Browsing by Author "Cheng, Hsin-Jung"

Now showing 1 - 2 of 2

EDGE-COMPUTING CONVOLUTIONAL NEURAL NETWORK WITH HOMOGRAPHY-AUGMENTED DATA FOR FACIAL EMOTION RECOGNITION
(2019-01-01)
Li, Yan-Ying
;
Cheng, Hsin-Jung
;
Liu, Yen
;
Shen, Chih-Tsung
;
資訊工程學系
We design a convolutional neural network with homography-augmented data to deal with facial emotion recognition applications. Different to other convolutional neural networks, our AsicNet is well-designed for embedded CPU and even aiming for ASIC, such as Intel Movidius VPU. We adjust the architecture of our AsicNet and train our AsicNet on the GPU server, meanwhile we consider the computation costs of embedded systems and ASICs. Moreover, we reconsider the deep learning flow and train the homography-augmented data so as to reach higher accuracy. Experimental results on both FER2013 anf JAFFE face datasets show that our AsicNet can not only have high accuracy (72:42% on FER2013; 99:82% on JAFFE) as compared to the state-of-arts but also reach 41.22 millisecond (24.26 FPS) on the embedded CPU and 15.25 millisecond (65.57 FPS) on Intel Movidius VPU to tell the facial emotion from a face image.
Mufti-objective optimal planning for designing relief delivery systems
(2007-11-01)
Tzeng, Gwo-Hshiung
;
Cheng, Hsin-Jung
;
Huang, Tsung Dow
;
科技管理研究所
;
Institute of Management of Technology
The fatal earthquake on September 21, 1999 caused significant damages to Taiwan, which made the national government focus on strengthening relief systems regarding natural disasters. Disaster prevention, protection, and reconstruction are the major areas of focus to reduce human suffering and damage from disasters. A key point is the ability to enhance the distribution of relief materials effectively. In this study, we construct a relief-distribution model using the mufti-objective programming method for designing relief delivery systems in a real case. The model features three objectives: minimizing the total cost, minimizing the total travel time, and maximizing the minimal satisfaction during the planning period. The first two objectives pursue the efficiency goal, whereas the third pursue fairness-making best effort to ensure relief commodity delivery to all demand points. Results of an empirical study are presented and suggestions are given for future research. (C) 2007 Elsevier Ltd. All rights reserved.