S
Shun-Feng Su
Researcher at National Taiwan University of Science and Technology
Publications - 256
Citations - 5987
Shun-Feng Su is an academic researcher from National Taiwan University of Science and Technology. The author has contributed to research in topics: Fuzzy control system & Fuzzy logic. The author has an hindex of 35, co-authored 231 publications receiving 4358 citations. Previous affiliations of Shun-Feng Su include National Taiwan Normal University & Purdue University.
Papers
More filters
Book ChapterDOI
iPhone as Multi-CAM and Multi-viewer
TL;DR: The proposed system can be provides four iPhones or iPads to catching and watching the current images by the WiFi networks and the resolution of images and frame per second are also adjusted by the traffics of WiFi networks.
Journal ArticleDOI
Practically Predefined-Time Adaptive Fuzzy Tracking Control for Nonlinear Stochastic Systems.
TL;DR: In this paper , a semiglobally practically predefined-time adaptive fuzzy tracking control algorithm is proposed with a fuzzy system used to approximate the unknown part of the system, where the settling time can be arbitrarily adjusted in a mean value sense, and such freedom can be used to improve the stochastic finite/fixed-time control results.
Journal ArticleDOI
Adaptive asymptotic tracking control for nonlinear systems with state constraints and input saturation
TL;DR: In this paper , an adaptive asymptotic tracking control scheme is designed for strict-feedback nonlinear systems with state constraints and input saturation, where fuzzy logic systems and command filtered technique are applied to handle the uncertainties and the problem of complexity explosion in adaptive backstepping method, respectively.
Journal ArticleDOI
Adaptive asymptotic tracking control for multi-input and multi-output nonlinear systems with unknown hysteresis inputs
TL;DR: In this paper , a novel adaptive asymptotic tracking control strategy is proposed for multi-input and multi-output nonlinear systems with unknown backlash-like hysteresis inputs, where the dependence on the system model is removed through fuzzy logic systems and elaborately designed adaptive laws.
Proceedings ArticleDOI
Analysis of Layer Efficiency and Layer Reduction on Pre-Trained Deep Learning Models
TL;DR: This work exploits the activation and gradient output and weight in each layer of the pre-trained models to measure its efficiencies and estimates the efficiencies using measurements and uses the method for continuous layer reductions for validation.