1
|
Zhao Y, Gao W, Ku S. Optimization of the game improvement and data analysis model for the early childhood education major via deep learning. Sci Rep 2023; 13:20273. [PMID: 37985677 PMCID: PMC10662176 DOI: 10.1038/s41598-023-46060-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/14/2023] [Accepted: 10/27/2023] [Indexed: 11/22/2023] Open
Abstract
An ever-growing portion of the economy is dedicated to the field of education, intensifying the urgency of identifying strategies to secure the sector's enduring prosperity and elevate educational standards universally. This study introduces a model for enhancing games and optimizing data analysis within the context of early childhood education (ECE) majors, hinging on deep learning (DL). This approach aims to enhance the quality of instruction provided to ECE majors and refine the effectiveness of their professional pursuits. This study commences by examining the incorporation of DL technologies within the domain of ECE and delving into their fundamental underpinnings. Subsequently, it expounds upon the design philosophy underpinning ECE games operating within the framework of DL. Finally, it outlines the game improvement and data analysis (GIADA) model tailored to ECE majors. This model is constructed upon DL technology and further refined through the integration of convolutional neural networks (CNN). Empirical findings corroborate that the DL-CNN GIADA model achieves data analysis accuracy ranging from 83 to 93% across four datasets, underscoring the pronounced optimization prowess bestowed by CNN within the DL-based GIADA model. This study stands as an invaluable reference for the application and evolution of artificial intelligence technology within the realm of education, thereby contributing substantively to the broader landscape of educational advancement.
Collapse
Affiliation(s)
- Yu Zhao
- Department of Preschool Education, Nanyang Vocational College of Agriculture, Nanyang City, 473000, China.
| | - WenWen Gao
- Department of Command Tactics, Henan Police College, ZhengZhou City, 450000, China
| | - ShanShan Ku
- Department of Agricultural Engineering, Nanyang Vocational College of Agriculture, Nanyang City, 473000, China
| |
Collapse
|
2
|
Wang H, Jiang J, Gan JQ, Wang H. Motor Imagery EEG Classification Based on a Weighted Multi-Branch Structure Suitable for Multisubject Data. IEEE Trans Biomed Eng 2023; 70:3040-3051. [PMID: 37186527 DOI: 10.1109/tbme.2023.3274231] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/17/2023]
Abstract
OBJECTIVE Electroencephalogram (EEG) signal recognition based on deep learning technology requires the support of sufficient data. However, training data scarcity usually occurs in subject-specific motor imagery tasks unless multisubject data can be used to enlarge training data. Unfortunately, because of the large discrepancies between data distributions from different subjects, model performance could only be improved marginally or even worsened by simply training on multisubject data. METHOD This article proposes a novel weighted multi-branch (WMB) structure for handling multisubject data to solve the problem, in which each branch is responsible for fitting a pair of source-target subject data and adaptive weights are used to integrate all branches or select branches with the largest weights to make the final decision. The proposed WMB structure was applied to six well-known deep learning models (EEGNet, Shallow ConvNet, Deep ConvNet, ResNet, MSFBCNN, and EEG_TCNet) and comprehensive experiments were conducted on EEG datasets BCICIV-2a, BCICIV-2b, high gamma dataset (HGD) and two supplementary datasets. RESULT Superior results against the state-of-the-art models have demonstrated the efficacy of the proposed method in subject-specific motor imagery EEG classification. For example, the proposed WMB_EEGNet achieved classification accuracies of 84.14%, 90.23%, and 97.81% on BCICIV-2a, BCICIV-2b and HGD, respectively. CONCLUSION It is clear that the proposed WMB structure is capable to make good use of multisubject data with large distribution discrepancies for subject-specific EEG classification.
Collapse
|
3
|
Wang P, Cao X, Zhou Y, Gong P, Yousefnezhad M, Shao W, Zhang D. A comprehensive review on motion trajectory reconstruction for EEG-based brain-computer interface. Front Neurosci 2023; 17:1086472. [PMID: 37332859 PMCID: PMC10272365 DOI: 10.3389/fnins.2023.1086472] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/01/2022] [Accepted: 05/03/2023] [Indexed: 06/20/2023] Open
Abstract
The advance in neuroscience and computer technology over the past decades have made brain-computer interface (BCI) a most promising area of neurorehabilitation and neurophysiology research. Limb motion decoding has gradually become a hot topic in the field of BCI. Decoding neural activity related to limb movement trajectory is considered to be of great help to the development of assistive and rehabilitation strategies for motor-impaired users. Although a variety of decoding methods have been proposed for limb trajectory reconstruction, there does not yet exist a review that covers the performance evaluation of these decoding methods. To alleviate this vacancy, in this paper, we evaluate EEG-based limb trajectory decoding methods regarding their advantages and disadvantages from a variety of perspectives. Specifically, we first introduce the differences in motor execution and motor imagery in limb trajectory reconstruction with different spaces (2D and 3D). Then, we discuss the limb motion trajectory reconstruction methods including experiment paradigm, EEG pre-processing, feature extraction and selection, decoding methods, and result evaluation. Finally, we expound on the open problem and future outlooks.
Collapse
Affiliation(s)
| | | | | | | | | | - Wei Shao
- *Correspondence: Wei Shao, ; Daoqiang Zhang,
| | | |
Collapse
|
4
|
Recognition of EEG based on Improved Black Widow Algorithm optimized SVM. Biomed Signal Process Control 2023. [DOI: 10.1016/j.bspc.2022.104454] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/02/2022]
|
5
|
Korkmaz OE, Aydemir O, Oral EA, Ozbek IY. A novel probabilistic and 3D column P300 stimulus presentation paradigm for EEG-based spelling systems. Neural Comput Appl 2023. [DOI: 10.1007/s00521-023-08329-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/18/2023]
|
6
|
Akram F, Alwakeel A, Alwakeel M, Hijji M, Masud U. A Symbols Based BCI Paradigm for Intelligent Home Control Using P300 Event-Related Potentials. SENSORS (BASEL, SWITZERLAND) 2022; 22:10000. [PMID: 36560369 PMCID: PMC9781197 DOI: 10.3390/s222410000] [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: 10/28/2022] [Revised: 12/06/2022] [Accepted: 12/15/2022] [Indexed: 06/17/2023]
Abstract
Brain-Computer Interface (BCI) is a technique that allows the disabled to interact with a computer directly from their brain. P300 Event-Related Potentials (ERP) of the brain have widely been used in several applications of the BCIs such as character spelling, word typing, wheelchair control for the disabled, neurorehabilitation, and smart home control. Most of the work done for smart home control relies on an image flashing paradigm where six images are flashed randomly, and the users can select one of the images to control an object of interest. The shortcoming of such a scheme is that the users have only six commands available in a smart home to control. This article presents a symbol-based P300-BCI paradigm for controlling home appliances. The proposed paradigm comprises of a 12-symbols, from which users can choose one to represent their desired command in a smart home. The proposed paradigm allows users to control multiple home appliances from signals generated by the brain. The proposed paradigm also allows the users to make phone calls in a smart home environment. We put our smart home control system to the test with ten healthy volunteers, and the findings show that the proposed system can effectively operate home appliances through BCI. Using the random forest classifier, our participants had an average accuracy of 92.25 percent in controlling the home devices. As compared to the previous studies on the smart home control BCIs, the proposed paradigm gives the users more degree of freedom, and the users are not only able to control several home appliances but also have an option to dial a phone number and make a call inside the smart home. The proposed symbols-based smart home paradigm, along with the option of making a phone call, can effectively be used for controlling home through signals of the brain, as demonstrated by the results.
Collapse
Affiliation(s)
- Faraz Akram
- Department of Biomedical Engineering, Riphah International University, Islamabad 46000, Pakistan
| | - Ahmed Alwakeel
- Sensor Networks and Cellular Systems Research Center, University of Tabuk, Tabuk 71491, Saudi Arabia
- Faculty of Computers & Information Technology, University of Tabuk, Tabuk 71491, Saudi Arabia
| | - Mohammed Alwakeel
- Faculty of Computers & Information Technology, University of Tabuk, Tabuk 71491, Saudi Arabia
| | - Mohammad Hijji
- Faculty of Computers & Information Technology, University of Tabuk, Tabuk 71491, Saudi Arabia
| | - Usman Masud
- Faculty of Electrical and Electronics Engineering, University of Engineering and Technology, Taxila 47050, Pakistan
- Department of Electrical Communication Engineering, University of Kassel, 34127 Kassel, Germany
| |
Collapse
|
7
|
Liu S, Zhang J, Wang A, Wu H, Zhao Q, Long J. Subject adaptation convolutional neural network for EEG-based motor imagery classification. J Neural Eng 2022; 19. [PMID: 36270467 DOI: 10.1088/1741-2552/ac9c94] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/23/2022] [Accepted: 10/21/2022] [Indexed: 01/11/2023]
Abstract
Objective.Deep transfer learning has been widely used to address the nonstationarity of electroencephalogram (EEG) data during motor imagery (MI) classification. However, previous deep learning approaches suffer from limited classification accuracy because the temporal and spatial features cannot be effectively extracted.Approach.Here, we propose a novel end-to-end deep subject adaptation convolutional neural network (SACNN) to handle the problem of EEG-based MI classification. Our proposed model jointly optimizes three modules, i.e. a feature extractor, a classifier, and a subject adapter. Specifically, the feature extractor simultaneously extracts the temporal and spatial features from the raw EEG data using a parallel multiscale convolution network. In addition, we design a subject adapter to reduce the feature distribution shift between the source and target subjects by using the maximum mean discrepancy. By minimizing the classification loss and the distribution discrepancy, the model is able to extract the temporal-spatial features to the prediction of a new subject.Main results.Extensive experiments are carried out on three EEG-based MI datasets, i.e. brain-computer interface (BCI) competition IV dataset IIb, BCI competition III dataset IVa, and BCI competition IV dataset I, and the average accuracy reaches to 86.42%, 81.71% and 79.35% on the three datasets respectively. Furthermore, the statistical analysis also indicates the significant performance improvement of SACNN.Significance.This paper reveals the importance of the temporal-spatial features on EEG-based MI classification task. Our proposed SACNN model can make fully use of the temporal-spatial information to achieve the purpose.
Collapse
Affiliation(s)
- Siwei Liu
- College of Information Science and Technology, Jinan University, Guangzhou 510632, People's Republic of China
| | - Jia Zhang
- College of Information Science and Technology, Jinan University, Guangzhou 510632, People's Republic of China
| | - Andong Wang
- Tensor Learning Team, RIKEN AIP, Tokyo, Japan
| | - Hanrui Wu
- College of Information Science and Technology, Jinan University, Guangzhou 510632, People's Republic of China
| | - Qibin Zhao
- Tensor Learning Team, RIKEN AIP, Tokyo, Japan
| | - Jinyi Long
- College of Information Science and Technology, Jinan University, Guangzhou 510632, People's Republic of China.,Guangdong Key Laboratory of Traditional Chinese Medicine Information Technology, Guangzhou 510632, People's Republic of China.,Pazhou Lab, Guangzhou 510335, People's Republic of China
| |
Collapse
|
8
|
Wang YM, Wei CL, Wang MW. Factors influencing students' adoption intention of brain–computer interfaces in a game-learning context. LIBRARY HI TECH 2022. [DOI: 10.1108/lht-12-2021-0506] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
PurposeA research framework that explains adoption intention in students with regard to brain–computer interface (BCI) games in the learning context was proposed and empirically examined.Design/methodology/approachIn this study, an approach integrating the decomposed theory of planned behavior, perceived playfulness, risk and the task–technology fit (TTF) concept was used to assess data collected using a post-experiment questionnaire from a student sample in Taiwan. The research model was tested using the partial least-squares structural equation modeling (PLS-SEM) technique.FindingsAttitude, subjective norms and TTF were shown to impact intention to play the BCI game significantly, while perceived behavioral control did not show a significant impact. The influence of superiors and peers was found to positively predict subjective norms. With the exception of perceived ease of use, all of the proposed antecedents were found to impact attitude toward BCI games. Technology facilitating conditions and BCI technology characteristics were shown to positively determine perceived behavior control and TTF, respectively. However, the other proposed factors did not significantly influence the latter two dependents.Originality/valueThis research contributes to the nascent literature on BCI games in the context of learning by highlighting the influence of belief-related psychological factors on user acceptance of BCI games. Moreover, this study highlights the important, respective influences of perceived playfulness, risk and TTF on users' perceptions of a game, body monitoring and technology implementation, each of which is known to influence willingness to play.
Collapse
|
9
|
Domingo MC. An Overview of Machine Learning and 5G for People with Disabilities. SENSORS 2021; 21:s21227572. [PMID: 34833648 PMCID: PMC8622934 DOI: 10.3390/s21227572] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/11/2021] [Revised: 11/10/2021] [Accepted: 11/11/2021] [Indexed: 11/23/2022]
Abstract
Currently, over a billion people, including children (or about 15% of the world’s population), are estimated to be living with disability, and this figure is going to increase to beyond two billion by 2050. People with disabilities generally experience poorer levels of health, fewer achievements in education, fewer economic opportunities, and higher rates of poverty. Artificial intelligence and 5G can make major contributions towards the assistance of people with disabilities, so they can achieve a good quality of life. In this paper, an overview of machine learning and 5G for people with disabilities is provided. For this purpose, the proposed 5G network slicing architecture for disabled people is introduced. Different application scenarios and their main benefits are considered to illustrate the interaction of machine learning and 5G. Critical challenges have been identified and addressed.
Collapse
Affiliation(s)
- Mari Carmen Domingo
- Department of Network Engineering, BarcelonaTech (UPC) University, 08860 Castelldefels, Spain
| |
Collapse
|
10
|
Sarmiento LC, Villamizar S, López O, Collazos AC, Sarmiento J, Rodríguez JB. Recognition of EEG Signals from Imagined Vowels Using Deep Learning Methods. SENSORS (BASEL, SWITZERLAND) 2021; 21:6503. [PMID: 34640824 PMCID: PMC8512781 DOI: 10.3390/s21196503] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 08/24/2021] [Revised: 09/17/2021] [Accepted: 09/24/2021] [Indexed: 01/27/2023]
Abstract
The use of imagined speech with electroencephalographic (EEG) signals is a promising field of brain-computer interfaces (BCI) that seeks communication between areas of the cerebral cortex related to language and devices or machines. However, the complexity of this brain process makes the analysis and classification of this type of signals a relevant topic of research. The goals of this study were: to develop a new algorithm based on Deep Learning (DL), referred to as CNNeeg1-1, to recognize EEG signals in imagined vowel tasks; to create an imagined speech database with 50 subjects specialized in imagined vowels from the Spanish language (/a/,/e/,/i/,/o/,/u/); and to contrast the performance of the CNNeeg1-1 algorithm with the DL Shallow CNN and EEGNet benchmark algorithms using an open access database (BD1) and the newly developed database (BD2). In this study, a mixed variance analysis of variance was conducted to assess the intra-subject and inter-subject training of the proposed algorithms. The results show that for intra-subject training analysis, the best performance among the Shallow CNN, EEGNet, and CNNeeg1-1 methods in classifying imagined vowels (/a/,/e/,/i/,/o/,/u/) was exhibited by CNNeeg1-1, with an accuracy of 65.62% for BD1 database and 85.66% for BD2 database.
Collapse
Affiliation(s)
- Luis Carlos Sarmiento
- Departamento de Tecnología, Universidad Pedagógica Nacional, Bogotá 111321, Colombia; (O.L.); (A.C.C.); (J.S.)
| | - Sergio Villamizar
- Department of Electrical and Electronics Engineering, School of Engineering, Universidad Nacional de Colombia, Bogotá 111321, Colombia; (S.V.); (J.B.R.)
| | - Omar López
- Departamento de Tecnología, Universidad Pedagógica Nacional, Bogotá 111321, Colombia; (O.L.); (A.C.C.); (J.S.)
| | - Ana Claros Collazos
- Departamento de Tecnología, Universidad Pedagógica Nacional, Bogotá 111321, Colombia; (O.L.); (A.C.C.); (J.S.)
| | - Jhon Sarmiento
- Departamento de Tecnología, Universidad Pedagógica Nacional, Bogotá 111321, Colombia; (O.L.); (A.C.C.); (J.S.)
| | - Jan Bacca Rodríguez
- Department of Electrical and Electronics Engineering, School of Engineering, Universidad Nacional de Colombia, Bogotá 111321, Colombia; (S.V.); (J.B.R.)
| |
Collapse
|
11
|
De Venuto D, Mezzina G. A Single-Trial P300 Detector Based on Symbolized EEG and Autoencoded-(1D)CNN to Improve ITR Performance in BCIs. SENSORS 2021; 21:s21123961. [PMID: 34201381 PMCID: PMC8226883 DOI: 10.3390/s21123961] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/12/2021] [Revised: 06/02/2021] [Accepted: 06/07/2021] [Indexed: 12/01/2022]
Abstract
In this paper, we propose a breakthrough single-trial P300 detector that maximizes the information translate rate (ITR) of the brain–computer interface (BCI), keeping high recognition accuracy performance. The architecture, designed to improve the portability of the algorithm, demonstrated full implementability on a dedicated embedded platform. The proposed P300 detector is based on the combination of a novel pre-processing stage based on the EEG signals symbolization and an autoencoded convolutional neural network (CNN). The proposed system acquires data from only six EEG channels; thus, it treats them with a low-complexity preprocessing stage including baseline correction, windsorizing and symbolization. The symbolized EEG signals are then sent to an autoencoder model to emphasize those temporal features that can be meaningful for the following CNN stage. This latter consists of a seven-layer CNN, including a 1D convolutional layer and three dense ones. Two datasets have been analyzed to assess the algorithm performance: one from a P300 speller application in BCI competition III data and one from self-collected data during a fluid prototype car driving experiment. Experimental results on the P300 speller dataset showed that the proposed method achieves an average ITR (on two subjects) of 16.83 bits/min, outperforming by +5.75 bits/min the state-of-the-art for this parameter. Jointly with the speed increase, the recognition performance returned disruptive results in terms of the harmonic mean of precision and recall (F1-Score), which achieve 51.78 ± 6.24%. The same method used in the prototype car driving led to an ITR of ~33 bit/min with an F1-Score of 70.00% in a single-trial P300 detection context, allowing fluid usage of the BCI for driving purposes. The realized network has been validated on an STM32L4 microcontroller target, for complexity and implementation assessment. The implementation showed an overall resource occupation of 5.57% of the total available ROM, ~3% of the available RAM, requiring less than 3.5 ms to provide the classification outcome.
Collapse
|