Human Activity Recognition Using LSTM Architecture

The covid 19 pandemic has made everything virtual, including education. It is difficult to tell if students are focused or not due to online education. To help teachers, we are developing a framework for recognizing and assessing student focus. By using the concept of brain-computer communication, we can find the student's concentration level. The data obtained from the electroencephalogram (EEG) signals is used as a data set to predict concentration levels. A four-channel device is used to capture brain waves. The data were preprocessed and feature extraction was performed to determine the concentration level as active or inactive. In this method, we use a multiclass approach to develop a deep learning model that uses LSTM to classify concentration into low, or high concentration levels with accuracy of 88%. © 2022 IEEE.

Electroencephalography and Self-assessment Evaluation of Engagement with Online Exhibitions: Case Study of Google Arts and Culture

The COVID-19 pandemic has and will continue to have an unprecedented impact on museums and exhibition galleries worldwide, with online visitors to museums and exhibitions increasing significantly. The most common method used by web user experience researchers to study user engagement is questionnaires, usually conducted after the user has completed the website experience and relying on the user’s memory and lingering feelings. Therefore, the purpose of this paper is to propose a new method of assessment based on a combination of user electroencephalography (EEG) signals and a self-assessment questionnaire (UES-SF). Since EEG signal measurement is a practical method to detect sequential changes in brain activity without significant time delays, it can comprehend visitors’ unconscious and sensory responses to online exhibitions. This paper employed the Google Arts & Culture (GA&C) website as an example to study 4 different exhibition formats and their impact on user engagement. The questionnaire results showed that the “game interaction” was significantly higher (p < 0.05) in terms of participation than the “2D information Kiosks” and “3D virtual exhibitions” and was the marginally significant (0.05 < p < 0.10) than “video explanation”. However, when we combined the EEG data, we could determine that “game interaction” had the highest user engagement, followed by “video explanation”, “3D virtual exhibition”, and the “2D information kiosk”. Therefore, our new evaluation approach can assist online exhibition user experience researchers in understanding the impact of different forms of interaction on engagement more comprehensively. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

New-Onset Seizures as an Acute Presentation With Atypical EEG Findings in a Previously Healthy Child With Asymptomatic COVID-19 Infection.

Coronavirus disease 2019 (COVID-19) infection is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). This infection usually presents with upper respiratory symptoms; however, it can also present with a wide variety of other multisystem and neurological symptoms, including seizures. There are several proposed mechanisms by which COVID-19 can cause systemic signs of infections, including neurological complications and seizures. This case report describes a pediatric patient without a previously documented history of epilepsy who was admitted for new-onset focal seizures with impaired consciousness. No other cause and triggers of seizures were found, and the child was tested positive for COVID-19 infection. The patient had six electroclinical seizures during EEG. Video EEG findings showed atypical features of onset of intermittent rhythmic delta activity (IRDA) slowing over the left hemisphere with evolution/generalization of rhythmic delta/theta activity and without clear typical generalized epileptiform discharges. These EEG findings correlated with a clinical change of behavior arrest, staring, and yawning. Similar spells were reported multiple times a day prior to the admission, and past EEG was normal. A review of current literature on COVID-19 and neurological manifestations in children, including new seizures and prior diagnosis of epilepsy, is also provided in this case report. The clinical experience in children with newly diagnosed or chronic epilepsy suggests that exacerbation of seizures, especially from systemic effects such as those caused by severe COVID-19 infection, will be a major concern.

Design and Implementation of Real-Time Bio Signals Management System based on HL7 FHIR for Healthcare Services

Recently, attention has been focused on services that combine medical technology with ICT technologies such as artificial intelligence, big data, Internet of Things, and block chains. In addition, Research on healthcare services that can collect bio signal data through wearable sensors using IoT technology and monitor and manage health based on the collected data is increasing significantly. In particular, in a situation where the world is entering a rapidly aging society, health care services are being researched and developed in the direction of preventing diseases in advance and maintaining a healthy life. Healthcare services are bringing important changes in the pandemic era caused by covid-19. There is a need for a system capable of efficiently sharing and exchanging information of heterogeneous services to prevent emergencies and support optimal medical services. In this paper, we designed and developed a system that can collect, convert, and store bio-signals from various wearable sensors into international standard data to develop such healthcare services. HL7 (health level seven) FHIR (fast healthcare interoperability resources) applied mutandis in this paper is a standard protocol for data exchange between medical information systems of real-Time collected bio signals. In this paper, we implement an interface module that converts bio signals such as EEG (electroencephalography), ECG (electrocardiogram), EMG (electromyography), and PPG (photoplethysmography) collected in real time from a wearable sensor into a message structure defined by HL7 FHIR. The interface module consists of a client part and a server part. The client part generates a variety of signal data from the healthcare service user and delivers the message to the server part. The server part is designed and implemented to parse the received message by segment field unit and transmit whether the message is abnormal or not to the client part. The system designed and implemented in this paper will be utilized as a technology that can mutually share and exchange medical information in a customized healthcare service that reflects the needs of various customers and a telemedicine system. © 2021 IEEE.

High-Precise Bipolar Disorder Detection by Using Radial Basis Functions Based Neural Network

Presently, several million people suffer from major depressive and bipolar disorders. Thus, the modelling, characterization, classification, diagnosis, and analysis of such mental disorders bears great significance in medical research. Electroencephalogram records provide important information to improve clinical diagnosis and are very useful in the scientific community. In this work, electroencephalogram records and patient data from the Hospital Virgen de la Luz in Cuenca (Spain) were processed for a correct classification of bipolar disorders. This work implemented an innovative radial basis function-based neural network employing a fuzzy means algorithm. The results show that the proposed method is an effective approach for discrimination of two kinds of classes, i.e., bipolar disorder patients and healthy persons. The proposed algorithm achieved the best performance compared with other machine learning techniques such as Bayesian linear discriminant analysis, Gaussian naive Bayes, decision trees, K-nearest neighbour, or support vector machine, showing a very high accuracy close to 97%. Therefore, the neural network technique presented could be used as a new tool for the diagnosis of bipolar disorder, considering the possibility of integrating this method into medical software.

Simultaneous Classification of Both Mental Workload and Stress Level Suitable for an Online Passive Brain-Computer Interface.

Research studies on EEG-based mental workload detection for a passive BCI generally focus on classifying cognitive states associated with the performance of tasks at different levels of difficulty, with no other aspects of the user's mental state considered. However, in real-life situations, different aspects of the user's state such as their cognitive (e.g., level of mental workload) and affective (e.g., level of stress/anxiety) states will often change simultaneously, and performance of a BCI system designed considering just one state may be unreliable. Moreover, multiple mental states may be relevant to the purposes of the BCI-for example both mental workload and stress level might be related to an aircraft pilot's risk of error-and the simultaneous prediction of states may be critical in maximizing the practical effectiveness of real-life online BCI systems. In this study we investigated the feasibility of performing simultaneous classification of mental workload and stress level in an online passive BCI. We investigated both subject-specific and cross-subject classification approaches, the latter with and without the application of a transfer learning technique to align the distributions of data from the training and test subjects. Using cross-subject classification with transfer learning in a simulated online analysis, we obtained accuracies of 77.5 ± 6.9% and 84.1 ± 5.9%, across 18 participants for mental workload and stress level detection, respectively.

Motor-Imagery EEG-Based BCIs in Wheelchair Movement and Control: A Systematic Literature Review.

The pandemic emergency of the coronavirus disease 2019 (COVID-19) shed light on the need for innovative aids, devices, and assistive technologies to enable people with severe disabilities to live their daily lives. EEG-based Brain-Computer Interfaces (BCIs) can lead individuals with significant health challenges to improve their independence, facilitate participation in activities, thus enhancing overall well-being and preventing impairments. This systematic review provides state-of-the-art applications of EEG-based BCIs, particularly those using motor-imagery (MI) data, to wheelchair control and movement. It presents a thorough examination of the different studies conducted since 2010, focusing on the algorithm analysis, features extraction, features selection, and classification techniques used as well as on wheelchair components and performance evaluation. The results provided in this paper could highlight the limitations of current biomedical instrumentations applied to people with severe disabilities and bring focus to innovative research topics.

Deep Learning-Based Stroke Disease Prediction System Using Real-Time Bio Signals.

The emergence of an aging society is inevitable due to the continued increases in life expectancy and decreases in birth rate. These social changes require new smart healthcare services for use in daily life, and COVID-19 has also led to a contactless trend necessitating more non-face-to-face health services. Due to the improvements that have been achieved in healthcare technologies, an increasing number of studies have attempted to predict and analyze certain diseases in advance. Research on stroke diseases is actively underway, particularly with the aging population. Stroke, which is fatal to the elderly, is a disease that requires continuous medical observation and monitoring, as its recurrence rate and mortality rate are very high. Most studies examining stroke disease to date have used MRI or CT images for simple classification. This clinical approach (imaging) is expensive and time-consuming while requiring bulky equipment. Recently, there has been increasing interest in using non-invasive measurable EEGs to compensate for these shortcomings. However, the prediction algorithms and processing procedures are both time-consuming because the raw data needs to be separated before the specific attributes can be obtained. Therefore, in this paper, we propose a new methodology that allows for the immediate application of deep learning models on raw EEG data without using the frequency properties of EEG. This proposed deep learning-based stroke disease prediction model was developed and trained with data collected from real-time EEG sensors. We implemented and compared different deep-learning models (LSTM, Bidirectional LSTM, CNN-LSTM, and CNN-Bidirectional LSTM) that are specialized in time series data classification and prediction. The experimental results confirmed that the raw EEG data, when wielded by the CNN-bidirectional LSTM model, can predict stroke with 94.0% accuracy with low FPR (6.0%) and FNR (5.7%), thus showing high confidence in our system. These experimental results demonstrate the feasibility of non-invasive methods that can easily measure brain waves alone to predict and monitor stroke diseases in real time during daily life. These findings are expected to lead to significant improvements for early stroke detection with reduced cost and discomfort compared to other measuring techniques.

Continuous electroencephalography characteristics and acute symptomatic seizures in COVID-19 patients.

OBJECTIVE: As concerns regarding neurological manifestations in COVID-19 (coronavirus disease 2019) patients increase, limited data exists on continuous electroencephalography (cEEG) findings in these patients. We present a retrospective cohort study of cEEG monitoring in COVID-19 patients to better explore this knowledge gap. METHODS: Among 22 COVID-19 patients, 19 underwent cEEGs, and 3 underwent routine EEGs (<1 h). Demographic and clinical variables, including comorbid conditions, discharge disposition, survival and cEEG findings, were collected. RESULTS: cEEG was performed for evaluation of altered mental status (n = 17) or seizure-like events (n = 5). Five patients, including 2 with epilepsy, had epileptiform abnormalities on cEEG. Two patients had electrographic seizures without a prior epilepsy history. There were no acute neuroimaging findings. Periodic discharges were noted in one-third of patients and encephalopathic EEG findings were not associated with IV anesthetic use. CONCLUSIONS: Interictal epileptiform abnormalities in the absence of prior epilepsy history were rare. However, the discovery of asymptomatic seizures in two of twenty-two patients was higher than previously reported and is therefore of concern. SIGNIFICANCE: cEEG monitoring in COVID-19 patients may aid in better understanding an epileptogenic potential of SARS-CoV2 infection. Nevertheless, larger studies utilizing cEEG are required to better examine acute epileptic risk in COVID-19 patients.