Browsing by Author "Chen, Shi-An"

Now showing 1 - 20 of 30

A Hierarchal Classifier for Identifying Independent Components
(2012)
Lin, Chin-Teng
;
Wang, Yu-Kai
;
Chen, Shi-An
;
電控工程研究所
;
Institute of Electrical and Control Engineering
Brain-computer interface (BCI) has shown explosive growth for multiple applications in the recently years. Removing artifacts and selecting useful brain sources are essential in BCI research. Independent Component Analysis (ICA) has been proven as an effective technique to remove artifacts and many brain related researches are based on ICA. However, the useful independent components with brain sources are usually selected manually according to the scalp-plots. This is great inconvenience and a barrier for real-time BCI applications of EEG. In this investigation, a two-layer automatic identification model is proposed to select useful brain sources. It is based on neural network including support vector machine with radial basis function (SVMRBF) and self-organizing map (SOM). In the first layer, SVM discriminates useful independent components from the artifact effectively. In the second layer, these selected useful components are automatically classified to different spatial brain sources according to SOM. This study suggests this model to one general application for EEG study. It can reduce the effect of subjective judgment and improve the performance of EEG analysis.
A Novel 16-Channel Wireless System for Electroencephalography Measurements With Dry Spring-Loaded Sensors
(2014-06-01)
Liao, Lun-De
;
Wu, Shang-Lin
;
Liou, Chang-Hong
;
Lu, Shao-Wei
;
Chen, Shi-An
Understanding brain function using electroencephalography (EEG) is an important issue for cerebral nervous system diseases, especially for epilepsy and Alzheimer\'s disease. Many EEG measurement systems are used reliably to study these diseases, but their bulky size and the use of wet sensors make them uncomfortable and inconvenient for users. To overcome the limitations of conventional EEG measurement systems, a wireless and wearable multichannel EEG measurement system is proposed in this paper. This system includes a wireless data acquisition device, dry spring-loaded sensors, and a size-adjustable soft cap. We compared the performance of the proposed system using dry versus conventional wet sensors. A significant positive correlation between readings from wet and dry sensors was achieved, thus demonstrating the performance of the system. Moreover, four different features of EEG signals (i.e., normal, eye-blinking, closed-eyes, and teeth-clenching signals) were measured by 16 dry sensors to ensure that they could be detected in real-life cognitive neuroscience applications. Thus, we have shown that it is possible to reliably measure EEG signals using the proposed system. This paper presents novel insights into the field of cognitive neuroscience, showing the possibility of studying brain function under real-life conditions.
A Novel Classification Method for Motor Imagery Based on Brain-Computer Interface
(2014)
Chen, Chih-Yu
;
Wu, Chun-Wei
;
Lin, Chin-Teng
;
Chen, Shi-An
;
電機學院
Brain computer interface (BCI) is known as a good way to communicate between brain and computer or other device. There are many kinds of physiological signal can operate BCI systems. Motor imagery (MI) has been demonstrated to be a good way to operate a BCI system. In some recent studies about MI based BCI systems, low accuracy rate and time consuming are common problems. In this thesis, a novel motor imagery algorithm is proposed to improve the accuracy rate and computational efficiency at the same time. The architecture of many BCI system is quite complex and they involve time consuming processing. The electroencephalography (EEG) signal is the most commonly used inputs for BCI applications but EEG is often contaminated with noise. To overcome such drawbacks, in this paper we use the common spatial pattern (CSP) for feature extraction from EEG and the linear discriminant analysis (LDA) for motor imagery classification. In this study, CSP and LDA have been used to reduce the artifact and classify MI-based EEG signal. We have used two-level cross validation scheme to determine the subject specific best time window and number of CSP features. We have compared the performance of our system with BCI competition results. This novel algorithm with high accuracy rate and efficiency can be applied to real time BCI system in real-life applications.
A Vectorcardiogram-based Classification System for the Detection of Myocardial Infarction
(2011)
Huang, Chih-Sheng
;
Ko, Li-Wei
;
Lu, Shao-Wei
;
Chen, Shi-An
;
Lin, Chin-Teng
Myocardial infarction (MI), generally known as a heart attack, is one of the top leading causes of mortality in the world. In clinical diagnosis, cardiologists generally utilize 12-lead ECG system to classify patients into MI symptoms: 1. ST segment elevation, 2. ST segment depression or T wave inversion. However unstable ischemic syndromes have rapidly changing supply versus demand characteristics that is one of the several limitations of 12-lead ECG system for MI detection. In addition, the ECG sensor placements of 12-lead system is not easily donned and doffed for tele-healthcare monitoring at home. Vectorcardiogram (VCG) system in clinic is another type of diagnosis plot which represents the magnitude and direction of the electrical potential in the form of a vector loop during cardiac electric activity. The VCG system can easily acquire three ECG waves from X, Y, Z directions to composite vector signal in space and the VCG signals can be transferred to 12-lead ECG signal through Dower transformation and vice versa. Hence, this study attempts to develop a VCG-based classification system for the detection of Myocardial infarction. In the experiment results, the proposed system can select the proper ECG features based on cardiologist's knowledge and proposed principal moments of QRS complex. The classification performance of MI detection can be reached to 99.89% of sensitivity, 92.51% of specificity, 95.35% of positive predictive value, and 96.96% overall accuracy with maximum-likelihood classifier (MLC).
A Wireless Electrooculography-based Human-Computer Interface for Baseball Game
(2013-01-01)
Lin, Chin-Teng
;
Wu, Shang-Lin
;
Jiang, Wei-Ling
;
Liang, Jyun-Wei
;
Chen, Shi-An
Gaming control becomes popular based on the development of human-computer interface (HCI). Among many kinds of physiological signals, Electrooculography (EOG) signal is more stable which can be used to control HCI systems based on eye movement detection and signal processing methods. However, there are currently no effective multi-directional classification methods for monitoring eye movements. In addition, many EOG-based HCI systems have been developed with traditional wet electrodes. Those traditional electrodes require conductive gel and skin preparation on some users. Here, we describe a signal processing method used in a wireless EOG-based HCI system with dry electrodes for detecting eye movements to have 9 options. This system includes wireless EOG signal acquisition device, dry electrodes and an EOG signal processing algorithm. The EOG signal processing algorithm is based on 9 options of eye movement and blink signals. The results demonstrated an application of baseball game control using the proposed wireless HCI system. This system provides an effective and convenient method for eye movement detection.
An EEG-based brain-computer interface for dual task driving detection
(2014-04-10)
Wang, Yu-Kai
;
Chen, Shi-An
;
Lin, Chin-Teng
;
資訊工程學系
;
腦科學研究中心
The development of brain-computer interfaces (BCI) for multiple applications has undergone extensive growth in recent years. Since distracted driving is a significant cause of traffic accidents, this study proposes one BCI system based on EEG for distracted driving. The removal of artifacts and the selection of useful brain sources are the essential and critical steps in the application of electroencephalography (EEG)-based BCI. In the first model, artifacts are removed, and useful brain sources are selected based on the independent component analysis (ICA). In the second model, all distracted and concentrated EEG epochs are recognized with a self-organizing map (SOM). This BCI system automatically identified independent components with artifacts for removal and detected distracted driving through the specific brain sources which are also selected automatically. The accuracy of the proposed system approached approximately 90% for the recognition of EEG epochs of distracted and concentrated driving according to the selected frontal and left motor components. (C) 2013 Published by Elsevier B.V.
An EEG-Based Brain-Computer Interface for Dual Task Driving Detection
(2011)
Lin, Chin-Teng
;
Wang, Yu-Kai
;
Chen, Shi-An
;
腦科學研究中心
;
Brain Research Center
A novel detective model for driver distraction was proposed in this study. Driver distraction is a significant cause of traffic accidents during these years. To study human cognition under a specific driving task, one virtual reality (VR)-based simulation was built. Unexpected car deviations and mathematics questions with stimulus onset asynchrony (SOA) were designed. Electroencephalography (EEG) is a good index for the distraction level to monitor the effects of the dual tasks. Power changing in Frontal and Motor cortex were extracted for the detective model by independent component analysis (ICA). All distracting and non-distracting EEG epochs could be revealed the existence by self-organizing map (SOM). The results presented that this system approached about 90% accuracy to recognize the EEG epochs of non-distracting driving, and might be practicable for daily life.
An Inflatable and Wearable Wireless System for Making 32-Channel Electroencephalogram Measurements
(2016-07)
Yu, Yi-Hsin
;
Lu, Shao-Wei
;
Chuang, Chun-Hsiang
;
King, Jung-Tai
;
Chang, Che-Lun
Potable electroencephalography (EEG) devices have become critical for important research. They have various applications, such as in brain-computer interfaces (BCI). Numerous recent investigations have focused on the development of dry sensors, but few concern the simultaneous attachment of high-density dry sensors to different regions of the scalp to receive qualified EEG signals from hairy sites. An inflatable and wearable wireless 32-channel EEG device was designed, prototyped, and experimentally validated for making EEG signal measurements; it incorporates spring-loaded dry sensors and a novel gasbag design to solve the problem of interference by hair. The cap is ventilated and incorporates a circuit board and battery with a high-tolerance wireless (Bluetooth) protocol and low power consumption characteristics. The proposed system provides a 500/250 Hz sampling rate, and 24 bit EEG data to meet the BCI system data requirement. Experimental results prove that the proposed EEG system is effective in measuring audio event-related potential, measuring visual event-related potential, and rapid serial visual presentation. Results of this work demonstrate that the proposed EEG cap system performs well in making EEG measurements and is feasible for practical applications.
Analyzing Effect of Distraction Caused by Dual-Tasks on Sharing of Brain Resources Using SOM
(2010)
Wang, Yu-Kai
;
Pal, Nikhil R.
;
Lin, Chin-Teng
;
Chen, Shi-An
;
資訊工程學系
Drivers' distraction is widely recognized as a leading cause of car accidents. To investigate the distracting effect of dual-tasks involving driving and answering mathematical equations in the stimulus onset asynchrony (SOA) conditions, we design five different cases: two cases involving single-tasks and three cases involving dual-tasks. We have found that there is no statistically significant change in the behavioral data among the three dual-tasks. This raises an important question - is there any detectable effect of the dual tasks on the brain waves? To answer this, we use the Self-Organizing Map (SOM) to recognize the changes, if any, in the Electroencephalography (EEG) dynamics associated with such dual-tasks. Our SOM analysis based on independent components corresponding to EEG signals extracted from Frontal and Motor areas revealed that single-and dual-tasks have distinguishable signatures in the EEG signals. Specifically, each of the two single-task conditions is clustered in a distinct spatial area of the map. Two of the dual-tasks also exhibit distinct spatial clusters, while the third case although shows differences from the other two, the neurons corresponding to this case are sub-clustered reflecting the fact that different subjects may give different priorities to the tasks when confronted with two tasks simultaneously. SOM-based exploratory analysis reveals the existence of distinct EEG signatures among the distracting and non-distracting tasks, although there is no any noticeable difference in the behavioral data among these cases.
CNN-based hybrid-order texture segregation as early vision processing and its implementation on CNN-UM
(2007-10-01)
Lin, Chin-Teng
;
Huang, Chao-Hui
;
Chen, Shi-An
;
電控工程研究所
;
Institute of Electrical and Control Engineering
In this paper, a biologically inspired, CNN-based, multi-channel, texture boundary detection technique is presented. The proposed approach is similar to human vision system. The algorithm is simple and straightforward such that it can be implemented on the cellular neural networks (CNNs). CNN contains several important advantages, such as efficient real-time processing capability and feasible very large-scale integration (VLSI) implementation. The proposed algorithm also had been widely tested on synthetic texture images. Those texture images are randomly selected from the Brodatz textures database [1]. According to our simulation results, the boundaries of uniform textures can be detected quite successfully. For the nonuniform or nonregular textures, the results also indicate meaningful properties, and the properties also are consistent to the human visual sensation. The proposed algorithm also has been implemented on the CNN Universal Machine (CNN-UM), and yields similar results as the simulation on the PC. Based on the efficient performance of CNN-UM, the algorithm becomes very fast.
CNN-based local motion estimation chip for image stabilization processing
(2006)
Lin, Chin-Teng
;
Chen, Shi-An
;
Cheng, Ying-Chang
;
Chung, Jen-Feng
;
電控工程研究所
This paper is to investigate a novel design for local motion vectors (LMVs) of image sequences, which are often used in a digital image stabilization (IS) system. The IS technique removes unwanted shaking phenomenon in image sequences captured by hand-held camcorders. It includes two main parts such. as motion estimation and compensation. Most of computation power occurs in the part of motion estimation. In order to reduce this complexity, an idea, which integrates an adaptive-threshold method and cellular neural networks (CNN) architecture, is designed to improve this problem. The design only implements the most important local motion estimation with the array size of 19x25 pixels. Experimental results with HSPICE simulation and CNNUM are shown that the proposed architecture fast searches the location of possible LVMs and has the capability of real-time operations. The complete design has integrated into the total area of 8.1mm(2) by using TSMC 0.35 mu m mixed-signal process.
Common Spatial Pattern and Linear Discriminant Analysis for Motor Imagery Classification
(2013)
Wu, Shang-Lin
;
Wu, Chun-Wei
;
Pal, Nikhil R.
;
Chen, Chih-Yu
;
Chen, Shi-An
A Brain-Computer Interface (BCI) system provides a convenient way of communication for healthy subjects and subjects who suffer from severe diseases such as amyotrophic lateral sclerosis (ALS). Motor imagery (MI) is one of the popular ways of designing BCI systems. The architecture of many BCI system is quite complex and they involve time consuming processing. The electroencephalography (EEG) signal is the most commonly used inputs for BCI applications but EEG is often contaminated with noise. To overcome such drawbacks, in this paper we use the common spatial pattern (CSP) for feature extraction from EEG and the linear discriminant analysis (LDA) for motor imagery classification. In this study, CSP and LDA have been used to reduce the artifact and classify MI-based EEG signal. We have used two-level cross validation scheme to determine the subject specific best time window and number of CSP features. We have compared the performance of our system with BCI competition results. We have also experimented with MI data generated in our lab. The proposed system is found to produce good results. In particular, using our EEG data for MI movements, we have obtained an average classification accuracy of 80% for two subjects using only 9 channels, without any feature selection. This proposed MI-based BCI system may be used in real life applications.
Controlling a Human-Computer Interface System With a Novel Classification Method that Uses Electrooculography Signals
(2013-08-01)
Wu, Shang-Lin
;
Liao, Lun-De
;
Lu, Shao-Wei
;
Jiang, Wei-Ling
;
Chen, Shi-An
Electrooculography (EOG) signals can be used to control human-computer interface (HCI) systems, if properly classified. The ability to measure and process these signals may help HCI users to overcome many of the physical limitations and inconveniences in daily life. However, there are currently no effective multidirectional classification methods for monitoring eye movements. Here, we describe a classification method used in a wireless EOG-based HCI device for detecting eye movements in eight directions. This device includes wireless EOG signal acquisition components, wet electrodes and an EOG signal classification algorithm. The EOG classification algorithm is based on extracting features from the electrical signals corresponding to eight directions of eye movement (up, down, left, right, up-left, down-left, up-right, and down-right) and blinking. The recognition and processing of these eight different features were achieved in real-life conditions, demonstrating that this device can reliably measure the features of EOG signals. This system and its classification procedure provide an effective method for identifying eye movements. Additionally, it may be applied to study eye functions in real-life conditions in the near future.
Design of the Multi-channel Electroencephalography-based Brain-Computer Interface with Novel Dry Sensors
(2012)
Wu, Shang-Lin
;
Liao, Lun-De
;
Liou, Chang-Hong
;
Chen, Shi-An
;
Ko, Li-Wei
The traditional brain-computer interface (BCI) system measures the electroencephalography (EEG) signals by the wet sensors with the conductive gel and skin preparation processes. To overcome the limitations of traditional BCI system with conventional wet sensors, a wireless and wearable multi-channel EEG-based BCI system is proposed in this study, including the wireless EEG data acquisition device, dry spring-loaded sensors, a size-adjustable soft cap. The dry spring-loaded sensors are made of metal conductors, which can measure the EEG signals without skin preparation and conductive gel. In addition, the proposed system provides a size-adjustable soft cap that can be used to fit user's head properly. Indeed, the results are shown that the proposed system can properly and effectively measure the EEG signals with the developed cap and sensors, even under movement. In words, the developed wireless and wearable BCI system is able to be used in cognitive neuroscience applications.
EEG-based Brain Dynamics of Driving Distraction
(2011)
Lin, Chin-Teng
;
Chen, Shi-An
;
Ko, Li-Wei
;
Wang, Yu-Kai
;
電控工程研究所
Distraction during driving has been recognized as a significant cause of traffic accidents. The aim of this study is to investigate Electroencephalography (EEG) -based brain dynamics in response to driving distraction. To study human cognition under specific driving tasks in a simulated driving experiment, this study utilized two simulated events including unexpected car deviations and mathematics questions. The raw data were first separated into independent brain sources by Independent Component Analysis. Then, the EEG power spectra were used to evaluate the time-frequency brain dynamics. Results showed that increases of theta band and beta band power were observed in the frontal cortex. Further analysis demonstrated that reaction time and multiple cortical EEG power had high correlation. Thus, this study suggested that the features extracted by EEG signal processing, which were the theta power increases in frontal area, could be used as the distracted indexes for early detection of driver inattention in real driving.
EEG-based Brain-computer Interface for Smart Living Environment Auto-adjustment
(2010)
Lin, Chin-Teng
;
Lin, Fu-Chang
;
Chen, Shi-An
;
Lu, Shao-Wei
;
Chen, Te-Chi
An EEG-based smart living environmental control system to auto-adjust the living environment is proposed in this study. Many environmental control systems have been proposed to improve human life quality in recent years. However, there is little research focused on environment control by using a human's physiological state directly. Even though some studies have proposed brain computer interface-based (BCI-based) environmental control systems, most of them encountered signal quality decline during long-term physiological monitoring with conventional wet electrodes. Moreover, such BCI-based environmental control systems are actively controlled by users; less close-loop feedback capability can be provided between environment and user for automation. Based on the advance of our technique for BCI and the improvement of micro-electro-mechanical-system-based (MEMS-based) dry electrode sensors, we combined these techniques to demonstrate an auto-adjustable living environment control system, e. g., illumination of light and fan speed of air conditioner, depends on the physiological change of the user, even for long-term physiological monitoring. The system is structured with five units: a wireless portable EEG acquisition circuit unit, an interactive flow control unit with a real-time physiology signal processing unit, which is implemented on a dual-core processor, an environment controller unit and a host system for data storage and display. The proposed system has been verified in a simulated environment and the experimental results show that the air conditioner and the lights can be successfully and automatically adjusted in real-time based on the subject's physiological changes, which indicate the proposed system can be implemented and constructed in the practical smart living environment or for other applications.
EEG-based Cognitive State Monitoring and Predition by Using the Self-Constructing Neural Fuzzy System
(2010)
Lin, Fu-Chang
;
Ko, Li-Wei
;
Chen, Shi-An
;
Chen, Ching-Fu
;
Lin, Chin-Teng
Driver's cognitive state monitoring has been implicated as a causal factor for the safety driving issue, especially when the driver fell asleep or distracted in driving. In our past studies, we found that the EEG power spectrum changes were highly correlated with the driver's driving behavior performance. In this study, we attempt to construct an EEG-based self-constructing neural fuzzy system to monitor and predict the driver's cognitive state. The difficulties in developing such a system are lack of significant index for detecting drowsiness and the interference of the complicated noise in a realistic and dynamic driving environment. Our experimental results including correlation and prediction show that the performances of our proposed system are significantly higher than using the traditional neural networks. Besides, the proposed EEG-based self-constructing neural fuzzy system can be generalized and applied in the subjects' independent sessions. This unique advantage can be widely used in the real-life applications.
EEG-Based Motion Sickness Estimation Using Principal Component Regression
(2011)
Ko, Li-Wei
;
Wei, Chun-Shu
;
Chen, Shi-An
;
Lin, Chin-Teng
;
腦科學研究中心
Driver's cognitive state monitoring system has been implicated as a causal factor for the safety driving issue, especially when the driver fell asleep or distracted in driving. However, the limitation in developing this system is lack of a major indicator which can be applied to a realistic application. In our past studies, we investigated the physiological changes in the transition of driver's cognitive state by using EEG power spectrum analysis and found that the features in the occipital area were highly correlated with the driver's driving performance. In this study, we construct an EEG-based self-constructed neural fuzzy system to estimate the driver's cognitive state by using the EEG features from the occipital area. Experimental results show that the proposed system had the better performance than other neural networks. Moreover, the proposed system can not only be limited to apply to individual subjects but also sufficiently works in between subjects.
Fuzzy adaptive synchronization of time-reversed chaotic systems via a new adaptive control strategy
(2013-02-10)
Li, Shih-Yu
;
Yang, Cheng-Hsiung
;
Chen, Shi-An
;
Ko, Li-Wei
;
Lin, Chin-Teng
A novel adaptive control strategy is proposed herein to increase the efficiency of adaptive control by combining Takagi-Sugeno (T-S) fuzzy modeling and the Ge-Yao-Chen (GYC) partial region stability theory. This approach provides two major contributions: (1) increased synchronization efficiency, especially for parameters tracing and (2) a simpler controller design. Two simulated cases are presented for comparison: Case 1 utilizes normal adaptive synchronization, whereas Case 2 utilizes the Takagi-Sugeno (T-S) fuzzy model-based Lorenz systems to realize adaptive synchronization via the new adaptive scheme. The simulation results demonstrate the effectiveness and feasibility of our new adaptive strategy. (C) 2012 Elsevier Inc. All rights reserved.
Gaming Controlling via Brain-Computer Interface Using Multiple Physiological Signals
(2014)
Chen, Shi-An
;
Chen, Chih-Hao
;
Lin, Theng-Wei
;
Ko, Li-Wei
;
Lin, Chin-Teng
using physiological signals to control braincomputer interface (BCI) becomes more popular. Among many kinds of physiological signals, Electrooculography (EOG) signal is more stable which can be used to control BCI systems based on eye movement detection and signal processing methods. Also, the use of electroencephalographic (EEG) signals has become the most common approach for a BCI because of their usability and strong reliability. In this paper, we described a signal processing method, which uses a wireless EEG-based BCI system designed to be worn near forehead that can detect both EEG and EOG signals, for detecting eye movements to have 9 direction controls (via EOG) and one action of execution (via EEG). This system included a wireless EEG signal acquisition device, a mechanism that can be worn stably, and an application program (APP) with signal processing algorithms. This algorithm and its classification procedure provided an effective method for identifying eye movements and attention. Finally, we designed a baseball game to test the BCI system. The results demonstrated that player can control the game well with high accuracy.