Skip to content

Brain computer interfaces, a review.

文献信息

DOI10.3390/s120201211
PMID22438708
期刊Sensors (Basel, Switzerland)
影响因子3.5
JCR 分区Q2
发表年份2012
被引次数363
关键词文物, 脑机接口 (BCI), 脑-机接口, 协作传感器系统, 脑电图 (EEG)
文献类型Journal Article, Research Support, Non-U.S. Gov't, Review
ISSN1424-8220
页码1211-79
期号12(2)
作者Luis Fernando Nicolas-Alonso, Jaime Gomez-Gil

一句话小结

本研究回顾了脑机接口(BCI)的最新发展,重点分析了其信号采集、预处理、特征提取和分类等关键步骤的技术进展及其优缺点。通过深入探讨BCI在帮助严重残疾人士实现交流和控制外部设备中的应用,强调了该领域在改善生活质量和推动神经工程研究中的重要意义。

在麦伴科研 (maltsci.com) 搜索更多文献

文物 · 脑机接口 (BCI) · 脑-机接口 · 协作传感器系统 · 脑电图 (EEG)

摘要

脑机接口(BCI)是一种硬件和软件通信系统,允许仅通过大脑活动来控制计算机或外部设备。BCI研究的直接目标是为严重残疾人士提供交流能力,这些人由于神经肌肉疾病(如肌萎缩侧索硬化症、脑干中风或脊髓损伤)而完全瘫痪或“锁定”。在此,我们回顾了BCI的最新发展,探讨构成标准BCI的不同步骤:信号采集、预处理或信号增强、特征提取、分类和控制接口。我们讨论了它们的优点、缺点及最新进展,并调查了科学文献中报告的多种技术,以设计BCI的每个步骤。首先,回顾审查了用于信号采集步骤的神经成像方式,每种方式监测不同的功能性脑活动,如电活动、磁活动或代谢活动。其次,回顾讨论了不同的电生理控制信号,这些信号确定用户的意图,可以在脑活动中检测到。第三,回顾包括一些用于信号增强步骤的技术,以处理控制信号中的伪影并提高性能。第四,回顾研究了一些用于特征提取和分类步骤的数学算法,这些算法将控制信号中的信息转换为操作计算机或其他设备的命令。最后,回顾提供了各种BCI应用的概述,这些应用控制着一系列设备。

英文摘要

A brain-computer interface (BCI) is a hardware and software communications system that permits cerebral activity alone to control computers or external devices. The immediate goal of BCI research is to provide communications capabilities to severely disabled people who are totally paralyzed or 'locked in' by neurological neuromuscular disorders, such as amyotrophic lateral sclerosis, brain stem stroke, or spinal cord injury. Here, we review the state-of-the-art of BCIs, looking at the different steps that form a standard BCI: signal acquisition, preprocessing or signal enhancement, feature extraction, classification and the control interface. We discuss their advantages, drawbacks, and latest advances, and we survey the numerous technologies reported in the scientific literature to design each step of a BCI. First, the review examines the neuroimaging modalities used in the signal acquisition step, each of which monitors a different functional brain activity such as electrical, magnetic or metabolic activity. Second, the review discusses different electrophysiological control signals that determine user intentions, which can be detected in brain activity. Third, the review includes some techniques used in the signal enhancement step to deal with the artifacts in the control signals and improve the performance. Fourth, the review studies some mathematic algorithms used in the feature extraction and classification steps which translate the information in the control signals into commands that operate a computer or other device. Finally, the review provides an overview of various BCI applications that control a range of devices.

麦伴智能科研服务

智能阅读回答你对文献的任何问题,帮助理解文献中的复杂图表和公式
定位观点定位某个观点在文献中的蛛丝马迹
加入知识库完成数据提取,报告撰写等更多高级知识挖掘功能

主要研究问题

  1. BCI技术在不同类型的神经肌肉疾病中的应用效果如何?
  2. 在信号增强过程中,哪些技术最有效地减少了伪影对控制信号的影响?
  3. 各种神经成像方式在信号采集中的优缺点是什么?
  4. 当前BCI研究中有哪些新的数学算法被用于特征提取和分类?
  5. 除了医疗领域,BCI还有哪些潜在的应用场景?

核心洞察

研究背景和目的

脑机接口(BCI)是一种硬件和软件通信系统,允许大脑活动直接控制计算机或外部设备。BCI的主要目标是为严重残疾的患者提供交流能力,特别是那些因神经肌肉疾病如肌萎缩侧索硬化症或脊髓损伤而完全瘫痪的人。本综述旨在探讨BCI的最新进展,包括信号获取、预处理、特征提取、分类及控制接口等步骤的不同技术及其应用。

主要方法/材料/实验设计

BCI系统的设计通常包括以下五个主要步骤:

  1. 信号获取:通过不同的神经成像技术(如EEG、MEG、ECoG、fMRI等)捕捉脑信号。
  2. 信号预处理:对获取的信号进行噪声减少和伪影处理。
  3. 特征提取:从预处理后的信号中提取具有区分性的信息。
  4. 分类:将提取的特征向量分类,以识别用户的意图。
  5. 控制接口:将分类结果转化为可操作的命令。
Mermaid diagram

关键结果和发现

  • 信号获取:EEG因其高时间分辨率和相对低成本成为最常用的神经成像技术。尽管EEG信号易受伪影影响,但通过先进的信号处理技术可以提高信号质量。
  • 信号处理:多种特征提取和分类算法(如PCA、ICA、SVM等)已被应用于BCI系统中,以提高分类精度和信息传输速率。
  • 应用领域:BCI在通信、运动恢复、环境控制、移动和娱乐等领域展现出广泛的应用潜力。

主要结论/意义/创新性

BCI技术的进步为严重残疾患者提供了新的沟通和控制渠道,显著提高了他们的生活质量。尽管BCI技术仍面临诸多挑战,如信号质量、信息传输速率及用户培训时间等,但其在医疗和日常生活中的应用前景广阔。未来的研究应集中于提高信号处理的有效性和BCI系统的用户友好性。

研究局限性和未来方向

  • 局限性:现有BCI系统在信号处理和用户适应性方面仍存在挑战,尤其是在实际应用中,信号的非平稳性和高噪声水平影响了分类精度。
  • 未来方向:未来的研究应致力于优化信号获取技术,特别是非侵入性方法的提高,以及开发自适应学习算法,以提高BCI的实时性和可靠性。此外,BCI的商业化应用需要更大范围的验证和推广,以便为更广泛的人群服务。

总结

BCI技术作为一种新兴的交互方式,正在逐步改变残疾人士的生活方式。通过不断的技术创新和应用探索,BCI有望在未来实现更广泛的应用,为人们带来更多的便利和可能性。

参考文献

  1. xDAWN algorithm to enhance evoked potentials: application to brain-computer interface. - Bertrand Rivet;Antoine Souloumiac;Virginie Attina;Guillaume Gibert - IEEE transactions on bio-medical engineering (2009)
  2. Visual and electrical evoked response recorded from subdural electrodes implanted above the visual cortex in normal dogs under two methods of anesthesia. - E Margalit;J D Weiland;R E Clatterbuck;G Y Fujii;M Maia;M Tameesh;G Torres;S A D'Anna;S Desai;D V Piyathaisere;A Olivi;E de Juan;Mark S Humayun - Journal of neuroscience methods (2003)
  3. Brain-computer interfaces based on the steady-state visual-evoked response. - M Middendorf;G McMillan;G Calhoun;K S Jones - IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society (2000)
  4. BCI Competition 2003--Data sets Ib and IIb: feature extraction from event-related brain potentials with the continuous wavelet transform and the t-value scalogram. - Vladimir Bostanov - IEEE transactions on bio-medical engineering (2004)
  5. Self-regulation of slow cortical potentials in psychiatric patients: schizophrenia. - F Schneider;B Rockstroh;H Heimann;W Lutzenberger;R Mattes;T Elbert;N Birbaumer;M Bartels - Biofeedback and self-regulation (1992)
  6. Functional mapping of human sensorimotor cortex with electrocorticographic spectral analysis. II. Event-related synchronization in the gamma band. - N E Crone;D L Miglioretti;B Gordon;R P Lesser - Brain : a journal of neurology (1998)
  7. P300-Based Brain-Computer Interface Communication: Evaluation and Follow-up in Amyotrophic Lateral Sclerosis. - Stefano Silvoni;Chiara Volpato;Marianna Cavinato;Mauro Marchetti;Konstantinos Priftis;Antonio Merico;Paolo Tonin;Konstantinos Koutsikos;Fabrizio Beverina;Francesco Piccione - Frontiers in neuroscience (2009)
  8. Multiclass common spatial patterns and information theoretic feature extraction. - Moritz Grosse-Wentrup;Martin Buss - IEEE transactions on bio-medical engineering (2008)
  9. Development and quantitative performance evaluation of a noninvasive EMG computer interface. - Changmok Choi;Silvestro Micera;Jacopo Carpaneto;Jung Kim - IEEE transactions on bio-medical engineering (2009)
  10. Characterization of four-class motor imagery EEG data for the BCI-competition 2005. - Alois Schlögl;Felix Lee;Horst Bischof;Gert Pfurtscheller - Journal of neural engineering (2005)

引用本文的文献

  1. Sensors in collaboration increase individual potentialities. - Gonzalo Pajares - Sensors (Basel, Switzerland) (2012)
  2. Adaptive Laplacian filtering for sensorimotor rhythm-based brain-computer interfaces. - Jun Lu;Dennis J McFarland;Jonathan R Wolpaw - Journal of neural engineering (2013)
  3. Assisted closed-loop optimization of SSVEP-BCI efficiency. - Jacobo Fernandez-Vargas;Hanns U Pfaff;Francisco B Rodríguez;Pablo Varona - Frontiers in neural circuits (2013)
  4. Ectopic eyes outside the head in Xenopus tadpoles provide sensory data for light-mediated learning. - Douglas J Blackiston;Michael Levin - The Journal of experimental biology (2013)
  5. New evidence for therapies in stroke rehabilitation. - Bruce H Dobkin;Andrew Dorsch - Current atherosclerosis reports (2013)
  6. Electrical stimulation of embryonic neurons for 1 hour improves axon regeneration and the number of reinnervated muscles that function. - Yang Liu;Robert M Grumbles;Christine K Thomas - Journal of neuropathology and experimental neurology (2013)
  7. Gyroscope-driven mouse pointer with an EMOTIV® EEG headset and data analysis based on Empirical Mode Decomposition. - Gerardo Rosas-Cholula;Juan Manuel Ramirez-Cortes;Vicente Alarcon-Aquino;Pilar Gomez-Gil;Jose de Jesus Rangel-Magdaleno;Carlos Reyes-Garcia - Sensors (Basel, Switzerland) (2013)
  8. Automatic and direct identification of blink components from scalp EEG. - Wanzeng Kong;Zhanpeng Zhou;Sanqing Hu;Jianhai Zhang;Fabio Babiloni;Guojun Dai - Sensors (Basel, Switzerland) (2013)
  9. EEG-response consistency across subjects in an active oddball task. - Yvonne Höller;Aljoscha Thomschewski;Jürgen Bergmann;Martin Kronbichler;Julia S Crone;Elisabeth V Schmid;Kevin Butz;Peter Höller;Eugen Trinka - PloS one (2013)
  10. EOG artifact correction from EEG recording using stationary subspace analysis and empirical mode decomposition. - Hong Zeng;Aiguo Song;Ruqiang Yan;Hongyun Qin - Sensors (Basel, Switzerland) (2013)

... (353 更多 篇文献)


© 2025 MaltSci 麦伴科研 - 我们用人工智能技术重塑科研