1
|
AL-Quraishi MS, Tan WH, Elamvazuthi I, Ooi CP, Saad NM, Al-Hiyali MI, Karim H, Azhar Ali SS. Cortical signals analysis to recognize intralimb mobility using modified RNN and various EEG quantities. Heliyon 2024; 10:e30406. [PMID: 38726180 PMCID: PMC11079093 DOI: 10.1016/j.heliyon.2024.e30406] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/03/2024] [Revised: 04/17/2024] [Accepted: 04/25/2024] [Indexed: 05/12/2024] Open
Abstract
Electroencephalogram (EEG) signals are critical in interpreting sensorimotor activities for predicting body movements. However, their efficacy in identifying intralimb movements, such as the dorsiflexion and plantar flexion of the foot, remains suboptimal. This study aims to explore whether various EEG signal quantities can effectively recognize intralimb movements to facilitate the development of Brain-Computer Interface (BCI) devices for foot rehabilitation. This research involved twenty-two healthy, right-handed participants. EEG data were collected using 21 electrodes positioned over the motor cortex, while two electromyography (EMG) electrodes recorded the onset of ankle joint movements. The study focused on analyzing slow cortical potential (SCP) and sensorimotor rhythms (SMR) in alpha and beta bands from the EEG. Five key features-fourth-order Autoregressive feature, variance, waveform length, standard deviation, and permutation entropy-were extracted. A modified Recurrent Neural Network (RNN) including Long Short-term Memory (LSTM) and Gated Recurrent Unit (GRU) algorithms was developed for movement recognition. These were compared against conventional machine learning algorithms, including nonlinear Support Vector Machine (SVM) and k Nearest Neighbourhood (kNN) classifiers. The performance of the proposed models was assessed using two data schemes: within-subject and across-subjects. The findings demonstrated that the GRU and LSTM models significantly outperformed traditional machine learning algorithms in recognizing different EEG signal quantities for intralimb movement. The study indicates that deep learning models, particularly GRU and LSTM, hold superior potential over standard machine learning techniques in identifying intralimb movements using EEG signals. Where the accuracies of LSTM for within and across subjects were 98.87 ± 1.80 % and 87.38 ± 0.86 % respectively. Whereas the accuracy of GRU within and across subjects were 99.18 ± 1.28 % and 86.44 ± 0.69 % respectively. This advancement could significantly benefit the development of BCI devices aimed at foot rehabilitation, suggesting a new avenue for enhancing physical therapy outcomes.
Collapse
Affiliation(s)
- Maged S. AL-Quraishi
- Interdisciplinary Research Center for Smart Mobility and Logistics (IRC-SML), King Fahd University of Petroleum & Minerals (KFUPM), Dhahran, 31261, Saudi Arabia
| | - Wooi Haw Tan
- Center of Digital Home, Faculty of Engineering, Multimedia University, 63100, Cyberjaya, Selangor, Malaysia
| | - Irraivan Elamvazuthi
- Department of Electrical and Electronic Engineering, Universiti Teknologi PETRONAS, Bandar Seri Iskandar, 36210, Perak, Malaysia
| | - Chee Pun Ooi
- Center of Digital Home, Faculty of Engineering, Multimedia University, 63100, Cyberjaya, Selangor, Malaysia
| | - Naufal M. Saad
- Department of Electrical and Electronic Engineering, Universiti Teknologi PETRONAS, Bandar Seri Iskandar, 36210, Perak, Malaysia
| | - Mohammed Isam Al-Hiyali
- Department of Electrical and Electronic Engineering, Universiti Teknologi PETRONAS, Bandar Seri Iskandar, 36210, Perak, Malaysia
| | - H.A. Karim
- Center of Digital Home, Faculty of Engineering, Multimedia University, 63100, Cyberjaya, Selangor, Malaysia
| | - Syed Saad Azhar Ali
- Interdisciplinary Research Center for Smart Mobility and Logistics (IRC-SML), King Fahd University of Petroleum & Minerals (KFUPM), Dhahran, 31261, Saudi Arabia
- Aerospace Engineering Department, King Fahd University of Petroleum & Minerals (KFUPM), Dhahran, 31261, Saudi Arabia
| |
Collapse
|
2
|
Karakullukcu N, Yilmaz B. Detection of Movement Intention in EEG-Based Brain-Computer Interfaces Using Fourier-Based Synchrosqueezing Transform. Int J Neural Syst 2021; 32:2150059. [PMID: 34806939 DOI: 10.1142/s0129065721500593] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
Patients with motor impairments need caregivers' help to initiate the operation of brain-computer interfaces (BCI). This study aims to identify and characterize movement intention using multichannel electroencephalography (EEG) signals as a means to initiate BCI systems without extra accessories/methodologies. We propose to discriminate the resting and motor imagery (MI) states with high accuracy using Fourier-based synchrosqueezing transform (FSST) as a feature extractor. FSST has been investigated and compared with other popular approaches in 28 healthy subjects for a total of 6657 trials. The accuracy and f-measure values were obtained as 99.8% and 0.99, respectively, when FSST was used as the feature extractor and singular value decomposition (SVD) as the feature selection method and support vector machines as the classifier. Moreover, this study investigated the use of data that contain certain amount of noise without any preprocessing in addition to the clean counterparts. Furthermore, the statistical analysis of EEG channels with the best discrimination (of resting and MI states) characteristics demonstrated that F4-Fz-C3-Cz-C4-Pz channels and several statistical features had statistical significance levels, [Formula: see text], less than 0.05. This study showed that the preparation of the movement can be detected in real-time employing FSST-SVD combination and several channels with minimal pre-processing effort.
Collapse
Affiliation(s)
- Nedime Karakullukcu
- Electrical and Computer Engineering Department, Graduate School of Engineering and Sciences, Abdullah Gul University, 38080 Kayseri, Turkey.,Biomedical Instrumentation and Signal Analysis, Laboratory (BISA-Lab), School of Engineering, Abdullah Gul University, 38080 Kayseri, Turkey
| | - Bülent Yilmaz
- Electrical and Computer Engineering Department, Graduate School of Engineering and Sciences, Abdullah Gul University, 38080 Kayseri, Turkey.,Electrical-Electronics Engineering Department, School of Engineering, Abdullah Gul University, 38080 Kayseri, Turkey.,Biomedical Instrumentation and Signal Analysis Laboratory (BISA-Lab), School of Engineering, Abdullah Gul University, 38080 Kayseri, Turkey
| |
Collapse
|
3
|
Sosnowska A, Gollee H, Vučković A. MRCP as a biomarker of motor action with varying degree of central and peripheral contribution as defined by ultrasound imaging. J Neurophysiol 2021; 126:249-263. [PMID: 33978487 DOI: 10.1152/jn.00028.2021] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/22/2022] Open
Abstract
Motor imagination is an alternative rehabilitation strategy for people who cannot execute real movements. However, it is still a matter of debate to which degree it involves activation of deeper muscle structures, which cannot be detected by surface electromyography (SEMG). Sixteen able-bodied participants performed cue based isometric ankle plantar flexion (active movement) followed by active relaxation under four conditions: executed movements with two levels of muscle contraction (fully executed and attempted movements, EM and AM) and motor imagination with and without detectable muscle twitches (IT and I). The most prominent peaks and distinctive phases of movement-related cortical potential (MRCP) were compared between conditions. Ultrasound imaging (USI) and SEMG were used to detect movements. IT showed spatially distinctive significant differences compared to both I and AM during active movement preparation and reafferentation phase; further widespread differences were found between IT and AM during active movement execution and posteriorly during preparation for active relaxation. EM and AM showed the largest differences frontally during active movement planning and posteriorly during execution of active relaxation. Movement preparation positivity P1 showed a significant difference in amplitude between IT and AM but not between IT and I. USI can detect subliminal movements (twitches) better than SEMG. MRCP is a biomarker sensitive to different levels of muscle contraction and relaxation. IT is a motor condition distinguishable from both I and AM. EEG biomarkers of movements could be used to identify pathological conditions, that manifest themselves during either active contraction or active relaxation.NEW & NOTEWORTHY Ultrasound imaging can detect subtle muscle movements (twitches) that are not detectable with electromyography. Almost a quarter of trials of imagined movements in able-bodied people are accompanied by twitches. Analysis of movement-related cortical potential showed that motor imagination with twitches is a condition distinguishable from motor imagination without twitches and from motor attempts.
Collapse
Affiliation(s)
- A Sosnowska
- Biomedical Engineering Research Division, School of Engineering, University of Glasgow, Glasgow, United Kingdom
| | - H Gollee
- Biomedical Engineering Research Division, School of Engineering, University of Glasgow, Glasgow, United Kingdom
| | - A Vučković
- Biomedical Engineering Research Division, School of Engineering, University of Glasgow, Glasgow, United Kingdom
| |
Collapse
|
4
|
Sabzevari M, Imani E. Separation of movement direction concepts based on independent component analysis algorithm, linear discriminant analysis, deep belief network, artificial and fuzzy neural networks. Biomed Signal Process Control 2020. [DOI: 10.1016/j.bspc.2020.101950] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
5
|
Tabernig CB, Lopez CA, Carrere LC, Spaich EG, Ballario CH. Neurorehabilitation therapy of patients with severe stroke based on functional electrical stimulation commanded by a brain computer interface. J Rehabil Assist Technol Eng 2018; 5:2055668318789280. [PMID: 31191948 PMCID: PMC6453036 DOI: 10.1177/2055668318789280] [Citation(s) in RCA: 18] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/05/2017] [Accepted: 06/21/2018] [Indexed: 02/06/2023] Open
Abstract
Introduction Brain computer interface is an emerging technology to treat the sequelae of stroke. The purpose of this study was to explore the motor imagery related desynchronization of sensorimotor rhythms of stroke patients and to assess the efficacy of an upper limb neurorehabilitation therapy based on functional electrical stimulation controlled by a brain computer interface. Methods Eight severe chronic stroke patients were recruited. The study consisted of two stages: screening and therapy. During screening, the ability of patients to desynchronize the contralateral oscillatory sensorimotor rhythms by motor imagery of the most affected hand was assessed. In the second stage, a therapeutic intervention was performed. It involved 20 sessions where an electrical stimulator was activated when the patient's cerebral activity related to motor imagery was detected. The upper limb was assessed, before and after the intervention, by the Fugl-Meyer score (primary outcome). Spasticity, motor activity, range of movement and quality of life were also evaluated (secondary outcomes). Results Desynchronization was identified in all screened patients. Significant post-treatment improvement (p < 0.05) was detected in the primary outcome measure and in the majority of secondary outcome scores. Conclusions The results suggest that the proposed therapy could be beneficial in the neurorehabilitation of stroke individuals.
Collapse
Affiliation(s)
- Carolina B Tabernig
- Laboratorio de Ingeniería en Rehabilitación e Investigaciones Neuromusculares y Sensoriales (LIRINS), Facultad de Ingeniería, Universidad Nacional de Entre Ríos, Oro Verde, Argentina
| | - Camila A Lopez
- Fundación Rosarina de Neuro-rehabilitación, Rosario, Argentina
| | - Lucía C Carrere
- Laboratorio de Ingeniería en Rehabilitación e Investigaciones Neuromusculares y Sensoriales (LIRINS), Facultad de Ingeniería, Universidad Nacional de Entre Ríos, Oro Verde, Argentina
| | - Erika G Spaich
- SMI®, Department of Health Science and Technology, Aalborg University, Denmark
| | | |
Collapse
|
6
|
Mahmoodi M, Abadi BM, Khajepur H, Harirchian MH. A robust beamforming approach for early detection of readiness potential with application to brain-computer interface systems. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2017; 2017:2980-2983. [PMID: 29060524 DOI: 10.1109/embc.2017.8037483] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
Early detection of intention to move, at self-paced voluntary movements from the activities of neural current sources on the motor cortex, can be an effective approach to brain-computer interface (BCI) systems. Achieving high sensitivity and pre-movement negative latency are important issues for increasing the speed of BCI and other rehabilitation and neurofeedback systems used by disabled and stroke patients and helps enhance their movement abilities. Therefore, developing high-performance extractors or beamformers is a necessary task in this regard. In this paper, for the sake of improving the beamforming performance in well reconstruction of sources of readiness potential, related to hand movement, one kind of surface spatial filter (spherical spline derivative on electrode space) and the linearly constrained minimum variance (LCMV) beamformer are utilized jointly. Moreover, in order to achieve better results, the real head model of each subject was created, using individual head MRI, and was used in beamformer algorithm. Also, few optimizations were done on reconstructed source signal powers to help our template matching classifier with detection of movement onset for five healthy subjects. Our classification results show an average true positive rate (TPR) of 77.1% and 73.1%, false positive rate (FPR) of 28.96% and 28.74% and latency of -512.426 ±396. 7ms and - 360.29 ±252. 16 ms from signals of current sources of motor cortex and sensor space respectively. It can be seen that the proposed method has reliable sensitivity and is faster in prediction of movement onset and more reliable to be used for online BCI in future.
Collapse
|
7
|
Aliakbaryhosseinabadi S, Kamavuako EN, Jiang N, Farina D, Mrachacz-Kersting N. Classification of EEG signals to identify variations in attention during motor task execution. J Neurosci Methods 2017; 284:27-34. [DOI: 10.1016/j.jneumeth.2017.04.008] [Citation(s) in RCA: 21] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2017] [Revised: 04/12/2017] [Accepted: 04/13/2017] [Indexed: 10/19/2022]
|