Types Of Biosignals Research Articles

A Systematic Review on Machine Learning / Deep Learning Model-based Detection of Sleep Apnea Using Bio-Signals

Backgrounds: Sleep Apnea (SA) is a sleep-related breathing disorder diagnosed in clinical laboratories. The gold standard is Polysomnography (PSG), a multi-parameter evaluation of a sleep monitoring system that records the biological signals during overnight sleep. Apart from PSG recording, apnea events are recorded by various other bio-signals called Electrocardiogram (ECG), Electroencephalogram (EEG), Oxygen Saturation level (SpO2), etc. Further evaluation of the recorded bio-signals is tedious and time-consuming as experts perform it manually. Aiming to overcome the disadvantage without compromising accuracy, scientists focus on developing robust measurements of SA by using Machine Learning (ML) and Deep Learning (DL) models. Method: This study aimed to analyze the recent research findings in the field of sleep apnea classification and various machine learning and deep learning methods implemented in detecting SA. This study revealed the best-performing technique considering different types of bio-signals used for analysis and the respective ML or DL models used for automatic detection Result: The studies and patents included in this review underwent a precise screening process using PRISMA guidelines. The literature study is comprised of three different analysis tools to showcase the review process and provide evidence for the research findings obtained in the respective publications. The publications considered were limited to the last decade. Conclusion: This review delivers the key finding that ECG signals-based detection of sleep apnea using deep learning model-based deep neural network classifiers will provide more accurate and robust classification, which will pave the way for possible future research directions.

An NLP-based system for modulating virtual experiences using speech instructions

The application of virtual reality (VR) technology in rehabilitation is a research area that has been attracting remarkable attention recently, especially as an intervention with learning and developmental disorders such as dyslexia and autism. Multi-modal VR-based rehabilitative systems can provide a rich experience to patients by responding to various types of bio-signals. This paper proposes a framework for incorporating voice input in rehabilitative games. The proposed framework equips collaborative learning environments with voice based interaction which allows for a more dynamic flow of therapy sessions between physically impaired patients and specialists in a rehabilitative VR environment. The proposed framework’s pipeline begins with a speech recognition module to parse utterances into sentences. Next, comes the feature extraction module to identify the intent of the user and entities as well. Finally, we modulate the 3D environment in Unity. The framework was designed in a way that guarantees smooth integration with any game or 3D environment. Several technologies were tested in terms of accuracy and speed to increase the overall performance of the pipeline. To the best of our knowledge, this research is the first to do the following: 1) build a dataset of instructions, inspired by a product already used in the healthcare market, 2) based on which we could realize a multi-modal system, with voice as one of the modalities, for the context of VR-based rehabilitation. We evaluate every stage in the system pipeline, and we show that we can achieve considerable results on each of these stages including the speech recognition module, with a 5.64% word error rate, and on intent classification where the BiLSTM model outperforms BERT in the Named Entity Recognition by 11% in terms of the F1-score. We envisage the proposed system to lend itself well to emerging healthcare frameworks in the Metaverse.

Wearable Biosensors for Body Computing (Adv. Funct. Mater. 39/2021)

Wearable Biosensors Research advances in wearable biosensors have made it easier to collect a variety of biosignals and transform them into actionable health information. Body computing systems based on wearable biosensors and intelligent data analysis have the potential to achieve reliable noninvasive monitoring of health and body status. These wearable systems are expected to enable personalized and preventative healthcare. In article number 2008087, Ali Javey, Yuanjing Lin, and Mallika Bariya highlight key considerations for wearable sensors, including materials and structures, power and communication schemes, and types of biosignals.

Fatigue Evaluation through Machine Learning and a Global Fatigue Descriptor.

Research in physiology and sports science has shown that fatigue, a complex psychophysiological phenomenon, has a relevant impact in performance and in the correct functioning of our motricity system, potentially being a cause of damage to the human organism. Fatigue can be seen as a subjective or objective phenomenon. Subjective fatigue corresponds to a mental and cognitive event, while fatigue referred as objective is a physical phenomenon. Despite the fact that subjective fatigue is often undervalued, only a physically and mentally healthy athlete is able to achieve top performance in a discipline. Therefore, we argue that physical training programs should address the preventive assessment of both subjective and objective fatigue mechanisms in order to minimize the risk of injuries. In this context, our paper presents a machine-learning system capable of extracting individual fatigue descriptors (IFDs) from electromyographic (EMG) and heart rate variability (HRV) measurements. Our novel approach, using two types of biosignals so that a global (mental and physical) fatigue assessment is taken into account, reflects the onset of fatigue by implementing a combination of a dimensionless (0-1) global fatigue descriptor (GFD) and a support vector machine (SVM) classifier. The system, based on 9 main combined features, achieves fatigue regime classification performances of 0.82 ± 0.24, ensuring a successful preventive assessment when dangerous fatigue levels are reached. Training data were acquired in a constant work rate test (executed by 14 subjects using a cycloergometry device), where the variable under study (fatigue) gradually increased until the volunteer reached an objective exhaustion state.

Classification of pilots’ mental states using a multimodal deep learning network

An automation system for detecting the pilot's diversified mental states is an extremely important and essential technology, as it could prevent catastrophic accidents caused by the deteriorated cognitive state of pilots. Various types of biosignals have been employed to develop the system, since they accompany neurophysiological changes corresponding to the mental state transitions. In this study, we aimed to investigate the feasibility of a robust detection system of the pilot's mental states (i.e., distraction, workload, fatigue, and normal) based on multimodal biosignals (i.e., electroencephalogram, electrocardiogram, respiration, and electrodermal activity) and a multimodal deep learning (MDL) network. To do this, first, we constructed an experimental environment using a flight simulator in order to induce the different mental states and to collect the biosignals. Second, we designed the MDL architecture – which consists of a convolutional neural network and long short-term memory models – to efficiently combine the information of the different biosignals. Our experimental results successfully show that utilizing multimodal biosignals with the proposed MDL could significantly enhance the detection accuracy of the pilot's mental states.

DECODING OF SIMPLE HAND MOVEMENTS BY FRACTAL ANALYSIS OF ELECTROMYOGRAPHY (EMG) SIGNAL

Analysis of body movement is the most important aspect of rehabilitation science. Hand movement as one of the major movements of humans has aroused the attention of many researchers. For this purpose, decoding of movements by analysis of the related bio signals is very important. In this research, complexity analysis of Electromyography (EMG) signal that was recorded due to simple hand movements is done. For this purpose, we employ fractal dimension as the indicator of complexity of signal in this research. The EMG signal was recorded from subjects while they did six simple hand movements and accordingly we applied fractal analysis on the signal. The result of our analysis showed that the EMG signal has the greatest and lowest fractal dimension in case of lateral (for holding thin, flat objects) and hook (for supporting a heavy load) hand movements. The capability seen in this research can be applied to the analysis of other types of bio signals in order to investigate the reaction of humans to different types of stimuli.

Ubiquitous Healthcare System for Analysis of Chronic Patients’ Biological and Lifelog Data

For the prevention and management of diseases in chronic patients, attention has been directed at ubiquitous healthcare systems in order to reduce medical expenses and provide high-quality medical services at different places, including hospitals and homes. In this paper, a ubiquitous healthcare system has been proposed in order to care for a chronic patient, to be used by a nurse or a care professional at the patient’s residence. It comprises a portable bio-signal acquisition device, smartphone application, and ubiquitous health server. The smartphone application collects the patient information, including lifelog and the bio-signals from the device, and transfers the patient information through bio-signals to the ubiquitous health server. The ubiquitous health server monitors the bio-signals with the help of lifelog, analyzes the patient’s health state, and alerts medical staff on symptoms of any illness. The proposed system collects five types of bio-signals from patients using the acquisition device, automatically monitors and analyzes their bio-data with lifelog, displays the state of their health as determined by the analysis, using graphical representation, such that the doctor can understand the patient’s condition and undertake an appropriate medical treatment procedure.

The Intensity Recognition of Tension Emotion Based on Multi-physiological Signals

Background: Emotion recognition is among the hot topics in the field of psychology and engineering. As a type of emotion, tension plays an important role in daily life. As such, tension intensity recognition (TIR) is of greatly value. Method: This study employed selected clips of a horror movie to elicit tension of different intensity levels, during which four types of bio-signals were collected from 4 participants. These signals included electroencephalogram (EEG), electrocardiogram (ECG), respiration (RSP) and electrodermal activity (EDA) signals. After that, a support vector machine (SVM) based classification was performed to differentiate fear tension levels, employing features extracted from multi-physiological signals. Results: EEG analysis showed that the power spectrum of EEG signals present monotonic changes with the increase of intensity at specific brain regions. The recognition accuracy using features from multiple physiology signals reached 83.33%. Conclusion: To our knowledge, this is among the first studies to evaluate emotion intensity levels using multiple electro-physiological signals. Our study demonstrated the feasibility and effectiveness of using these physiological features for the assessment of tension levels, providing further insights in the field of quantitative emotion studies.

Time–frequency based feature selection for discrimination of non-stationary biosignals

Abstract This research proposes a generic methodology for dimensionality reduction upon time–frequency representations applied to the classification of different types of biosignals. The methodology directly deals with the highly redundant and irrelevant data contained in these representations, combining a first stage of irrelevant data removal by variable selection, with a second stage of redundancy reduction using methods based on linear transformations. The study addresses two techniques that provided a similar performance: the first one is based on the selection of a set of the most relevant time–frequency points, whereas the second one selects the most relevant frequency bands. The first methodology needs a lower quantity of components, leading to a lower feature space; but the second improves the capture of the time-varying dynamics of the signal, and therefore provides a more stable performance. In order to evaluate the generalization capabilities of the methodology proposed it has been applied to two types of biosignals with different kinds of non-stationary behaviors: electroencephalographic and phonocardiographic biosignals. Even when these two databases contain samples with different degrees of complexity and a wide variety of characterizing patterns, the results demonstrate a good accuracy for the detection of pathologies, over 98%. The results open the possibility to extrapolate the methodology to the study of other biosignals.