Brain-Computer Interface (BCI), in essence, aims at controlling different assistive devices through the utilization of brain waves. It is worth noting that the application of BCI is not limited to medical applications, and hence, the research in this field has gained due attention. Moreover, the significant number of related publications over the past two decades further indicates the consistent improvements and breakthroughs that have been made in this particular field. Nonetheless, it is also worth mentioning that with these improvements, new challenges are constantly discovered. This article provides a comprehensive review of the state-of-the-art of a complete BCI system. First, a brief overview of electroencephalogram (EEG)-based BCI systems is given. Secondly, a considerable number of popular BCI applications are reviewed in terms of electrophysiological control signals, feature extraction, classification algorithms, and performance evaluation metrics. Finally, the challenges to the recent BCI systems are discussed, and possible solutions to mitigate the issues are recommended.

/pdf/current-status-challenges-and-possible-solutions-of-eeg-4el4wek5td.pdf

Current Status, Challenges, and Possible Solutions of EEG-Based Brain-Computer Interface: A Comprehensive Review

Over the past couple of decades, many telecommunication industries have passed through the different facets of the digital revolution by integrating artificial intelligence (AI) techniques into the way they run and define their processes. Relevant data acquisition, analysis, harnessing, and mining are now fully considered vital drivers for business growth in these industries. Machine learning, a subset of artificial intelligence (AI), can assist, particularly in learning patterns in big data chunks, intelligent extrapolative extraction of data and automatic decision-making in predictive learning. Firstly, in this paper, a detailed performance benchmarking of adaptive learning capacities of different key machine-learning-based regression models is provided for extrapolative analysis of throughput data acquired at the different user communication distances to the gNodeB transmitter in 5G new radio networks. Secondly, a random forest (RF)-based machine learning model combined with a least-squares boosting algorithm and Bayesian hyperparameter tuning method for further extrapolative analysis of the acquired throughput data is proposed. The proposed model is herein referred to as the RF-LS-BPT method. While the least-squares boosting algorithm is engaged to turn the possible RF weak learners to form stronger ones, resulting in a single strong prediction model, the Bayesian hyperparameter tuning automatically determines the best RF hyperparameter values, thereby enabling the proposed RF-LS-BPT model to obtain desired optimal prediction performance. The application of the proposed RF-LS-BPT method showed superior prediction accuracy over the ordinary random forest model and six other machine-learning-based regression models on the acquired throughput data. The coefficient of determination (Rsq) and mean absolute error (MAE) values obtained for the throughput prediction at different user locations using the proposed RF-LS-BPT method range from 0.9800 to 0.9999 and 0.42 to 4.24, respectively. The standard RF models attained 0.9644 to 0.9944 Rsq and 5.47 to 12.56 MAE values. The improved throughput prediction accuracy of the proposed RF-LS-BPT method demonstrates the significance of hyperparameter tuning/optimization in developing precise and reliable machine-learning-based regression models. The projected model would find valuable applications in throughput estimation and modeling in 5G and beyond 5G wireless communication systems.

/pdf/machine-learning-based-boosted-regression-ensemble-combined-12uba1ao.pdf

Machine Learning-Based Boosted Regression Ensemble Combined with Hyperparameter Tuning for Optimal Adaptive Learning

Sensing interfaces relying on head or facial gestures provide effective solutions for hands-free scenarios. Most of these interfaces utilize sensors attached to the face, as well as into the mouth, being either obtrusive or limited in input bandwidth. In this paper, we propose ChewIt -- a novel intraoral input interface. ChewIt resembles an edible object that allows users to perform various hands-free input operations, both simply and discreetly. Our design is informed by a series of studies investigating the implications of shape, size, locations for comfort, discreetness, maneuverability, and obstructiveness. Additionally, we evaluated potential gestures that users could use to interact with such an intraoral interface.

ChewIt. An Intraoral Interface for Discreet Interactions

Background: By 2030, the global population of people older than 60 years is expected to be higher than the number of children under 10 years, resulting in major health and social care system implications worldwide. Without a supportive environment, whether social or built, diminished functional ability may arise in older people. Functional ability comprises an individual's intrinsic capacity and people's interaction with their environment enabling them to be and do what they value. Objectives: This evidence and gap map aims to identify primary studies and systematic reviews of health and social support services as well as assistive devices designed to support functional ability among older adults living at home or in other places of residence. Search Methods: We systematically searched from inception to August 2018 in: MEDLINE, EMBASE, Cochrane Database of Systematic Reviews, CENTRAL, CINAHL, PsycINFO, AgeLine, Campbell Library, ASSIA, Social Science Citation Index and Social Policy & Practice. We conducted a focused search for grey literature and protocols of studies (e.g., ProQuest Theses and Dissertation Global, conference abstract databases, Help Age, PROSPERO, Cochrane and Campbell libraries and ClinicalTrials.gov). Selection Criteria: Screening and data extraction were performed independently in duplicate according to our intervention and outcome framework. We included completed and on-going systematic reviews and randomized controlled trials of effectiveness on health and social support services provided at home, assistive products and technology for personal indoor and outdoor mobility and transportation as well as design, construction and building products and technology of buildings for private use such as wheelchairs, and ramps. Data Collection and Analysis: We coded interventions and outcomes, and the number of studies that assessed health inequities across equity factors. We mapped outcomes based on the International Classification of Function, Disability and Health (ICF) adapted categories: intrinsic capacities (body function and structures) and functional abilities (activities). We assessed methodological quality of systematic reviews using the AMSTAR II checklist. Main Results: After de-duplication, 10,783 records were screened. The map includes 548 studies (120 systematic reviews and 428 randomized controlled trials). Interventions and outcomes were classified using domains from the International Classification of Function, Disability and Health (ICF) framework. Most systematic reviews (n = 71, 59%) were rated low or critically low for methodological quality. The most common interventions were home-based rehabilitation for older adults (n = 276) and home-based health services for disease prevention (n = 233), mostly delivered by visiting healthcare professionals (n = 474). There was a relative paucity of studies on personal mobility, building adaptations, family support, personal support and befriending or friendly visits. The most measured intrinsic capacity domains were mental function (n = 269) and neuromusculoskeletal function (n = 164). The most measured outcomes for functional ability were basic needs (n = 277) and mobility (n = 160). There were few studies which evaluated outcome domains of social participation, financial security, ability to maintain relationships and communication. There was a lack of studies in low- and middle-income countries (LMICs) and a gap in the assessment of health equity issues. Authors' Conclusions: There is substantial evidence for interventions to promote functional ability in older adults at home including mostly home-based rehabilitation for older adults and home-based health services for disease prevention. Remotely delivered home-based services are of greater importance to policy-makers and practitioners in the context of the COVID-19 pandemic. This map of studies published prior to the pandemic provides an initial resource to identify relevant home-based services which may be of interest for policy-makers and practitioners, such as home-based rehabilitation and social support, although these interventions would likely require further adaptation for online delivery during the COVID-19 pandemic. There is a need to strengthen assessment of social support and mobility interventions and outcomes related to making decisions, building relationships, financial security, and communication in future studies. More studies are needed to assess LMIC contexts and health equity issues.

Health, social care and technological interventions to improve functional ability of older adults living at home: An evidence and gap map

BACKGROUND Commercially-made low-cost electroencephalography (EEG) devices have become increasingly available over the last decade. One of these devices, Emotiv EPOC, is currently used in a wide variety of settings, including brain-computer interface (BCI) and cognitive neuroscience research. PURPOSE The aim of this study was to chart peer-reviewed reports of Emotiv EPOC projects to provide an informed summary on the use of this device for scientific purposes. METHODS We followed a five-stage methodological framework for a scoping review that included a systematic search using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR) guidelines. We searched the following electronic databases: PsychINFO, MEDLINE, Embase, Web of Science, and IEEE Xplore. We charted study data according to application (BCI, clinical, signal processing, experimental research, and validation) and location of use (as indexed by the first author’s address). RESULTS We identified 382 relevant studies. The top five publishing countries were the United States (n = 35), India (n = 25), China (n = 20), Poland (n = 17), and Pakistan (n = 17). The top five publishing cities were Islamabad (n = 11), Singapore (n = 10), Cairo, Sydney, and Bandung (n = 7 each). Most of these studies used Emotiv EPOC for BCI purposes (n = 277), followed by experimental research (n = 51). Thirty-one studies were aimed at validating EPOC as an EEG device and a handful of studies used EPOC for improving EEG signal processing (n = 12) or for clinical purposes (n = 11). CONCLUSIONS In its first 10 years, Emotiv EPOC has been used around the world in diverse applications, from control of robotic limbs and wheelchairs to user authentication in security systems to identification of emotional states. Given the widespread use and breadth of applications, it is clear that researchers are embracing this technology.

/pdf/10-years-of-epoc-a-scoping-review-of-emotiv-s-portable-eeg-21bc7wcox9.pdf

10 years of EPOC: A scoping review of Emotiv’s portable EEG device

Epileptic patients suffer from an epileptic brain seizure caused by the temporary and unpredicted electrical interruption. Conventionally, the electroencephalogram (EEG) signals are manually studied by medical practitioners as it records the electrical activities from the brain. This technique consumes a lot of time, and the outputs are unreliable. In a bid to address this problem, a new structure for detecting an epileptic seizure is proposed in this study. The EEG signals obtained from the University of Bonn, Germany, and real-time medical records from the Senthil Multispecialty Hospital, India, were used. These signals were disintegrated into six frequency subbands that employed discrete wavelet transform (DWT) and extracted twelve statistical functions. In particular, seven best features were identified and further fed into k-Nearest Neighbor (kNN), naïve Bayes, Support Vector Machine (SVM), and Decision Tree classifiers for two-type and three-type classifications. Six statistical parameters were employed to measure the performance of these classifications. It has been found that different combinations of features and classifiers produce different results. Overall, the study is a first attempt to find the best combination feature set and classifier for 16 different 2-class and 3-class classification challenges of the Bonn and Senthil real-time clinical dataset.

/pdf/on-the-use-of-wavelet-domain-and-machine-learning-for-the-3gh0ae4q.pdf

On the Use of Wavelet Domain and Machine Learning for the Analysis of Epileptic Seizure Detection from EEG Signals

A vital perception in designing human-machine interfaces for people with disabilities is hands-free control. It is important in setting up communication among a machine and the part of human body. Nowadays, hands-free control is extensively used to help disabled people to control the wheelchair. The hands-free control functions are not only helpful to elderly and disabled, but also useful for normal people who might require using their hands for other tasks at the same time. As a result, normal people are capable of manipulating multiple tasks at the same time. The wheelchair is manoeuvred using brainwaves, eyes and facial muscles movements, voice, tongue, gesture. The mobility using a powered wheelchair improves the quality of life of the aged people and the people with mobility impairments significantly. These powered wheelchairs can be actuated using various high-level control interfaces. In this review, the use of natural biological signals and non-biological signal to do the hands-free control of powered wheelchair is presented in this article.

High-level hands-free control of wheelchair - a review.

Atrial fibrillation (A-fib) is the most common cardiac disorder. To efficiently treat or inhibit, an automatic detection based on electrocardiograph (ECG) monitoring is significantly required. ECG is a key function in the analysis of the heart functioning and diagnostic of diseases. Currently, a computer based system is used to analyze the ECG signal. The main aim of this project is to analyze a heart malfunctions named as A-fib, using discrete wavelet transforms (DWT). The ECG signals were decomposed into time-frequency representations using DWT, and the statistical features were calculated to describe their distribution. The DWT detailed coefficients are used to obtain various parameters of the ECG signal such as the mean, variance, standard deviation, and entropy of the signal. An analysis had been made with these parameters of various patients with normal heart functioning and A-fib to identify the disorder. Keywords: Atrial fibrillation, Electrocardiogram, Discrete wavelet transforms.

Detection of artial fibrillation disorder by ecg using discrete wavelet transforms

The health organisation has suffered from the lack of diagnosis support systems and physicians in India. Further, the physicians are struggling to treat many patients, and the hospitals also have the lack of a radiologist especially in rural areas; thus, almost all cases are handled by a single physician, leading to many misdiagnoses. Computer aided diagnostic systems are being developed to address this problem. The current study aimed to review the different methods to detect pneumonia using neural networks and compare their approach and results. For the best comparisons, only papers with the same data set Chest X-ray14 are studied.

/pdf/a-review-on-detection-of-pneumonia-in-chest-x-ray-images-2d5wg5t2.pdf

Sharmila Ashok

Papers

On the Use of Wavelet Domain and Machine Learning for the Analysis of Epileptic Seizure Detection from EEG Signals

High-level hands-free control of wheelchair - a review.

Detection of artial fibrillation disorder by ecg using discrete wavelet transforms

A Review on Detection of Pneumonia in Chest X-ray Images Using Neural Networks

Fall Detection System Using IoT