Pan He, Ding Peng, Wang Fan, Li Tianwen, Zhao Lei, Nan Wenya, Fu Yunfa, Gong Anmin
Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China.
Brain Cognition and Brain-Computer Intelligence Integration Group, Kunming University of Science and Technology, Kunming, China.
Front Hum Neurosci. 2024 Jun 5;18:1429130. doi: 10.3389/fnhum.2024.1429130. eCollection 2024.
Although brain-computer interface (BCI) is considered a revolutionary advancement in human-computer interaction and has achieved significant progress, a considerable gap remains between the current technological capabilities and their practical applications. To promote the translation of BCI into practical applications, the gold standard for online evaluation for classification algorithms of BCI has been proposed in some studies. However, few studies have proposed a more comprehensive evaluation method for the entire online BCI system, and it has not yet received sufficient attention from the BCI research and development community. Therefore, the qualitative leap from analyzing and modeling for offline BCI data to the construction of online BCI systems and optimizing their performance is elaborated, and then user-centred is emphasized, and then the comprehensive evaluation methods for translating BCI into practical applications are detailed and reviewed in the article, including the evaluation of the usability (including effectiveness and efficiency of systems), the evaluation of the user satisfaction (including BCI-related aspects, etc.), and the evaluation of the usage (including the match between the system and user, etc.) of online BCI systems. Finally, the challenges faced in the evaluation of the usability and user satisfaction of online BCI systems, the efficacy of online BCI systems, and the integration of BCI and artificial intelligence (AI) and/or virtual reality (VR) and other technologies to enhance the intelligence and user experience of the system are discussed. It is expected that the evaluation methods for online BCI systems elaborated in this review will promote the translation of BCI into practical applications.
尽管脑机接口(BCI)被认为是人机交互领域的一项革命性进展,并且已经取得了显著进步,但当前的技术能力与其实际应用之间仍存在相当大的差距。为了推动BCI向实际应用的转化,一些研究中提出了BCI分类算法在线评估的金标准。然而,很少有研究针对整个在线BCI系统提出更全面的评估方法,并且它尚未得到BCI研发社区的充分关注。因此,本文阐述了从离线BCI数据的分析和建模到在线BCI系统构建及其性能优化的质的飞跃,强调了以用户为中心,然后详细介绍并综述了将BCI转化为实际应用的综合评估方法,包括在线BCI系统的可用性评估(包括系统的有效性和效率)、用户满意度评估(包括与BCI相关的方面等)以及使用情况评估(包括系统与用户的匹配度等)。最后,讨论了在线BCI系统可用性和用户满意度评估、在线BCI系统功效以及BCI与人工智能(AI)和/或虚拟现实(VR)等技术集成以增强系统智能和用户体验方面所面临的挑战。期望本综述中阐述的在线BCI系统评估方法将推动BCI向实际应用的转化。