Automatically Identified EEG Signals of Movement Intention Based on CNN Network (End-To-End)

Shahini, Nahal; Bahrami, Zeinab; Sheykhivand, Sobhan; Marandi, Saba; Danishvar, Morad; Daneshvar, Sabalan; Roosta, Yousef

doi:10.3390/electronics11203297

Cited by 17 publications

(10 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is envisaged that BCI would enable robots to exhibit human-like observation, interpretation, and emotional expression skills. Following are the three primary perspectives that have been used to analyze emotions [40]: a.…”

Section: Discussionmentioning

confidence: 99%

Customized 2D CNN Model for the Automatic Emotion Recognition Based on EEG Signals

et al. 2023

Self Cite

View full text Add to dashboard Cite

Automatic emotion recognition from electroencephalogram (EEG) signals can be considered as the main component of brain–computer interface (BCI) systems. In the previous years, many researchers in this direction have presented various algorithms for the automatic classification of emotions from EEG signals, and they have achieved promising results; however, lack of stability, high error, and low accuracy are still considered as the central gaps in this research. For this purpose, obtaining a model with the precondition of stability, high accuracy, and low error is considered essential for the automatic classification of emotions. In this research, a model based on Deep Convolutional Neural Networks (DCNNs) is presented, which can classify three positive, negative, and neutral emotions from EEG signals based on musical stimuli with high reliability. For this purpose, a comprehensive database of EEG signals has been collected while volunteers were listening to positive and negative music in order to stimulate the emotional state. The architecture of the proposed model consists of a combination of six convolutional layers and two fully connected layers. In this research, different feature learning and hand-crafted feature selection/extraction algorithms were investigated and compared with each other in order to classify emotions. The proposed model for the classification of two classes (positive and negative) and three classes (positive, neutral, and negative) of emotions had 98% and 96% accuracy, respectively, which is very promising compared with the results of previous research. In order to evaluate more fully, the proposed model was also investigated in noisy environments; with a wide range of different SNRs, the classification accuracy was still greater than 90%. Due to the high performance of the proposed model, it can be used in brain–computer user environments.

show abstract

Section: Discussionmentioning

confidence: 99%

Customized 2D CNN Model for the Automatic Emotion Recognition Based on EEG Signals

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…to the mentioned abilities of type-II fuzzy sets, the belonging functions of type-II fuzzy activation functions are used instead of the usual activation functions in the proposed model's hidden layers to deal with uncertainties, measurement noises, and improve detection accuracy [19][20][21].…”

Section: Suggested Methodsmentioning

confidence: 99%

“…The total number of learnable/adjustable parameters when using the type-II fuzzy activation function is only 3C(C is the number of hidden units), indicating that this number is relatively small when compared to the total number of ordinary DNN weights. Due to the mentioned abilities of type-II fuzzy sets, the belonging functions of type-II fuzzy activation functions are used instead of the usual activation functions in the proposed model's hidden layers to deal with uncertainties, measurement noises, and improve detection accuracy [19][20][21].…”

Section: Type-ii Fuzzy Setmentioning

confidence: 99%

Acute Leukemia Diagnosis Based on Images of Lymphocytes and Monocytes Using Type-II Fuzzy Deep Network

et al. 2023

Self Cite

View full text Add to dashboard Cite

A cancer diagnosis is one of the most difficult medical challenges. Leukemia is a type of cancer that affects the bone marrow and/or blood and accounts for approximately 8% of all cancers. Understanding the epidemiology and trends of leukemia is critical for planning. Specialists diagnose leukemia using morphological analysis, but there is a possibility of error in diagnosis. Since leukemia is so difficult to diagnose, intelligent methods of diagnosis are required. The primary goal of this study is to develop a novel method for extracting features hierarchically and accurately, in order to diagnose various types of acute leukemia. This method distinguishes between acute leukemia types, namely Acute Lymphocytic Leukemia (ALL) and Acute Myeloid Leukemia (AML), by distinguishing lymphocytes from monocytes. The images used in this study are obtained from the Shahid Ghazi Tabatabai Oncology Center in Tabriz. A type-II fuzzy deep network is designed for this purpose. The proposed model has an accuracy of 98.8% and an F1-score of 98.9%, respectively. The results show that the proposed method has a high diagnostic performance. Furthermore, the proposed method has the ability to generalize more satisfactorily and has a stronger learning performance than other methods.

show abstract

“…The convolution operation extracts local features in the single-channel dimension, reduces the size of the vector dimension, and sets the size of the convolution kernel to , and performs feature learning through a sliding convolution window on the signal dimension, and the step size is set to 1. In order to avoid the necrosis of neurons in the RELU activation function during the training process, resulting in poor training results [9], a nonlinear activation function Swish [10] with better performance is introduced to speed up model training and regularize the overall network. effect.…”

Section: Overall Model Architecturementioning

confidence: 99%

Sentiment recognition model of EEG signals combined with one-dimensional convolution and BiBASRU-AT

Zhu

Wang

Ding

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

To address the problems of low accuracy of EEG emotion sentiment and insufficient feature extraction ability of recurrent model, an EEG sentiment recognition model combining one-dimensional convolution and BiBASRU-AT is proposed. The data set is preprocessed in segments to expand the number of samples, and 62 channel local emotional features are extracted from one-dimensional convolution; The built-in self-attention simple recurrent unit is constructed to capture the multi-channel fusion features and the dependence between channels. The soft attention mechanism identifies the key features that have a great impact on the identification of emotional tendencies, and the linear layer outputs the positive, neutral and negative emotion recognition results. The experimental results on the EEG data set(SEED) show that the model achieves an average classification accuracy of 90.24%, which is higher than the excellent deep learning model compared with the experiment. The built-in self-attention simple recurrent unit has stronger feature capture ability, which proves the effectiveness of the model.

show abstract

Automatically Identified EEG Signals of Movement Intention Based on CNN Network (End-To-End)

Cited by 17 publications

References 34 publications

Customized 2D CNN Model for the Automatic Emotion Recognition Based on EEG Signals

Customized 2D CNN Model for the Automatic Emotion Recognition Based on EEG Signals

Acute Leukemia Diagnosis Based on Images of Lymphocytes and Monocytes Using Type-II Fuzzy Deep Network

Sentiment recognition model of EEG signals combined with one-dimensional convolution and BiBASRU-AT

Contact Info

Product

Resources

About