检索结果-内蒙古大学图书馆

EEG motor imagery decoding: a framework for comparative analysis with channel attention mechanisms

JOURNAL OF NEURAL ENGINEERING 2024年第3期21卷 036020-036020页

作者： Wimpff, Martin Gizzi, Leonardo Zerfowski, Jan Yang, Bin Univ Stuttgart Inst Signal Proc & Syst Theory Stuttgart Germany Fraunhofer Inst Mfg Engn & Automat IPA Stuttgart Germany Charite Univ Med Berlin Clin Neurotechnol Lab Dept Psychiat & Neurosci Charite Campus Mitte CCM Berlin Germany

Objective. The objective of this study is to investigate the application of various channel attention mechanisms within the domain of brain-computer interface (BCI) for motor imagery decoding. Channel attention mechanisms can be seen as a powerful evolution of spatial filters traditionally used for motor imagery decoding. This study systematically compares such mechanisms by integrating them into a lightweight architecture framework to evaluate their impact. Approach. We carefully construct a straightforward and lightweight baseline architecture designed to seamlessly integrate different channel attention mechanisms. This approach is contrary to previous works which only investigate one attention mechanism and usually build a very complex, sometimes nested architecture. Our framework allows us to evaluate and compare the impact of different attention mechanisms under the same circumstances. The easy integration of different channel attention mechanisms as well as the low computational complexity enables us to conduct a wide range of experiments on four datasets to thoroughly assess the effectiveness of the baseline model and the attention mechanisms. Results. Our experiments demonstrate the strength and generalizability of our architecture framework as well as how channel attention mechanisms can improve the performance while maintaining the small memory footprint and low computational complexity of our baseline architecture. Significance. Our architecture emphasizes simplicity, offering easy integration of channel attention mechanisms, while maintaining a high degree of generalizability across datasets, making it a versatile and efficient solution for electroencephalogram motor imagery decoding within BCIs.

关键词： deep learning attention brain-computer-interface motor imagery EEG decoding

来源：评论

学校读者我要写书评

暂无评论

Development of an Analog Front-End for brain-computer interfaces 17

Development of an Analog Front-End for Brain-Computer Interf...

引用

17th Conference on Ph.D Research in Microelectronics and Electronics (PRIME)

作者： Doliwa, Sebastian Erbsloh, Andreas Seidl, Karsten Iossifidis, Ioannis Univ Appl Sci Ruhr West Inst Comp Sci Mulheim Germany Univ Duisburg Essen Elect Components & Circuits Duisburg Germany Fraunhofer Inst Microelect Circuits & Syst Duisburg Germany

ISBN: (纸本)9781665467001

In the context of the development of an implantable embedded system interfacing brain activity and enabling paralyzed patients to interact with devices that are usable on an everyday basis, we designed a real-time-suitable, low-power hardware architecture with an artifact-suppressing analog front-end, connected to a neural signal processing pipeline. As part of the ultra low-noise analog front-end (four-channel), the common average referencing (CAR) algorithm is implemented to reduce spurious signals from the environment by recording the adjacent electrodes of an invasive microelectrode array (MEA). A Field-Programmable Gate Array (FPGA) is used for data acquisition of extracellular spike activity and data transmission via Ethernet to a host computer for external processing of neural signals. The presented prototype achieves an SNR of 38 dB by applying spike inputs with amplitudes of 100 mu V using commercially available components.

关键词： brain-computer-interface biomedical circuit low-noise amplifier embedded processing FPGA

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Decoding Model of Upper Limb Movement Intention From EEG Signals Based on Attention State Estimation

引用

IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING 2021年 29卷 2008-2016页

作者： Bi, Luzheng Xia, Shengchao Fei, Weijie Beijing Inst Technol Sch Mech Engn Beijing 100081 Peoples R China

Decoding the motion intention of the human upper limb from electroencephalography (EEG) signals has important practical values. However, existing decoding models are built under the attended state while subjects perform motion tasks. In practice, people are often distracted by other tasks or environmental factors, which may impair decoding performance. To address this problem, in this paper, we propose a hierarchical decoding model of human upper limb motion intention from EEG signals based on attention state estimation. The proposed decoding model includes two components. First, the attention state detection (ASD) component estimates the attention state during the upper limb movement. Next, the motion intention recognition (MIR) component decodes the motion intention by using the decoding models built under the attended and distracted states. The experimental results show that the proposed hierarchical decoding model performs well under the attended and distracted states. This work can advance the application of human movement intention decoding and provides new insights into the study of brain-machine interfaces.

关键词： Decoding Electroencephalography brain modeling Task analysis Variable speed drives Licenses Integrated circuits EEG brain-computer-interface attention states upper limb motion intention hierarchical decoding model

来源：评论

学校读者我要写书评

暂无评论

brainwear: Towards Multi-modal Garment Integrated EEG 25

Brainwear: Towards Multi-modal Garment Integrated EEG

引用

ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) / ACM International Symposium on Wearable computers (ISWC)

作者： Vargas, Juan F. Zhou, Bo Bello, Hymalai Lukowicz, Paul DFKI GmbH Berlin Germany TU Kaiserslautern Kaiserslautern Germany

ISBN: (纸本)9781450384629

We aim to facilitate broad use of EEG sensing in multi-modal smart garments by developing an open-source EEG sensing module with the state-of-the-art analog front-end that is pin/protocol-compatible with popular ecosystems in the wearable and DIY community. The EEG functionality is validated with the neuroscience standard n-back memory load task. We also demonstrate the seamless integration of EEG electrodes with low-frequency Force Sensitive Resistors (FSR) and high-frequency piezoelectric sensors within a single probe. Finally, we show the embedding of the entire setup in a textile baseball cap. We also present how signals from the different modalities complement each other under situations such as motion artifacts and different activities from an unobtrusive head-worn garment. The system is available to the community through a public GitHub repository.

关键词： Wearable EEG brain-computer-interface Open-source toolkit

来源：评论

学校读者我要写书评

暂无评论

Inter-subject Deep Transfer Learning for Motor Imagery EEG Decoding 10

Inter-subject Deep Transfer Learning for Motor Imagery EEG D...

引用

10th International IEEE-EMBS Conference on Neural Engineering (NER)

作者： Wei, Xiaoxi Ortega, Pablo Faisal, A. Aldo Imperial Coll London Brain & Behav Lab Dept Comp London England Imperial Coll London Brain & Behav Lab Dept Bioengn London England

ISBN: (纸本)9781728143378

Convolutional neural networks (CNNs) have become a powerful technique to decode EEG and have become the benchmark for motor imagery EEG brain-computer-interface (BCI) decoding. However, it is still challenging to train CNNs on multiple subjects' EEG without decreasing individual performance. This is known as the negative transfer problem, i.e. learning from dissimilar distributions causes CNNs to misrepresent each of them instead of learning a richer representation. As a result, CNNs cannot directly use multiple subjects' EEG to enhance model performance directly. To address this problem, we extend deep transfer learning techniques to the EEG multi-subject training case. We propose a multi-branch deep transfer network, the Separate-Common-Separate Network (SCSN) based on splitting the network's feature extractors for individual subjects. We also explore the possibility of applying Maximum-mean discrepancy (MMD) to the SCSN (SCSN-MMD) to better align distributions of features from individual feature extractors. The proposed network is evaluated on the BCI Competition IV 2a dataset (BCICIV2a dataset) and our online recorded dataset. Results show that the proposed SCSN (81.8%, 53.2%) and SCSN-MMD (81.8%, 54.8%) outperformed the benchmark CNN (73.4%, 48.8%) on both datasets using multiple subjects. Our proposed networks show the potential to utilise larger multi-subject datasets to train an EEG decoder without being influenced by negative transfer.

关键词： brain-computer-interface EEG multi-subject deep learning transfer learning online decoding

来源：评论

学校读者我要写书评

暂无评论

Intelligent agent for real-world applications on robotic edutainment and humanized co-learning

引用

JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING 2020年第8期11卷 3121-3139页

作者： Lee, Chang-Shing Wang, Mei-Hui Tsai, Yi-Lin Ko, Li-Wei Tsai, Bo-Yu Hung, Pi-Hsia Lin, Lu-An Kubota, Naoyuki Natl Univ Tainan Dept Comp Sci & Informat Engn Tainan Taiwan Natl Chiao Tung Univ Inst Bioinformat & Syst Biol Hsinchu Taiwan Natl Univ Tainan Dept Educ Tainan Taiwan Taiwan Go Assoc Taipei Taiwan Tokyo Metropolitan Univ Grad Sch Syst Design Tokyo Japan

Dynamic assessment with an intelligent agent can differentiate the capabilities and proficiency of students. It can therefore be advocated as an interactive approach to conduct assessments on students in learning systems. Facebook AI Research proposed ELF OpenGo, an open-source reimplementation of the AlphaZero algorithm. They also developed Darkforest, which displays the competence and skills of high-level amateur Go players. To enable these open-source AI bots to assist humans at different levels in learning Go, this paper proposes an intelligent agent for real-world applications in robotic edutainment and humanized co-learning. To achieve this, we successfully constructed an OpenGo Darkforest (OGD) cloud platform using these AI bots and further combined the brain computer interface with the OGD cloud platform to observe the relationship between the brainwaves and win rates of human Go players. The intelligent agent also converted human brainwaves into physiological indices and reflected these in the robot to express human feelings or emotions in real-time. For future educational applications, this paper also presents intelligent robot teachers learning together with students in Taiwan and Japan. More than 200 students have been co-learning with intelligent robot teachers in Tainan, Kaohsiung, Taipei, and Tokyo from 2018 to 2019. The learning performance and feedback from students and teachers has been extremely positive, especially from remedial students.

关键词： Intelligent agent Dynamic assessment Humanized co-learning Robot edutainment brain-computer-interface

来源：评论

学校读者我要写书评

暂无评论

A simplified design of a cEEGrid ear-electrode adapter for the OpenBCI biosensing platform

引用

HARDWAREX 2022年 12卷 e00357页

作者： Knierim, Michael T. Schemmer, Max Bauer, Niklas Karlsruhe Inst Technol KIT Inst Informat Syst & Mkt IISM Kaiserstr 89-93 D-76133 Karlsruhe Germany

We present a simplified design of an ear-centered sensing system built around the OpenBCI Cyton & Daisy biosignal amplifiers and the flex-printed cEEGrid ear-EEG electrodes. This design reduces the number of components that need to be sourced, reduces mechanical artefacts on the recording data through better cable placement, and simplifies the assem-bly. Besides describing how to replicate and use the system, we highlight promising appli-cation scenarios, particularly the observation of large-amplitude activity patterns (e.g., facial muscle activities) and frequency-band neural activity (e.g., alpha and beta band power modulations for mental workload detection). Further, examples for common mea-surement artefacts and methods for removing them are provided, introducing a prototyp-ical application of adaptive filters to this system. Lastly, as a promising use case, we present findings from a single-user study that highlights the system's capability of detecting jaw clenching events robustly when contrasted with 26 other facial activities. Thereby, the sys-tem could, for instance, be used to devise applications that reduce pathological jaw clench-ing and teeth grinding (bruxism). These findings underline that the system represents a valuable prototyping platform for advancing ear-based electrophysiological sensing sys-tems and a low-cost alternative to current commercial alternatives. (c) 2022 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY license (http://***/licenses/by/4.0/).

关键词： OpenBCI cEEGrid brain-computer-interface Wearables

来源：评论

学校读者我要写书评

暂无评论

Technical innovations in stroke rehabilitation - a survey for development of a non-invasive, brainwave-guided, functional muscle stimulation

引用

BMC NEUROLOGY 2022年第1期22卷 194-194页

作者： Liebl, Stefanie Tischendorf, Tim Winterlich, Julia Schaal, Tom West Saxon Univ Appl Sci Zwickau Dept Publ Hlth & Hlth Care Management Kornmarkt 1 D-08056 Zwickau Germany Univ Appl Sci Mittweida Albert Schweitzer Str 22 D-09848 Mittweida Saxony Germany

Background Stroke is one of the most frequent causes of death in Germany and the developed countries. After a stroke, those affected often suffer particularly from functional motor restrictions of the upper extremities. Newer techniques such as the BCI-FES systems aim to establish a communication channel between the brain and external devices with a neuromuscular intervention. The electrical activity of the brain is measured, processed, translated into control signals and can then be used to control an application. Methods As a mixed-methods design (exploratory design), eight guideline-based expert interviews were conducted first. For the quantitative expert survey, 95 chief physicians from the field of neuromedicine in rehabilitation facilities nationwide were subsequently invited to participate in an online survey. Results In our data analysis, we found that doctors are largely open-minded towards new technical rehabilitation systems. In addition to the proper functioning of the system, they consider the understanding of the functionality and the meaningfulness of the system to be particularly important. In addition, the system should be motivating for individuals, generate meaningful movements, be easy to use, evidence-based and quick to set up. Concerns were expressed regarding the understanding of the system's processes, especially in the acute phase after a stroke, as well as the excessive expectation of results from the system on the part of the persons. The experts named stroke patients in rehabilitation phase C, which is about mobilization and recovery, as well as all persons who can understand the language requirements as benefiting groups of people. Conclusion The present study shows that more research should and must be done in the field of BCI-FES interfaces, and various development trends have been identified. The system has the potential to play a leading role in the rehabilitation of stroke patients in the future. Nevertheless, more work should be do

关键词： brain-computer-interface EEG Stroke Motor rehabilitation Functional electrical stimulation

来源：评论

学校读者我要写书评

暂无评论

A system approach for closed-loop assessment of neuro-visual function based on convolutional neural network analysis of EEG signals

A system approach for closed-loop assessment of neuro-visual...

引用

Conference on Neurophotonics part of SPIE Photonics Europe Conference

作者： Stock, Simon C. Armengol-Urpi, Alexandre Kovacs, Balint Maier, Heiko Gerdes, Marius Stork, Wilhelm Sarma, Sanjay E. Karlsruhe Inst Technol Karlsruhe Germany MIT Cambridge MA 02139 USA

ISBN: (数字)9781510634930

ISBN: (纸本)9781510634930;9781510634923

We propose a generalized, modular, closed-loop system for objective assessment of human visual parameters. Our system presents periodical visual stimuli to the patient's field of view and analyses the consequent evoked brain potentials elicited in the occipital lobe and recorded through EEG. The analysis of the monitored EEG data is performed in an end-to-end fashion by a convolutional neural network (CNN). We propose a novel CNN architecture for EEG signal analysis that can be trained utilizing the benefits of multi-task learning. The closedloop attribute of our system allows for a real-time adaptation of the subsequent stimuli to further examine a potentially damaged area or increase the granularity of the exploration. Interchangeability is provided in terms of software modules, stimulus type, visual hardware, EEG acquisition device and EEG electrodes. Initially, the system is designed to monitor visual field loss originating from glaucoma or damage to the optic nerve using a virtual reality (VR) headset for the stimuli presentation. The modular architecture of our system paves the way for the assessment and monitoring of other neuro-visual functions.

关键词： Neuroscience brain-computer-interface EEG Ophthalmology Deep Learning Convolutional Neural Networks System Design

来源：评论

学校读者我要写书评

暂无评论

A Robust Encoding Scheme for Delivering Artificial Sensory Information via Direct brain Stimulation

引用

IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING 2019年第10期27卷 1994-2004页

作者： Bjanes, David A. Moritz, Chet T. Univ Washington Ctr Neurotechnol Dept Elect & Comp Engn Seattle WA 98195 USA CALTECH Dept Biol Pasadena CA 91125 USA Univ Washington Dept Elect & Comp Engn Seattle WA 98195 USA Univ Washington Dept Rehabil Med Seattle WA 98195 USA Univ Washington Dept Physiol & Biophys Seattle WA 98195 USA Univ Washington Ctr Neurotechnol Seattle WA 98195 USA

Innovations for creating somatosensation via direct electrical stimulation of the brain will be required for the next generation of bi-directional cortical neuroprostheses. The current lack of tactile perception and proprioceptive input likely imposes a fundamental limit on speed and accuracy of brain-controlled prostheses or re-animated limbs. This study addresses the unique challenge of identifying a robust, high bandwidth sensory encoding scheme in a high-dimensional parameter space. Previous studies demonstrated single dimensional encoding schemes delivering low bandwidth sensory information, but no comparison has been performed across parameters, nor with update rates suitable for real-time operation of a neuroprosthesis. Here, we report the first comprehensive measurement of the resolution of key stimulation parameters such as pulse amplitude, pulse width, frequency, train interval and number of pulses. Surprisingly, modulation of stimulation frequency was largely undetectable. While we initially expected high frequency content to be an ideal candidate for passing high throughput sensory signals to the brain, we found only modulation of very low frequencies were detectable. Instead, the charge-per-phase of each pulse yields the highest resolution sensory signal, and is the key parameter modulating perceived intensity. The stimulation encoding patterns were designed for high-bandwidth information transfer that will be required for bi-directional brain interfaces. Our discovery of the stimulation features which best encode perceived intensity have significant implications for design of any neural interface seeking to convey information directly to the brain via electrical stimulation.

关键词： brain-computer-interface cortical neuroprosthesis electrical stimulation sensory perception sensory stimulation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：