Browsing by Author "Lee, Tzu-Chang"

Now showing 1 - 2 of 2

An agent-based model for queue formation of powered two-wheelers in heterogeneous traffic
(2016-11-01)
Lee, Tzu-Chang
;
Wong, K. I.
;
運輸與物流管理系註：原交通所+運管所
;
Department of Transportation and Logistics Management
This paper presents an agent-based model (ABM) for simulating the queue formation of powered two-wheelers (PTWs) in heterogeneous traffic at a signalized intersection. The main novelty is that the proposed interaction rule describing the position choice behavior of PTWs when queuing in heterogeneous traffic can capture the stochastic nature of the decision making process. The interaction rule is formulated as a multinomial logit model, which is calibrated by using a microscopic traffic trajectory dataset obtained from video footage. The ABM is validated against the survey data for the vehicular trajectory patterns, queuing patterns, queue lengths, and discharge rates. The results demonstrate that the proposed model is capable of replicating the observed queue formation process for heterogeneous traffic. (C) 2016 Elsevier B.V. All rights reserved.
HEAD MOTION RECOGNITION USING A SMART HELMET FOR MOTORCYCLE RIDERS
(2019-01-01)
Wong, K. I.
;
Chen, Yi-Chung
;
Lee, Tzu-Chang
;
Wang, Sheng-Min
;
運輸與物流管理系註：原交通所+運管所
This paper presents a head motion detection and recognition study using a smart helmet for motorcycle rider which can potential be used for the analysis of behavior of motorcycle riders. The smart helmet is a full face motorcycle helmet integrated with an intelligent system embedded an Inertial Measurement Unit (IMU) sensor. In the analysis, the motions and the corresponding signals are assessed with the video footage with a data acquisition and visualization platform. We introduce a feature extraction methodology to extract the most discriminant features from the signal data, and the head motion recognition problem is formulated as a machine-learning based classification model. Experiment results show that gyroscope sensor data is more useful than accelerometer sensor data for head motion recognition and the classification accuracy for different head motions ranges from 95.9% to 99.1%.