Noninvasive brain–computer interfaces using fNIRS, EEG, and hybrid EEG-fNIRS
- 문서 유형
- 연구출판물 · 저서
- 등재
- ESCIScopus
- 저널 순위
- JCR Q3Scopus Q2
- 저널
- BRAIN-COMPUTER INTERFACESpp.297 · 2024
- 피인용
- Scopus 2
- FWCI (Scopus)
- 0.99
- JCR IF
- JCR 2023 1.8
- ISSN
- 2326-263X
저자
- Nazeer, Hammad제1저자Department of Mechatronics and Biomedical Engineering, Air University, Islamabad, Federal Capital Territory, Pakistan
- Naseer, NomanDepartment of Mechatronics and Biomedical Engineering, Air University, Islamabad, Federal Capital Territory, Pakistan
- 칸 말리크 나시르 아프잘Department of Electrical Engineering, School of Engineering, Prince Sattam Bin Abdul Aziz University, Al-Kharj, Saudi Arabia
- 홍금식School of Mechanical Engineering, Pusan National University, Busan, South Korea
초록
A brain–computer interface (BCI) is an advanced communication system that integrates both hardware and software components. Its main objective is to facilitate user interaction with the surroundings using various external devices. The BCI includes an artificial intelligence system trained to recognize specific patterns within brain signals. These patterns are then converted into commands for a range of applications, such as controlling robotic arms, wheelchairs, or assessing the user's mental state. They can function as communication tools, aid in restoring motor functions for individuals dealing with conditions like amyotrophic lateral sclerosis (ALS), spinal cord injuries, or persistent locked-in states and as neurorehabilitation aids to improve motor and cognitive capabilities in specific situations. In noninvasive BCI, wearable devices are used to measure brains signals. These noninvasive BCIs uses electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) techniques for brain data acquisition. EEG and fNIRS are wearable, portable devices, safe, low cost, and popular techniques used in BCI applications. Along with their individual utilization, the combination of both techniques proved to be effective and significant in BCI applications with higher number of commands and classification complexity. In this chapter brain-signal acquisition, strategies for eliminating noise, methods to extract and select relevant features, and classification methods pertaining to fNIRS-BCI, EEG-BCI, and the combined EEG-fNIRS hBCI methods are discussed.
키워드
식별자
- Scopus EID
- 2-s2.0-85213780671



로그인
연구물 목록으로