1
|
Zheng M, Yang B. A deep neural network with subdomain adaptation for motor imagery brain-computer interface. Med Eng Phys 2021; 96:29-40. [PMID: 34565550 DOI: 10.1016/j.medengphy.2021.08.006] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/30/2021] [Revised: 08/15/2021] [Accepted: 08/17/2021] [Indexed: 10/20/2022]
Abstract
BACKGROUND The nonstationarity problem of EEG is very serious, especially for spontaneous signals, which leads to the poor effect of machine learning related to spontaneous signals, especially in related tasks across time, which correspondingly limits the practical use of brain-computer interface (BCI). OBJECTIVE In this paper, we proposed a new transfer learning algorithm, which can utilize the labeled motor imagery (MI) EEG data at the previous time to achieve better classification accuracies for a small number of labeled EEG signals at the current time. METHODS We introduced an adaptive layer into the full connection layer of a deep convolution neural network. The objective function of the adaptive layer was designed to minimize the Local Maximum Mean Discrepancy (LMMD) and the prediction error while minimizing the distance within each class (DWC) and maximizing the distance between classes within each domain (DBCWD). We verified the effectiveness of the proposed algorithm on two public datasets. RESULTS The classification accuracy of the proposed algorithm was higher than other comparison algorithms, and the paired t-test results also showed that the performance of the proposed algorithm was significantly different from that of other algorithms. The results of the confusion matrix and feature visualization showed the effectiveness of the proposed algorithm. CONCLUSION Experimental results showed that the proposed algorithm can achieve higher classification accuracy than other algorithms when there was only a small amount of labeled MI EEG data at the current time. It can be promising to be applied to the field of BCI.
Collapse
Affiliation(s)
- Minmin Zheng
- School of Mechatronic Engineering and Automation, Research Center of Brain Computer Engineering, Shanghai University, Shanghai, China; School of Mechanical and Electrical Engineering, Putian University, Fujian, China
| | - Banghua Yang
- School of Mechatronic Engineering and Automation, Research Center of Brain Computer Engineering, Shanghai University, Shanghai, China.
| |
Collapse
|
2
|
Wu D, Wang X, Wu S. A Hybrid Method Based on Extreme Learning Machine and Wavelet Transform Denoising for Stock Prediction. ENTROPY 2021; 23:e23040440. [PMID: 33918679 PMCID: PMC8070264 DOI: 10.3390/e23040440] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 03/08/2021] [Revised: 04/02/2021] [Accepted: 04/07/2021] [Indexed: 11/16/2022]
Abstract
The trend prediction of the stock is a main challenge. Accidental factors often lead to short-term sharp fluctuations in stock markets, deviating from the original normal trend. The short-term fluctuation of stock price has high noise, which is not conducive to the prediction of stock trends. Therefore, we used discrete wavelet transform (DWT)-based denoising to denoise stock data. Denoising the stock data assisted us to eliminate the influences of short-term random events on the continuous trend of the stock. The denoised data showed more stable trend characteristics and smoothness. Extreme learning machine (ELM) is one of the effective training algorithms for fully connected single-hidden-layer feedforward neural networks (SLFNs), which possesses the advantages of fast convergence, unique results, and it does not converge to a local minimum. Therefore, this paper proposed a combination of ELM- and DWT-based denoising to predict the trend of stocks. The proposed method was used to predict the trend of 400 stocks in China. The prediction results of the proposed method are a good proof of the efficacy of DWT-based denoising for stock trends, and showed an excellent performance compared to 12 machine learning algorithms (e.g., recurrent neural network (RNN) and long short-term memory (LSTM)).
Collapse
|
3
|
Motor Imagery Classification Based on a Recurrent-Convolutional Architecture to Control a Hexapod Robot. MATHEMATICS 2021. [DOI: 10.3390/math9060606] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/07/2023]
Abstract
Advances in the field of Brain-Computer Interfaces (BCIs) aim, among other applications, to improve the movement capacities of people suffering from the loss of motor skills. The main challenge in this area is to achieve real-time and accurate bio-signal processing for pattern recognition, especially in Motor Imagery (MI). The significant interaction between brain signals and controllable machines requires instantaneous brain data decoding. In this study, an embedded BCI system based on fist MI signals is developed. It uses an Emotiv EPOC+ Brainwear®, an Altera SoCKit® development board, and a hexapod robot for testing locomotion imagery commands. The system is tested to detect the imagined movements of closing and opening the left and right hand to control the robot locomotion. Electroencephalogram (EEG) signals associated with the motion tasks are sensed on the human sensorimotor cortex. Next, the SoCKit processes the data to identify the commands allowing the controlled robot locomotion. The classification of MI-EEG signals from the F3, F4, FC5, and FC6 sensors is performed using a hybrid architecture of Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. This method takes advantage of the deep learning recognition model to develop a real-time embedded BCI system, where signal processing must be seamless and precise. The proposed method is evaluated using k-fold cross-validation on both created and public Scientific-Data datasets. Our dataset is comprised of 2400 trials obtained from four test subjects, lasting three seconds of closing and opening fist movement imagination. The recognition tasks reach 84.69% and 79.2% accuracy using our data and a state-of-the-art dataset, respectively. Numerical results support that the motor imagery EEG signals can be successfully applied in BCI systems to control mobile robots and related applications such as intelligent vehicles.
Collapse
|
4
|
Moghaddari M, Lighvan MZ, Danishvar S. Diagnose ADHD disorder in children using convolutional neural network based on continuous mental task EEG. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2020; 197:105738. [PMID: 32927404 DOI: 10.1016/j.cmpb.2020.105738] [Citation(s) in RCA: 30] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/31/2020] [Accepted: 08/31/2020] [Indexed: 06/11/2023]
Abstract
BACKGROUND AND OBJECTIVE Attention-Deficit/Hyperactivity Disorder (ADHD) is a chronic behavioral disorder in children. Children with ADHD face many difficulties in maintaining their concentration and controlling their behaviors. Early diagnosis of this disorder is one of the most important challenges in its control and treatment. No definitive expert method has been found to detect this disorder early. Our goal in this study is to develop an assistive tool for physicians to recognize ADHD children from healthy children using electroencephalography (EEG) based on a continuous mental task. METHODS We used EEG signals recorded from 31 ADHD children and 30 healthy children. In this study, we developed a deep learning model using a convolutional neural network that have had significant performance in image processing fields. For this purpose, we first preprocessed EEG signals to eliminate noise and artifacts. Then we segmented preprocessed samples into more samples. We extracted the theta, alpha, beta, and gamma frequency bands from each segmented sample and formed a color RGB image with three channels. Eventually, we imported the resulting images into a 13-layer convolutional neural network for feature extraction and classification. RESULTS The proposed model was evaluated by 5-fold cross validation for train, evaluation, and test data and achieved an average accuracy of 99.06%, 97.81%, 97.47% for segmented samples. The average accuracy for subject-based test samples was 98.48%. Also, the performance of the model was evaluated using the confusion matrix with precision, recall, and f1-score metrics. The results of these metrics also confirmed the outstanding performance of the model. CONCLUSIONS The accuracy, precision, recall, and f1-score of our model were better than all previous works for diagnosing ADHD in children. Based on these prominent and reliable results, this technique can be used as an assistive tool for the physicians in the early diagnosis of ADHD in children.
Collapse
Affiliation(s)
- Majid Moghaddari
- Department of Electronic and Computer Engineering, University of Tabriz, Tabriz, Iran
| | - Mina Zolfy Lighvan
- Department of Electronic and Computer Engineering, University of Tabriz, Tabriz, Iran.
| | - Sebelan Danishvar
- Department of Electronic and Computer Engineering, University of Tabriz, Tabriz, Iran; Department of Electronic and Computer Engineering, College of Engineering, Design and Physical Sciences, Brunel University, UK
| |
Collapse
|
5
|
Li Z, Zhang S, Pan J. Advances in Hybrid Brain-Computer Interfaces: Principles, Design, and Applications. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE 2019; 2019:3807670. [PMID: 31687006 PMCID: PMC6800963 DOI: 10.1155/2019/3807670] [Citation(s) in RCA: 15] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 06/20/2019] [Revised: 09/09/2019] [Accepted: 09/17/2019] [Indexed: 11/23/2022]
Abstract
Conventional brain-computer interface (BCI) systems have been facing two fundamental challenges: the lack of high detection performance and the control command problem. To this end, the researchers have proposed a hybrid brain-computer interface (hBCI) to address these challenges. This paper mainly discusses the research progress of hBCI and reviews three types of hBCI, namely, hBCI based on multiple brain models, multisensory hBCI, and hBCI based on multimodal signals. By analyzing the general principles, paradigm designs, experimental results, advantages, and applications of the latest hBCI system, we found that using hBCI technology can improve the detection performance of BCI and achieve multidegree/multifunctional control, which is significantly superior to single-mode BCIs.
Collapse
Affiliation(s)
- Zina Li
- South China Normal University, Guangzhou 510631, China
| | - Shuqing Zhang
- South China Normal University, Guangzhou 510631, China
| | - Jiahui Pan
- South China Normal University, Guangzhou 510631, China
| |
Collapse
|
6
|
Takahashi K, Kato K, Mizuguchi N, Ushiba J. Precise estimation of human corticospinal excitability associated with the levels of motor imagery-related EEG desynchronization extracted by a locked-in amplifier algorithm. J Neuroeng Rehabil 2018; 15:93. [PMID: 30384845 PMCID: PMC6211493 DOI: 10.1186/s12984-018-0440-5] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/10/2017] [Accepted: 10/18/2018] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND Physical motor exercise aided by an electroencephalogram (EEG)-based brain-computer interface (BCI) is known to improve motor recovery in patients with stroke. In such a BCI paradigm, event-related desynchronization (ERD) in the alpha and beta bands extracted from EEG recorded over the primary sensorimotor area (SM1) is often used, since ERD has been suggested to be associated with an increase of corticospinal excitability. Recently, we demonstrated a novel online lock-in amplifier (LIA) algorithm to estimate the amplitude modulation of motor-related SM1 ERD. With this algorithm, the delay time, accuracy, and stability to estimate motor-related SM1 ERD were significantly improved compared with the conventional fast Fourier transformation (FFT) algorithm. These technical improvements to extract an ERD trace imply a potential advantage for a better trace of the excitatory status of the SM1 in a BCI context. Therefore, the aim of this study was to assess the precision of LIA-based ERD tracking for estimation of corticospinal excitability using a transcranial magnetic stimulation (TMS) paradigm. METHODS The motor evoked potentials (MEPs) induced by single-pulse TMS over the primary motor cortex depending on the magnitudes of SM1 ERD (i.e., 35% and 70%) extracted by the online LIA or FFT algorithm were monitored during a motor imagery task of wrist extension in 17 healthy participants. Then, the peak-to-peak amplitudes of MEPs and their variabilities were assessed to investigate the precision of the algorithms. RESULTS We found greater MEP amplitude evoked by single-pulse TMS triggered by motor imagery-related alpha SM1 ERD than at rest. This enhancement was associated with the magnitude of ERD in both FFT and LIA algorithms. Moreover, we found that the variabilities of peak-to-peak MEP amplitudes at 35% and 70% ERDs calculated by the novel online LIA algorithm were smaller than those extracted using the conventional FFT algorithm. CONCLUSIONS The present study demonstrated that the calculation of motor imagery-related SM1 ERDs using the novel online LIA algorithm led to a more precise estimation of corticospinal excitability than when the ordinary FFT-based algorithm was used.
Collapse
Affiliation(s)
- Kensho Takahashi
- Faculty of Science and Technology, Keio University, 3-14-1 Hiyoshi, Kohoku-ku, Yokohama, Kanagawa, 223-8522, Japan
| | - Kenji Kato
- Faculty of Science and Technology, Keio University, 3-14-1 Hiyoshi, Kohoku-ku, Yokohama, Kanagawa, 223-8522, Japan.,Department of Rehabilitation Medicine, Keio University School of Medicine, 35 Shinanomachi, Shinjuku, Tokyo, 160-8582, Japan.,Present address: Center of Assistive Robotics and Rehabilitation for Longevity and Good Health, National Center for Geriatrics and Gerontology, 7-430, Morioka-cho, Obu, Aichi, 474-8511, Japan
| | - Nobuaki Mizuguchi
- Faculty of Science and Technology, Keio University, 3-14-1 Hiyoshi, Kohoku-ku, Yokohama, Kanagawa, 223-8522, Japan.,The Japan Society for the Promotion of Science, 5-3-1 Kojimachi, Chiyoda-ku, Tokyo, 102-0083, Japan
| | - Junichi Ushiba
- Faculty of Science and Technology, Keio University, 3-14-1 Hiyoshi, Kohoku-ku, Yokohama, Kanagawa, 223-8522, Japan. .,Keio Institute of Pure and Applied Sciences (KiPAS), Keio University, 3-14-1 Hiyoshi, Kohoku-ku, Yokohama, Kanagawa, 223-8522, Japan. .,Department of Biosciences and Informatics, Faculty of Science and Technology, Keio University, 3-14-1 Hiyoshi, Kouhoku-ku, Yokohama, Kanagawa, 223-8522, Japan.
| |
Collapse
|