proposed method searches for the optimized combination of quality layers for extraction through slowly reducing the simulated temperature according to the characteristics of frames in different temporal levels. Wang and Jia [7] discuss a new multiscale image segmentation algorithm based on the SVM approximation criteria in this paper. Most current multiscale image segmentation algorithms are based on the restricted empirica1 risk minimization, and the approximation of multiscale image segmentation was poor.