EEG-based Motion Intention Recognition via Multi-task RNNs

Abstract

Recognition of human intention based on Electroencephalography (EEG) signals attracts strong research interest in pattern recognition because of its promising applications that enable non-muscular communications and controls. Over the past few years, most EEG-based recognition works make significant efforts to learn extracted features to explore specific patterns between a segment of EEG signals and the corresponding activities. Unfortunately, vectorization-based feature representations, either vector-like or matrix-like ones, suffer from massive signal noise and difficulties of exploiting signal correlations between adjacent sensors of EEG signals. Most importantly, EEG signals are represented by one unique frequency and then fed into the subsequent learning model. Neglecting different frequencies of EEG signals can be detrimental to activity recognition because a particular frequency of EEG signals is more helpful to recognize some activities. Inspired by this idea, we propose to extract EEG signals with different frequencies and introduce a novel Multi-task deep learning model to learn the human intentions. We have conducted extensive experiments on a publicly available EEG benchmark dataset and compared our method with many state-of-the-art algorithms. The experimental results demonstrate that the proposed Multi-task deep recurrent neural network outperforms all the compared methods in a multi-class scenario.

Reducing Response Time in Motor Imagery Using A Headband and Deep Learning

“…Most of the previous studies on motor imagery classification applied ML/DL algorithms use EEG recordings greater than 10 s. The BCI devices were both low-intrusive and intrusive. Both Zhang et al [ 27 ] and Chen et al [ 28 ] classified 5 intentions (eyes closed, opening-closing both feet, both fists, left fist, and right fist) with the LSTM technique achieving an accuracy close to 98%, but using 120 s-session size from MI-EEG dataset recorded with a high-intrusive EEG cap (Electro-Cap International USA). Rodriguez et al [ 25 ] achieved 80% accuracy applying convolutional neural networks (CNN) and LSTMs layers to learn 4 motion intentions of a single user (hand, foot, mathematical activity, and relaxation state), but the response time was 30 s. Garcia-Moreno et al [ 13 ] also used CNN+LSTM to classify 2 intentions (right and left hands), reaching 98.9% accuracy for 20 s response time.…”

Estimation of Hand Motion from Piezoelectric Soft Sensor Using Deep Recurrent Network

“…We introduce the structure of the network using the Long-Short Term Memory (LSTM) units for predicting outputs and utilized the estimated result in our glove system. Several previous studies have already used the LSTM unit for processing of sequential sensor data [11,12,20,21] and the performance of the network was demonstrated.…”

Interhemispheric Brain Switching Correlates with Severity of Sleep-Disordered Breathing for Obstructive Sleep Apnea Patients

“…EEG is the most common tool used in sleep research [10][11][12][13][14][15][16]. Recently, EEG coherence analysis has garnered considerable interests to study the functional asymmetry of the brain [17][18][19][20][21][22]. A fundamental left-right brain switching mechanism is observed across the animal kingdom from invertebrates through to birds and mammals, including.…”