SendrenSheng-Dong Xu

Prof. SendrenSheng-Dong Xu

Department of Power Mechanical Engineering, National Tsing Hua University, Hsinchu, Taiwan
orcid

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 August 2022 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
Long JinLong Jin
Long Jin
FZFan Zhang
Fan Zhang
MLMei Liu
Mei Liu
SendrenSheng-Dong XuSendrenSheng-Dong Xu
SendrenSheng-Dong Xu
Most schemes of trajectory tracking control of redundant manipulators consider only the position of the end-effector with little regard for its orientation, and reduce the feasible region of decision variables when introducing multiple levels of joint limits. To remedy these weaknesses, this article constructs a model predictive tracking control of position and orientation (MPTCPO) scheme for redundant manipulators, which is able to achieve the simultaneous control of position and orientation of the end-effector. The proposed MPTCPO scheme simultaneously minimizes the tracking error, joint-velocity norm, and joint-acceleration norm. In the meantime, it directly handles three levels of joint limits of joint angle, joint velocity, and joint acceleration without reducing the feasible region of decision variables without conversion required. In addition, a finite-time convergent neural dynamics (FTCND) model is designed to find the optimal solution of the proposed scheme. Computer simulations and physical experiments confirm the feasibility and accuracy of the proposed MPTCPO scheme solved by the FTCND model.

19 January 2019 in Applied Sciences
Verified
Journal Article
Open access
PDF file
SendrenSheng-Dong XuSendrenSheng-Dong Xu
SendrenSheng-Dong Xu
CCChun-Chao Chang
Chun-Chao Chang
CSChien-Tien Su
Chien-Tien Su
PPPham Quoc Phu
Pham Quoc Phu
This paper discusses using computer-aided diagnosis (CAD) to distinguish between hepatocellular carcinoma (HCC), i.e., the most common type of primary liver malignancy and a leading cause of death in people with cirrhosis worldwide, and liver abscess based on ultrasound image texture features and a support vector machine (SVM) classifier. Among 79 cases of liver diseases including 44 cases of liver cancer and 35 cases of liver abscess, this research extracts 96 features including 52 features of the gray-level co-occurrence matrix (GLCM) and 44 features of the gray-level run-length matrix (GLRLM) from the regions of interest (ROIs) in ultrasound images. Three feature selection models—(i) sequential forward selection (SFS), (ii) sequential backward selection (SBS), and (iii) F-score—are adopted to distinguish the two liver diseases. Finally, the developed system can classify liver cancer and liver abscess by SVM with an accuracy of 88.875%. The proposed methods for CAD can provide diagnostic assistance while distinguishing these two types of liver lesions.

19 August 2019 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
SendrenSheng-Dong XuSendrenSheng-Dong Xu
SendrenSheng-Dong Xu
Hsu-Chih HuangHsu-Chih Huang
Hsu-Chih Huang
YKYu-Chieh Kung
Yu-Chieh Kung
YCYung-Yu Chu
Yung-Yu Chu
This paper presents a networked multirobot cyber-physical system (CPS) that employs artificial immune fuzzy optimization to achieve distributed formation control of embedded mobile robots. The artificial immune system (AIS) algorithm is combined with fuzzy system to develop a hybrid optimization technique, called AIS-fuzzy. This metaheuristics is applied to design the intelligent 3rd cyber and 4th cognition levels in the networked multirobot CPS 5C structure of embedded robots to accomplish distributed formation control. The proposed CPS cyber and cognition levels with AIS-fuzzy paradigm incorporate with the first, second and fifth levels by means of robotic sensors and actuators. A broadcast leader-follower distributed control approach is presented to avoid the communication delay issues found in traditional graph theory based consensus multirobot CPSs under a directed network topology. SoPC (System-on-a-Programmable-Chip) methodology is adopted to present a pragmatic networked multirobot CPS in the field-programmable gate array (FPGA) chips. The presented SoPC-based AIS-fuzzy multirobot CPS features the seamless integration of computation, networking, and physical robotic processes. Experimental results are obtained, and comparative analyses are provided to illustrate the effectiveness and merits of the proposed multirobot CPS to perform distributed formation control of embedded mobile robots.

16 January 2023 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
GZGuangyu Zhu
Guangyu Zhu
JDJiacun Ding
Jiacun Ding
YWYun Wei
Yun Wei
YYYang Yi
Yang Yi
SendrenSheng-Dong XuSendrenSheng-Dong Xu
SendrenSheng-Dong Xu
EQEdmond Qwu
Edmond Qwu
Urban rail transit (URT) is vulnerable to natural disasters and social emergencies including fire, storm and epidemic (such as COVID-19), and real-time origin-destination (OD) flow prediction provides URT operators with important information to ensure the safety of URT system. However, hindered by the high dimensionality of OD flow and the lack of supportive information reflecting the real-time passenger flow changes, study in this area is at the beginning stage. A novel model consisting of two stages is proposed for OD flow prediction. The first stage predicts the inflows of all stations by Long Short-Term Memory (LSTM) in real time, where the dimension is reduced compared with predicting OD flows directly. In the second stage, the notion of separation rate, namely, the proportion of inbound passengers bounding for another station, is estimated. Finally, The OD flow is predicted by multiplying the inflow and separation rate. Experiments based on Hangzhou Metro dataset show the proposed model outperforms the contrast model in weighted mean average error (WMAE) and weighted mean square error (WMSE). Results also suggest that the proposed prediction model performs better on weekdays than on weekends, and with greater accuracy on larger OD flows.

28 May 2018 in Applied Sciences
Verified
Journal Article
Open access
PDF file
SCSheng-Yi Chiu
Sheng-Yi Chiu
CCChung-Cheng Chiu
Chung-Cheng Chiu
SendrenSheng-Dong XuSendrenSheng-Dong Xu
SendrenSheng-Dong Xu
Background subtraction is a mainstream algorithm for moving object detection in video surveillance systems. It segments moving objects by using the difference between the background and input images. The key to background subtraction is to establish a reliable initial background. In this study, we propose a background subtraction algorithm based on category entropy analysis that dynamically creates color categories for each pixel in the images. The algorithm uses the concept of a joint category to build background categories that can adapt to the color disturbance of the background. Furthermore, in order to overcome dynamic background environments, this paper proposes the concept of color category entropy to estimate the number of necessary background categories and establish sufficient and representative background categories to adapt to dynamic background environments. In addition, recent mainstream methods for background subtraction were implemented and analyzed in comparison with our algorithm.

1 June 2014 in IET Control Theory & Applications
Verified
Journal Article
Open access
PDF file
SendrenSheng-Dong XuSendrenSheng-Dong Xu
SendrenSheng-Dong Xu
YLYi‐Kuo Liu
Yi‐Kuo Liu
This study studies the fault‐tolerant control (FTC) design based on the Takagi‐Sugeno (T‐S) fuzzy system models and terminal‐sliding‐mode control (TSMC). This hybrid scheme can keep the advantages of both methods. By using the T‐S fuzzy models to approximate the original non‐linear system, the online computation burden can be alleviated since most of the T‐S parameters can be offline computed. Moreover, TSMC not only owns the merits, including robustness to uncertainties and/or disturbances, fast response and easy implementation, but also performs better than conventional sliding‐mode control (SMC) since the system states of TSMC will converge in finite time to the control objective point, that is, equivalent point, after the system states intersect sliding surface. Both of the active and passive FTC design schemes are presented. The proposed analytical results are also applied to the FTC for the attitude stabilisation of a spacecraft. Simulation results demonstrate the benefits of the proposed scheme.