Li B.H.,Xian Electronic and Science University |
Liu S.Y.,Xian Electronic and Science University |
Li Z.G.,Xi'an Jiaotong University
Multimedia Tools and Applications | Year: 2011
As is well known, greedy algorithm is usually used as local optimization method in many heuristic algorithms such as ant colony optimization, taboo search, and genetic algorithms, and it is significant to increase the convergence speed and learning accuracy of greedy search in the space of equivalence classes of Bayesian network structures. An improved algorithm, I-GREEDY-E is presented based on mutual information and conditional independence tests to firstly make a draft about the real network, and then greedily explore the optimal structure in the space of equivalence classes starting from the draft. Numerical experiments show that both the BIC score and structure error have some improvement, and the number of iterations and running time are greatly reduced. Therefore the structure with highest degree of data matching can be relatively faster determined by the improved algorithm. © 2011 Springer Science+Business Media, LLC.
Liu J.,Xian Electronic and Science University |
Luo S.,Zhejiang University
2013 3rd International Conference on Consumer Electronics, Communications and Networks, CECNet 2013 - Proceedings | Year: 2013
This paper analyzes the present application of intelligent traffic light control systems and points out the advantages of controlling traffic lights according to the traffic information collected using video cameras. A novel method that recognizes the detection area based on Hough transformation, and computes the number of vehicles based on the detected boundaries between the windshields and the hoods is proposed. Furthermore, the time complexity of the image erosion algorithm involved is improved. Experiments indicate that the proposed procedure can achieve fast and high-precision recognition for crowded vehicles thus is efficient in practice. © 2013 IEEE.
Liu J.-W.,Xian Electronic and Science University |
Han B.-H.,Xian Electronic and Science University
Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science) | Year: 2014
In order to realize quick recovery for regular shredded paper with text, a feature matching algorithm based on the edge pixels of the broken pieces was proposed. Firstly, two-dimensional gray vectors were constructed through the analysis of the edge pixel points of the shredded paper images. Then, by introducing the similarity index of the pixel gray value, regular broken piece image based two-dimensional matching vectors for the gray values of edge pixel points were constructed. Additionally, a mathematical model for two-dimensional gray matching was built. Constraints on lines were introduced during the transversal matching for broken piece images to reduce longitudinal errors. Meanwhile, longitudinal matching was optimized to achieve a quick match for regular shredded paper with text. Simulation shows that, only 21(and 34) artificial adjustments were required to recover a Chinese (English) paperwork, composed of up to 209 pieces, during the matching process.