Physiological Signals Research Articles

Reduced Graphene Oxide Interlocked Carbonized Loofah for Energy Harvesting and Physiological Signal Monitoring

Reduced Graphene Oxide Interlocked Carbonized Loofah for Energy Harvesting and Physiological Signal Monitoring

Association of Visual-Based Signals with Electroencephalography Patterns in Enhancing the Drowsiness Detection in Drivers with Obstructive Sleep Apnea.

Individuals with obstructive sleep apnea (OSA) face increased accident risks due to excessive daytime sleepiness. PERCLOS, a recognized drowsiness detection method, encounters challenges from image quality, eyewear interference, and lighting variations, impacting its performance, and requiring validation through physiological signals. We propose visual-based scoring using adaptive thresholding for eye aspect ratio with OpenCV for face detection and Dlib for eye detection from video recordings. This technique identified 453 drowsiness (PERCLOS ≥ 0.3 || CLOSDUR ≥ 2 s) and 474 wakefulness episodes (PERCLOS < 0.3 and CLOSDUR < 2 s) among fifty OSA drivers in a 50 min driving simulation while wearing six-channel EEG electrodes. Applying discrete wavelet transform, we derived ten EEG features, correlated them with visual-based episodes using various criteria, and assessed the sensitivity of brain regions and individual EEG channels. Among these features, theta-alpha-ratio exhibited robust mapping (94.7%) with visual-based scoring, followed by delta-alpha-ratio (87.2%) and delta-theta-ratio (86.7%). Frontal area (86.4%) and channel F4 (75.4%) aligned most episodes with theta-alpha-ratio, while frontal, and occipital regions, particularly channels F4 and O2, displayed superior alignment across multiple features. Adding frontal or occipital channels could correlate all episodes with EEG patterns, reducing hardware needs. Our work could potentially enhance real-time drowsiness detection reliability and assess fitness to drive in OSA drivers.

HybMED: A Hybrid Neural Network Training Processor with Multi-Sparsity Exploitation for Internet of Medical Things.

Cloud-based training and edge-based inference modes for Artificial Intelligence of Medical Things (AIoMT) applications suffer from accuracy degradation due to physiological signal variations among patients. On-chip learning can overcome this issue by online adaptation of neural network parameters for user-specific tasks. However, existing on-chip learning processors have limitations in terms of versatility, resource utilization, and energy efficiency. We propose HybMED, which is a novel neural signal processor that supports on-chip hybrid neural network training using a composite direct feedback alignment-based paradigm. HybMED is suitable for general-purpose health monitoring AIoMT devices. It improves resource utilization and area efficiency by the reconfigurable homogeneous core with heterogeneous data flow and enhances energy efficiency by exploiting sparsity at different granularities. The chip was fabricated by TSMC 40nm process and tested in multiple physiological signal processing tasks, demonstrating an average improvement in accuracy of 41.16% following online few-shot learning. The chip demonstrates an area efficiency of 1.17 GOPS/mm2 and an energy efficiency of 1.58 TOPS/W. Compared to the previous state-of-the-art physiological signal processors with on-chip learning, the chip achieves a 65× improvement in area efficiency and 1.48× improvement in energy efficiency, respectively.

Wearable smart contact lenses: A critical comparison of three physiological signals outputs for health monitoring

Smart contact lenses (SCLs) have been considered as novel wearable devices for out-of-hospital and self-monitoring applications. They are capable of non-invasively and continuously monitoring physiological signals in the eyes, including vital biophysical (e.g., intraocular of pressure, temperature, and electrophysiological signal) and biochemical signals (e.g., pH, glucose, protein, nitrite, lactic acid, and ions). Recent progress mainly focuses on the rational design of wearable SCLs for physiological signal monitoring, while also facilitating the treatment of various ocular diseases. It covers contact lens materials, fabrication technologies, and integration methods. We also highlight and discuss a critical comparison of SCLs with electrical, microfluidic, and optical signal outputs in health monitoring. Their advantages and disadvantages could help researchers to make decisions when developing SCLs with desired properties for physiological signal monitoring. These unique capabilities make SCLs promising diagnostic and therapeutic tools. Despite the extensive research in SCLs, new technologies are still in their early stages of development and there are a few challenges to be addressed before these SCLs technologies can be successfully commercialized particularly in the form of rigorous clinical trials.

Evaluation of physiological response and synchronisation errors during synchronous and pseudosynchronous stimulation trials

Rhythm perception and synchronisation is musical ability with neural basis defined as the ability to perceive rhythm in music and synchronise body movements with it. The study aimed to check the errors of synchronisation and physiological response as a reaction of the subjects to metrorhythmic stimuli of synchronous and pseudosynchronous stimulation (synchronisation with an externally controlled rhythm, but in reality controlled or produced tone by tapping) Nineteen subjects without diagnosed motor disorders participated in the study. Two tests were performed, where the electromyography signal and reaction time were recorded using the NORAXON system. In addition, physiological signals such as electrodermal activity and blood volume pulse were measured using the Empatica E4. Study 1 consisted of adapting the finger tapping test in pseudosynchrony with a given metrorhythmic stimulus with a selection of preferred, choices of decreasing and increasing tempo. Study 2 consisted of metrorhythmic synchronisation during the heel stomping test. Numerous correlations and statistically significant parameters were found between the response of the subjects with respect to their musical education, musical and sports activities. Most of the differentiating characteristics shown evidence of some group division in the undertaking of musical activities. The use of detailed analyses of synchronisation errors can contribute to the development of methods to improve the rehabilitation process of subjects with motor dysfunction, and this will contribute to the development of an expert system that considers personalised musical preferences.

Two Signaling Modes Are Better than One: Flux-Independent Signaling by Ionotropic Glutamate Receptors Is Coming of Age.

Glutamate is the major excitatory neurotransmitter in the central nervous system. Glutamatergic transmission can be mediated by ionotropic glutamate receptors (iGluRs), which mediate rapid synaptic depolarization that can be associated with Ca2+ entry and activity-dependent change in the strength of synaptic transmission, as well as by metabotropic glutamate receptors (mGluRs), which mediate slower postsynaptic responses through the recruitment of second messenger systems. A wealth of evidence reported over the last three decades has shown that this dogmatic subdivision between iGluRs and mGluRs may not reflect the actual physiological signaling mode of the iGluRs, i.e., α-amino-3-hydroxy-5-methyl-4-isoxasolepropionic acid (AMPA) receptors (AMPAR), kainate receptors (KARs), and N-methyl-D-aspartate (NMDA) receptors (NMDARs). Herein, we review the evidence available supporting the notion that the canonical iGluRs can recruit flux-independent signaling pathways not only in neurons, but also in brain astrocytes and cerebrovascular endothelial cells. Understanding the signaling versatility of iGluRs can exert a profound impact on our understanding of glutamatergic synapses. Furthermore, it may shed light on novel neuroprotective strategies against brain disorders.

A multimodal physiological dataset for driving behaviour analysis

Physiological signal monitoring and driver behavior analysis have gained increasing attention in both fundamental research and applied research. This study involved the analysis of driving behavior using multimodal physiological data collected from 35 participants. The data included 59-channel EEG, single-channel ECG, 4-channel EMG, single-channel GSR, and eye movement data obtained via a six-degree-of-freedom driving simulator. We categorized driving behavior into five groups: smooth driving, acceleration, deceleration, lane changing, and turning. Through extensive experiments, we confirmed that both physiological and vehicle data met the requirements. Subsequently, we developed classification models, including linear discriminant analysis (LDA), MMPNet, and EEGNet, to demonstrate the correlation between physiological data and driving behaviors. Notably, we propose a multimodal physiological dataset for analyzing driving behavior(MPDB). The MPDB dataset’s scale, accuracy, and multimodality provide unprecedented opportunities for researchers in the autonomous driving field and beyond. With this dataset, we will contribute to the field of traffic psychology and behavior.

A multimodal shared network with a cross-modal distribution constraint for continuous emotion recognition

Continuous emotion recognition has been a compelling topic in affective computing because it can interpret human emotions subtly and continuously. Existing studies have achieved advanced emotion recognition performance using multimodal knowledge. However, these studies generally ignore the circumstances where some particular modalities are missing in the inference phase and thus become sensitive to the absence of modalities. To resolve this issue, we propose a novel multimodal shared network with a cross-modal distribution constraint, i.e. the DS-Net, which aims to improve the robustness of the model to missing modalities. The training process of the proposed network generally includes two components: multimodal shared space modeling and a cross-modal distribution matching constraint. The former utilizes the local and temporal information of multimodal signals for multimodal shared space modeling, while the latter further enhances the multimodal shared space via a loose constraint method. Coupled with the latter, the former can effectively exploit the complementarity between videos and peripheral physiological signals (PPSs), thus enhancing the discriminative capability of the shared space. Based on the shared space, the DS-Net works during the inference phase with only one modality input and can leverage multimodal knowledge to improve emotion recognition accuracy. Comprehensive experiments were conducted on two public datasets. Results demonstrate that the proposed method is competitive or superior to the current state-of-the-art methods. Further experiments indicate that the proposed method can be extended to handle other modalities and to deal with partially missing modalities, demonstrating its potential in real-world applications.

A Breathable, Stretchable, and Self‐Calibrated Multimodal Electronic Skin Based on Hydrogel Microstructures for Wireless Wearables

AbstractBiomimetic electronic skins (e‐skins) are widely used in wearables, smart prosthesis and soft robotics. However, multimodal e‐skins, especially those based on hydrogels, face multiple challenges for practical applications, involving multi‐sensing signal mutual interference, low breathability and stretchability. Here, a breathable and stretchable multimodal e‐skin with a multilayer film microstructure is developed to achieve self‐calibrated sensing of any two of three stimuli: strain, temperature, and humidity, with minimal crosstalk. Hydrogel fibers with different shapes are designed for strain and temperature sensing modules, and the hydrogel film is developed as a humidity sensing module. The multimodal e‐skin exhibits impressive sensing performance, including a low strain detection limit (0.03%), strain linearity (R2 = 0.990), high‐temperature sensitivity (1.77%/°C), and a wide humidity detection range (33–98% RH). Interestingly, due to the directional anisotropy in strain sensitivity of different shaped fibers, the e‐skin realizes self‐calibrated detection of strain and temperature in different directions. By introducing porous elastomer encapsulation membranes, the breathability and wearing comfort of the e‐skin are attained, while the high stretchability (100% strain) is maintained. Furthermore, a personalized human‐machine interaction system is created by integrating the e‐skin with a wireless circuit to realize real‐time and wireless gesture recognition, physiological signals monitoring, and smart prosthesis.

Multi-Functional Nano-Doped Hollow Fiber from Microfluidics for Sensors and Micromotors.

Nano-doped hollow fiber is currently receiving extensive attention due to its multifunctionality and booming development. However, the microfluidic fabrication of nano-doped hollow fiber in a simple, smooth, stable, continuous, well-controlled manner without system blockage remains challenging. In this study, we employ a microfluidic method to fabricate nano-doped hollow fiber, which not only makes the preparation process continuous, controllable, and efficient, but also improves the dispersion uniformity of nanoparticles. Hydrogel hollow fiber doped with carbon nanotubes is fabricated and exhibits superior electrical conductivity (15.8 S m-1), strong flexibility (342.9%), and versatility as wearable sensors for monitoring human motions and collecting physiological electrical signals. Furthermore, we incorporate iron tetroxide nanoparticles into fibers to create magnetic-driven micromotors, which provide trajectory-controlled motion and the ability to move through narrow channels due to their small size. In addition, manganese dioxide nanoparticles are embedded into the fiber walls to create self-propelled micromotors. When placed in a hydrogen peroxide environment, the micromotors can reach a top speed of 615 μm s-1 and navigate hard-to-reach areas. Our nano-doped hollow fiber offers a broad range of applications in wearable electronics and self-propelled machines and creates promising opportunities for sensors and actuators.

Effects of product personalisation degree on user perception in car front design

The front facia gives the car vivid features; accordingly, and an appropriate product personalisation degree (PD) can improve product branding, related to the appearance design, while avoiding excessive design features. This study investigates the effects of the car front facia PD on user perceptions and proposes design guidelines for vehicle designers and manufacturers. An open-ended experiment was conducted with 30 participants using 60 car fronts to study user emotions and preferences related to product personality based on questionnaire and physiological electrical signal evaluation results. The features were extracted using the chaos theory and cvxEDA algorithm. The obtained results indicate that the PD was consistent with user emotions. Furthermore, when the consistency between PD and user emotions is high, a significant variation in user preferences can be observed. Therefore, when designing high-PD products, the sub-item product personalisation degree (sub-item PD) should be carefully managed, considering the overall logic and coherence. Highlights Product personalisation degree is positively correlated with the subjective and objective emotions of users. The impact of product personalisation degree on user preferences and subjective emotions is not always the same, particularly pleasure and arousal. When product personalisation degree is highly correlated with the subjective and objective emotions of users, the user preferences are highly differentiated.

An End-to-End Musical Instrument System That Translates Electromyogram Biosignals to Synthesized Sound

Abstract This article presents a custom system combining hardware and sortware that sense physiological signals of the performer's body resulting from muscle contraction and translates them to computer-synthesized sound. Our goal was to build upon the history of research in the field to develop a complete, integrated system that could be used by nonspecialist musicians. We describe the Embodied AudioVisual Interaction Electromyogram, an end-to-end system, spanning wearable sensing on the musician's body, custom microcontroller-based biosignal acquisition hardware, machine learning– based gesture-to-sound mapping middleware, and software-based granular synthesis sound output. A novel hardware design digitizes the electromyogram signals from the muscle with minimal analog preprocessing and treats it in an audio signal-processing chain as a class-compliant audio and wireless MIDI interface. The mapping layer implements an interactive machine learning workflow in a reinforcement learning configuration and can map gesture features to auditory metadata in a multidimensional information space. The system adapts existing machine learning and synthesis modules adapted to work with the hardware, resulting in an integrated, end-to-end system. We explore its potential as a digital musical instrument through a series of public presentations and concert performance by a range of musical practitioners.

FedUSL: A Federated Annotation Method for Driving Fatigue Detection based on Multimodal Sensing Data

Single-modal data has a limitation on fatigue detection, while the shortage of labeled data is pervasive in multimodal sensing data. Besides, it is a time-consuming task for board-certified experts to manually annotate the physiological signals, especially hard for EEG sensor data. To solve this problem, we propose FedUSL (Federated Unified Space Learning), a federated annotation method for multimodal sensing data in the driving fatigue detection scenario, which has the innate ability to exploit more than four multimodal data simultaneously for correlations and complementary with low complexity. To validate the efficiency of the proposed method, we first collect the multimodal data (aka, camera, physiological sensor) through simulated fatigue driving. The data is then preprocessed and features are extracted to form a usable multimodal dataset. Based on the dataset, we analyze the performance of the proposed method. The experimental results demonstrate that FedUSL outperforms other approaches for driver fatigue detection with carefully selected modal combinations, especially when a modality contains only \(10\% \) labeled data.

Flexible Meso Electronics and Photonics Based on Cocoon Silk and Applications.

Flexible electronics, applicable to enlarged health, AI big data medications, etc., have been one of the most important technologies of this century. Due to its particular mechanical properties, biocompatibility, and biodegradability, cocoon silk (or SF, silk fibroin) plays a key role in flexible electronics/photonics. The review begins with an examination of the hierarchical meso network structures of SF materials and introduces the concepts of meso reconstruction, meso doping, and meso hybridization based on the correlation between the structure and performance of silk materials. The SF meso functionalization was developed according to intermolecular nuclear templating. By implementation of the techniques of meso reconstruction and functionalization in the refolding of SF materials, extraordinary performance can be achieved. Relying on this strategy, particularly designed flexible electronic and photonic components can be developed. This review covers the latest ideas and technologies of meso flexible electronics and photonics based on SF materials/meso functionalization. As silk materials are biocompatible and human skin-friendly, SF meso flexible electronic/photonic components can be applied to wearable or implanted devices. These devices are applicable in human physiological signals and activities sensing/monitoring. In the case of human-machine interaction, the devices can be applicable in in-body information transmission, computation, and storage, with the potential for the combination of artificial intelligence and human intelligence.

Self supervised learning based emotion recognition using physiological signals.

The significant role of emotional recognition in the field of human-machine interaction has garnered the attention of many researchers. Emotion recognition based on physiological signals can objectively reflect the most authentic emotional states of humans. However, existing labeled Electroencephalogram (EEG) datasets are often of small scale. In practical scenarios, a large number of unlabeled EEG signals are easier to obtain. Therefore, this paper adopts self-supervised learning methods to study emotion recognition based on EEG. Specifically, experiments employ three pre-defined tasks to define pseudo-labels and extract features from the inherent structure of the data. Experimental results indicate that self-supervised learning methods have the capability to learn effective feature representations for downstream tasks without any manual labels.

Real-time Single-Channel EOG removal based on Empirical Mode Decomposition

In recent years, single-channel physiological recordings have gained popularity in portable health devices and research settings due to their convenience. However, the presence of electrooculogram (EOG) artifacts can significantly degrade the quality of the recorded data, impacting the accuracy of essential signal features. Consequently, artifact removal from physiological signals is a crucial step in signal processing pipelines. Current techniques often employ Independent Component Analysis (ICA) to efficiently separate signal and artifact sources in multichannel recordings. However, limitations arise when dealing with single or a few channel measurements in minimal instrumentation or portable devices, restricting the utility of ICA. To address this challenge, this paper introduces an innovative artifact removal algorithm utilizing enhanced empirical mode decomposition to extract the intrinsic mode functions (IMFs). Subsequently, the algorithm targets the removal of segments related to EOG by isolating them within these IMFs. The proposed method is compared with existing single-channel EEG artifact removal algorithms, demonstrating superior performance. The findings demonstrate the effectiveness of our approach in isolating artifact components, resulting in a reconstructed signal characterized by a strong correlation and a power spectrum closely resembling the ground-truth EEG signal. This outperforms the existing methods in terms of artifact removal. Additionally, the proposed algorithm exhibits significantly reduced execution time, enabling real-time online analysis.

Impact of Indoor Air Quality and Multi-domain Factors on Human Productivity and Physiological Responses: A Comprehensive Review

Indoor environmental quality (IEQ) significantly impacts human health, well-being, and productivity. However, a comprehensive and in-depth review of the combined effects of IAQ and other multi-domain factors on human productivity is lacking. There has not been any prior review that encapsulates the impact of multi-domain factors on productivity and physiological responses of occupants. To address this gap, this review paper investigates and highlights the impact of IAQ and multi-domain factors (thermal, visual, and acoustic) on human productivity and occupant well-being in the built environment. The review explores various research methods, including evaluation of human productivity and creativity, data collection, and physiological signal analysis. We also examined the interactions between IAQ and multi-domain factors, as well as strategies for optimizing productivity through integrated building design and smart systems. The key findings from this review reveal that IAQ significantly impacts human productivity and occupant well-being, with interactions between IAQ and other IEQ factors further impacting these effects. Despite advances in the field, there are several limitations and gaps in the current research methods and study designs, including small sample sizes, limited and insufficient experimental design and control, reliance on laboratory or simulated environments, lack of follow-up and long-term data, and lack of robust performance metrics. The review proposes future research directions, including specific applications, and follow-up work to address these limitations and further advance the understanding of IAQ and multi-domain factors in the built environment. The implications of this review for policy and practice include the need for holistic and integrated approaches to IAQ and IEQ management, with a focus on creating healthy and productive indoor environments. This review emphasizes the importance of considering the complex interplay between IAQ and multi-domain factors, as well as the potentials of adopting smart control systems and sustainable design strategies to optimize productivity and occupant well-being in the built environment. By addressing these critical issues, we can enhance the overall quality of life for building occupants and contribute to a more sustainable future.

A Low-Cost Smart Wearable Glove for Non-Invasive Health Monitoring

Wearable physiological signal monitoring systems hold notable potential in the future of personal healthcare by seamlessly integrating into daily life, providing continuous monitoring, and aiding in the early detection of health issues. This research presents a wearable health monitoring glove, with a focus on cost-effectiveness while maintaining efficiency for developing countries. The wearable glove can track vital physiological indicators like Blood Pressure, Body Temperature, Glucose level, Blood Oxygen Saturation, Hemoglobin level, ECG, Room Temperature, Humidity, and Motion Tracking. A user-friendly interface facilitates easy interaction, while efforts in energy-efficient design and power management aim to prolong battery life. Also, real-time data monitoring ensures precision in signal analysis and the extraction of vital health data of individuals. The proposed wearable hand glove utilizes a collection of sensors and integrates them towards the diverse detection of skin humidity, temperature, blood oxygen, hemoglobin, etc. non-invasively. Apart from its technical features, the research explores potential applications in healthcare, fitness tracking, and research fields, presenting a versatile solution. Beyond its technical attributes, the research explores potential applications in medical and personal healthcare, fitness tracking, sports, etc. Collaborative efforts with regulatory bodies assess the feasibility of obtaining necessary approvals or certifications, while scalability considerations pave the way for potential mass production and market deployment.

Exploratory Data Analysis Based Design and Implementation of Student Stress Detection Using Machine Learning Approaches

The administration of stress is fundamental in perceiving the degrees of stress that can prevent our own and social prosperity. As per the World Wellbeing Association, roughly one of every four people experience pressure related mental issues, prompting mental and financial issues, unfortunate working environment connections, and even self-destruction in serious cases. Guiding is a vital asset to assist people with adapting to pressure. While stress can't be totally kept away from, preventive measures can help with overseeing feelings of anxiety. At the moment, only experts in medicine and physiology can tell if someone is stressed or not. Nonetheless, the conventional technique for distinguishing pressure in view of self-revealed replies from people is untrustworthy. Using physiological signals to automate the detection of stress levels, a more accurate and objective strategy for reducing health risks and enhancing society's well-being is available. A significant social contribution that can improve people's lives is the detection of stress levels. The IT business has presented new advancements and items that guide in the recognition of feelings of anxiety in workers, which is basic in upgrading their presentation. Albeit a few associations offer emotional well-being plans for their workers, the issue stays testing to make due. The machine is subjected to exploratory data analysis (EDA) in order to determine its accuracy. EDA is utilized on dataset so individual boundaries will be broke down with exactness and plotted in graph.The organization of stress is central in seeing the levels of pressure that can forestall our own and social success. According to the World Prosperity Affiliation, around one of each and every four individuals experience pressure related mental issues, provoking mental and monetary issues, lamentable work space associations, and, surprisingly, implosion in serious cases. Directing is an essential resource for help individuals with adjusting to pressure. While stress can't be completely avoided, preventive measures can assist with supervising sensations of nervousness. At this time, only specialists in physiology and medicine can determine whether a person is stressed or not. Regardless, the regular method for recognizing tension considering self-uncovered answers from individuals is conniving. Utilizing physiological signs to robotize the discovery of feelings of anxiety, a more precise and objective procedure for decreasing wellbeing chances and upgrading society's prosperity is accessible. A critical social commitment that can further develop individuals' lives is the location of feelings of anxiety. The IT business has introduced new progressions and things that aide in the acknowledgment of sensations of nervousness in laborers, which is fundamental in redesigning their show. Yet a couple of affiliations offer close to home prosperity plans for their laborers, the issue stays testing to make due. The machine is exposed to exploratory information examination (EDA) to decide its precision. EDA is used on dataset so individual limits will be destitute down with precision and plotted in chart.

Deep Learning‐Assisted Sensitive 3C‐SiC Sensor for Long‐Term Monitoring of Physical Respiration

AbstractIn human life, respiration serves as a crucial physiological signal. Continuous real‐time respiration monitoring can provide valuable insights for the early detection and management of several respiratory diseases. High‐sensitivity, noninvasive, comfortable, and long‐term stable respiration devices are highly desirable. In spite of this, existing respiration sensors cannot provide continuous long‐term monitoring due to the erosion from moisture, fluctuations in body temperature, and many other environmental factors. This research developed a wearable thermal‐based respiration sensor made of cubic silicon carbide (3C‐SiC) using a microfabrication process. The results showed that as a result of the Joule heating effect in the robustness 3C‐SiC material, the sensor offered high sensitivity with the negative temperature coefficient of resistance of approximately 5,200ppmK‐1, an excellent response to respiration and long‐term stability monitoring. Furthermore, by incorporating a deep learning model, this fabricated sensor can develop advanced capabilities to distinguish between the four distinct breath patterns: slow, normal, fast, and deep breathing, and provide an impressive classification accuracy rate of ≈ 99.7%. The results of this research represent a significant step in developing wearable respiration sensors for personal healthcare systems.