Search

Your search keyword '"Su, Mu‐Chun"' showing total 281 results
Start Over Author "Su, Mu‐Chun"
281 results on '"Su, Mu‐Chun"'

1. VSGM -- Enhance robot task understanding ability through visual semantic graph

Author

Tsai, Cheng Yu and Su, Mu-Chun

Subjects
Computer Science - Robotics, Computer Science - Artificial Intelligence, Computer Science - Computer Vision and Pattern Recognition
Abstract

In recent years, developing AI for robotics has raised much attention. The interaction of vision and language of robots is particularly difficult. We consider that giving robots an understanding of visual semantics and language semantics will improve inference ability. In this paper, we propose a novel method-VSGM (Visual Semantic Graph Memory), which uses the semantic graph to obtain better visual image features, improve the robot's visual understanding ability. By providing prior knowledge of the robot and detecting the objects in the image, it predicts the correlation between the attributes of the object and the objects and converts them into a graph-based representation; and mapping the object in the image to be a top-down egocentric map. Finally, the important object features of the current task are extracted by Graph Neural Networks. The method proposed in this paper is verified in the ALFRED (Action Learning From Realistic Environments and Directives) dataset. In this dataset, the robot needs to perform daily indoor household tasks following the required language instructions. After the model is added to the VSGM, the task success rate can be improved by 6~10%., Comment: 16 pages, 7 figures

Published
2021

7. The Jacobian Matrix-Based Learning Machine in Student

Author

Hsieh, Yi-Zeng, Su, Mu-Chun, Jeng, Yu-Lin, Hutchison, David, Series Editor, Kanade, Takeo, Series Editor, Kittler, Josef, Series Editor, Kleinberg, Jon M., Series Editor, Mattern, Friedemann, Series Editor, Mitchell, John C., Series Editor, Naor, Moni, Series Editor, Pandu Rangan, C., Series Editor, Steffen, Bernhard, Series Editor, Terzopoulos, Demetri, Series Editor, Tygar, Doug, Series Editor, Weikum, Gerhard, Series Editor, Huang, Tien-Chi, editor, Lau, Rynson, editor, Huang, Yueh-Min, editor, Spaniol, Marc, editor, and Yuen, Chun-Hung, editor

Published
2017
Full Text
View/download PDF

8. The Implementation of a Kinect-Based Postural Assessment System

Author

Su, Mu-Chun, Lin, Sheng-Hung, Lee, Shu-Fang, Huang, Yu-Shiang, Chen, Huang-Ren, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Weikum, Gerhard, Series editor, Chang, Carl K., editor, Chiari, Lorenzo, editor, Cao, Yu, editor, Jin, Hai, editor, Mokhtari, Mounir, editor, and Aloulou, Hamdi, editor

Published
2016
Full Text
View/download PDF

11. The Development of a Robot-Based Learning Companion: A User-Centered Design Approach

Author

Hsieh, Yi-Zeng, Su, Mu-Chun, and Chen, Sherry Y.

Abstract

A computer-vision-based method is widely employed to support the development of a variety of applications. In this vein, this study uses a computer-vision-based method to develop a playful learning system, which is a robot-based learning companion named RobotTell. Unlike existing playful learning systems, a user-centered design (UCD) approach is applied to assess the interface design of the RobotTell System so that the human-robot interaction can be enhanced during the design process. More specifically, the interface of the RobotTell system is assessed based on Nielsen's heuristics. Based on the results of Nielsen's heuristic evaluation, three versions of the RobotTell system were produced. The implications for the design of these three versions of the RobotTell system are discussed.

Published
2015
Full Text
View/download PDF

20. Design of an Interactive Table for Mixed-Reality Learning Environments

Author

Su, Mu-Chun, Chen, Gwo-Dong, Tsai, Yi-Shan, Yao, Ren-Hao, Chou, Chung-Kuang, Jinawi, Yohannes Budiono, Huang, De-Yuan, Hsieh, Yi-Zeng, Lin, Shih-Chieh, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Nierstrasz, Oscar, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Sudan, Madhu, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Vardi, Moshe Y., Series editor, Weikum, Gerhard, Series editor, Chang, Maiga, editor, Kuo, Rita, editor, Kinshuk, editor, Chen, Gwo-Dong, editor, and Hirose, Michitaka, editor

Published
2009
Full Text
View/download PDF

30. A self-learning neuro-fuzzy system

Author

DeClaris, Nicholas, Su, Mu-Chun, Goos, Gerhard, editor, Hartmanis, Juris, editor, van Leeuwen, Jan, editor, Antsaklis, Panos, editor, Kohn, Wolf, editor, Nerode, Anil, editor, and Sastry, Shankar, editor

Published
1995
Full Text
View/download PDF

41. Application of a SOM-based optimization algorithm in minimizing construction time for secant pile wall

Author

Chen, Jieh-Haur, Su, Mu-Chun, and Huang, De-Yuan

Subjects
Mathematical optimization -- Methods, Scheduling (Management) -- Methods, Construction and materials industries, Engineering and manufacturing industries, Science and technology
Abstract

Construction time matters for activities where rental equipment must be used. The building of a secant pile wall requires the rental of equipment and finding the optimal sequence to minimize the construction time is one way to lower construction costs. In this study we develop an effective and efficient optimization algorithm, which we call self-organizing feature map (SOM)- based optimization (SOMO), to minimize the construction time. The algorithm is applied to a case study to obtain the optimal sequences for both primary and secondary bored piles for a secant pile wall. The new SOMO algorithm is developed based on the ability of the human brain to produce topologically ordered mapping, so as to exploit better solutions via updating the weighting vectors of the neurons in a self-organizing topological way that occurs in the evolution of the feature map for optimization. Given detailed building time of the 16 activities of each bored pile, we find that 143.92 h or 27.21% of the original construction can be saved. The optimal sequences for both primary and secondary bored piles are also determined. The practicability of the SOMO algorithm is substantiated. DOI: 10.1061/(ASCE)CO.1943-7862.0000222 CE Database subject headings: Construction management; Optimization; Walls; Piles; Time factors. Author keywords: Construction time; Optimization; Self-organizing feature map (SOM); Secant pile wall; SOMO algorithm; Optimal sequencing.

Published
2010

Catalog

Books, media, physical & digital resources
See catalog results