A Review of the State of the Art in Non-Contact Sensing for COVID-19

Feasibility Study on the Use of Infrared Cameras for Skin Cancer Detection under a Proposed Data Degradation Model

Infrared thermography is considered a useful technique for diagnosing several skin pathologies but it has not been widely adopted mainly due to its high cost. Here, we investigate the feasibility of using low-cost infrared cameras with microbolometer technology for detecting skin cancer. For this purpose, we collected infrared data from volunteer subjects using a high-cost/high-quality infrared camera. We propose a degradation model to assess the use of lower-cost imagers in such a task. The degradation model was validated by mimicking video acquisition with the low-cost cameras, using data originally captured with a medium-cost camera. The outcome of the proposed model was then compared with the infrared video obtained with actual cameras, achieving an average Pearson correlation coefficient of more than 0.9271. Therefore, the model successfully transfers the behavior of cameras with poorer characteristics to videos acquired with higher-quality cameras. Using the proposed model, we simulated the acquisition of patient data with three different lower-cost cameras, namely, Xenics Gobi-640, Opgal Therm-App, and Seek Thermal CompactPRO. The degraded data were used to evaluate the performance of a skin cancer detection algorithm. The Xenics and Opgal cameras achieved accuracies of 84.33% and 84.20%, respectively, and sensitivities of 83.03% and 83.23%, respectively. These values closely matched those from the non-degraded data, indicating that employing these lower-cost cameras is appropriate for skin cancer detection. The Seek camera achieved an accuracy of 82.13% and a sensitivity of 79.77%. Based on these results, we conclude that this camera is appropriate for less critical applications.

Two-Stream Convolutional Neural Networks for Breathing Pattern Classification: Real-Time Monitoring of Respiratory Disease Patients

A two-stream convolutional neural network (TCNN) for breathing pattern classification has been devised for the continuous monitoring of patients with infectious respiratory diseases. The TCNN consists of a convolutional neural network (CNN)-based autoencoder and classifier. The encoder of the autoencoder generates deep compressed feature maps, which contain the most important information constituting data. These maps are concatenated with feature maps generated by the classifier to classify breathing patterns. The TCNN, single-stream CNN (SCNN), and state-of-the-art classification models were applied to classify four breathing patterns: normal, slow, rapid, and breath holding. The input data consisted of chest tissue hemodynamic responses measured using a wearable near-infrared spectroscopy device on 14 healthy adult participants. Among the classification models evaluated, random forest had the lowest classification accuracy at 88.49%, while the TCNN achieved the highest classification accuracy at 94.63%. In addition, the proposed TCNN performed 2.6% better in terms of classification accuracy than an SCNN (without an autoencoder). Moreover, the TCNN mitigates the issue of declining learning performance with increasing network depth, as observed in the SCNN model. These results prove the robustness of the TCNN in classifying breathing patterns despite using a significantly smaller number of parameters and computations compared to state-of-the-art classification models.

Noncontact Sensors for Vital Signs Measurement: A Narrative Review

Vital signs are crucial for monitoring changes in patient health status. This review compared the performance of noncontact sensors with traditional methods for measuring vital signs and investigated the clinical feasibility of noncontact sensors for medical use. We searched the Medical Literature Analysis and Retrieval System Online (MEDLINE) database for articles published through September 30, 2023, and used the key search terms "vital sign," "monitoring," and "sensor" to identify relevant articles. We included studies that measured vital signs using traditional methods and noncontact sensors and excluded articles not written in English, case reports, reviews, and conference presentations. In total, 129 studies were identified, and eligible articles were selected based on their titles, abstracts, and full texts. Three articles were finally included in the review, and the types of noncontact sensors used in each selected study were an impulse radio ultrawideband radar, a microbend fiber-optic sensor, and a mat-type air pressure sensor. Participants included neonates in the neonatal intensive care unit, patients with sleep apnea, and patients with coronavirus disease. Their heart rate, respiratory rate, blood pressure, body temperature, and arterial oxygen saturation were measured. Studies have demonstrated that the performance of noncontact sensors is comparable to that of traditional methods of vital signs measurement. Noncontact sensors have the potential to alleviate concerns related to skin disorders associated with traditional skin-contact vital signs measurement methods, reduce the workload for healthcare providers, and enhance patient comfort. This article reviews the medical use of noncontact sensors for measuring vital signs and aimed to determine their potential clinical applicability.

A Flexible Terahertz Metamaterial Sensor for Pesticide Sensing and Detection

Terahertz (THz) waves have garnered significant interest across various fields, particularly in high-sensitivity sensing applications. Metamaterials can be employed in THz sensors, specifically for refractive index sensing and pesticide detection due to their high-sensitivity characteristics. In this Article, a dual-band flexible THz metamaterial sensor based on polyimide is proposed for refractive index and pesticide sensing, which is fabricated using ultraviolet (UV) lithography technology and measured by a THz time-domain spectroscope (TDS) system. The resonant frequencies of the sensor are at 0.37 and 1.13 THz, with transmission rates of 2.9% and 0.3%, respectively. With an analyte layer attached to the sensor's surface, the sensitivity of refractive index sensing can be calculated as 0.09 and 0.28 THz/RIU (refractive index unit) at the two resonant frequencies. In order to validate the exceptional pesticide sensing performance of the sensor, chlorpyrifos-methyl acetone solutions with various concentrations are added on it. Furthermore, a monolayer of graphene is coated on the sensor's surface, which is proved capable of improving pesticide sensing sensitivity at low concentrations due to strong π-π stacking interactions with π-electrons in chlorpyrifos-methyl solutions. Therefore, the graphene-coated sensor can be utilized in detecting pesticide solutions with low concentrations, and the sensor without graphene is preferred for high concentration detection. This work provides a novel option for the THz metamaterial sensor with high sensitivity covering a wide pesticide concentration range.

Co-Infection between Dengue Virus and SARS-CoV-2 in Cali, Colombia

The co-occurrence of COVID-19 with endemic diseases is a public health concern that may affect patient prognosis and outcomes. The objective of this study was to describe the clinical characteristics of patients with dengue virus (DENV) and SARS-CoV-2 co-infections and compare their outcomes against those of COVID-19 patients without dengue. A cross-sectional study was conducted in patients with SARS-CoV-2 infection who attended a single center in Cali, Colombia, from March 2020 to March 2021. All patients who were tested by both real-time polymerase chain reaction for SARS-CoV-2 and IgM/NS1 for DENV were included. Dengue was diagnosed as having either an IgM- or an NS1- positive test. A total of 90 patients were included (72 with COVID-19 only and 18 with co-infection). Patients with co-infection had more dyspnea (61.1% versus 22.2%; P = 0.003) as well as higher oxygen desaturation (53.3% versus 13.4%; P = 0.002) and neutrophil-to-lymphocyte ratio (5.59 versus 3.84; P = 0.038) than patients with COVID-19 alone. The proportion of patients classified with moderate to severe COVID-19 was higher in the co-infection group (88.3% versus 47.8%; P = 0.002). Also, co-infection was associated with an increased need for mechanical ventilation (P = 0.06), intensive care unit (ICU) initial management (P = 0.02), and ICU admission during hospitalization (P = 0.04) compared with COVID-19 only. The ICU mortality rate was 66.6% in patients with co-infection versus 29.4% in patients infected with only SARS-CoV-2 (P < 0.05). The possibility of DENV and SARS-CoV2 co-infection occurred in the convergence of both epidemic waves. Co-infection was associated with worse clinical outcomes and higher mortality in ICU-admitted patients than in patients with the COVID-19 only.

Modification of a Conventional Deep Learning Model to Classify Simulated Breathing Patterns: A Step toward Real-Time Monitoring of Patients with Respiratory Infectious Diseases

The emergence of the global coronavirus pandemic in 2019 (COVID-19 disease) created a need for remote methods to detect and continuously monitor patients with infectious respiratory diseases. Many different devices, including thermometers, pulse oximeters, smartwatches, and rings, were proposed to monitor the symptoms of infected individuals at home. However, these consumer-grade devices are typically not capable of automated monitoring during both day and night. This study aims to develop a method to classify and monitor breathing patterns in real-time using tissue hemodynamic responses and a deep convolutional neural network (CNN)-based classification algorithm. Tissue hemodynamic responses at the sternal manubrium were collected in 21 healthy volunteers using a wearable near-infrared spectroscopy (NIRS) device during three different breathing conditions. We developed a deep CNN-based classification algorithm to classify and monitor breathing patterns in real time. The classification method was designed by improving and modifying the pre-activation residual network (Pre-ResNet) previously developed to classify two-dimensional (2D) images. Three different one-dimensional CNN (1D-CNN) classification models based on Pre-ResNet were developed. By using these models, we were able to obtain an average classification accuracy of 88.79% (without Stage 1 (data size reducing convolutional layer)), 90.58% (with 1 × 3 Stage 1), and 91.77% (with 1 × 5 Stage 1).

Nurses' Perceptions About Smart Beds in Hospitals

The purpose of this study was to examine nurses' perceptions of the smart mattress equipped with Internet of things, which are incorporated into patients' beds. In addition, their concerns and suggestions about smart mattress were explored. A total of 349 nurses in a tertiary hospital participated in a cross-sectional survey. Data were collected using questionnaires. Descriptive statistical analysis was used for survey data, whereas content analysis was used for qualitative data from open-ended questions. The participants' intention to accept the smart mattresses was 12.5 (SD, 1.73) on average, indicating a high level of acceptance. The participants expected the smart mattresses to decrease their physical work burden, improve work efficiency, and prevent pressure ulcers. However, they were concerned about an increase in other aspects of their workload and in patient safety problems due to false alarms, inaccuracies, and malfunctions of the device. Nurses suggested various features that can be integrated into smart mattress. It is critical to address nurses' perceptions, expectations, and concerns during the conceptual and developmental stage of new technology in order to improve the usability, acceptance, and adoption of smart mattresses and other new innovations in hospital settings.

A high Q-factor dual-band terahertz metamaterial absorber and its sensing characteristics

In this paper, a dual-band metamaterial absorber in the terahertz frequencies is proposed and its refractive index sensing characteristics is analyzed. The metamaterial structure is designed using a square metal ring with four T-shaped strips loaded outside of the ring, where the metal periodic array is on top of a silicon wafer backed with a metal ground plane. The resonant frequencies of the absorber are at 0.89 and 1.36 THz, whose absorption rates are both over 99% under normal TE and TM polarized incidences. The full widths at half maximum of them are 4.4 and 11.2 GHz, respectively, resulting in high quality factors (Q-factors) for these two frequency bands. The absorption rate of the absorber remains stable as the incident and polarized angles are changed. Several proposed metamaterial absorbers are experimentally fabricated and electron beam lithography (EBL) technology is employed. Good measurement results of the dual-band absorption performance are obtained using a terahertz time-domain spectroscopy system based on photoconductive antennas. Furthermore, the metamaterial absorber also shows sensing properties for analytes with different refractive indices or thicknesses. This work provides a new choice for the design of high-Q dual-band terahertz metamaterial absorbers and their application to refractive index sensing.

Few-Shot User-Adaptable Radar-Based Breath Signal Sensing

Vital signs estimation provides valuable information about an individual's overall health status. Gathering such information usually requires wearable devices or privacy-invasive settings. In this work, we propose a radar-based user-adaptable solution for respiratory signal prediction while sitting at an office desk. Such an approach leads to a contact-free, privacy-friendly, and easily adaptable system with little reference training data. Data from 24 subjects are preprocessed to extract respiration information using a 60 GHz frequency-modulated continuous wave radar. With few training examples, episodic optimization-based learning allows for generalization to new individuals. Episodically, a convolutional variational autoencoder learns how to map the processed radar data to a reference signal, generating a constrained latent space to the central respiration frequency. Moreover, autocorrelation over recorded radar data time assesses the information corruption due to subject motions. The model learning procedure and breathing prediction are adjusted by exploiting the motion corruption level. Thanks to the episodic acquired knowledge, the model requires an adaptation time of less than one and two seconds for one to five training examples, respectively. The suggested approach represents a novel, quickly adaptable, non-contact alternative for office settings with little user motion.

Advances in terahertz technology for cancer detection applications

Currently, there is an increasing demand for the diagnostic techniques that provide functional and morphological information with early cancer detection capability. Novel modern medical imaging systems driven by the recent advancements in technology such as terahertz (THz) and infrared radiation-based imaging technologies which are complementary to conventional modalities are being developed, investigated, and validated. The THz cancer imaging techniques offer novel opportunities for label free, non-ionizing, non-invasive and early cancer detection. The observed image contrast in THz cancer imaging studies has been mostly attributed to higher refractive index, absorption coefficient and dielectric properties in cancer tissue than that in the normal tissue due the local increase of the water molecule content in tissue and increased blood supply to the cancer affected tissue. Additional image contrast parameters and cancer biomarkers that have been reported to contribute to THz image contrast include cell structural changes, molecular density, interactions between agents (e.g., contrast agents and embedding agents) and biological tissue as well as tissue substances like proteins, fiber and fat etc. In this paper, we have presented a systematic and comprehensive review of the advancements in the technological development of THz technology for cancer imaging applications. Initially, the fundamentals principles and techniques for THz radiation generation and detection, imaging and spectroscopy are introduced. Further, the application of THz imaging for detection of various cancers tissues are presented, with more focus on the in vivo imaging of skin cancer. The data processing techniques for THz data are briefly discussed. Also, we identify the advantages and existing challenges in THz based cancer detection and report the performance improvement techniques. The recent advancements towards THz systems which are optimized and miniaturized are also reported. Finally, the integration of THz systems with artificial intelligent (AI), internet of things (IoT), cloud computing, big data analytics, robotics etc. for more sophisticated systems is proposed. This will facilitate the large-scale clinical applications of THz for smart and connected next generation healthcare systems and provide a roadmap for future research.

E-GCS: Detection of COVID-19 through classification by attention bottleneck residual network

Background

Recently,  the coronavirus disease 2019 (COVID-19)  has caused mortality of many people globally. Thus, there existed a need to detect this disease to prevent its further spread. Hence, the study aims to predict COVID-19 infected patients based on deep learning (DL) and image processing.

Objectives

The study intends to classify the normal and abnormal cases of COVID-19 by considering three different medical imaging modalities namely ultrasound imaging, X-ray images and CT scan images through introduced attention bottleneck residual network (AB-ResNet). It also aims to segment the abnormal infected area from normal images for localizing localising the disease infected area through the proposed edge based graph cut segmentation (E-GCS).

Methodology

AB-ResNet is used for classifying images whereas E-GCS segment the abnormal images. The study possess various advantages as it rely on DL and possess capability for accelerating the training speed of deep networks. It also enhance the network depth leading to minimum parameters, minimising the impact of vanishing gradient issue and attaining effective network performance with respect to better accuracy.

Results/Conclusion

Performance and comparative analysis is undertaken to evaluate the efficiency of the introduced system and results explores the efficiency of the proposed system in COVID-19 detection with high accuracy (99%).

Utility of thermal image scanning in screening for febrile patients in cold climates

BACKGROUND

Infrared thermography (IRT) for fever screening systems was introduced in not only general hospitals, but also orthopedic hospitals as a countermeasure against the spread of coronavirus disease 2019 (COVID-19). Despite the widespread use of IRT, various results have shown low and high efficacies, so the utility of IRT is controversial, especially in cold climates. The aims of this study were to investigate the utility of IRT in screening for fever in a cold climate and to devise suitable fever screening in orthopedic surgery for COVID-19.

METHODS

A total of 390 orthopedic surgery patients were enrolled to the outdoor group and 210 hospital staff members were enrolled to the indoor group. Thermographic temperature at the front of the face in the outdoor group was immediately measured after entering our hospital from a cold outdoor environment. Measurements for the indoor group were made after staying in the hospital (environmental temperature, 28 °C) for at least 5 h. Body temperature was then measured using an axillary thermometer >15 min later in both groups.

RESULTS

In the outdoor group, mean thermographic temperature was significantly lower than axillary temperature and IRT could not detect febrile patients with axillary temperatures >37.0 °C. Mean thermographic temperature was significantly lower in the outdoor group than in the indoor group. Sensitivity was 11.5% for the outdoor group, lower than that for the indoor group.

CONCLUSIONS

We verified that IRT was not accurate in a cold climate. IRT is inadequate as a screening method to accurately detect febrile individuals, so we believe that stricter countermeasures for second screening need to be employed to prevent nosocomial infections and disease clusters of COVID-19, even in orthopedic hospitals.

Statistical Study on Human Temperature Measurement by Infrared Thermography

Increased temperature in humans is the symptom of many infectious diseases and it is thus an important diagnostic tool. Infrared temperature measurement methods have been developed and applied over long periods due to their advantage of non-contact and fast measurements. This study deals with a statistical evaluation of the possibilities and limitations of infrared/thermographic human temperature measurement. A short review of the use of infrared temperature measurement in medical applications is provided. Experiments and statistics-based evaluation to confirm the expected accuracy and limits of thermography-based human temperature measurement are introduced. The results presented in this study show that the standard deviation of the thermographic measurement of the eyes maximum temperature was 0.4-0.9 °C and the mean values differences from the armpit measurement were up to 0.5 °C, based on the used IR camera, even though near ideal measurement conditions and permanent blackbody correction were used. It was also shown that a certain number of outliers must be assumed in such measurements. Extended analyses including simulations of true negative/false positive, sensitivity/specificity and receiver operating characteristics (ROC) curves are presented. The statistical evaluation as well as the extended analyses show that maximum eyes temperature is more relevant than a forehead temperature examination.

Intelligent Reflecting Surface-Based Non-LOS Human Activity Recognition for Next-Generation 6G-Enabled Healthcare System

Human activity monitoring is a fascinating area of research to support autonomous living in the aged and disabled community. Cameras, sensors, wearables, and non-contact microwave sensing have all been suggested in the past as methods for identifying distinct human activities. Microwave sensing is an approach that has lately attracted much interest since it has the potential to address privacy problems caused by cameras and discomfort caused by wearables, especially in the healthcare domain. A fundamental drawback of the current microwave sensing methods such as radar is non-line-of-sight and multi-floor environments. They need precise and regulated conditions to detect activity with high precision. In this paper, we have utilised the publicly available online database based on the intelligent reflecting surface (IRS) system developed at the Communications, Sensing and Imaging group at the University of Glasgow, UK (references 39 and 40). The IRS system works better in the multi-floor and non-line-of-sight environments. This work for the first time uses algorithms such as support vector machine Bagging and Decision Tree on the publicly available IRS data and achieves better accuracy when a subset of the available data is considered along specific human activities. Additionally, the work also considers the processing time taken by the classier in training stage when exposed to the IRS data which was not previously explored.

Sound Feedback for Social Distance: The Case for Public Interventions during a Pandemic

Within the field of movement sensing and sound interaction research, multi-user systems have gradually gained interest as a means to facilitate an expressive non-verbal dialogue. When tied with studies grounded in psychology and choreographic theory, we consider the qualities of interaction that foster an elevated sense of social connectedness, non-contingent to occupying one’s personal space. Upon reflection of the newly adopted social distancing concept, we orchestrate a technological intervention, starting with interpersonal distance and sound at the core of interaction. Materialised as a set of sensory face-masks, a novel wearable system was developed and tested in the context of a live public performance from which we obtain the user’s individual perspectives and correlate this with patterns identified in the recorded data. We identify and discuss traits of the user’s behaviour that were accredited to the system’s influence and construct four fundamental design considerations for physically distanced sound interaction. The study concludes with essential technical reflections, accompanied by an adaptation for a pervasive sensory intervention that is finally deployed in an open public space.

Stretchable graded multichannel self-powered respiratory sensor inspired by shark gill

Respiratory sensing provides a simple, non-invasive, and efficient way for medical diagnosis and health monitoring, but it relies on sensors that are conformal, accurate, durable, and sustainable working. Here, a stretchable, multichannel respiratory sensor inspired by the structure of shark gill cleft is reported. The bionic shark gill structure can convert transverse elastic deformation into longitudinal elastic deformation during stretching. Combining the optimized bionic shark gill structure with the piezoelectric and the triboelectric effect, the bionic shark gill respiratory sensor (BSG-RS) can produce a graded electrical response to different tensile strains. Based on this feature, BSG-RS can simultaneously monitor the breathing rate and breathing depth of the human body accurately, and realize the effective recognition of the different human body's breathing state under the supporting software. With good stretchability, wearability, accuracy, and long-term stability (50,000 cycles), BSG-RS is expected to be applied as self-powered smart wearables for mobile medical diagnostic analysis in the future.

A Survey on Machine Learning and Internet of Medical Things-Based Approaches for Handling COVID-19: Meta-Analysis

Early diagnosis, prioritization, screening, clustering, and tracking of patients with COVID-19, and production of drugs and vaccines are some of the applications that have made it necessary to use a new style of technology to involve, manage, and deal with this epidemic. Strategies backed by artificial intelligence (A.I.) and the Internet of Things (IoT) have been undeniably effective to understand how the virus works and prevent it from spreading. Accordingly, the main aim of this survey is to critically review the ML, IoT, and the integration of IoT and ML-based techniques in the applications related to COVID-19, from the diagnosis of the disease to the prediction of its outbreak. According to the main findings, IoT provided a prompt and efficient approach to tracking the disease spread. On the other hand, most of the studies developed by ML-based techniques aimed at the detection and handling of challenges associated with the COVID-19 pandemic. Among different approaches, Convolutional Neural Network (CNN), Support Vector Machine, Genetic CNN, and pre-trained CNN, followed by ResNet have demonstrated the best performances compared to other methods.

Heart rate prediction from facial video with masks using eye location and corrected by convolutional neural networks

Remote photoplethysmography (rPPG), which aims at measuring heart activities without any contact, has great potential in many applications. The emergence of novel coronavirus pneumonia COVID-19 has attracted worldwide attentions. Contact photoplethysmography (cPPG) methods need to contact the detection equipment with the patient, which may accelerate the spread of the epidemic. In the future, the non-contact heart rate detection will be an urgent need. However, existing heart rate measuring methods from facial videos are vulnerable to the less-constrained scenarios (e.g., with head movement and wearing a mask). In this paper, we proposed a method of heart rate detection based on eye location of region of interest (ROI) to solve the problem of missing information when wearing masks. Besides, a model to filter outliers based on residual network was conceived first by us and the better heart rate measurement accuracy was generated. To validate our method, we also created a mask dataset. The results demonstrated that after using our method for correcting the heart rate (HR) value measured with the traditional method, the accuracy reaches 4.65 bpm, which is 0.42 bpm higher than that without correction.

A Study of the Detection of SARS-CoV-2 ORF1ab Gene by the Use of Electrochemiluminescent Biosensor Based on Dual-Probe Hybridization

To satisfy the need to develop highly sensitive methods for detecting the severe acute respiratory syndrome coronavirus type 2 (SARS-CoV-2) and further enhance detection efficiency and capability, a new method was created for detecting SARS-CoV-2 of the open reading frames 1ab (ORF1ab) target gene by a electrochemiluminescence (ECL) biosensor based on dual-probe hybridization through the use of a detection model of "magnetic capture probes-targeted nucleic acids-Ru(bpy)₃²⁺ labeled signal probes". The detection model used magnetic particles coupled with a biotin-labeled complementary nucleic acid sequence of the SARS-CoV-2 ORF1ab target gene as the magnetic capture probes and Ru(bpy)₃²⁺ labeled amino modified another complementary nucleic acid sequence as the signal probes, which combined the advantages of the highly specific dual-probe hybridization and highly sensitive ECL biosensor technology. In the range of 0.1 fM~10 µM, the method made possible rapid and sensitive detection of the ORF1ab gene of the SARS-CoV-2 within 30 min, and the limit of detection (LOD) was 0.1 fM. The method can also meet the analytical requirements for simulated samples such as saliva and urine with the definite advantages of a simple operation without nucleic acid amplification, high sensitivity, reasonable reproducibility, and anti-interference solid abilities, expounding a new way for efficient and sensitive detection of SARS-CoV-2.

Personalized wearable electrodermal sensing-based human skin hydration level detection for sports, health and wellbeing

Personalized hydration level monitoring play vital role in sports, health, wellbeing and safety of a person while performing particular set of activities. Clinical staff must be mindful of numerous physiological symptoms that identify the optimum hydration specific to the person, event and environment. Hence, it becomes extremely critical to monitor the hydration levels in a human body to avoid potential complications and fatalities. Hydration tracking solutions available in the literature are either inefficient and invasive or require clinical trials. An efficient hydration monitoring system is very required, which can regularly track the hydration level, non-invasively. To this aim, this paper proposes a machine learning (ML) and deep learning (DL) enabled hydration tracking system, which can accurately estimate the hydration level in human skin using galvanic skin response (GSR) of human body. For this study, data is collected, in three different hydration states, namely hydrated, mild dehydration (8 hours of dehydration) and extreme mild dehydration (16 hours of dehydration), and three different body postures, such as sitting, standing and walking. Eight different ML algorithms and four different DL algorithms are trained on the collected GSR data. Their accuracies are compared and a hybrid (ML+DL) model is proposed to increase the estimation accuracy. It can be reported that hybrid Bi-LSTM algorithm can achieve an accuracy of 97.83%.

Machine learning empowered COVID-19 patient monitoring using non-contact sensing: An extensive review

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), which caused the coronavirus disease 2019 (COVID-19) pandemic, has affected more than 400 million people worldwide. With the recent rise of new Delta and Omicron variants, the efficacy of the vaccines has become an important question. The goal of various studies has been to limit the spread of the virus by utilizing wireless sensing technologies to prevent human-to-human interactions, particularly for healthcare workers. In this paper, we discuss the current literature on invasive/contact and non-invasive/non-contact technologies (including Wi-Fi, radar, and software-defined radio) that have been effectively used to detect, diagnose, and monitor human activities and COVID-19 related symptoms, such as irregular respiration. In addition, we focused on cutting-edge machine learning algorithms (such as generative adversarial networks, random forest, multilayer perceptron, support vector machine, extremely randomized trees, and k-nearest neighbors) and their essential role in intelligent healthcare systems. Furthermore, this study highlights the limitations related to non-invasive techniques and prospective research directions.

•

This article describes cutting-edge technology (invasive/non-invasive) and its role in the recognition of COVID-19 symptoms.

•

This article summarizes state-of-art machine-learning algorithms and their roles in modern healthcare systems.

•

This article presents the challenges associated with wireless sensing techniques and potential future research directions.

Noninvasive Detection of Respiratory Disorder Due to COVID-19 at the Early Stages in Saudi Arabia

The Kingdom of Saudi Arabia has suffered from COVID-19 disease as part of the global pandemic due to severe acute respiratory syndrome coronavirus 2. The economy of Saudi Arabia also suffered a heavy impact. Several measures were taken to help mitigate its impact and stimulate the economy. In this context, we present a safe and secure WiFi-sensing-based COVID-19 monitoring system exploiting commercially available low-cost wireless devices that can be deployed in different indoor settings within Saudi Arabia. We extracted different activities of daily living and respiratory rates from ubiquitous WiFi signals in terms of channel state information (CSI) and secured them from unauthorized access through permutation and diffusion with multiple substitution boxes using chaos theory. The experiments were performed on healthy participants. We used the variances of the amplitude information of the CSI data and evaluated their security using several security parameters such as the correlation coefficient, mean-squared error (MSE), peak-signal-to-noise ratio (PSNR), entropy, number of pixel change rate (NPCR), and unified average change intensity (UACI). These security metrics, for example, lower correlation and higher entropy, indicate stronger security of the proposed encryption method. Moreover, the NPCR and UACI values were higher than 99% and 30, respectively, which also confirmed the security strength of the encrypted information.

Rapid Detection of Coronavirus (COVID-19) Using Microwave Immunosensor Cavity Resonator

This paper presents a rapid diagnostic device for the detection of the pandemic coronavirus (COVID-19) using a micro-immunosensor cavity resonator. Coronavirus has been declared an international public health crisis, so it is important to design quick diagnostic methods for the detection of infected cases, especially in rural areas, to limit the spread of the virus. Herein, a proof-of-concept is presented for a portable laboratory device for the detection of the SARS-CoV-2 virus using electromagnetic biosensors. This device is a microwave cavity resonator (MCR) composed of a sensor operating at industrial, scientific and medical (ISM) 2.45 GHz inserted in 3D housing. The changes of electrical properties of measured serum samples after passing the sensor surface are presented. The three change parameters of the sensor are resonating frequency value, amplitude and phase of the reflection coefficient |S₁₁|. This immune-sensor offers a portable, rapid and accurate diagnostic method for the SARS-CoV-2 virus, which can enable on-site diagnosis of infection. Medical validation for the device is performed through biostatistical analysis using the ROC (Receiver Operating Characteristic) method. The predictive accuracy of the device is 63.3% and 60.6% for reflection and phase, respectively. The device has advantages of low cost, low size and weight and rapid response. It does need a trained technician to operate it since a software program operates automatically. The device can be used at ports’ quarantine units, hospitals, etc.

A comprehensive review of COVID-19 biology, diagnostics, therapeutics, and disease impacting the central nervous system

The ongoing COVID-19 pandemic, caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), is a highly transmissible disease. SARS-CoV-2 is estimated to have infected over 153 million people and to have caused over 3.2 million global deaths since its emergence in December 2019. SARS-CoV-2 is the seventh coronavirus known to infect humans, and like other coronaviruses, SARS-CoV-2 infection is characterized by a variety of symptoms including general flu-like symptoms such as a fever, sore throat, fatigue, and shortness of breath. Severe cases often display signs of pneumonia, lymphopenia, acute kidney injury, cardiac injury, cytokine storms, lung damage, acute respiratory distress syndrome (ARDS), multiple organ failure, sepsis, and death. There is evidence that around 30% of COVID-19 cases have central nervous system (CNS) or peripheral nervous system (PNS) symptoms along with or in the absence of the previously mentioned symptoms. In cases of CNS/PNS impairments, patients display dizziness, ataxia, seizure, nerve pain, and loss of taste and/or smell. This review highlights the neurological implications of SARS-CoV-2 and provides a comprehensive summary of the research done on SARS-CoV-2 pathology, diagnosis, therapeutics, and vaccines up to May 5.

Application of machine learning in CT images and X-rays of COVID-19 pneumonia

ABSTRACT

Coronavirus disease (COVID-19) has spread worldwide. X-ray and computed tomography (CT) are 2 technologies widely used in image acquisition, segmentation, diagnosis, and evaluation. Artificial intelligence can accurately segment infected parts in X-ray and CT images, assist doctors in improving diagnosis efficiency, and facilitate the subsequent assessment of the severity of the patient infection. The medical assistant platform based on machine learning can help radiologists make clinical decisions and helper in screening, diagnosis, and treatment. By providing scientific methods for image recognition, segmentation, and evaluation, we summarized the latest developments in the application of artificial intelligence in COVID-19 lung imaging, and provided guidance and inspiration to researchers and doctors who are fighting the COVID-19 virus.

COVID-19 digital contact tracing applications and techniques: A review post initial deployments

The coronavirus disease 2019 (COVID-19) is a severe global pandemic that has claimed millions of lives and continues to overwhelm public health systems in many countries. The spread of COVID-19 pandemic has negatively impacted the human mobility patterns such as daily transportation-related behavior of the public. There is a requirement to understand the disease spread patterns and its routes among neighboring individuals for the timely implementation of corrective measures at the required placement. To increase the effectiveness of contact tracing, countries across the globe are leveraging advancements in mobile technology and Internet of Things (IoT) to aid traditional manual contact tracing to track individuals who have come in close contact with identified COVID-19 patients. Even as the first administration of vaccines begins in 2021, the COVID-19 management strategy will continue to be multi-pronged for the foreseeable future with digital contact tracing being a vital component of the response along with the use of preventive measures such as social distancing and the use of face masks. After some months of deployment of digital contact tracing technology, deeper insights into the merits of various approaches and the usability, privacy, and ethical trade-offs involved are emerging. In this paper, we provide a comprehensive analysis of digital contact tracing solutions in terms of their methodologies and technologies in the light of the new data emerging about international experiences of deployments of digital contact tracing technology. We also provide a discussion on open challenges such as scalability, privacy, adaptability and highlight promising directions for future work.

Evaluation of biases in remote photoplethysmography methods

This work investigates the estimation biases of remote photoplethysmography (rPPG) methods for pulse rate measurement across diverse demographics. Advances in photoplethysmography (PPG) and rPPG methods have enabled the development of contact and noncontact approaches for continuous monitoring and collection of patient health data. The contagious nature of viruses such as COVID-19 warrants noncontact methods for physiological signal estimation. However, these approaches are subject to estimation biases due to variations in environmental conditions and subject demographics. The performance of contact-based wearable sensors has been evaluated, using off-the-shelf devices across demographics. However, the measurement uncertainty of rPPG methods that estimate pulse rate has not been sufficiently tested across diverse demographic populations or environments. Quantifying the efficacy of rPPG methods in real-world conditions is critical in determining their potential viability as health monitoring solutions. Currently, publicly available face datasets accompanied by physiological measurements are typically captured in controlled laboratory settings, lacking diversity in subject skin tones, age, and cultural artifacts (e.g, bindi worn by Indian women). In this study, we collect pulse rate and facial video data from human subjects in India and Sierra Leone, in order to quantify the uncertainty in noncontact pulse rate estimation methods. The video data are used to estimate pulse rate using state-of-the-art rPPG camera-based methods, and compared against ground truth measurements captured using an FDA-approved contact-based pulse rate measurement device. Our study reveals that rPPG methods exhibit similar biases when compared with a contact-based device across demographic groups and environmental conditions. The mean difference between pulse rates measured by rPPG methods and the ground truth is found to be ~2% (1 beats per minute (b.p.m.)), signifying agreement of rPPG methods with the ground truth. We also find that rPPG methods show pulse rate variability of ~15% (11 b.p.m.), as compared to the ground truth. We investigate factors impacting rPPG methods and discuss solutions aimed at mitigating variance.

Non-Contact Monitoring and Classification of Breathing Pattern for the Supervision of People Infected by COVID-19

During the pandemic of coronavirus disease-2019 (COVID-19), medical practitioners need non-contact devices to reduce the risk of spreading the virus. People with COVID-19 usually experience fever and have difficulty breathing. Unsupervised care to patients with respiratory problems will be the main reason for the rising death rate. Periodic linearly increasing frequency chirp, known as frequency-modulated continuous wave (FMCW), is one of the radar technologies with a low-power operation and high-resolution detection which can detect any tiny movement. In this study, we use FMCW to develop a non-contact medical device that monitors and classifies the breathing pattern in real time. Patients with a breathing disorder have an unusual breathing characteristic that cannot be represented using the breathing rate. Thus, we created an Xtreme Gradient Boosting (XGBoost) classification model and adopted Mel-frequency cepstral coefficient (MFCC) feature extraction to classify the breathing pattern behavior. XGBoost is an ensemble machine-learning technique with a fast execution time and good scalability for predictions. In this study, MFCC feature extraction assists machine learning in extracting the features of the breathing signal. Based on the results, the system obtained an acceptable accuracy. Thus, our proposed system could potentially be used to detect and monitor the presence of respiratory problems in patients with COVID-19, asthma, etc.

Novel Deep Convolutional Neural Network-Based Contextual Recognition of Arabic Handwritten Scripts

Offline Arabic Handwriting Recognition (OAHR) has recently become instrumental in the areas of pattern recognition and image processing due to its application in several fields, such as office automation and document processing. However, OAHR continues to face several challenges, including high variability of the Arabic script and its intrinsic characteristics such as cursiveness, ligatures, and diacritics, the unlimited variation in human handwriting, and the lack of large public databases. In this paper, we introduce a novel context-aware model based on deep neural networks to address the challenges of recognizing offline handwritten Arabic text, including isolated digits, characters, and words. Specifically, we propose a supervised Convolutional Neural Network (CNN) model that contextually extracts optimal features and employs batch normalization and dropout regularization parameters. This aims to prevent overfitting and further enhance generalization performance when compared to conventional deep learning models. We employ a number of deep stacked-convolutional layers to design the proposed Deep CNN (DCNN) architecture. The model is extensively evaluated and shown to demonstrate excellent classification accuracy when compared to conventional OAHR approaches on a diverse set of six benchmark databases, including MADBase (Digits), CMATERDB (Digits), HACDB (Characters), SUST-ALT (Digits), SUST-ALT (Characters), and SUST-ALT (Names). A further experimental study is conducted on the benchmark Arabic databases by exploiting transfer learning (TL)-based feature extraction which demonstrates the superiority of our proposed model in relation to state-of-the-art VGGNet-19 and MobileNet pre-trained models. Finally, experiments are conducted to assess comparative generalization capabilities of the models using another language database , specifically the benchmark MNIST English isolated Digits database, which further confirm the superiority of our proposed DCNN model.

Internet of Everything (IoE) Taxonomies: A Survey and a Novel Knowledge-Based Taxonomy

The paradigm of the Internet of everything (IoE) is advancing toward enriching people’s lives by adding value to the Internet of things (IoT), with connections among people, processes, data, and things. This paper provides a survey of the literature on IoE research, highlighting concerns in terms of intelligence services and knowledge creation. The significant contributions of this study are as follows: (1) a systematic literature review of IoE taxonomies (including IoT); (2) development of a taxonomy to guide the identification of critical knowledge in IoE applications, an in-depth classification of IoE enablers (sensors and actuators); (3) validation of the defined taxonomy with 50 IoE applications; and (4) identification of issues and challenges in existing IoE applications (using the defined taxonomy) with regard to insights about knowledge processes. To the best of our knowledge, and taking into consideration the 76 other taxonomies compared, this present work represents the most comprehensive taxonomy that provides the orchestration of intelligence in network connections concerning knowledge processes, type of IoE enablers, observation characteristics, and technological capabilities in IoE applications.

Common-Mode Noise Reduction in Noncontact Biopotential Acquisition Circuit Based on Imbalance Cancellation of Electrode-Body Impedance

Biopotential sensing technology with electrodes has a great future in medical treatment and human—machine interface, whereas comfort and longevity are two significant problems during usage. Noncontact electrode is a promising alternative to achieve more comfortable and long term biopotential signal recordings than contact electrode. However, it could pick up a significantly higher level of common-mode (CM) noise, which is hardly solved with passive filtering. The impedance imbalance at the electrode-body interface is a limiting factor of this problem, which reduces the common mode rejection ratio (CMRR) of the amplifier. In this work, we firstly present two novel CM noise reduction circuit designs. The circuit designs are based on electrode-body impedance imbalance cancellation. We perform circuit analysis and circuit simulations to explain the principles of the two circuits, both of which showed effectiveness in CM noise rejection. Secondly, we proposed a practical approach to detect and monitor the electrode-body impedance imbalance change. Compared with the conventional approach, it has certain advantages in interference immunity, and good linearity for capacitance. Lastly, we show experimental evaluation results on one of the designs we proposed. The results indicated the validity and feasibility of the approach.