J
Jeng-Shyang Pan
Researcher at Shandong University of Science and Technology
Publications - 889
Citations - 14887
Jeng-Shyang Pan is an academic researcher from Shandong University of Science and Technology. The author has contributed to research in topics: Digital watermarking & Computer science. The author has an hindex of 50, co-authored 789 publications receiving 11645 citations. Previous affiliations of Jeng-Shyang Pan include National Kaohsiung Normal University & Technical University of Ostrava.
Papers
More filters
Book ChapterDOI
Directional Discriminant Analysis for Image Feature Extraction
TL;DR: In this article, a novel subspace learning algorithm based on nearest feature line and directional derivative gradient is proposed in order to extract the local discriminant features of the samples and a discriminant power criterion is used to find the most discriminant direction.
Book ChapterDOI
A Cooperative Evolution Framework Based on Fish Migration Optimization
TL;DR: In this article , a cooperative evolution framework based on fish migration optimization (CEFMO) is proposed, which divides the whole swarm into several subsets and introduces an evaluation function, at the end of each iteration, all the individuals are evaluated and when the evaluation result meets the conditions, the cooperative evolution is triggered.
Journal ArticleDOI
Joint Channel Pruning and Quantization-Based CNN Network Learning with Mobile Computing-Based Image Recognition
TL;DR: In this article, a target detection network was designed for hardware platforms with limited computing resources, using pruning and quantization methods to compress, and demonstrate in VOC dataset and RSOD dataset on the actual hardware platform.
Book ChapterDOI
Chromatographic Peak Identification Based on Bayesian Classification Model
TL;DR: In this paper, a chromatographic peak recognition algorithm for dissolved gas in transformer oil based on continuous Bayesian classification model was proposed to solve the problems of peak shift and baseline jitter after longterm operation of the transformer oil chromatography online monitoring device.
Journal Article
Petri Nets Based Max-flow/Min-cut Modeling and Analyzing
TL;DR: Algorithms for generating models from a given flow network and its residual network are introduced based on the PNs theory and combined to simulate the classic Ford-Fulkerson for solving the max-flow/min-cut and finding flow distributions when themax-flow achieves.