1
|
Khan RA, Rashid N, Shahzaib M, Malik UF, Arif A, Iqbal J, Saleem M, Khan US, Tiwana M. A novel framework for classification of two-class motor imagery EEG signals using logistic regression classification algorithm. PLoS One 2023; 18:e0276133. [PMID: 37682884 PMCID: PMC10490872 DOI: 10.1371/journal.pone.0276133] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/24/2022] [Accepted: 09/29/2022] [Indexed: 09/10/2023] Open
Abstract
Robotics and artificial intelligence have played a significant role in developing assistive technologies for people with motor disabilities. Brain-Computer Interface (BCI) is a communication system that allows humans to communicate with their environment by detecting and quantifying control signals produced from different modalities and translating them into voluntary commands for actuating an external device. For that purpose, classification the brain signals with a very high accuracy and minimization of the errors is of profound importance to the researchers. So in this study, a novel framework has been proposed to classify the binary-class electroencephalogram (EEG) data. The proposed framework is tested on BCI Competition IV dataset 1 and BCI Competition III dataset 4a. Artifact removal from EEG data is done through preprocessing, followed by feature extraction for recognizing discriminative information in the recorded brain signals. Signal preprocessing involves the application of independent component analysis (ICA) on raw EEG data, accompanied by the employment of common spatial pattern (CSP) and log-variance for extracting useful features. Six different classification algorithms, namely support vector machine, linear discriminant analysis, k-nearest neighbor, naïve Bayes, decision trees, and logistic regression, have been compared to classify the EEG data accurately. The proposed framework achieved the best classification accuracies with logistic regression classifier for both datasets. Average classification accuracy of 90.42% has been attained on BCI Competition IV dataset 1 for seven different subjects, while for BCI Competition III dataset 4a, an average accuracy of 95.42% has been attained on five subjects. This indicates that the model can be used in real time BCI systems and provide extra-ordinary results for 2-class Motor Imagery (MI) signals classification applications and with some modifications this framework can also be made compatible for multi-class classification in the future.
Collapse
Affiliation(s)
- Rabia Avais Khan
- Department of Mechatronics Engineering, National University of Sciences & Technology, Islamabad, Pakistan
| | - Nasir Rashid
- Department of Mechatronics Engineering, National University of Sciences & Technology, Islamabad, Pakistan
- Robot Design and Development Lab, National Centre of Robotics and Automation (NCRA), Punjab, Pakistan
| | - Muhammad Shahzaib
- Department of Mechatronics Engineering, National University of Sciences & Technology, Islamabad, Pakistan
| | - Umar Farooq Malik
- Department of Mechatronics Engineering, National University of Sciences & Technology, Islamabad, Pakistan
| | - Arshia Arif
- Department of Mechatronics Engineering, National University of Sciences & Technology, Islamabad, Pakistan
| | - Javaid Iqbal
- Department of Mechatronics Engineering, National University of Sciences & Technology, Islamabad, Pakistan
- Robot Design and Development Lab, National Centre of Robotics and Automation (NCRA), Punjab, Pakistan
| | - Mubasher Saleem
- Department of Mechatronics Engineering, National University of Sciences & Technology, Islamabad, Pakistan
| | - Umar Shahbaz Khan
- Department of Mechatronics Engineering, National University of Sciences & Technology, Islamabad, Pakistan
- Robot Design and Development Lab, National Centre of Robotics and Automation (NCRA), Punjab, Pakistan
| | - Mohsin Tiwana
- Department of Mechatronics Engineering, National University of Sciences & Technology, Islamabad, Pakistan
- Robot Design and Development Lab, National Centre of Robotics and Automation (NCRA), Punjab, Pakistan
| |
Collapse
|
2
|
Gao F, Wu G, Guo S, Dai W, Shuang F. Solving DC power flow problems using quantum and hybrid algorithms. Appl Soft Comput 2023. [DOI: 10.1016/j.asoc.2023.110147] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/06/2023]
|
3
|
Niu X, Ma W. An ensemble learning model based on differentially private decision tree. COMPLEX INTELL SYST 2023. [DOI: 10.1007/s40747-023-01017-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/18/2023]
Abstract
AbstractUsing differential privacy to provide privacy protection for classification algorithms has become a research hotspot in data mining. In this paper, we analyze the defects in the differentially private decision tree named Maxtree, and propose an improved model DPtree. DPtree can use the Fayyad theorem to process continuous features quickly, and can adjust privacy budget adaptively according to sample category distributions in leaf nodes. Moreover, to overcome the inevitable decline of classification ability of differentially private decision trees, we propose an ensemble learning model for DPtree, namely En-DPtree. In the voting process of En-DPtree, we propose a multi-population quantum genetic algorithm, and introduce immigration operators and elite groups to search the optimal weights for base classifiers. Experiments show that the performance of DPtree is better than Maxtree, and En-DPtree is always superior to other competitive algorithms.
Collapse
|
4
|
Parallel genetic algorithm based common spatial patterns selection on time–frequency decomposed EEG signals for motor imagery brain-computer interface. Biomed Signal Process Control 2023. [DOI: 10.1016/j.bspc.2022.104397] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
|
5
|
Zhu S, Hosni SI, Huang X, Wan M, Borgheai SB, McLinden J, Shahriari Y, Ostadabbas S. A dynamical graph-based feature extraction approach to enhance mental task classification in brain-computer interfaces. Comput Biol Med 2023; 153:106498. [PMID: 36634598 DOI: 10.1016/j.compbiomed.2022.106498] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/29/2022] [Revised: 12/08/2022] [Accepted: 12/27/2022] [Indexed: 12/31/2022]
Abstract
Graph theoretic approaches in analyzing spatiotemporal dynamics of brain activities are under-studied but could be very promising directions in developing effective brain-computer interfaces (BCIs). Many existing BCI systems use electroencephalogram (EEG) signals to record and decode human neural activities noninvasively. Often, however, the features extracted from the EEG signals ignore the topological information hidden in the EEG temporal dynamics. Moreover, existing graph theoretic approaches are mostly used to reveal the topological patterns of brain functional networks based on synchronization between signals from distinctive spatial regions, instead of interdependence between states at different timestamps. In this study, we present a robust fold-wise hyperparameter optimization framework utilizing a series of conventional graph-based measurements combined with spectral graph features and investigate its discriminative performance on classification of a designed mental task in 6 participants with amyotrophic lateral sclerosis (ALS). Across all of our participants, we reached an average accuracy of 71.1%±4.5% for mental task classification by combining the global graph-based measurements and the spectral graph features, higher than the conventional non-graph based feature performance (67.1%±7.5%). Compared to using either one of the graphic features (66.3%±6.5% for the eigenvalues and 65.9%±5.2% for the global graph features), our feature combination strategy shows considerable improvement in both accuracy and robustness performance. Our results indicate the feasibility and advantage of the presented fold-wise optimization framework utilizing graph-based features in BCI systems targeted at end-users.
Collapse
Affiliation(s)
- Shaotong Zhu
- The Department of Electrical and Computer Engineering, Northeastern University, 360 Huntington Ave, Boston, MA 02115, USA
| | - Sarah Ismail Hosni
- The Electrical, Computer, and Biomedical Engineering Department, University of Rhode Island, Kingston, RI 02881, USA
| | - Xiaofei Huang
- The Department of Electrical and Computer Engineering, Northeastern University, 360 Huntington Ave, Boston, MA 02115, USA
| | - Michael Wan
- The Department of Electrical and Computer Engineering, Northeastern University, 360 Huntington Ave, Boston, MA 02115, USA
| | - Seyyed Bahram Borgheai
- The Electrical, Computer, and Biomedical Engineering Department, University of Rhode Island, Kingston, RI 02881, USA
| | - John McLinden
- The Electrical, Computer, and Biomedical Engineering Department, University of Rhode Island, Kingston, RI 02881, USA
| | - Yalda Shahriari
- The Electrical, Computer, and Biomedical Engineering Department, University of Rhode Island, Kingston, RI 02881, USA
| | - Sarah Ostadabbas
- The Department of Electrical and Computer Engineering, Northeastern University, 360 Huntington Ave, Boston, MA 02115, USA.
| |
Collapse
|
6
|
A biased genetic algorithm hybridized with VNS for the two-dimensional knapsack packing problem with defects. Appl Soft Comput 2022. [DOI: 10.1016/j.asoc.2022.108479] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
|
7
|
Jin J, Sun H, Daly I, Li S, Liu C, Wang X, Cichocki A. A Novel Classification Framework Using the Graph Representations of Electroencephalogram for Motor Imagery based Brain-Computer Interface. IEEE Trans Neural Syst Rehabil Eng 2021; 30:20-29. [PMID: 34962871 DOI: 10.1109/tnsre.2021.3139095] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
Abstract
The motor imagery (MI) based brain-computer interfaces (BCIs) have been proposed as a potential physical rehabilitation technology. However, the low classification accuracy achievable with MI tasks is still a challenge when building effective BCI systems. We propose a novel MI classification model based on measurement of functional connectivity between brain regions and graph theory. Specifically, motifs describing local network structures in the brain are extracted from functional connectivity graphs. A graph embedding model called Ego-CNNs is then used to build a classifier, which can convert the graph from a structural representation to a fixed-dimensional vector for detecting critical structure in the graph. We validate our proposed method on four datasets, and the results show that our proposed method produces high classification accuracies in two-class classification tasks (92.8% for dataset 1, 93.4% for dataset 2, 96.5% for dataset 3, and 80.2% for dataset 4) and multiclass classification tasks (90.33% for dataset 1). Our proposed method achieves a mean Kappa value of 0.88 across nine participants, which is superior to other methods we compared it to. These results indicate that there is a local structural difference in functional connectivity graphs extracted under different motor imagery tasks. Our proposed method has great potential for motor imagery classification in future studies.
Collapse
|
8
|
Dokur Z, Olmez T. Classification of motor imagery electroencephalogram signals by using a divergence based convolutional neural network. Appl Soft Comput 2021. [DOI: 10.1016/j.asoc.2021.107881] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
|