1
|
Aljalal M, Aldosari SA, AlSharabi K, Alturki FA. EEG-Based Detection of Mild Cognitive Impairment Using DWT-Based Features and Optimization Methods. Diagnostics (Basel) 2024; 14:1619. [PMID: 39125495 PMCID: PMC11312237 DOI: 10.3390/diagnostics14151619] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/11/2024] [Revised: 07/13/2024] [Accepted: 07/25/2024] [Indexed: 08/12/2024] Open
Abstract
In recent years, electroencephalography (EEG) has been investigated for identifying brain disorders. This technique involves placing multiple electrodes (channels) on the scalp to measure the brain's activities. This study focuses on accurately detecting mild cognitive impairment (MCI) from the recorded EEG signals. To achieve this, this study first introduced discrete wavelet transform (DWT)-based approaches to generate reliable biomarkers for MCI. These approaches decompose each channel's signal using DWT into a set of distinct frequency band signals, then extract features using a non-linear measure such as band power, energy, or entropy. Various machine learning approaches then classify the generated features. We investigated these methods on EEGs recorded using 19 channels from 29 MCI patients and 32 healthy subjects. In the second step, the study explored the possibility of decreasing the number of EEG channels while preserving, or even enhancing, classification accuracy. We employed multi-objective optimization techniques, such as the non-dominated sorting genetic algorithm (NSGA) and particle swarm optimization (PSO), to achieve this. The results show that the generated DWT-based features resulted in high full-channel classification accuracy scores. Furthermore, selecting fewer channels carefully leads to better accuracy scores. For instance, with a DWT-based approach, the full-channel accuracy achieved was 99.84%. With only four channels selected by NSGA-II, NSGA-III, or PSO, the accuracy increased to 99.97%. Furthermore, NSGA-II selects five channels, achieving an accuracy of 100%. The results show that the suggested DWT-based approaches are promising to detect MCI, and picking the most useful EEG channels makes the accuracy even higher. The use of a small number of electrodes paves the way for EEG-based diagnosis in clinical practice.
Collapse
Affiliation(s)
- Majid Aljalal
- Department of Electrical Engineering, College of Engineering, King Saud University, Riyadh 11421, Saudi Arabia; (S.A.A.); (K.A.); (F.A.A.)
| | | | | | | |
Collapse
|
2
|
Aljalal M, Aldosari SA, Molinas M, Alturki FA. Selecting EEG channels and features using multi-objective optimization for accurate MCI detection: validation using leave-one-subject-out strategy. Sci Rep 2024; 14:12483. [PMID: 38816409 PMCID: PMC11139961 DOI: 10.1038/s41598-024-63180-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/29/2024] [Accepted: 05/27/2024] [Indexed: 06/01/2024] Open
Abstract
Effective management of dementia requires the timely detection of mild cognitive impairment (MCI). This paper introduces a multi-objective optimization approach for selecting EEG channels (and features) for the purpose of detecting MCI. Firstly, each EEG signal from each channel is decomposed into subbands using either variational mode decomposition (VMD) or discrete wavelet transform (DWT). A feature is then extracted from each subband using one of the following measures: standard deviation, interquartile range, band power, Teager energy, Katz's and Higuchi's fractal dimensions, Shannon entropy, sure entropy, or threshold entropy. Different machine learning techniques are used to classify the features of MCI cases from those of healthy controls. The classifier's performance is validated using leave-one-subject-out (LOSO) cross-validation (CV). The non-dominated sorting genetic algorithm (NSGA)-II is designed with the aim of minimizing the number of EEG channels (or features) and maximizing classification accuracy. The performance is evaluated using a publicly available online dataset containing EEGs from 19 channels recorded from 24 participants. The results demonstrate a significant improvement in performance when utilizing the NSGA-II algorithm. By selecting only a few appropriate EEG channels, the LOSO CV-based results show a significant improvement compared to using all 19 channels. Additionally, the outcomes indicate that accuracy can be further improved by selecting suitable features from different channels. For instance, by combining VMD and Teager energy, the SVM accuracy obtained using all channels is 74.24%. Interestingly, when only five channels are selected using NSGA-II, the accuracy increases to 91.56%. The accuracy is further improved to 95.28% when using only 8 features selected from 7 channels. This demonstrates that by choosing informative features or channels while excluding noisy or irrelevant information, the impact of noise is reduced, resulting in improved accuracy. These promising findings indicate that, with a limited number of channels and features, accurate diagnosis of MCI is achievable, which opens the door for its application in clinical practice.
Collapse
Affiliation(s)
- Majid Aljalal
- Department of Electrical Engineering, College of Engineering, King Saud University, Riyadh, Saudi Arabia.
| | - Saeed A Aldosari
- Department of Electrical Engineering, College of Engineering, King Saud University, Riyadh, Saudi Arabia
| | - Marta Molinas
- Department of Engineering Cybernetics, Norwegian University of Science and Technology, Trondheim, Norway
| | - Fahd A Alturki
- Department of Electrical Engineering, College of Engineering, King Saud University, Riyadh, Saudi Arabia
| |
Collapse
|
3
|
Soler A, Giraldo E, Molinas M. EEG source imaging of hand movement-related areas: an evaluation of the reconstruction and classification accuracy with optimized channels. Brain Inform 2024; 11:11. [PMID: 38703311 PMCID: PMC11069493 DOI: 10.1186/s40708-024-00224-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/04/2024] [Accepted: 04/04/2024] [Indexed: 05/06/2024] Open
Abstract
The hand motor activity can be identified and converted into commands for controlling machines through a brain-computer interface (BCI) system. Electroencephalography (EEG) based BCI systems employ electrodes to measure the electrical brain activity projected at the scalp and discern patterns. However, the volume conduction problem attenuates the electric potential from the brain to the scalp and introduces spatial mixing to the signals. EEG source imaging (ESI) techniques can be applied to alleviate these issues and enhance the spatial segregation of information. Despite this potential solution, the use of ESI has not been extensively applied in BCI systems, largely due to accuracy concerns over reconstruction accuracy when using low-density EEG (ldEEG), which is commonly used in BCIs. To overcome these accuracy issues in low channel counts, recent studies have proposed reducing the number of EEG channels based on optimized channel selection. This work presents an evaluation of the spatial and temporal accuracy of ESI when applying optimized channel selection towards ldEEG number of channels. For this, a simulation study of source activity related to hand movement has been performed using as a starting point an EEG system with 339 channels. The results obtained after optimization show that the activity in the concerned areas can be retrieved with a spatial accuracy of 3.99, 10.69, and 14.29 mm (localization error) when using 32, 16, and 8 channel counts respectively. In addition, the use of optimally selected electrodes has been validated in a motor imagery classification task, obtaining a higher classification performance when using 16 optimally selected channels than 32 typical electrode distributions under 10-10 system, and obtaining higher classification performance when combining ESI methods with the optimal selected channels.
Collapse
Affiliation(s)
- Andres Soler
- Department of Engineering Cybernetics, Norwegian University of Science and Technology, Trondheim, Norway.
| | - Eduardo Giraldo
- Department of Electrical Engineering, Universidad Tecnológica de Pereira, Pereira, Colombia
| | - Marta Molinas
- Department of Engineering Cybernetics, Norwegian University of Science and Technology, Trondheim, Norway
| |
Collapse
|
4
|
Zameer A, Naz S, Raja MAZ, Hafeez J, Ali N. Neuro-Evolutionary Framework for Design Optimization of Two-Phase Transducer with Genetic Algorithms. MICROMACHINES 2023; 14:1677. [PMID: 37763840 PMCID: PMC10535456 DOI: 10.3390/mi14091677] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/03/2023] [Revised: 08/21/2023] [Accepted: 08/25/2023] [Indexed: 09/29/2023]
Abstract
Multilayer piezocomposite transducers are widely used in many applications where broad bandwidth is required for tracking and detection purposes. However, it is difficult to operate these multilayer transducers efficiently under frequencies of 100 kHz. Therefore, this work presents the modeling and optimization of a five-layer piezocomposite transducer with ten variables of nonuniform layer thicknesses and different volume fractions by exploiting the strength of the genetic algorithm (GA) with a one-dimensional model (ODM). The ODM executes matrix manipulation by resolving wave equations and produces mechanical output in the form of pressure and electrical impedance. The product of gain and bandwidth is the required function to be maximized in this multi-objective and multivariate optimization problem, which is a challenging task having ten variables. Converting it into the minimization problem, the reciprocal of the gain-bandwidth product is considered. The total thickness is adjusted to keep the central frequency at approximately 50-60 kHz. Piezocomposite transducers with three active materials, PZT5h, PZT4d, PMN-PT, and CY1301 polymer, as passive materials were designed, simulated, and statistically evaluated. The results show significant improvement in gain bandwidth compared to previous existing techniques.
Collapse
Affiliation(s)
- Aneela Zameer
- Department of Computer and Information Sciences, Pakistan Institute of Engineering and Applied Sciences, Nilore, Islamabad 45650, Pakistan
| | - Sidra Naz
- Department of Electrical Engineering, Pakistan Institute of Engineering and Applied Sciences, Nilore, Islamabad 45650, Pakistan
| | - Muhammad Asif Zahoor Raja
- Future Technology Research Center, National Yunlin University of Science and Technology, 123 University Road, Section 3, Douliou, Yunlin 64002, Taiwan
| | - Jehanzaib Hafeez
- Department of Computer and Information Sciences, Pakistan Institute of Engineering and Applied Sciences, Nilore, Islamabad 45650, Pakistan
| | - Nasir Ali
- Department of Computer and Information Sciences, Pakistan Institute of Engineering and Applied Sciences, Nilore, Islamabad 45650, Pakistan
| |
Collapse
|
5
|
Akhand MAH, Maria MA, Kamal MAS, Murase K. Improved EEG-based emotion recognition through information enhancement in connectivity feature map. Sci Rep 2023; 13:13804. [PMID: 37612354 PMCID: PMC10447430 DOI: 10.1038/s41598-023-40786-2] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2023] [Accepted: 08/16/2023] [Indexed: 08/25/2023] Open
Abstract
Electroencephalography (EEG), despite its inherited complexity, is a preferable brain signal for automatic human emotion recognition (ER), which is a challenging machine learning task with emerging applications. In any automatic ER, machine learning (ML) models classify emotions using the extracted features from the EEG signals, and therefore, such feature extraction is a crucial part of ER process. Recently, EEG channel connectivity features have been widely used in ER, where Pearson correlation coefficient (PCC), mutual information (MI), phase-locking value (PLV), and transfer entropy (TE) are well-known methods for connectivity feature map (CFM) construction. CFMs are typically formed in a two-dimensional configuration using the signals from two EEG channels, and such two-dimensional CFMs are usually symmetric and hold redundant information. This study proposes the construction of a more informative CFM that can lead to better ER. Specifically, the proposed innovative technique intelligently combines CFMs' measures of two different individual methods, and its outcomes are more informative as a fused CFM. Such CFM fusion does not incur additional computational costs in training the ML model. In this study, fused CFMs are constructed by combining every pair of methods from PCC, PLV, MI, and TE; and the resulting fused CFMs PCC + PLV, PCC + MI, PCC + TE, PLV + MI, PLV + TE, and MI + TE are used to classify emotion by convolutional neural network. Rigorous experiments on the DEAP benchmark EEG dataset show that the proposed CFMs deliver better ER performances than CFM with a single connectivity method (e.g., PCC). At a glance, PLV + MI-based ER is shown to be the most promising one as it outperforms the other methods.
Collapse
Affiliation(s)
- M A H Akhand
- Department of Computer Science and Engineering, Khulna University of Engineering & Technology, Khulna, 9203, Bangladesh.
| | - Mahfuza Akter Maria
- Department of Computer Science and Engineering, Khulna University of Engineering & Technology, Khulna, 9203, Bangladesh
| | - Md Abdus Samad Kamal
- Graduate School of Science and Technology, Gunma University, Kiryu, 376-8515, Japan
| | - Kazuyuki Murase
- Department of Information Technology, International Professional University of Technology in Osaka, 3-3-1 Umeda, Kita-ku, Osaka, 530-0001, Japan
| |
Collapse
|
6
|
EEG channel selection-based binary particle swarm optimization with recurrent convolutional autoencoder for emotion recognition. Biomed Signal Process Control 2023. [DOI: 10.1016/j.bspc.2023.104783] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/11/2023]
|
7
|
Neverlien ECS, Lu R, Kumar M, Molinas M. Decoding Emotions From EEG Responses Elicited by Videos Using Machine Learning Techniques on Two Datasets. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2023; 2023:1-4. [PMID: 38083098 DOI: 10.1109/embc40787.2023.10341106] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/18/2023]
Abstract
In recent times, we have seen extensive research in the field of EEG-based emotion identification. The majority of solutions suggested by current literature use sophisticated deep learning techniques for the identification of human emotions. These models are very complex and need huge resources to implement. Hence, in this work, a method for human emotion recognition is proposed which is based on much simpler architecture. For that, two publicly available datasets SEED and DEAP are used to perform experiments. First, the EEG signals of the two datasets are segmented into epochs of 1second duration. The epochs are also decomposed into different brain rhythms. The features computation is performed in two different ways, one is directly from the epochs and the other way is from the brain rhythms obtained after the decomposition of the epochs. Several features and their combination are examined with different classifiers. For the DEAP dataset baseline features are also utilised. It is observed that the support vector machine (SVM) has shown the best performance for the DEAP dataset when baseline feature correction and epoch decomposition are implemented together. The best achieved average accuracy is 96.50% and 96.71% for high versus low valence classes and high versus low arousal classes, respectively. For the SEED dataset, the best average accuracy of 86.89% is achieved using the multilayer perceptron (MLP) with 2 hidden layers.Clinical relevance- This work can be further explored to develop an automated mental health monitor which can assist doctors in their primary screening.
Collapse
|
8
|
Mwata-Velu T, Niyonsaba-Sebigunda E, Avina-Cervantes JG, Ruiz-Pinales J, Velu-A-Gulenga N, Alonso-Ramírez AA. Motor Imagery Multi-Tasks Classification for BCIs Using the NVIDIA Jetson TX2 Board and the EEGNet Network. SENSORS (BASEL, SWITZERLAND) 2023; 23:4164. [PMID: 37112504 PMCID: PMC10145994 DOI: 10.3390/s23084164] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 03/13/2023] [Revised: 04/15/2023] [Accepted: 04/17/2023] [Indexed: 06/19/2023]
Abstract
Nowadays, Brain-Computer Interfaces (BCIs) still captivate large interest because of multiple advantages offered in numerous domains, explicitly assisting people with motor disabilities in communicating with the surrounding environment. However, challenges of portability, instantaneous processing time, and accurate data processing remain for numerous BCI system setups. This work implements an embedded multi-tasks classifier based on motor imagery using the EEGNet network integrated into the NVIDIA Jetson TX2 card. Therefore, two strategies are developed to select the most discriminant channels. The former uses the accuracy based-classifier criterion, while the latter evaluates electrode mutual information to form discriminant channel subsets. Next, the EEGNet network is implemented to classify discriminant channel signals. Additionally, a cyclic learning algorithm is implemented at the software level to accelerate the model learning convergence and fully profit from the NJT2 hardware resources. Finally, motor imagery Electroencephalogram (EEG) signals provided by HaLT's public benchmark were used, in addition to the k-fold cross-validation method. Average accuracies of 83.7% and 81.3% were achieved by classifying EEG signals per subject and motor imagery task, respectively. Each task was processed with an average latency of 48.7 ms. This framework offers an alternative for online EEG-BCI systems' requirements, dealing with short processing times and reliable classification accuracy.
Collapse
Affiliation(s)
- Tat’y Mwata-Velu
- Centro de Investigación en Computación, Instituto Politécnico Nacional (CIC-IPN), Avenida Juan de Dios Bátiz Esquina Miguel Othón de Mendizábal Colonia Nueva Industrial Vallejo, Alcaldía Gustavo A. Madero, Ciudad de Mexico C.P. 07738, Mexico
- Institut Supérieur Pédagogique Technique de Kinshasa (I.S.P.T.-KIN), Av. de la Science 5, Gombe, Kinshasa 3287, Democratic Republic of the Congo; (E.N.-S.); (J.R.-P.)
- Telematics and Digital Signal Processing Research Groups (CAs), Department of Electronics Engineering, Universidad de Guanajuato, Salamanca 36885, Mexico;
| | - Edson Niyonsaba-Sebigunda
- Institut Supérieur Pédagogique Technique de Kinshasa (I.S.P.T.-KIN), Av. de la Science 5, Gombe, Kinshasa 3287, Democratic Republic of the Congo; (E.N.-S.); (J.R.-P.)
| | - Juan Gabriel Avina-Cervantes
- Telematics and Digital Signal Processing Research Groups (CAs), Department of Electronics Engineering, Universidad de Guanajuato, Salamanca 36885, Mexico;
| | - Jose Ruiz-Pinales
- Institut Supérieur Pédagogique Technique de Kinshasa (I.S.P.T.-KIN), Av. de la Science 5, Gombe, Kinshasa 3287, Democratic Republic of the Congo; (E.N.-S.); (J.R.-P.)
| | - Narcisse Velu-A-Gulenga
- Institut Supérieur Pédagogique de Kikwit (I.S.P. KIKWIT), Av Nzundu 2, Com. Lukolela, Kikwit 8211, Democratic Republic of the Congo
| | - Adán Antonio Alonso-Ramírez
- Instituto Tecnológico Nacional de México en Celaya (TecNM-Celaya), Av. Antonio García Cubas Pte 600, Celaya C.P. 38010, Guanajuato, Mexico;
| |
Collapse
|
9
|
Visual Affective Stimulus Database: A Validated Set of Short Videos. Behav Sci (Basel) 2022; 12:bs12050137. [PMID: 35621434 PMCID: PMC9138138 DOI: 10.3390/bs12050137] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/01/2022] [Revised: 05/02/2022] [Accepted: 05/05/2022] [Indexed: 12/10/2022] Open
Abstract
Two hundred and ninety-nine videos representing four categories (people, animals, objects, and scenes) were standardized using Adobe Premiere Pro CC 2018, with a unified duration of 3 s, a resolution of 1080 pixels/inch, and a size of 1920 × 1080 mm2. One-hundred and sixteen participants (mean age 22.60 ± 2.06 years; 51 males) assessed the videos by scoring, on a self-reported 9-point scale, three dimensions of emotion: valence, arousal, and dominance. The content was attributed a specific valence (positive, neutral, or negative) if more than 60% of the participants identified it with an emotion category. Results: In total, 242 short videos, including 112 positive videos, 47 neutral videos, and 83 negative videos, were retained in the video stimuli database. In the three-dimensional degree of emotion, the distribution relationship between them conformed to the fundamental characteristics of emotion. The internal consistency reliability coefficient for valence, arousal, and dominance was 0.968, 0.984, and 0.970. The internal consistency reliability of the emotional dimensions for people and faces, animals, objects, and scenes ranged between 0.799 and 0.968. Conclusions: The emotion short-video system contains multi-scene dynamic stimuli with good reliability and scoring distribution and is applicable in emotion and emotion-related research.
Collapse
|