A CNN-Based Deep Learning Approach for SSVEP Detection Targeting Binaural Ear-EEG.

This paper discusses a machine learning approach for detecting SSVEP at both ears with minimal channels. SSVEP is a robust EEG signal suitable for many BCI applications. It is strong at the visual cortex around the occipital area, but the SNR gets worse when detected from other areas of the head. To make use of SSVEP measured around the ears following the ear-EEG concept, especially for practical binaural implementation, we propose a CNN structure coupled with regressed softmax outputs to improve accuracy. Evaluating on a public dataset, we studied classification performance for both subject-dependent and subject-independent trainings. It was found that with the proposed structure using a group training approach, a 69.21% accuracy was achievable. An ITR of 6.42 bit/min given 63.49 % accuracy was recorded while only monitoring data from T7 and T8. This represents a 12.47% improvement from a single ear implementation and illustrates potential of the approach to enhance performance for practical implementation of wearable EEG.

Automatic Speech Discrimination Assessment Methods Based on Event-Related Potentials (ERP).

Speech discrimination is used by audiologists in diagnosing and determining treatment for hearing loss patients. Usually, assessing speech discrimination requires subjective responses. Using electroencephalography (EEG), a method that is based on event-related potentials (ERPs), could provide objective speech discrimination. In this work we proposed a visual-ERP-based method to assess speech discrimination using pictures that represent word meaning. The proposed method was implemented with three strategies, each with different number of pictures and test sequences. Machine learning was adopted to classify between the task conditions based on features that were extracted from EEG signals. The results from the proposed method were compared to that of a similar visual-ERP-based method using letters and a method that is based on the auditory mismatch negativity (MMN) component. The P3 component and the late positive potential (LPP) component were observed in the two visual-ERP-based methods while MMN was observed during the MMN-based method. A total of two out of three strategies of the proposed method, along with the MMN-based method, achieved approximately 80% average classification accuracy by a combination of support vector machine (SVM) and common spatial pattern (CSP). Potentially, these methods could serve as a pre-screening tool to make speech discrimination assessment more accessible, particularly in areas with a shortage of audiologists.

Brain Exercising Games With Consumer-Grade Single-Channel Electroencephalogram Neurofeedback: Pre-Post Intervention Study.

BACKGROUND: The aging population is one of the major challenges affecting societies worldwide. As the proportion of older people grows dramatically, so does the number of age-related illnesses such as dementia-related illnesses. Preventive care should be emphasized as an effective tool to combat and manage this situation. OBJECTIVE: The aim of this pilot project was to study the benefits of using neurofeedback-based brain training games for enhancing cognitive performance in the elderly population. In particular, aiming for practicality, the training games were designed to operate with a low-cost consumer-grade single-channel electroencephalogram (EEG) headset that should make the service scalable and more accessible for wider adoption such as for home use. METHODS: Our training system, which consisted of five brain exercise games using neurofeedback, was serviced at 5 hospitals in Thailand. Participants were screened for cognitive levels using the Thai Mental State Examination and Montreal Cognitive Assessment. Those who passed the criteria were further assessed with the Cambridge Neuropsychological Test Automated Battery (CANTAB) computerized cognitive assessment battery. The physiological state of the brain was also assessed using 16-channel EEG. After 20 sessions of training, cognitive performance and EEG were assessed again to compare pretraining and posttraining results. RESULTS: Thirty-five participants completed the training. CANTAB results showed positive and significant effects in the visual memory (delayed matching to sample [percent correct] P=.04), attention (median latency P=.009), and visual recognition (spatial working memory [between errors] P=.03) domains. EEG also showed improvement in upper alpha activity in a resting state (open-eyed) measured from the occipital area (P=.04), which similarly indicated improvement in the cognitive domain (attention). CONCLUSIONS: Outcomes of this study show the potential use of practical neurofeedback-based training games for brain exercise to enhance cognitive performance in the elderly population.

A Wearable In-Ear EEG Device for Emotion Monitoring.

For future healthcare applications, which are increasingly moving towards out-of-hospital or home-based caring models, the ability to remotely and continuously monitor patients' conditions effectively are imperative. Among others, emotional state is one of the conditions that could be of interest to doctors or caregivers. This paper discusses a preliminary study to develop a wearable device that is a low cost, single channel, dry contact, in-ear EEG suitable for non-intrusive monitoring. All aspects of the designs, engineering, and experimenting by applying machine learning for emotion classification, are covered. Based on the valence and arousal emotion model, the device is able to classify basic emotion with 71.07% accuracy (valence), 72.89% accuracy (arousal), and 53.72% (all four emotions). The results are comparable to those measured from the more conventional EEG headsets at T7 and T8 scalp positions. These results, together with its earphone-like wearability, suggest its potential usage especially for future healthcare applications, such as home-based or tele-monitoring systems as intended.

A game-based neurofeedback training system to enhance cognitive performance in healthy elderly subjects and in patients with amnestic mild cognitive impairment.

INTRODUCTION: This study examines the clinical efficacy of a game-based neurofeedback training (NFT) system to enhance cognitive performance in patients with amnestic mild cognitive impairment (aMCI) and healthy elderly subjects. The NFT system includes five games designed to improve attention span and cognitive performance. The system estimates attention levels by investigating the power spectrum of Beta and Alpha bands. METHODS: We recruited 65 women with aMCI and 54 healthy elderly women. All participants were treated with care as usual (CAU); 58 were treated with CAU + NFT (20 sessions of 30 minutes each, 2-3 sessions per week), 36 with CAU + exergame-based training, while 25 patients had only CAU. Cognitive functions were assessed using the Cambridge Neuropsychological Test Automated Battery both before and after treatment. RESULTS: NFT significantly improved rapid visual processing and spatial working memory (SWM), including strategy, when compared with exergame training and no active treatment. aMCI was characterized by impairments in SWM (including strategy), pattern recognition memory, and delayed matching to samples. CONCLUSION: In conclusion, treatment with NFT improves sustained attention and SWM. Nevertheless, NFT had no significant effect on pattern recognition memory and short-term visual memory, which are the other hallmarks of aMCI. The NFT system used here may selectively improve sustained attention, strategy, and executive functions, but not other cognitive impairments, which characterize aMCI in women.

Comparison of EEG measurement of upper limb movement in motor imagery training system.

BACKGROUND: One of the most promising applications for electroencephalogram (EEG)-based brain computer interface is for stroke rehabilitation. Implemented as a standalone motor imagery (MI) training system or as part of a rehabilitation robotic system, many studies have shown benefits of using them to restore motor control in stroke patients. Hand movements have widely been chosen as MI tasks. Although potentially more challenging to analyze, wrist and forearm movement such as wrist flexion/extension and forearm pronation/supination should also be considered for MI tasks, because these movements are part of the main exercises given to patients in conventional stroke rehabilitation. This paper will evaluate the effectiveness of such movements for MI tasks. METHODS: Three hand and wrist movement tasks which were hand opening/closing, wrist flexion/extension and forearm pronation/supination were chosen as motor imagery tasks for both hands. Eleven subjects participated in the experiment. All of them completed hand opening/closing task session. Ten subjects completed two MI task sessions which were hand opening/closing and wrist flexion/extension. Five subjects completed all three MI tasks sessions. Each MI task comprised 8 sessions spanning a 4 weeks period. For classification, feature extraction based on common spatial pattern (CSP) algorithm was used. Two types were implemented, one with conventional CSP (termed WB) and one with an increase number of features achieved by filtering EEG data into five bands (termed FB). Classification was done by linear discriminant analysis (LDA) and support vector machine (SVM). RESULTS: Eight-fold cross validation was applied on EEG data. LDA and SVM gave comparable classification accuracy. FB achieved significantly higher classification accuracy compared to WB. The accuracy of classifying wrist flexion/extension task were higher than that of classifying hand opening/closing task in all subjects. Classifying forearm pronation/supination task achieved higher accuracy than classifying hand opening/closing task in most subjects but achieved lower accuracy than classifying wrist flexion/extension task in all subjects. Significant improvements of classification accuracy were found in nine subjects when considering individual sessions of experiments of all MI tasks. The results of classifying hand opening/closing task and wrist flexion/extension task were comparable to the results of classifying hand opening/closing task and forearm pronation/supination task. Classification accuracy of wrist flexion/extension task and forearm pronation/supination task was lower than those of hand movement tasks and wrist movement tasks. CONCLUSION: High classification accuracy of the three MI tasks support the possibility of using EEG-based stroke rehabilitation system with these movements. Either LDA or SVM can equally be chosen as a classifier since the difference of their accuracies is not statistically significant. Significantly higher classification accuracy made FB more suitable for classifying MI task compared to WB. More training sessions could potentially lead to better accuracy as evident in most subjects in this experiment.

EEG-based emotion recognition using deep learning network with principal component based covariate shift adaptation.

Automatic emotion recognition is one of the most challenging tasks. To detect emotion from nonstationary EEG signals, a sophisticated learning algorithm that can represent high-level abstraction is required. This study proposes the utilization of a deep learning network (DLN) to discover unknown feature correlation between input signals that is crucial for the learning task. The DLN is implemented with a stacked autoencoder (SAE) using hierarchical feature learning approach. Input features of the network are power spectral densities of 32-channel EEG signals from 32 subjects. To alleviate overfitting problem, principal component analysis (PCA) is applied to extract the most important components of initial input features. Furthermore, covariate shift adaptation of the principal components is implemented to minimize the nonstationary effect of EEG signals. Experimental results show that the DLN is capable of classifying three different levels of valence and arousal with accuracy of 49.52% and 46.03%, respectively. Principal component based covariate shift adaptation enhances the respective classification accuracy by 5.55% and 6.53%. Moreover, DLN provides better performance compared to SVM and naive Bayes classifiers.

Real-time EEG-based happiness detection system.

We propose to use real-time EEG signal to classify happy and unhappy emotions elicited by pictures and classical music. We use PSD as a feature and SVM as a classifier. The average accuracies of subject-dependent model and subject-independent model are approximately 75.62% and 65.12%, respectively. Considering each pair of channels, temporal pair of channels (T7 and T8) gives a better result than the other area. Considering different frequency bands, high-frequency bands (Beta and Gamma) give a better result than low-frequency bands. Considering different time durations for emotion elicitation, that result from 30 seconds does not have significant difference compared with the result from 60 seconds. From all of these results, we implement real-time EEG-based happiness detection system using only one pair of channels. Furthermore, we develop games based on the happiness detection system to help user recognize and control the happiness.

Development of a low cost assistive listening system for hearing-impaired student classroom.

This paper describes the design, development, and tests of a low cost ALS. It was designed for hearing-impaired student classrooms. It utilised digital wireless technology and was aimed to be an alternative to a popular FM ALS. Key specifications include transmitting in 2.4 GHz ISM band with eight selectable transmission channels, battery operated and chargeable, pocket size, and ranged up to thirty metres. Audio characteristics and user tests show that it is comparable to a commercial system, currently employed in our partner school. The results also show that wearing an ALS clearly improves hearing of hearing-impaired students. Long-term usage by school children will be monitored to evaluate the system robustness and durability.