ECG and EEG based detection and multilevel classification of stress using machine learning for specified genders: A preliminary study.

Mental health, especially stress, plays a crucial role in the quality of life. During different phases (luteal and follicular phases) of the menstrual cycle, women may exhibit different responses to stress from men. This, therefore, may have an impact on the stress detection and classification accuracy of machine learning models if genders are not taken into account. However, this has never been investigated before. In addition, only a handful of stress detection devices are scientifically validated. To this end, this work proposes stress detection and multilevel stress classification models for unspecified and specified genders through ECG and EEG signals. Models for stress detection are achieved through developing and evaluating multiple individual classifiers. On the other hand, the stacking technique is employed to obtain models for multilevel stress classification. ECG and EEG features extracted from 40 subjects (21 females and 19 males) were used to train and validate the models. In the low&high combined stress conditions, RBF-SVM and kNN yielded the highest average classification accuracy for females (79.81%) and males (73.77%), respectively. Combining ECG and EEG, the average classification accuracy increased to at least 87.58% (male, high stress) and up to 92.70% (female, high stress). For multilevel stress classification from ECG and EEG, the accuracy for females was 62.60% and for males was 71.57%. This study shows that the difference in genders influences the classification performance for both the detection and multilevel classification of stress. The developed models can be used for both personal (through ECG) and clinical (through ECG and EEG) stress monitoring, with and without taking genders into account.

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.

Effectiveness of a programable body-worn digital hearing aid for older adults in a developing country: a randomized controlled trial with a cross-over design.

BACKGROUND: Hearing aids are important assistive devices for hearing rehabilitation. However, the cost of commonly available commercial hearing aids is often higher than the average monthly income of individuals in some developing countries. Therefore, there is a great need to locally produce cheaper, but still effective, hearing aids. The Thai-produced P02 hearing aid was designed to meet this requirement. OBJECTIVE: To compare the effectiveness of the P02 hearing aid with two common commercially available digital hearing aids (Clip-II™ and Concerto Basic®). METHODS: A prospective, randomized controlled trial with a cross-over design was conducted from October 2012 to September 2014 in a rural Thai community. There were 73 participants (mean age of 73.7 ± 7.3 years) included in this study with moderate to severe hearing loss who were assessed for hearing aid performance, including probe microphone real-ear measurement, functional gain, speech discrimination, and participant satisfaction with the overall quality of perceived sound and the design of the device. RESULTS: There were no statistically significant differences in functional gain or speech discrimination among the three hearing aids evaluated (p-value > 0.05). Real-ear measurements of the three hearing aids met the target curve in 93% of the participants. The best real-ear measurement of the hearing aid following the target curve was significantly lower than that of Clip-II™ and Concerto Basic® (p-value < 0.05) at high frequency. However, participants rated the overall quality of sound higher for the P02 hearing aid than that of Clip-II™ but lower than that of Concerto Basic® (p-value > 0.05). Participants revealed that the P02 hearing aid provided the highest satisfaction ratings for design and user-friendliness with statistical significance (p-value < 0.05). CONCLUSION: The P02 hearing aid was an effective device for older Thai adults with hearing disabilities. Additionally, its modern design, simplicity of use, and ease of maintenance were attractive to this group of individuals. These benefits support the rehabilitation potential of this hearing aid model and its positive impact on the quality of life of older adults in developing countries. TRIAL REGISTRATION: This study was registered under Clinicaltrial.gov NCT01902914 . Date of registration: July 18, 2013.

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.

The development of Thai monosyllabic word and picture lists applicable to interactive speech audiometry in preschoolers.

Interactive speech audiometry is the assessment of speech comprehension and phonological discrimination through automated means. In order for the performance of such assessments in preschoolers to be successful, the employed list of words and pictures must be easily recognized both linguistically and visually. That is, the children must be able to easily associate the sound they hear with the picture they see with a high degree of certainty. To this end, a Thai monosyllabic word and picture list called NCU-20 (NECTEC-CU-20) is proposed. The word lists for Thai vowel and consonant hearing tests are designed with an awareness of phonetic environments. Regarding Thai vowels, both monophthongs and diphthongs, with all qualities and quantities, are examined. Initial consonants are categorized based on places and manners of articulation. The effectiveness of the list is objectively and subjectively verified through Thai Textbook Corpus, Thai National Corpus, Zipf scores, a listening test of preschoolers with normal hearing, and our proposed ranking systems referred to as Tier-1st, Tier-3/3, and Overall Tier. The final suggested word and picture list comprises 45 items (words) covering 35 vowels and consonant groups in the Thai Language.

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.

A Tablet-Based Mobile Hearing Screening System for Preschoolers: Design and Validation Study.

BACKGROUND: Hearing ability is important for children to develop speech and language skills as they grow. After a mandatory newborn hearing screening, group or mass screening of children at later ages, such as at preschool age, is often practiced. For this practice to be effective and accessible in low-resource countries such as Thailand, innovative enabling tools that make use of pervasive mobile and smartphone technology should be considered. OBJECTIVE: This study aims to develop a cost-effective, tablet-based hearing screening system that can perform a rapid minimal speech recognition level test. METHODS: An Android-based screening app was developed. The screening protocol involved asking children to choose pictures corresponding to a set of predefined words heard at various sound levels offered in a specifically designed sequence. For the app, the set of words was validated, and their corresponding speech power levels were calibrated. We recruited 122 children, aged 4-5 years, during the development phase. Another 63 children of the same age were screened for their hearing abilities using the app in version 2. The results in terms of the sensitivity and specificity were compared with those measured using the conventional audiometric equipment. RESULTS: For screening purposes, the sensitivity of the developed screening system version 2 was 76.67% (95% CI 59.07-88.21), and the specificity was 95.83% (95% CI 89.77-98.37) for screening children with mild hearing loss (pure-tone average threshold at 1, 2, and 4 kHz, >20 dB). The time taken for the screening of each child was 150.52 (SD 19.07) seconds (95% CI 145.71-155.32 seconds). The average time used for conventional play audiometry was 11.79 (SD 3.66) minutes (95% CI 10.85-12.71 minutes). CONCLUSIONS: This study shows the potential use of a tablet-based system for rapid and mobile hearing screening. The system was shown to have good overall sensitivity and specificity. Overall, the idea can be easily adopted for systems based on other languages.

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.

Effectiveness of neurofeedback versus medication for attention-deficit/hyperactivity disorder.

BACKGROUND: Neurofeedback (NF) is an operant conditioning procedure that trains participants to self-regulate brain activity. NF is a promising treatment for attention-deficit/hyperactivity disorder (ADHD), but there have been only a few randomized controlled trials comparing the effectiveness of NF with medication with various NF protocols. The aim of this study was therefore to evaluate the effectiveness of unipolar electrode NF using theta/beta protocol compared with methylphenidate (MPH) for ADHD. METHODS: Children with newly diagnosed ADHD were randomly organized into NF and MPH groups. The NF group received 30 sessions of NF. Children in the MPH group were prescribed MPH for 12 weeks. Vanderbilt ADHD rating scales were completed by parents and teachers to evaluate ADHD symptoms before and after treatment. Student's t-test and Cohen's d were used to compare symptoms between groups and evaluate the effect size (ES) of each treatment, respectively. RESULTS: Forty children participated in the study. No differences in ADHD baseline symptoms were found between groups. After treatment, teachers reported significantly lower ADHD symptoms in the MPH group (P = 0.01), but there were no differences between groups on parent report (P = 0.55). MPH had a large ES (Cohen's d, 1.30-1.69), while NF had a moderate ES (Cohen's d, 0.49-0.68) for treatment of ADHD symptoms. CONCLUSION: Neurofeedback is a promising alternative treatment for ADHD in children who do not respond to or experience significant adverse effects from ADHD medication.

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.