http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A Hybrid Computational Intelligence Approach for the VRP Problem
Gang PENG,Kehan ZENG,Xiong YANG 한국정보기술융합학회 2013 JoC Vol.4 No.2
PGQ, a novel hybrid computational intelligence approach, in which Particle Swarm Optimization (PSO), Genetic Algorithm (GA) and quantum computation are integrated, is proposed to solve the Vehicle Routing Problem (VRP). In PSO, a quantum approach called QUP is proposed to update the particles. GA operators are employed to improve population quality. The simulation results indicate that the PGQ algorithm is very effective and is better than simple PSO and GA as well as PSO and GA mixed algorithm.
Occluded and Low Resolution Face Detection with Hierarchical Deformable Model
Xiong Yang,Gang Peng,Zhaoquan Cai,Kehan Zeng 한국정보기술융합학회 2013 JoC Vol.4 No.2
This paper presents a hierarchical deformable model for robust human face detection, especially with occlusions and under low resolution. By parsing, we mean inferring the parse tree (a configuration of the proposed hierarchical model) for each face instance. In modeling, a three-layer hierarchical model is built consisting of six nodes. For each node, an active basis model is trained, and their spatial relations such as relative locations and scales are modeled using Gaussian distributions. In computing, we run the learned active basis models on testing images to obtain bottom-up hypotheses, followed by explicitly testing the compatible relations among those hypotheses to do verification and construct the parse tree in a top-down manner. In experiments, we test our approach on CMU+MIT face test set with improved performance obtained.
A Secure Fingerprinted Multimedia Distribution Using Social Network Analysis
Cong-huan Ye,Zeng-gang Xiong,Yao-ming Ding,Xueming Zhang,Guangwei Wang,Fang Xu 보안공학연구지원센터 2016 International Journal of Security and Its Applicat Vol.10 No.4
Collusion attack is a very effective attack for digital fingerprinting system. In order to remove or attenuate the fingerprint information hidden in fingerprinted content, a number of users produce a new colluded copy through their own fingerprinted copies. In this paper, we address a novel collusion-resisting desynchronization fingerprinting approach using social network analysis. The novelty of this paper is that collusion attack occurred in a multimedia social network community with high probability. Different from all existing works, with desynchronization model constructed upon social network, the original image is desynchronized to get many similar copies which are different from each other, and then they are assigned and distributed to subscribers according to social network analysis. Theory analysis shows that the presented desynchronization distribution method has significantly better performance than those existing distribution schemes. The experimental results also show that the average colluded images even with only two desynchronized copies have poor visual quality. And the visual quality of colluded images does not improve apparently with the increase of the number of copies.
Cong-huan Ye,Zeng-gang Xiong,Yao-Ming Ding,Xueming Zhang,Guangwei Wang,Fang Xu 보안공학연구지원센터 2016 International Journal of Multimedia and Ubiquitous Vol.11 No.7
Average collusion attack is a very effective attack for digital fingerprinting system. Moreover, the commercial value of the colluded content is often time-sensitive. The more profit the colluder will make from it when the colluded copy is distributed earlier. This paper presents a new collusion-resilience approach with recursive chaotic desynchronization and social network. It has processed chaotic transformations due to random image grid based on chaos. The experimental results show that collusion even with only two copies results in degradation of the image metric, even if those traitors try to resynchronization using image registration technology. However, it will take expensive computational cost to do that, and the visual quality is degraded expensively with the increase of the number of fingerprinted copies.