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

Electroencephalography (EEG) signals to detect motor imagery have been used to help patients with low mobility. However, the regular brain computer interfaces (BCI) capturing the EEG signals usually require intrusive devices and cables linked to machines. Recently, some commercial low-intrusive BCI headbands have appeared, but with less electrodes than the regular BCIs. Some works have proved the ability of the headbands to detect basic motor imagery. However, all of these works have focused on the accuracy of the detection, using session sizes larger than 10 s, in order to improve the accuracy. These session sizes prevent actuators using the headbands to interact with the user within an adequate response time. In this work, we explore the reduction of time-response in a low-intrusive device with only 4 electrodes using deep learning to detect right/left hand motion imagery. The obtained model is able to lower the detection time while maintaining an acceptable accuracy in the detection. Our findings report an accuracy above 83.8% for response time of 2 s overcoming the related works with both low- and high-intrusive devices. Hence, our low-intrusive and low-cost solution could be used in an interactive system with a reduced response time of 2 s.

[1]  Jessilyn Dunn,et al.  Wearables and the medical revolution. , 2018, Personalized medicine.

[2]  Tapas Mondal,et al.  Wearable Sensors for Remote Health Monitoring , 2017, Sensors.

[3]  Brent Lance,et al.  EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces , 2016, Journal of neural engineering.

[4]  Guang-Zhong Yang,et al.  Deep Learning for Health Informatics , 2017, IEEE Journal of Biomedical and Health Informatics.

[5]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[6]  Domenico Prattichizzo,et al.  Haptic Assistive Bracelets for Blind Skier Guidance , 2016, AH.

[7]  Ugur Halici,et al.  A novel deep learning approach for classification of EEG motor imagery signals , 2017, Journal of neural engineering.

[8]  Juhan Nam,et al.  Multimodal Deep Learning , 2011, ICML.

[9]  Murat Kaya,et al.  A large electroencephalographic motor imagery dataset for electroencephalographic brain computer interfaces , 2018, Scientific Data.

[10]  Ahmed Zoha,et al.  Health management and pattern analysis of daily living activities of people with dementia using in-home sensors and machine learning techniques , 2018, PloS one.

[12]  K.-R. Muller,et al.  The Berlin brain-computer interface: EEG-based communication without subject training , 2006, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[13]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[14]  Lina Yao,et al.  EEG-based Motion Intention Recognition via Multi-task RNNs , 2018, SDM.

[15]  Amit Konar,et al.  Performance analysis of left/right hand movement classification from EEG signal by intelligent algorithms , 2011, 2011 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB).

[16]  Wolfram Burgard,et al.  Deep learning with convolutional neural networks for EEG decoding and visualization , 2017, Human brain mapping.

[17]  Lina Yao,et al.  A Survey on Deep Learning based Brain Computer Interface: Recent Advances and New Frontiers , 2019, ArXiv.

[18]  Fabien Lotte,et al.  Signal Processing Approaches to Minimize or Suppress Calibration Time in Oscillatory Activity-Based Brain–Computer Interfaces , 2015, Proceedings of the IEEE.

[19]  Shirin Enshaeifar,et al.  IoT-Stream: A Lightweight Ontology for Internet of Things Data Streams and Its Use with Data Analytics and Event Detection Services † , 2020, Sensors.

[20]  María José Rodríguez-Fórtiz,et al.  A CNN-LSTM Deep Learning Classifier for Motor Imagery EEG Detection Using a Low-invasive and Low-Cost BCI Headband , 2020, 2020 16th International Conference on Intelligent Environments (IE).

[21]  Klaus Moessner,et al.  Analysing real world data streams with spatio-temporal correlations: Entropy vs. Pearson correlation , 2018 .

[22]  André P. Calitz,et al.  Human activity recognition using deep electroencephalography learning , 2020, Biomed. Signal Process. Control..

[23]  Shouqian Sun,et al.  Single-trial EEG classification of motor imagery using deep convolutional neural networks , 2017 .

[24]  R. Leeb,et al.  BCI Competition 2008 { Graz data set B , 2008 .

[25]  Junaidah Bte Mustafa Kamal.,et al.  Remote health monitoring. , 2013 .

[26]  Giuseppe Fico,et al.  Co-creating with consumers and stakeholders to understand the benefit of Internet of Things in Smart Living Environments for Ageing Well: the approach adopted in the Madrid Deployment Site of the ACTIVAGE Large Scale Pilot , 2017 .

[27]  Alvaro Uribe-Quevedo,et al.  Facial Expression Detection Employing a Brain Computer Interface , 2018, 2018 9th International Conference on Information, Intelligence, Systems and Applications (IISA).

[28]  María José Rodríguez-Fórtiz,et al.  A Microservices e-Health System for Ecological Frailty Assessment Using Wearables , 2020, Sensors.

[29]  Jin-Woo Jeong,et al.  Motor Imagery EEG Classification Using Capsule Networks† , 2019, Sensors.

[30]  María Bermúdez-Edo,et al.  Spatio-Temporal Analysis for Smart City Data , 2018, WWW.

[31]  Zhen Li,et al.  Recognition of Brain Waves of Left and Right Hand Movement Imagery with Portable Electroencephalographs , 2015, ArXiv.

[32]  Lina Yao,et al.  EEG-based Intention Recognition from Spatio-Temporal Representations via Cascade and Parallel Convolutional Recurrent Neural Networks , 2017, ArXiv.

[33]  Lina Yao,et al.  Intent Recognition in Smart Living Through Deep Recurrent Neural Networks , 2017, ICONIP.

[34]  María Bermúdez-Edo,et al.  Designing a Smart Mobile Health System for Ecological Frailty Assessment in Elderly , 2019, UCAmI.

[35]  Athanasios V. Vasilakos,et al.  Brain computer interface: control signals review , 2017, Neurocomputing.

[36]  Valer Jurcak,et al.  10/20, 10/10, and 10/5 systems revisited: Their validity as relative head-surface-based positioning systems , 2007, NeuroImage.

[37]  Kazuyuki Aihara,et al.  Logistic Regression for Single Trial EEG Classification , 2006, NIPS.

[38]  C. Quinn,et al.  Digital assessment of falls risk, frailty, and mobility impairment using wearable sensors , 2019, npj Digital Medicine.

[39]  Anikó Ekárt,et al.  A Deep Evolutionary Approach to Bioinspired Classifier Optimisation for Brain-Machine Interaction , 2019, Complex..

[40]  Pawan Lingras,et al.  Identifying users and activities with cognitive signal processing from a wearable headband , 2016, 2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC).

[41]  Geoffrey E. Hinton,et al.  Regularizing Neural Networks by Penalizing Confident Output Distributions , 2017, ICLR.

[42]  Tiago H. Falk,et al.  Deep learning-based electroencephalography analysis: a systematic review , 2019, Journal of neural engineering.

[43]  Aimin Jiang,et al.  LSTM-Based EEG Classification in Motor Imagery Tasks , 2018, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[44]  D J Nutt,et al.  LSD‐induced entropic brain activity predicts subsequent personality change , 2016, Human brain mapping.

[45]  S. Coyle,et al.  Brain–computer interfaces: a review , 2003 .