Article
Computer Science, Information Systems
Jaiteg Singh, Farman Ali, Rupali Gill, Babar Shah, Daehan Kwak
Summary: Rehabilitation using EEG-assisted Brain-Computer Interface (BCI) is a potential approach for restoring or enhancing damaged muscles and motor systems. This literature review explores the latest developments in BCI and motor control for rehabilitation, as well as typical EEG apparatuses for BCI-driven rehabilitation. It also summarizes significant studies using machine learning techniques for rehabilitation assessment.
Review
Chemistry, Analytical
Kais Belwafi, Sofien Gannouni, Hatim Aboalsamh
Summary: BCI systems have a wide range of applications in restoring capabilities for people with severe motor disabilities, with a growing number of systems being developed. There is a significant interest in implementing BCIs on portable platforms, with smaller size, faster loading times, lower cost, fewer resources, and lower power consumption compared to full PCs.
Article
Neurosciences
Xiyuan Jiang, Emily Lopez, James R. Stieger, Carol M. Greco, Bin He
Summary: The study found that experienced meditators outperformed control subjects in both 1D and 2D cursor control tasks, with fewer BCI inefficient subjects in the meditator group. Neurophysiological differences were also observed between the two groups, indicating higher resting SMR predictor, more stable resting mu rhythm, and larger control signal contrast in meditators.
FRONTIERS IN NEUROSCIENCE
(2021)
Article
Engineering, Biomedical
Kangning Wang, Shuang Qiu, Wei Wei, Weibo Yi, Huiguang He, Minpeng Xu, Tzyy-Ping Jung, Dong Ming
Summary: This study investigates the vigilance levels in brain-computer interface (BCI) tasks by analyzing EEG patterns and performances. The results show that specific neural patterns for high and low vigilance levels are relatively stable across sessions. Differential entropy features significantly differ between different vigilance levels and BCI tasks, with the theta frequency band features playing a critical role in vigilance estimation. This study provides a foundation for further research in vigilance estimation in BCI applications.
JOURNAL OF NEURAL ENGINEERING
(2023)
Article
Psychology, Multidisciplinary
Shuang Liang, Mingbo Yin, Yecheng Huang, Xiubin Dai, Qiong Wang
Summary: The proposed nuclear norm regularized deep neural network framework (NRDNN) captures structural information among different brain regions in EEG decoding. It can learn the high-level representations of EEG signals within multiple brain regions and automatically adjust the contributions of them. Experimental results demonstrate that the proposed NRDNN achieves state-of-the-art performance by leveraging structural information.
FRONTIERS IN PSYCHOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Xiang Li, Jingjing Chen, Nanlin Shi, Chen Yang, Puze Gao, Xiaogang Chen, Yijun Wang, Shangkai Gao, Xiaorong Gao
Summary: This study proposes a hybrid brain-computer interface system that combines electroencephalogram (EEG) with magnetoencephalogram (MEG) in order to enhance BCI performance. The hybrid system, compared to using EEG alone, achieves higher signal quality and a wider effective bandwidth with the incorporation of MEG. Simultaneous recording experiments demonstrate that the hybrid system achieves a significantly higher information transfer rate than either modality alone, and also improves the classification accuracy of BCI illiterate participants.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Hardware & Architecture
Jian Zhao, Dan Li, Jing Pu, Yue Meng, Asma Sbeih, Abdulsattar Abdullah Hamad
Summary: This study introduces a new BCI model based on SSVEP and eye gaze indications for the Smart home application, which could be helpful for Augmentative Communication. The technique presented in this study can support the other BCI-managed applications with high precision, multiple instructions, and fast response.
COMPUTERS & ELECTRICAL ENGINEERING
(2022)
Article
Engineering, Biomedical
Weihua Pei, Xiaoting Wu, Xiang Zhang, Aihua Zha, Sen Tian, Yijun Wang, Xiaorong Gao
Summary: A PreG electrode was developed for EEG signal acquisition, offering a short installation time and good comfort. While the PreG electrode showed lower impedance compared to wet electrodes, there was no significant difference in performance in Brain-Computer Interface experiments between the two types of electrodes.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2022)
Article
Chemistry, Analytical
Lisa-Marie Vortmann, Pascal Weidenbach, Felix Putze
Summary: With the emergence of lightweight and low-cost EEG headsets, the feasibility of consumer-oriented brain-computer interfaces (BCI) is increasing. The combination of portable smartphones and easy-to-use EEG dry electrode headbands provides intriguing new applications and methods of human-computer interaction. This study integrated user attentional state awareness into a smartphone application for an augmented reality written language translator, using a low-cost EEG device. While the results did not fully support the assumption that BCI improves usability, the study showed promising paths towards mobile consumer-oriented BCI usage.
Article
Neurosciences
Songwei Li, Junyi Duan, Yu Sun, Xinjun Sheng, Xiangyang Zhu, Jianjun Meng
Summary: Motor imagery (MI) is commonly used in brain-computer interface (BCI) strategies, but fatigue can affect mental states. A study with 12 healthy participants showed that fatigue increased but engagement decreased during specific sessions, while BCI performances remained stable despite changes in mental states.
FRONTIERS IN NEUROSCIENCE
(2021)
Review
Neurosciences
Shireen Fathima, Sheela Kiran Kore
Summary: Electroencephalogram (EEG) is commonly used for monitoring mental activities, with optimization techniques playing a vital role in brain-computer interfaces (BCI). Utilizing high-resolution multi-channel EEG devices, optimization functions have achieved reliable outcomes in device control.
FRONTIERS IN NEUROSCIENCE
(2021)
Article
Engineering, Electrical & Electronic
Shiwei Cheng, Jialing Wang, Danyi Sheng, Yijian Chen
Summary: Biometric authentication using a hybrid brain-computer interface (BCI), combining electroencephalogram (EEG) and eye movement data features, achieved an average accuracy of 84.36% (highest 88.35%) in identifying shoulder surfers in anti-shoulder-surfing experiments, outperforming single feature-based approaches. Additional experiments demonstrated the effectiveness of the approach in reducing user misidentification. This approach holds great potential for implementing hybrid BCI authentication in anti-shoulder-surfing applications.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Computer Science, Information Systems
Eman A. Abdel-Ghaffar, Mohamed Daoudi
Summary: Brain signals have been proposed as a strong biometric due to their unique characteristics. However, there are challenges in using them for cryptographic key generation due to the non stationary nature of EEG signals. In this study, the stability of using EEG signals for personal authentication and key generation is investigated, achieving high accuracy in authentication and generating unique and repeatable keys.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Weichen Huang, Wei Wu, Molly V. Lucas, Haiyun Huang, Zhenfu Wen, Yuanqing Li
Summary: Emotion regulation is crucial for daily life by helping individuals deal with social problems and safeguarding mental and physical health. However, evaluating the efficacy of emotion regulation and assessing individual improvement remains challenging. This study used neurofeedback training and an EEG-based BCI system to enable effective emotion regulation.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Fei Wang, Weiwei Zhang, Zongfeng Xu, Jingyu Ping, Hao Chu
Summary: In this study, a new method is proposed to adapt to new subjects in aBCI, addressing individual differences and data bias. The deep multi-source adaptation transfer network (DMATN) is used to achieve adaptation between correlated source domain and target domain, resulting in promising performance on the SEED dataset.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Engineering, Biomedical
Jin Han, Minpeng Xu, Xiaolin Xiao, Weibo Yi, Tzyy-Ping Jung, Dong Ming
Summary: This study developed a high-speed BCI system with more than 200 targets, encoded by a combination of electroencephalography features. The system achieved high accuracy and information transfer rate in offline and online experiments, showing promise for extending BCI's application scenarios.
JOURNAL OF NEURAL ENGINEERING
(2023)
Article
Neurosciences
Hei-Yin Hydra Ng, Changwei W. Wu, Feng-Ying Huang, Chih-Mao Huang, Chia-Fen Hsu, Yi-Ping Chao, Tzyy-Ping Jung, Chun-Hsiang Chuang
Summary: Practicing mindfulness can lead to the development of emotional regulation skills, and studies have suggested that it promotes functional connectivity in the brain. To examine the changes in effective connectivity due to mindfulness training, EEG signals were analyzed. The results showed that low-gamma band effective connectivity increased globally after mindfulness training, and high-beta band effective connectivity increased during breathing. The changes in effective connectivity in the right lateral prefrontal area predicted mindfulness and emotional regulation abilities.
JOURNAL OF NEUROSCIENCE RESEARCH
(2023)
Article
Computer Science, Artificial Intelligence
Chao Lyu, Yuhui Shi, Lijun Sun, Chin-Teng Lin
Summary: This article proposes a novel algorithm for community detection in multiplex networks. The algorithm decomposes the problem into two parts, detecting specific community partitions for each component layer and finding the composite community structure shared by all layers. Experimental results demonstrate that the algorithm outperforms classical and state-of-the-art algorithms in community detection on multiplex networks.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2023)
Article
Computer Science, Artificial Intelligence
Leijie Zhang, Ye Shi, Yu-Cheng Chang, Chin-Teng Lin
Summary: In this article, a federated fuzzy neural network (FedFNN) with evolutionary rule learning (ERL) is proposed to handle non-IID issues and data uncertainties. The FedFNN maintains a global set of rules in a server and a personalized subset of these rules for each local client. ERL encourages rule variations by activating superior rules and deactivating inferior rules for local clients with non-IID data. Experimental results demonstrate the superiority of the FedFNN over existing methods.
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2023)
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)
Article
Neurosciences
Rong Li, Minpeng Xu, Jia You, Xiaoyu Zhou, Jiayuan Meng, Xiaolin Xiao, Tzyy-Ping Jung, Dong Ming
Summary: A novel lateralized visual discrimination paradigm was used to investigate the effects of steady-state visual evoked potentials (SSVEPs) on visuospatial selective attention. The results showed that SSVEPs had frequency-specific effects on left-right attentional asymmetries in both behavior and neural activities.
FRONTIERS IN NEUROSCIENCE
(2023)
Editorial Material
Computer Science, Information Systems
Weiping Ding, Jun Liu, Chin-Teng Lin, Dariusz Mrozek
INFORMATION SCIENCES
(2023)
Review
Computer Science, Interdisciplinary Applications
Yi-Ling Fan, Fang-Rong Hsu, Yuhling Wang, Lun-De Liao
Summary: Zebrafish have been widely used in biomedical research due to their stress response, behavior differences, and sensitivity to drug treatments. Advancements in AI technology have enabled automated tracking, image recognition, and data analysis, enhancing efficiency and insights in research. AI applications in zebrafish research include behavior analysis, genomics, and neuroscience, helping researchers analyze images, uncover gene-biology relationships, and understand complex neural networks. Further advancements in AI technology are expected to enhance zebrafish research, improving our understanding of this important animal model.
MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING
(2023)
Article
Computer Science, Interdisciplinary Applications
Chin-Teng Lin, Yuhling Wang, Sheng-Fu Chen, Kuan-Chih Huang, Lun-De Liao
Summary: This study aims to develop a multichannel, high-resolution (24-bit), and high-sampling-rate brain-computer interface (BCI) device that transmits signals via Wi-Fi. The system is based on a Cortex-M4 microcontroller with a Wi-Fi subsystem, providing improved signal quality. EEG data is received through Wi-Fi transmission and saved for offline analysis via a LabVIEW-based user interface. The system was validated through ERP and SSVEP experiments, demonstrating its suitability for recording EEG measurements and potential in practical applications.
MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING
(2023)
Article
Engineering, Biomedical
Hsiu-Ching Liu, Chu-Han Huang, Min-Ren Chiang, Ru-Siou Hsu, Tsu-Chin Chou, Tsai-Te Lu, I-Chi Lee, Lun-De Liao, Shih-Hwa Chiou, Zhong-Hong Lin, Shang-Hsiu Hu
Summary: A mussel-inspired nitric oxide-release microreservoir (MINOR) that combines the features of reactive oxygen species (ROS) scavengers and sustained NO release is developed for TBI therapy. MINOR demonstrates remarkable efficacy in enhancing recovery in mice.
ADVANCED HEALTHCARE MATERIALS
(2023)
Article
Computer Science, Artificial Intelligence
Ayman Elgharabawy, Mukesh Prasad, Chin-Teng Lin
Summary: This paper proposes a new native ranker neural network to address the problem of multi-label ranking. The network uses a new activation and error functions and architecture to deal with incomparable preference orders. The evaluation shows that PNN outperforms five previously proposed methods in terms of accurate results with high computational efficiency.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Fuyuan Xiao, Zehong Cao, Chin-Teng Lin
Summary: Complex evidence theory (CET) is an effective and interpretable method for uncertainty reasoning in knowledge-based systems. This paper proposes a complex conflict coefficient to measure the conflict between complex mass functions or complex basic belief assignments (CBBAs) in CET. The proposed coefficient satisfies desired conflict measurement properties and is validated through numerical examples.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Hongxia Li, Zhongyi Cai, Jingya Wang, Jiangnan Tang, Weiping Ding, Chin-Teng Lin, Ye Shi
Summary: Federated learning is a new learning paradigm where multiple clients collaboratively train a machine learning model while protecting privacy. Personalized federated learning extends this paradigm by learning personalized models to overcome client heterogeneity. This paper investigates the impact of federated learning algorithms on self-attention and reveals negative impacts on self-attention in the presence of data heterogeneity. Based on this, a novel Transformer-based federated learning framework called FedTP is proposed, which learns personalized self-attention for each client while aggregating other parameters among the clients.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Engineering, Biomedical
Jinzhao Zhou, Yiqun Duan, Yingying Zou, Yu-Cheng Chang, Yu-Kai Wang, Chin-Teng Lin
Summary: A novel EEG recognition method called Speech2EEG is proposed, which leverages pretrained speech features to improve the accuracy of EEG recognition. It adapts a pretrained speech processing model to the EEG domain, extracts multichannel temporal embeddings, and integrates them using various aggregation methods. Experimental results show that the proposed method achieves state-of-the-art performance on challenging MI datasets with accuracies of 89.5% and 84.07%.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(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)