【Title】A Squeezed Artificial Neural Network for the Symbolic Network Reliability Functions of Binary-State Networks
【Speaker】Dr. Wei-Chang Yeh
【Host】Dr. Yanfu Li
【Time】10:00-11:00am, May 18th (Friday), 2018
【Venue】Room N412, Shunde Building

【Abstract】Network reliability is an important index to the provision of useful information for decision support in the modern world. There is always a need to calculate symbolic network reliability functions (SNRFs) due to dynamic and rapid changes in network parameters. In this brief, the proposed squeezed artificial neural network (SqANN) approach uses the Monte Carlo simulation to estimate the corresponding reliability of a given designed matrix from the Box-Behnken design, and then the Taguchi method is implemented to find the appropriate number of neurons and activation functions of the hidden layer and the output layer in ANN to evaluate SNRFs. According to the experimental results of the benchmark networks, the comparison appears to support the superiority of the proposed SqANN method over the traditional ANN-based approach with at least 16.6% improvement in the median absolute deviation in the cost of extra 2 s on average for all experiments.
 
【Short Bio】Yeh is currently a distinguished professor of the Department of Industrial Engineering and Engineering Management at Tsing Hua University in HsinChu,Taiwan. He received his M.S. and Ph.D. from the Department of Industrial Engineering at the University of Texas at Arlington. The majority of his research is focused around algorithms, including exact solution methods and soft computing. He has published more than 250 research papers in highly ranked journals and conference papers and has been awarded the Outstanding Research Award twice, the Distinguished Scholars Research Project once, and an Overseas Research Fellowship twice by the Ministry of Science and Technology in Taiwan. He has been invited to serve as an Associate Editor of the two top reliability related journals, namely, the IEEE Transactions on Reliability and Reliability Engineering & System Safety. He proposed a novel soft computing algorithm called the simplified swarm optimization (SSO) and demonstrated the simplicity, effectiveness, and efficiency of his SSO for solving NP-hard problems. He has been granted 50 patents and ear an International Fellow, the Guoguang Invention Medal as well as the titles of Outstanding Inventor of Taiwan and Doctor of Erudition, by the Chinese Innovation and Invention Society.