Browsing by Author "Shih, Wen-Yuah"

Now showing 1 - 7 of 7

A Hybrid Preference-Aware Recommendation Algorithm for Live Streaming Channels
(2013-01-01)
Yang, Tzu-Wei
;
Shih, Wen-Yuah
;
Huang, Jiun-Long
;
Ting, Wei-Chih
;
Liu, Pin-Chuan
With the advances of video streaming technology, live streaming services also become more and more popular. However, there may be thousands of online channels at the same time, and most viewers are not willing to go through one by one for finding the channels they are interested in. In view of this, we propose a hybrid preference-aware recommendation algorithm to recommend channels to viewers. We use logs of a live streaming service, Twitch.tv, to measure the performance of our algorithm and other existing algorithms, and experimental results show that the accuracy of our algorithm is higher than those of other algorithms.
An intelligent driver location system for smart parking
(2014-04-01)
Lan, Kun-Chan
;
Shih, Wen-Yuah
;
資訊工程學系
;
Department of Computer Science
It is often frustrating for drivers to find parking spaces, and parking itself is costly in almost every major city in the world. Here we propose a crowdsourcing solution by exploiting sensors in smart-phones to collect real-time parking availability information. We design a phone-based system to track a driver's trajectory to detect when they are about to leave their parking spot. We focus on the efficiency and accuracy of using a phone to monitor the driver's walking trajectory, applying a waist-mounted PDR method that can measure the driver's moving distance with a high accuracy. In addition, we design a map matching algorithm to calibrate the direction errors when the driver is in an indoor environment, using widely-available building floor plans. The results of our experiment show that we can achieve about 98% accuracy in estimating the user's walking distance, with an overall location error of about 0.48 m. (C) 2013 Elsevier Ltd. All rights reserved.
Early Detection of Neurological Disease Using a Smartphone: A Case Study
(2015)
Lan, Kun-Chan
;
Shih, Wen-Yuah
;
資訊工程學系
;
Department of Computer Science
Diagnosing Parkinson\'s disease (PD) is often difficult, especially in its early stages. It has been estimated that nearly 40% of people with the disease may not be diagnosed. Traditionally, the diagnosis of Parkinson\'s disease often requires a doctor to observe the patient over time to recognize signs of rigidity. In this work, we propose a PDR-based method to continuously monitor and record the patient\'s gait characteristics using a smart-phone. Our tool could be useful in providing an early warning to the PD patient to seek medical assistance and help the doctor diagnose the disease earlier.
Early Diagnosis of Parkinson's Disease using a Smartphone
(2014-01-01)
Lan, Kun-Chan
;
Shih, Wen-Yuah
;
資訊工程學系
;
Department of Computer Science
Diagnosing Parkinson's disease (PD) is often difficult, especially in its early stages. It has been estimated that nearly 40% of people with the disease may not be diagnosed. Traditionally, the diagnosis of Parkinson's disease often requires a doctor to observe the patient over time to recognize signs of rigidity. In this work, we propose a PDR-based method to continuously monitor and record the patient's gait characteristics using a smart-phone. Our tool could be useful in providing an early warning to the PD patient to seek medical assistance and help the doctor diagnose the disease earlier.
On Calibrating the Sensor Errors of a PDR-Based Indoor Localization System
(2013-04-01)
Lan, Kun-Chan
;
Shih, Wen-Yuah
;
資訊工程學系
;
Department of Computer Science
Many studies utilize the signal strength of short-range radio systems (such as WiFi, ultrasound and infrared) to build a radio map for indoor localization, by deploying a large number of beacon nodes within a building. The drawback of such an infrastructure-based approach is that the deployment and calibration of the system are costly and labor-intensive. Some prior studies proposed the use of Pedestrian Dead Reckoning (PDR) for indoor localization, which does not require the deployment of beacon nodes. In a PDR system, a small number of sensors are put on the pedestrian. These sensors (such as a G-sensor and gyroscope) are used to estimate the distance and direction that a user travels. The effectiveness of a PDR system lies in its success in accurately estimating the user's moving distance and direction. In this work, we propose a novel waist-mounted based PDR that can measure the user's step lengths with a high accuracy. We utilize vertical acceleration of the body to calculate the user's change in height during walking. Based on the Pythagorean Theorem, we can then estimate each step length using this data. Furthermore, we design a map matching algorithm to calibrate the direction errors from the gyro using building floor plans. The results of our experiment show that we can achieve about 98.26% accuracy in estimating the user's walking distance, with an overall location error of about 0.48 m.
Using Floor Plan to Calibrate Sensor Error for Indoor Localization
(2013)
Lan, Kun-Chan
;
Shih, Wen-Yuah
;
資訊工程學系
;
Department of Computer Science
Some prior studies proposed the use of Pedestrian Dead Reckoning (PDR) for indoor localization, in which a small number of inertial sensors are put on the pedestrian. These sensors (such as a G-sensor and gyroscope) are used to estimate the distance and direction that a user travels. The effectiveness of a PDR system lies in its success in accurately estimating the user\'s moving distance and direction. In this work, we design a map matching algorithm to calibrate the sensor errors using building floor plans. The results of our experiment show that we can achieve an overall location error of about 0.48 meter.
Using Smart-Phones and Floor Plans for Indoor Location Tracking
(2014-04-01)
Lan, Kun-Chan
;
Shih, Wen-Yuah
;
資訊工程學系
;
Department of Computer Science
We implement pedestrian dead reckoning (PDR) for indoor localization. With a waist-mounted PDR based system on a smart-phone, we estimate the user's step length that utilizes the height change of the waist based on the Pythagorean Theorem. We propose a zero velocity update (ZUPT) method to address sensor drift error: Simple harmonic motion and a low-pass filtering mechanism combined with the analysis of gait characteristics. This method does not require training to develop the step length model. Exploiting the geometric similarity between the user trajectory and the floor map, our map matching algorithm includes three different filters to calibrate the direction errors from the gyro using building floor plans. A sliding-window-based algorithm detects corners. The system achieved 98% accuracy in estimating user walking distance with a waist-mounted phone and 97% accuracy when the phone is in the user's pocket. ZUPT improves sensor drift error (the accuracy drops from 98% to 84% without ZUPT) using 8 Hz as the cut-off frequency to filter out sensor noise. Corner length impacted the corner detection algorithm. In our experiments, the overall location error is about 0.48 meter.