Browsing by Author "Lin, Ken-Yu"

Now showing 1 - 2 of 2

Building a construction procurement negotiation training game model: Learning experiences and outcomes
(2014-11-01)
Dzeng, Ren-Jye
;
Lin, Ken-Yu
;
Wang, Pei-Ru
;
交大名義發表
;
National Chiao Tung University
Game-based education is a promising method for encouraging student learning. Although learning construction procurement and negotiation require hands-on practice, in most construction management courses at the college level, this subject is taught by using lectures and case studies. In this study, a construction procurement and negotiation game was developed, and paper-based and web-based versions were implemented. The game enables students to play the role of contractors or suppliers and generate profits by negotiating and procuring or selling reinforcing steel in a simulated market with a probabilistic nature. The experimental results indicate that playing both versions of the game increased student learning motivation, satisfaction and outcomes. Students awarded the web-based game higher assessment scores than they did for the paper-based game. Students playing either version of the game also achieved higher test scores than students who were taught using the traditional approach did. However, for students with work experience, playing the paper-based game resulted in higher scores than the web-based game scores.
Machine Learning Hyperparameter Fine Tuning Service on Dynamic Cloud Resource Allocation System - taking Heart Sounds as an Example
(2018-01-01)
Peng, Yu-Hsiang
;
Chuang, Chia-Chuan
;
Wu, Zhou-Jin
;
Chou, Chia-Wei
;
Chen, Hui-Shan
The hyperparameters tuning of machine learning has always been a difficult and time-consuming task in deep learning area. In many practical applications, the hyperparameter tuning directly affects the accuracy. Therefore, the tuning optimization of hyperparameters is an important topic. At present, hyperparameters can only be set manually based on experience, and use Violent Enumeration, Random Search or through Grid Search to try and error, lack of effective automatic search parameters. In this study, we proposed a machine learning hyperparameter fine tuning service on dynamic cloud resource allocation system, which leverages several mainstream hyperparameter tuning methods such as flyperopt and Optunity. In the meanwhile, various tuning methods are measured and compared by example application in this work. Finally, we dedicated actual case - Heart Sounds, and then tested it. In order to verify that the system service can not only automate the task of tuning, but also break through the limitation of the number of adjustable parameters. Furthermore the proposed hyperparameter fine tune system makes optimization process more efficient.