Review
Chemistry, Analytical
Chama Belkhiria, Atlal Boudir, Christophe Hurter, Vsevolod Peysakhovich
Summary: Electro-oculography-based brain-computer interface is a relevant technology that has influences in various fields. It records activities related to users' intention, perception, and motor decisions, and converts them into commands for external hardware control. In the aeronautics field, it is explored as a tool to replace manual commands and accelerate user intention.
Article
Chemistry, Analytical
Chin-Teng Lin, Wei-Ling Jiang, Sheng-Fu Chen, Kuan-Chih Huang, Lun-De Liao
Summary: An HCI system based on electrooculography (EOG) that includes eye-state detection and ten saccade movements differentiation has been proposed in this study to assist people with disabilities. The system provides an eye-dialing interface to improve the lives of individuals with disabilities, showcasing good performance of the classification algorithm.
Article
Mathematics, Interdisciplinary Applications
Fatma Latifoglu, Ramis Ileri, Esra Demirci
Summary: This study proposes a method to assist in diagnosing and following up dyslexia by analyzing skipping lines and back to eye movements while reading from electrooculography signals. The 2D-CNN classifier achieved a success rate of 99% in classifying these movement signals.
CHAOS SOLITONS & FRACTALS
(2021)
Article
Engineering, Biomedical
Yajun Zhou, Tianyou Yu, Wei Gao, Weichen Huang, Zilin Lu, Qiyun Huang, Yuanqing Li
Summary: In this study, a shared robotic arm control system based on hybrid asynchronous BCI and computer vision was presented. The BCI model, which combines steady-state visual evoked potentials (SSVEPs) and blink-related electrooculography (EOG) signals, allows users to control the robotic arm in three-dimensional environments and accomplish tasks such as grasping a target. Results showed high accuracy and efficiency in robot movement, with shorter completion time compared to direct BCI control. This research demonstrates the feasibility and effectiveness of merging hybrid asynchronous BCI and computer vision for controlling a robotic arm.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2023)
Article
Engineering, Electrical & Electronic
Jisoo Ha, Kang-Min Choi, Chang-Hwan Im
Summary: Eye-tracking technology has been widely used in neuromarketing, but camera-based eye-trackers are expensive, hindering their widespread adoption. This study developed a method to estimate eye gaze coordinates using electrooculography (EOG) signals, which showed promising results in terms of reliability and gender differences in neuromarketing tests.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Review
Chemistry, Analytical
Seunghyeb Ban, Yoon Jae Lee, Ka Ram Kim, Jong-Hoon Kim, Woon-Hong Yeo
Summary: Eye movements are primary responses reflecting voluntary intention and conscious selection, providing critical information about physical/psychological health, perception, intention, and preference. With advancements in wearable device technologies, eye tracking has greatly improved and found numerous applications in enhancing human activities. This paper summarizes the latest research on materials, sensors, and integrated systems for monitoring eye movements and enabling human-machine interfaces.
Article
Neurosciences
Jun Zhang, Shouwei Gao, Kang Zhou, Yi Cheng, Shujun Mao
Summary: This paper proposes an online hybrid BCI system that combines SSVEP and eye movements to improve the performance of BCI systems. The SSVEP is induced by flashing 20 buttons evenly distributed in the GUI, while eye movements are generated by the subject continuously staring at the target after the flash. The CCA method and FBCCA method are used to detect SSVEP, and the electrooculography (EOG) waveform is used to detect eye movements. A decision-making method based on SSVEP and EOG features is proposed to further enhance the performance of the hybrid BCI system. The system achieves an average accuracy of 94.75% and an information transfer rate of 108.63 bits/min.
FRONTIERS IN HUMAN NEUROSCIENCE
(2023)
Article
Multidisciplinary Sciences
Haitao Liu, Fei Liao, Pedro de la Villa
Summary: The study revealed that the EOG response amplitude was significantly greater in the left eye compared to the right eye for light bars moving from right to left, but similar for light bars moving vertically. Horizontal stimuli were found to generate significant interocular differences in EOG response amplitude.
Article
Nanoscience & Nanotechnology
Ata Jedari Golparvar, Murat Kaya Yapici
Summary: The study demonstrates a personal assistive device based on graphene textiles, which uses eye movements to control a mouse cursor and navigate a robot, showcasing the potential of graphene textiles in wearable eye tracking and eye-operated remote object interaction, and achieving satisfactory experimental results.
BEILSTEIN JOURNAL OF NANOTECHNOLOGY
(2021)
Article
Computer Science, Information Systems
Ha Na Jo, Sung Woo Park, Han Gyeol Choi, Seok Hyun Han, Tae Seon Kim
Summary: This paper reports the development of an HCI method that can acquire EOG and sEMG signals through electrodes integrated into bone conduction headphones, and transmit commands through eye movements and biting movements. The experimental results show that the interface has high accuracy and precision in command recognition, and achieves fast typing speed in virtual keyboard applications.
Article
Psychology, Biological
Germano Gallicchio, Donghyun Ryu, Mudit Krishnani, Guy L. Tasker, Alessandra Pecunioso, Robin C. Jackson
Summary: This study aimed to evaluate the use of electrooculography (EOG) in studying eye activity during motor behavior. The results showed that EOG can provide valid and accurate temporal measurements and distinguish different frequencies of activity. EOG features were also found to predict performance accuracy and higher-frequency activity was associated with smoother movement execution.
Article
Neurosciences
Johannes Kirchner, Tamara Watson, Niko A. Busch, Markus Lappe
Summary: This study observed that people make large dynamic overshoots when making a saccadic eye movement within a blink but their eyes are back on target by the time the eyelids are open. We used electrooculography (EOG) to measure eye movements even when the lid is down and introduced a novel procedure to subtract blink-related EOG components. These findings challenge the current view that within-blink saccades are programmed as slow but straight saccades.
JOURNAL OF NEUROPHYSIOLOGY
(2022)
Article
Neurosciences
Johannes Gruenwald, Sebastian Sieghartsleitner, Christoph Kapeller, Josef Scharinger, Kyousuke Kamada, Peter Brunner, Christoph Guger
Summary: This study systematically characterizes the fundamental signal properties of HGA in ECoG signals, including the high-gamma frequency band, HGA bandwidth, and the temporal dynamics of HGA. The results show significant variations in these signal properties across subjects and cognitive/behavioral tasks, highlighting the importance of optimizing experiment design and HGA estimation.
FRONTIERS IN NEUROSCIENCE
(2023)
Article
Computer Science, Information Systems
Alejandro Benitez Fernandez, Barbaro N. Socarras Hernandez, Justo M. Herrera Rodriguez, Bruno da Silva, Carlos R. Vazquez-Seisdedos
Summary: Abnormal eye movements are important indicators for diagnosing diseases affecting the central nervous system and measuring the progress of neurodegenerative diseases. Electro-oculography is a widely used technique for monitoring horizontal and vertical eye movements in response to visual stimuli, requiring stimulus-response synchronization, low latency, and real-time response. The proposed system based on FPGA enhances the accuracy of generated signals and shows excellent results in stimulus-response synchronism and stimulus waveform quality.
Article
Mathematical & Computational Biology
Ze Zhang, Dandan Li, Yao Zhao, Zhihao Fan, Jie Xiang, Xuedong Wang, Xiaohong Cui
Summary: This study designed a multi-instruction SSVEP speller based on dry electrode. Through the combination of EOG and SSVEP signals, the speller can be flexibly controlled. The frequency of SSVEP stimulation sub-block is recoded in time and space by TSFC-SSVEP stimulation paradigm, which greatly improves the number of output instructions of BCI system in dry electrode environment.
FRONTIERS IN COMPUTATIONAL NEUROSCIENCE
(2023)
Letter
Public, Environmental & Occupational Health
Yan-Ren Lin, Nai-Rong Zhong, Cheng-Chieh Huang, Chih-Pei Su, Chien-Yu Shen, Lun-De Liao
ANNALS OF WORK EXPOSURES AND HEALTH
(2023)
Article
Computer Science, Artificial Intelligence
Chin-Teng Lin
Summary: Donald C. Wunsch II is a professor at the Missouri University of Science and Technology. He holds multiple degrees and has extensive research experience in various fields. His research interests include real-time learning, unsupervised learning, reinforcement learning, and their applications. He has received multiple international awards and held important positions in various institutions.
IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE
(2023)
Article
Chemistry, Analytical
Yuhling Wang, Yu-Lin Chen, Chih-Mao Huang, Li-Tzong Chen, Lun-De Liao
Summary: The ViCPAI system is a new visible CCD camera-guided photoacoustic imaging system that provides accurate positioning of the ultrasound probe and achieves reproducible positioning. The system utilizes a MATLAB-based platform with an intuitive user interface. Experimental results demonstrate that the ViCPAI system accurately locates target areas and is suitable for animal and clinical experiments.
Article
Computer Science, Software Engineering
Howe Yuan Zhu, Hsiang-Ting Chen, Chin-Teng Lin
Summary: Advancements in virtual reality technology have been beneficial for acrophobia research. Virtual reality height exposure is a reliable method of inducing stress with low variance across demographics. However, the impact of the increasing disparity between virtual and physical environments on stress levels remains unclear.
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2023)
Review
Computer Science, Artificial Intelligence
M. Tanveer, Aryan Rastogi, Vardhan Paliwal, M. A. Ganaie, A. K. Malik, Javier Del Ser, Chin-Teng Lin
Summary: This paper extensively reviews the use of ensemble deep learning methods for various speech signal related tasks and aims to comprehensively evaluate existing works and provide future directions for further development. It serves as a valuable resource for researchers in academia and industry working with speech signals.
Article
Computer Science, Artificial Intelligence
Yiqun Duan, Zhen Wang, Yi Li, Jianhang Tang, Yu-Kai Wang, Chin-Teng Lin
Summary: In this paper, a cross-task neural architecture search framework called CTNAS-EEG is proposed for EEG signal recognition, which can automatically design the network structure and improve the accuracy of EEG signal recognition. The framework explores and analyzes the differences in searched structures across different EEG tasks, and analyzes model performance by customizing the model structure for each human subject. The experimental results show that the proposed framework achieves state-of-the-art performance on various EEG tasks such as Motor Imagery and Emotion recognition.
Article
Multidisciplinary Sciences
Howe Yuan Zhu, Shayikh Nadim Hossain, Craig Jin, Avinash K. Singh, Minh Tran Duc Nguyen, Lil Deverell, Vincent Nguyen, Felicity S. Gates, Ibai Gorordo Fernandez, Marx Vergel Melencio, Julee-anne Renee Bell, Chin-Teng Lin
Summary: This research explores the potential of acoustic touch as a wearable spatial audio solution for assisting blind individuals in finding objects. The study shows that the wearable device effectively aids in object recognition and reaching, without significantly increasing the user's cognitive workload.
Article
Engineering, Biomedical
Yuhling Wang, Vassiliy Tsytsarev, Lun-De Liao
Summary: The study of epileptic seizures is closely related to neurovascular coupling. Laser speckle contrast imaging can provide information about cerebral blood flow in the area of epileptic activity, and combined with electrocorticography, it can evaluate the effectiveness of drugs in epileptic seizures and provide spatial and temporal information.
APL BIOENGINEERING
(2023)
Article
Engineering, Biomedical
Yi-Ju Ho, Hsiang-Lung Cheng, Lun-De Liao, Yu-Chun Lin, Hong-Chieh Tsai, Chih-Kuang Yeh
Summary: This study used oxygen-loaded microbubbles (OMBs) and ultrasound stimulation for sonoperfusion and local oxygen therapy, leading to the reduction of brain infarction size and neuroprotection. The results showed improved blood flow and oxygen levels, reduced brain infarction, and improved limb coordination, as well as activation of anti-inflammatory and anti-apoptosis responses and neuroprotection.
BIOMATERIALS RESEARCH
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Carlos Alfredo Tirado Cortes, Chin-Teng Lin, Tien-Thong Nguyen Do, Hsiang-Ting Chen
Summary: Previous studies have shown that natural walking can reduce the risk of VR sickness. However, many users still experience VR sickness when using VR headsets that allow free walking in room-scale spaces. This paper investigates VR sickness and postural instability during walking in an immersive virtual environment using an EEG headset and a full-body motion capture system. The experiment induced VR sickness by gradually increasing the translation gain beyond the user's detection threshold. The results reveal differences in postural stability and brain activities between participants with and without VR sickness symptoms.
2023 IEEE CONFERENCE VIRTUAL REALITY AND 3D USER INTERFACES, VR
(2023)
Article
Engineering, Biomedical
Lubin Meng, Xue Jiang, Jian Huang, Zhigang Zeng, Shan Yu, Tzyy-Ping Jung, Chin-Teng Lin, Ricardo Chavarriaga, Dongrui Wu
Summary: This paper proposes a narrow period pulse-based poisoning attack on EEG-based BCIs, which makes adversarial attacks easier to implement. By injecting poisoning samples into the training set, dangerous backdoors can be created in the machine learning model. Test samples with the backdoor key will be classified into the target class specified by the attacker. The distinguishing feature of this approach is that the backdoor key does not need to be synchronized with the EEG trials, making it very easy to implement. The effectiveness and robustness of the backdoor attack approach is demonstrated, raising a critical security concern for EEG-based BCIs and calling for urgent attention to address it.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2023)
Article
Automation & Control Systems
Leijie Zhang, Ye Shi, Yu-Cheng Chang, Chin-Teng Lin
Summary: This article proposes a robust fuzzy neural network (RFNN) to overcome the generalization and dimensionality issues in handling uncertainty in data. The RFNN has an adaptive inference engine that can handle samples with high-level uncertainty and dimensions. The inference engine can learn the firing strength adaptively and process the uncertainty in membership function values.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Computer Science, Artificial Intelligence
Weiping Ding, Yu Geng, Jiashuang Huang, Hengrong Ju, Haipeng Wang, Chin-Teng Lin
Summary: In this research, we propose a multigranularity random walk transformer model guided by an attention mechanism to find the regions that influence medical image recognition tasks. Our method improves interpretability in the field.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Chin-Teng Lin, Haichao Zhang, Liang Ou, Yu-Cheng Chang, Yu-Kai Wang
Summary: This article proposes an adaptive trust model to evaluate comprehensive trust values based on multiple pieces of evidence, using information fusion and reinforcement learning to increase the efficiency of cooperation in multiagent teaming. The performance of the trust model is verified through experiments and compared with human-designed fusion methods, showing better representation of agent performance in different scenario settings.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
(2023)
Article
Automation & Control Systems
Zeyi Liu, Fuyuan Xiao, Chin-Teng Lin, Zehong Cao
Summary: This article proposes a novel approach for evidential multisource data fusion based on game-theoretic analysis. By introducing the Shapley function, the negative influence of redundant evidence is mitigated, and the computational complexity of the fusion procedure is reduced.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)