SessionNet: Feature Similarity-Based Weighted Ensemble Learning for Motor Imagery Classification

Jeong

IEEE Trans. Neural Syst. Rehabil. Eng.

et al. 2022

Self Cite

Highly sophisticated control based on a braincomputer interface (BCI) requires decoding kinematic information from brain signals. The forearm is a region of the upper limb that is often used in everyday life, but intuitive movements within the same limb have rarely been investigated in previous BCI studies. In this study, we focused on various forearm movement decoding from electroencephalography (EEG) signals using a small number of samples. Ten healthy participants took part in an experiment and performed motor execution (ME) and motor imagery (MI) of the intuitive movement tasks (Dataset I). We propose a convolutional neural network using a channel-wise variational autoencoder (CVNet) based on inter-task transfer learning. We approached that training the reconstructed ME-EEG signals together will also achieve more sufficient classification performance with only a small amount of MI-EEG signals.The proposed CVNet was validated on our own Dataset I and a public dataset, BNCI Horizon 2020 (Dataset II). The classification accuracies of various movements are confirmed to be 0.83 (±0.04) and 0.69 (±0.04) for Dataset I and II, respectively. The results show that the proposed method exhibits performance increases of approximately 0.09∼0.27 and 0.08∼0.24 compared with the conventional models for Dataset I and II, respectively. The outcomes suggest that the training model for decoding imagined movements can be performed using data from ME and a small number of data samples from MI. Hence, it is presented the feasibility of BCI learning strategies that can sufficiently learn deep learning with a few amount of calibration dataset and time only, with stable performance.

Section: A Datasetsmentioning

confidence: 99%

Motor Imagery Classification Using Inter-Task Transfer Learning via a Channel-Wise Variational Autoencoder-Based Convolutional Neural Network

Jeong

IEEE Trans. Neural Syst. Rehabil. Eng.

et al. 2022

Self Cite

“…For each condition separately, the EEG signals were bandpass filtered in each of six frequency bands: theta (3-7 Hz), alpha (7-13 Hz), low beta (13-16 Hz), beta (16)(17)(18)(19)(20)(21)(22)(23)(24)(25)(26), gamma (26)(27)(28)(29)(30)(31)(32)(33)(34)(35)(36)(37)(38)(39)(40), and 'all' (3-40 Hz). The channel-specific bandpower for every single trial was calculated for the band-passed data using the equation:…”

Section: The Bandpower Approachmentioning

confidence: 99%

Artifacts in EEG-Based BCI Therapies: Friend or Foe?

McDermott

Raggam

Kirsch

et al. 2021

Sensors

EEG-based brain–computer interfaces (BCI) have promising therapeutic potential beyond traditional neurofeedback training, such as enabling personalized and optimized virtual reality (VR) neurorehabilitation paradigms where the timing and parameters of the visual experience is synchronized with specific brain states. While BCI algorithms are often designed to focus on whichever portion of a signal is most informative, in these brain-state-synchronized applications, it is of critical importance that the resulting decoder is sensitive to physiological brain activity representative of various mental states, and not to artifacts, such as those arising from naturalistic movements. In this study, we compare the relative classification accuracy with which different motor tasks can be decoded from both extracted brain activity and artifacts contained in the EEG signal. EEG data were collected from 17 chronic stroke patients while performing six different head, hand, and arm movements in a realistic VR-based neurorehabilitation paradigm. Results show that the artifactual component of the EEG signal is significantly more informative than brain activity with respect to classification accuracy. This finding is consistent across different feature extraction methods and classification pipelines. While informative brain signals can be recovered with suitable cleaning procedures, we recommend that features should not be designed solely to maximize classification accuracy, as this could select for remaining artifactual components. We also propose the use of machine learning approaches that are interpretable to verify that classification is driven by physiological brain states. In summary, whereas informative artifacts are a helpful friend in BCI-based communication applications, they can be a problematic foe in the estimation of physiological brain states.

“…Lee, Byeong-Hoo Et al. [25] Future age organizations will oblige a lot of information traffic and lower inertness. To fulfill these needs, it is crucial for investigate current otherworldly utilize or present new recurrence groups.…”

Section: Related Workmentioning

confidence: 99%

“…The method of ESVL basically focus on the estimation of optimal value of kernel and hyper plan. The value of optimality enhances the capacity of classification[24,25]. (B) LSTM (LONG SHORT TIME MEMORY) NETWORK The long short-term memory (LSTM) network removes the problem of gradients.…”

mentioning

confidence: 99%

Analysis of Motor Imagery EEG Classification Based on Feature Extraction and Machine Learning Algorithm

Chintamani¹

2021

ITII

The brain-computer interface provides the excellent potential to address nervous system-related activity. The function of the nervous system work between internal brain control and external human body physical structure. Some parts of the human body cannot generate the signal for the processing of the human brain, cannot recognize and identify human body parts' activity—the motor imagery EEG classification approach helps resolve such types of critical illness cause of death. The dimension and structure of motor imagery-based EEG data are very high and unsupported behaviors. The machine learning and another classification algorithm cannot handle these variants of EEG data directly. For the process of better classification of motor imagery, EEG needs transformation and extraction. The transform-based feature extraction process such as DCT, DWT, SFTF and some other harmonic frequency-based applied. In this paper presents the details analysis of feature extraction and classification algorithms for motor imagery EEG classification. The machine learning provides three types of an algorithm for classification, supervised, unsupervised and semi-supervised. This paper mainly focuses on the supervised machine learning algorithm. For the analysis of machine learning algorithm use BC competition-IV dataset. MATLAB software is used as a tool for the code of algorithms and measures standard parameters such as accuracy, sensitivity and specificity.