Browsing by Author "Chen, Yi-Yuan"

Now showing 1 - 13 of 13

An SOM-based algorithm for optimization with dynamic weight updating
(2007-06-01)
Chen, Yi-Yuan
;
Young, Kuu-Young
;
電控工程研究所
;
Institute of Electrical and Control Engineering
The self-organizing map (SOM), as a kind of unsupervised neural network, has been used for both static data management and dynamic data analysis. To further exploit its search abilities, in this paper we propose an SOM-based algorithm (SOMS) for optimization problems involving both static and dynamic functions. Furthermore, a new SOM weight updating rule is proposed to enhance the learning efficiency; this may dynamically adjust the neighborhood function for the SOM in learning system parameters. As a demonstration, the proposed SOMS is applied to function optimization and also dynamic trajectory prediction, and its performance compared with that of the genetic algorithm (GA) due to the similar ways both methods conduct searches.
Angle-of-Arrival (AOA) Visible Light Positioning (VLP) System Using Solar Cells With Third-Order Regression and Ridge Regression Algorithms
(2020-06-01)
Hong, Chong-You
;
Wu, Yu-Chun
;
Liu, Yang
;
Chow, Chi-Wai
;
Yeh, Chien-Hung
We put forward and demonstrate a angle-of-arrival (AOA) based visible-light-positioning (VLP) system using quadrant-solar-cell (QSC) and third-order ridge regression machine learning (RRML) to improve the positioning accuracy.
Applying SOM as a search mechanism for dynamic system
(2005)
Chen, Yi-Yuan
;
Young, Kuu- Young
;
電控工程研究所
;
Institute of Electrical and Control Engineering
The self-organizing map (SOM), as a kind of unsupervised neural network, has been applied for both static data management and dynamic data analysis. To further exploit its ability in search, in this paper, we employ the SOM as a searching mechanism for dynamic system. A learning scheme, consisting mainly of the SOM and the target dynamic system, is then proposed. The performance of this SOM-based learning scheme is especially compared with that of the genetic algorithm (GA) due to their resemblance in learning and searching. And, a new SOM weight updating rule is proposed to enhance learning efficiency, which may dynamically adjust the neighborhood function for the SOM in learning system parameters. For demonstration, the proposed learning scheme is applied for trajectory prediction, and its effectiveness evaluated via the simulations based on using the SOM, GA, and also Kalman filtering.
CMOS camera based visible light communication (VLC) using grayscale value distribution and machine learning algorithm
(2020-01-20)
Hsu, Ke-Ling
;
Wu, Yu-Chun
;
Chuang, Yu-Cheng
;
Chow, Chi-Wai
;
Liu, Yang
We demonstrate a visible light communication (VLC) system using light emitting diode (LED) backlight display panel and mobile-phone complementary-metal-oxide-semiconductor (CMOS) camera. The panel is primarily used for displaying advertisements. By modulating its backlight, dynamic contents (i.e. secondary information) can be transmitted wirelessly to users based on rolling shutter effect (RSE) of the CMOS camera. As different display content will be displayed on the panel, the VLC performance is significantly limited if the noise-ratio (NR) is too high. Here, we propose and demonstrate a CMOS RSE pattern demodulation scheme using grayscale value distribution (GVD) and machine learning algorithm (MLA) to significantly enhance the demodulation. (C) 2020 Optical Society of America under the terms of the OSA Open Access Publishing Agreement
Decoding CMOS Rolling-Shutter Pattern in Translational or Rotational Motions for VLC
(2019-04-01)
Chow, Chi-Wai
;
Li, Zhi-Qing
;
Chuang, Yu-Cheng
;
Liao, Xin-Lan
;
Lin, Kun-Hsien
We propose and demonstrate a CMOS rolling-shutter pattern decoding scheme based on two newly introduced schemes, named row grayscale redistribution and differential grayscale packet selection to improve the performance in decoding the CMOS rolling-shutter pattern in translational or rotational motions. Results show that even the CMOS image sensor is in translational or rotational motions, no significant signal degradation is observed at wireless transmission distance up to 150 cm. The maximum visible light communication data rate at different wireless transmission distances is also analyzed.
Integration of Multiple Views for a 3-D Indoor Surveillance System
(2010-11-01)
Chen, Yi-Yuan
;
Huang, Yung-Huang
;
Cheng, Yung-Cheng
;
Chen, Yong-Sheng
;
資訊工程學系
A conventional surveillance system uses multiple screens to separately display the acquired video streams. It may cause trouble to keep track of the moving targets due to the lack of spatial relationship among the camera views. This paper presents a surveillance system that can integrate multiple video contents into one single comprehensive view. To visualize the monitored area, the proposed system uses planar patches to approximate the 3-D model of the monitored environment and displays the video contents of cameras by applying dynamic texture mapping on the model. Therefore, this system can provide an efficient and practical way for interactive 3-D monitoring of the environment without complicated camera calibration and 3-D model reconstruction procedures. Moreover, the moving objects are extracted through foreground segmentation and then visualized through axis-aligned billboarding. In this way, the proposed system can provide security guards a better situational awareness of the monitored area, including the activities of the tracking targets.
Mitigation of performance degradation due to dynamic display contents in visible light communication using TV backlight and CMOS image sensor
(2018-08-20)
Chow, Chi-Wai
;
Shiu, Ruei-Jie
;
Liu, Yen-Chun
;
Wang, Wei-Chung
;
Liao, Xin-Lan
Here, we propose and demonstrate a performance degradation mitigation scheme in TV backlight and smart-phone-based visible light communication (VLC) system when the display content in the light-panel is dynamically changing. In order to evaluate the influence of the dynamic display contents to the VLC performance, we use a noise-ratio (NR) and noise-ratio standard deviation (NRSD) as the figure-of-merits for the bright-and-dark contrast of the display content; and the dispersal of the changing display content regarding the brightand-dark contrast respectively. Performances of 4 dynamic display contents with different combinations of NR and NRSD are analyzed. They are: low NR and low NRSD (NR 36.69%; NRSD = 0.0226); low NR and high NRSD (MR = 30.09%; NRSD = 0.2698); high NR and low NRSD (NR = 81.66%; NRSD = 0.0052); high NR and high NRSD (NR = 73.91%; and NRSD = 0.2717). The proposed scheme can work well; that is, even the transmission distance is up to 200 cm in both smart-phones. If the proposed scheme is not used, then high success rate can be observed only at the low NR and low NRSD display content when the transmission distance is < 100 cm. (C) 2018 Optical Society of America under the terms of the OSA Open Access Publishing Agreement
Robust Light Objects Recognition Based on Computer Vision
(2009)
Chen, Yi-Yuan
;
Lan, Kuen-Ming
;
Pai, Hung-, I
;
Chuang, Jen-Hui
;
Yuan, Chii-Yah
This paper proposes a recognition method for light objects in a video for real-time application and the movement of the surrounding objects. The method extracts the objects by considering known geometric arrangements and blinking frequency, while the latter is also used to remove the image noise. Therefore, locations of the light objects can be found rapidly, and the on-off blinking states of these objects can be recognized accordingly if the frame rate of the video is sufficient. Besides, it can be used in the image recognition unit of a light communication system.
Secure Mobile-Phone Based Visible Light Communications With Different Noise-Ratio Light-Panel
(2018-04-01)
Chow, Chi-Wai
;
Shiu, Ruei-Jie
;
Liu, Yen-Chun
;
Yeh, Chien-Hung
;
Liao, Xin-Lan
We propose and demonstrate a visible light communication (VLC) system using a light-panel and a mobile-phone camera. We also propose the rolling-shutter-effect (RSE) pattern synchronization and demodulation algorithms. By using our developed mobile-phone application program, the RSE pattern can be demodulated even at very low illuminance. As the light-panel will have different advertisements on it, we also define a noise-ratio (NR) as the figure-of-merit; hence, different VLC data rates can be adjusted according to different advertisement NR values. Experimental bit error rate measurements at different free-space transmission distances and different NRs are performed.
Using advertisement light-panel and CMOS image sensor with frequency-shift-keying for visible light communication
(2018-05-14)
Chow, Chi-Wai
;
Shiu, Ruei-Jie
;
Liu, Yen-Chun
;
Liao, Xin-Lan
;
Lin, Kun-Hsien
A frequency-shift-keying (FSK) visible light communication (VLC) system is proposed and demonstrated using advertisement light-panel as transmitter and mobile-phone image sensor as receiver. The developed application program (APP) in mobile-phone can retrieve the rolling shutter effect (RSE) pattern produced by the FSK VLC signal effectively. Here, we also define noise-ratio value (NRV) to evaluate the contrast of different advertisements displayed on the light-panel. Both mobile-phones under test can achieve success rate > 96% even when the transmission distance is up to 200 cm and the NRVs are low. (C) 2018 Optical Society of America under the terms of the OSA Open Access Publishing Agreement
Using logistic regression classification for mitigating high noise-ratio advisement light-panel in rolling-shutter based visible light communications
(2019-10-14)
Chuang, Yu-Cheng
;
Chow, Chi-Wai
;
Liu, Yang
;
Yeh, Chien-Hung
;
Liao, Xin-Lan
We propose and experimentally demonstrated a light-panel and image sensor based visible light communication (VLC) system using machine learning (ML) algorithm. The ML algorithm is compared with the traditional demodulation scheme and the experimental results show that even at very high noise-ratio (NR) light-panel display content, the proposed ML algorithm shows significant bit error rate (BER) improvement. (C) 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement
Using pre-distorted PAM-4 signal and parallel resistance circuit to enhance the passive solar cell based visible light communication
(2018-01-15)
Wang, Hao-Yu
;
Wu, Jhao-Ting
;
Chow, Chi-Wai
;
Liu, Yang
;
Yeh, Chien-Hung
Using solar cell (or photovoltaic cell) for visible light communication (VLC) is attractive. Apart from acting as a VLC receiver (Rx), the solar cell can provide energy harvesting. This can be used in self-powered smart devices, particularly in the emerging "Internet of Things (IoT)'' networks. Here, we propose and demonstrate for the first time using pre-distortion pulse-amplitude-modulation (PAM)-4 signal and parallel resistance circuit to enhance the transmission performance of solar cell Rx based VLC. Pre-distortion is a simple non-adaptive equalization technique that can significantly mitigate the slow charging and discharging of the solar cell. The equivalent circuit model of the solar cell and the operation of using parallel resistance to increase the bandwidth of the solar cell are discussed. By using the proposed schemes, the experimental results show that the data rate of the solar cell Rx based VLC can increase from 20 kbit/s to 1.25 Mbit/s (about 60 times) with the bit error-rate (BER) satisfying the 7% forward error correction (FEC) limit. (C) 2017 Elsevier B.V. All rights reserved.
Visible Light Communication Using Advertisement-Light-Board and Rolling-Shutter-Effect based CMOS Mobile-Phone Camera
(2018-01-01)
Shiu, Ruei-Jie
;
Liu, Yen-Chun
;
Chow, Chi-Wai
;
Wei, Liang-Yu
;
Hsu, Yung
We demonstrate a visible-light-communication (VLC) system using advertisement-light-board and CMOS-camera. Experiments at wireless transmission distances of 50cm, 100cm and 150cm are performed, and at data-rate of 720bit s, satisfying the forward-error-correction (FEC) threshold.