Article
Engineering, Biomedical
Yucun Zhong, Lin Yao, Yueming Wang
Summary: This study proposes a tactile-assisted calibration method for a motor imagery based BCI system, which significantly improves performance and reduces calibration time. By applying tactile stimulation to the hand wrist, the subjects are assisted in the MI task, resulting in better performance compared to the conventional calibration method.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2023)
Article
Engineering, Biomedical
Yucun Zhong, Lin Yao, Ji Wang, Yueming Wang
Summary: In this study, a tactile sensation assisted motor imagery training method is proposed to improve the performance of MI-based BCI. The training group received training with tactile stimulation, while the control group performed regular tasks. The results showed that the proposed training method significantly improved the performance of motor imagery.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2023)
Article
Chemistry, Multidisciplinary
Catalin Dumitrescu, Ilona-Madalina Costea, Augustin Semenescu
Summary: This paper investigates signal processing methods for the implementation of a brain-computer interface based on neurological phenomena during motor tasks. The research aims to allow users to manipulate virtual structures through brain activity, correlating with specific mental tasks. The results show that the use of biopotentials in human-computer interfaces is a viable method for applications in the field of BCI, with potential for improving cognitive performance.
APPLIED SCIENCES-BASEL
(2021)
Article
Biology
Huiying Li, Dongxue Zhang, Jingmeng Xie
Summary: A novel dual-attention-based adversarial network for motor imagery classification (MI-DABAN) is proposed, which leverages multiple subjects' knowledge to improve a single subject's classification performance. The method employs a clever adversarial learning method and two unshared attention blocks, resulting in effective and superior classification performance.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Computer Science, Interdisciplinary Applications
Fangzhou Xu, Xiaoyan Xu, Yanan Sun, Jincheng Li, Gege Dong, Yuandong Wang, Han Li, Lei Wang, Yingchun Zhang, Shaopeng Pang, Sen Yin
Summary: This study introduces a long short-term memory recurrent neural network for decoding electroencephalogram or electrocorticogram and implementing an effective brain-computer interface system. By combining the decoded features with a gradient boosting classifier, high recognition accuracies can be achieved.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2022)
Article
Engineering, Biomedical
Jing Luo, Weiwei Shi, Na Lu, Jie Wang, Hao Chen, Yaojie Wang, Xiaofeng Lu, Xiaofan Wang, Xinhong Hei
Summary: This study aims to develop an adaptable MI-BCI system for multiple subjects, utilizing a twin cascaded softmax convolutional neural network (TCSCNN) model. Experimental results demonstrate that the proposed TCSCNN significantly improves precision and convergence in multisubject MI recognition compared to state-of-the-art CNN models.
JOURNAL OF NEURAL ENGINEERING
(2021)
Article
Engineering, Biomedical
Mohammad Mahdi Togha, Mohammad Reza Salehi, Ebrahim Abiri
Summary: In this study, the combined LAE-CSP method outperforms other tested methods, especially showing better performance with only ten labeled samples per class. This approach effectively enhances the performance of motor imagery-based brain-computer interfaces by taking advantage of both LAE and CSP while compensating for their drawbacks.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Engineering, Multidisciplinary
Xiaolin Liu, Peirong Yan, Shuailei Zhang, Dezhi Zheng
Summary: This paper presents a novel interception method called long and short windows (LSWs) for brain-computer interfaces (BCI) based on motor imagery (MI) using electroencephalogram (EEG). The proposed LSW method improves the classification accuracies compared to the fixed-length time window method on both a public EEG dataset and a self-collected dataset. The results suggest that the LSW method offers a promising approach for the research of MI classification methods in BCI.
MEASUREMENT SCIENCE AND TECHNOLOGY
(2022)
Review
Chemistry, Analytical
Amardeep Singh, Ali Abdul Hussain, Sunil Lal, Hans W. Guesgen
Summary: The paper reviews recent advances and current status of MI-BCI systems, highlighting that the technology is mainly confined to controlled environments and commercial deployment is still pending.
Review
Chemistry, Analytical
Aurora Saibene, Mirko Caglioni, Silvia Corchs, Francesca Gasparini
Summary: In recent decades, there has been significant growth in the automatic recognition and interpretation of brain waves through EEG technologies, leading to the development of non-invasive brain-computer interfaces (BCIs) that allow communication between humans and external devices. This paper presents a systematic review of EEG-based BCIs, with a focus on the promising paradigm of motor imagery (MI) and the use of wearable devices. The review assesses the maturity levels of these systems from technological and computational perspectives, and also provides a comprehensive list of experimental paradigms and available datasets for benchmarking and guiding the development of new applications and computational models.
Article
Engineering, Biomedical
Jixiang Li, Yurong Li, Min Du
Summary: The research on intention recognition through brain-computer interface technology is crucial for the rehabilitation of stroke and spinal cord injury patients. In this study, an improved framework combining deep separation convolution neural network and extreme learning machine is proposed to enhance the recognition rate of motor intention. Experimental results demonstrate a recognition rate of 97.88% using the public EEGMMIDB datasets.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Automation & Control Systems
Biao Sun, Zhengkun Liu, Zexu Wu, Chaoxu Mu, Ting Li
Summary: This article proposes an end-to-end deep learning framework for classification of electroencephalogram-based motor imagery tasks. The framework utilizes graph convolutional neural networks to fully exploit the correlation of signals in the temporal and spatial domains. Two channel selection methods are proposed, and experimental results demonstrate the superiority of the proposed method in terms of classification accuracy and robustness.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Computer Science, Artificial Intelligence
Bin Shi, Quan Wang, Shuai Yin, Zan Yue, Yaping Huai, Jing Wang
Summary: The study proposed a new BHS method for selecting optimal channels in MI-based BCI. Through comparative experiments on test datasets, the results demonstrated that the BHS method significantly improved classification accuracy, outperforming the traditional CSP method.
Review
Chemistry, Analytical
Arrigo Palumbo, Vera Gramigna, Barbara Calabrese, Nicola Ielpo
Summary: Innovative aids, devices, and assistive technologies are needed to help individuals with severe disabilities live independently and improve overall health. Brain-Computer Interfaces using EEG data show potential for enhancing wheelchair control and movement in people with significant health challenges.
Article
Computer Science, Software Engineering
Guoyang Liu, Janet H. Hsiao, Weidong Zhou, Lan Tian
Summary: The Matlab-based real-time motor imagery brain-computer interface (MI-BCI) software enables individuals with motor dysfunction to interact with the outside world. It consists of a real-time EEG analysis platform and a model training platform. The software can analyze real-time EEG data and provide feedback, as well as train a CSP-based MI classification model. It is hoped that this software will contribute to the development of EEG-based MI paradigm design and EEG classification algorithms.
Article
Engineering, Biomedical
Yun S. Park, G. Rees Cosgrove, Joseph R. Madsen, Emad N. Eskandar, Leigh R. Hochberg, Sydney S. Cash, Wilson Truccolo
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2020)
Article
Clinical Neurology
David Fischer, Zachary D. Threlkeld, Yelena G. Bodien, John E. Kirsch, Susie Y. Huang, Pamela W. Schaefer, Otto Rapalino, Leigh R. Hochberg, Bruce R. Rosen, Brian L. Edlow
ANNALS OF NEUROLOGY
(2020)
Article
Engineering, Biomedical
Nir Even-Chen, Dante G. Muratore, Sergey D. Stavisky, Leigh R. Hochberg, Jaimie M. Henderson, Boris Murmann, Krishna V. Shenoy
NATURE BIOMEDICAL ENGINEERING
(2020)
Article
Multidisciplinary Sciences
Francis R. Willett, Donald T. Avansino, Leigh R. Hochberg, Jaimie M. Henderson, Krishna V. Shenoy
Summary: BCIs can restore communication for individuals with paralysis by decoding attempted handwriting movements, achieving typing speeds of 90 characters per minute with high accuracy. This approach opens new possibilities for BCIs and demonstrates the feasibility of decoding rapid, dexterous movements even years after paralysis.
Article
Clinical Neurology
David J. Lin, Kimberly S. Erler, Samuel B. Snider, Anna K. Bonkhoff, Julie A. DiCarlo, Nicole Lam, Jessica Ranford, Kristin Parlman, Audrey Cohen, Jennifer Freeburn, Seth P. Finklestein, Lee H. Schwamm, Leigh R. Hochberg, Steven C. Cramer
Summary: The study found that cognitive demands influenced upper extremity motor performance during recovery from acute stroke, with patients performing significantly worse on tasks with higher cognitive demands. Motor performance was related to cognitive dysfunction, especially in tasks involving cognitive demands, and neuroanatomic injury was associated with both the type of task and the location of the injury.
Article
Clinical Neurology
Jimmy C. Yang, Nitish M. Harid, Fabio A. Nascimento, Vasileios Kokkinos, Abigail Shaughnessy, Alice D. Lam, M. Brandon Westover, Thabele M. Leslie-Mazwi, Leigh R. Hochberg, Eric S. Rosenthal, Andrew J. Cole, Robert M. Richardson, Sydney S. Cash
Summary: There is currently no clear evidence-based treatment paradigm for refractory and super-refractory status epilepticus, but neurosurgical neuromodulation techniques may be considered as an alternative treatment option.
ANNALS OF CLINICAL AND TRANSLATIONAL NEUROLOGY
(2021)
Review
Clinical Neurology
Michael J. Young, Yelena G. Bodien, Joseph T. Giacino, Joseph J. Fins, Robert D. Truog, Leigh R. Hochberg, Brian L. Edlow
Summary: This thematic review discusses the neuroethical questions raised by recent advances in the diagnosis and treatment of disorders of consciousness, providing a clinically applicable framework for understanding the current taxonomy of these disorders and proposing an approach to identifying and evaluating actionable neuroethical issues in research and clinical care. The discussion highlights the importance of increased awareness about these issues and opportunities for optimizing ethically responsible care, especially in the context of the current surge in critically ill patients with disorders of consciousness associated with COVID-19 worldwide.
Editorial Material
Medicine, General & Internal
Leigh R. Hochberg, Sydney S. Cash
NEW ENGLAND JOURNAL OF MEDICINE
(2021)
Article
Neurosciences
Angelique C. Paulk, Yoav Kfir, Arjun R. Khanna, Martina L. Mustroph, Eric M. Trautmann, Dan J. Soper, Sergey D. Stavisky, Marleen Welkenhuysen, Barundeb Dutta, Krishna Shenoy, Leigh R. Hochberg, R. Mark Richardson, Ziv M. Williams, Sydney S. Cash
Summary: Neuropixels probes allow for simultaneous recordings from more than 200 cortical neurons in human participants during neurosurgical procedures. This technology provides valuable insights into human cognition and pathology.
NATURE NEUROSCIENCE
(2022)
Article
Audiology & Speech-Language Pathology
Miriam A. Goldberg, Leigh R. Hochberg, Dawn Carpenter, J. Matthias Walz
Summary: The development of the Manually Operated Communication System (MOCS) aimed to provide a speech-output technology for nonvocal ICU patients with manual dexterity impairments, potentially improving communication for this patient population in intensive care settings.
AUGMENTATIVE AND ALTERNATIVE COMMUNICATION
(2021)
Article
Computer Science, Cybernetics
Darrel R. Deo, Paymon Rezaii, Leigh R. Hochberg, Allison M. Okamura, Krishna Shenoy, Jaimie M. Henderson
Summary: Intracortical brain-computer interfaces (iBCIs) provide a means for paralysis patients to control devices with decoded brain signals, but further improvement is needed to approach able-bodied control levels. Providing proprioceptive feedback through mechanical haptic stimulation can enhance motor cortical neuron responses and iBCI control performance. Additionally, online iBCI cursor control with continuous skin-shear feedback led to slightly but significantly improved performance compared to visual feedback alone.
IEEE TRANSACTIONS ON HAPTICS
(2021)
Article
Neurosciences
Daniel B. Rubin, Tommy Hosman, Jessica N. Kelemen, Anastasia Kapitonava, Francis R. Willett, Brian F. Coughlin, Eric Halgren, Eyal Y. Kimchi, Ziv M. Williams, John D. Simeral, Leigh R. Hochberg, Sydney S. Cash
Summary: Replay of motor cortex neural activity may occur during sleep following motor learning in humans.
JOURNAL OF NEUROSCIENCE
(2022)
Article
Clinical Neurology
Kimberly S. Erler, Rui Wu, Julie A. DiCarlo, Marina F. Petrilli, Perman Gochyyev, Leigh R. Hochberg, Steven A. Kautz, Lee H. Schwamm, Steven C. Cramer, Seth P. Finklestein, David J. Lin
Summary: This study found that the mRS is related to domain-specific outcomes after stroke, confirming its established value in stroke trials. However, it does not precisely distinguish differences in impairment and function, nor does it sufficiently capture meaningful clinical changes across impairment, activities of daily living status, and mobility. These findings underscore the potential utility of incorporating detailed phenotypic measures along with the mRS in future stroke trials.
Article
Medicine, General & Internal
Jesse Dawson, Charles Y. Liu, Gerard E. Francisco, Steven C. Cramer, Steven L. Wolf, Anand Dixit, Jen Alexander, Rushna Ali, Benjamin L. Brown, Wuwei Feng, Louis DeMark, Leigh R. Hochberg, Steven A. Kautz, Arshad Majid, Michael W. O'Dell, David Pierce, Cecilia N. Prudente, Jessica Redgrave, Duncan L. Turner, Navzer D. Engineer, Teresa J. Kimberley
Summary: The study investigates the safety and efficacy of vagus nerve stimulation paired with rehabilitation for improving long-term arm function after ischemic stroke. Results from the randomized trial of 108 participants showed that the VNS group had significantly greater improvements in arm function scores on the first day after treatment completion and higher clinical response rates at 90 days post-treatment compared to the control group.
Article
Engineering, Biomedical
Guy H. Wilson, Sergey D. Stavisky, Francis R. Willett, Donald T. Avansino, Jessica N. Kelemen, Leigh R. Hochberg, Jaimie M. Henderson, Shaul Druckmann, Krishna Shenoy
JOURNAL OF NEURAL ENGINEERING
(2020)