Health Monitoring System Research Articles

Identification of People in a Household Using Ballistocardiography Signals Through Deep Learning

Background: Various sensor technologies have been developed to monitor the health of older adults; however, most of them require attachment to the skin. This study aimed to develop a health monitoring system, using a non-adhesive, non-invasive polyvinylidene difluoride piezoelectric sensor, with the patient being able to lead a normal daily life without being conscious of the sensor. The vibration signal from the human body surface obtained by the piezoelectric sensor, which is a ballistocardiography signal, contains information on the person’s heart and respiratory rates. We propose a method that enables individual identification based on the characteristics of the frequency components of the signal. Methods: Signals from ten subjects were acquired and a neural network was constructed, trained, and tested using 252 cases to identify five individuals, based on assuming the number of people in a household. Results: The classification probability and accuracy rate were obtained for all 252 cases, and good classification rates were obtained in almost all cases. Conclusions: Although it will be necessary to consider daily changes in such signals in the future, the system had good identification accuracy when five individuals were identified.

Recent progress in biocompatible miniature supercapacitors

With the advancement of wearable and implantable health and medical electronics, biocompatible miniature energy storage devices were developed rapidly. In particular, biocompatible miniature supercapacitors (BMSCs) have the advantages of conventional supercapacitors, such as high-power density, fast charging/discharging rate, and long operating lifetime, as well as strong selectivity of biocompatible materials. They are expected to play an important role in personalized electronic integration systems. Biocompatibility involves the biosafety of materials and relates to the mechanics and geometrical forms. For example, BMSCs should be thin and compact, ensuring ease of portability and comfort for users. They should also be flexible and stretchable to conform to the skin or tissue, providing stable power to electronics even under deformation. Furthermore, biodegradability/ bioabsorbability ensures they are both body- and environment-friendly. This review summarizes the recent research progress of BMSCs as wearable and implantable energy storage devices, including the basic requirements and the selection of the components. Additionally, the advanced applications of BMSCs in multifunctional integration systems for real-time health monitoring and medical treatment are introduced, along with the associated challenges and prospects.

Framework for a practical and cost-effective IoT-enhanced structural health monitoring and damage diagnostics system with digital twinning

Abstract Structural Health Monitoring (SHM) has emerged as a viable alternative to traditional visual and non-destructive assessment methods for civil infrastructure. The integration of sensor systems, the Internet of Things (IoT), and advanced data processing has further digitised SHM, leading to the development of Digital Twin (DT) technology, enabling dynamic, real-time simulations for proactive risk prediction and asset management. However, many existing DT-based SHM systems are costly, complex, and resource-intensive, limiting their practicality for small-scale implementations. This study investigates the feasibility of a practical and cost-effective SHM framework enhanced by DT technology for civil infrastructure. The hardware system explored two low-cost displacement sensors: a potentiometer contact sensor and an infrared non-contact sensor. During the static load testing, the potentiometer demonstrated high accuracy and stability, whilst the infrared sensor, despite higher noise, was effective for submillimetre measurements. These sensors were integrated with an IoT-enabled Arduino Nano 33 microcontroller for remote access via the cloud platform. The software system, “ReConTwin”, developed using open-source resources, provides near real-time updates, analysis, and damage diagnosis through an automated post-processing system. The calibrated DT replicated the force–displacement response, accurately estimated the applied load, and closely predicted mid-span strain and crack formations of a Reinforced Concrete (RC) beam specimen subjected to short-term static three-point bending loads in a controlled laboratory setting. The user-friendly design and compatibility with standard commercial computers enhance the accessibility and feasibility of the proposed DT-SHM framework, making it a promising scalable solution for widespread adoption in real-world civil infrastructure applications.

MOF-Based Bioelectronic Supercapacitors.

Metal-organic frameworks (MOFs) represent a highly promising material class for bioelectronic supercapacitors, characterized by their adjustable structures, extensive surface areas, and superior electrochemical properties. This research explores the synthesis and incorporation of MOF-based materials into bioelectronic devices aimed at energy storage and biosensing applications. The focus is on improving the electrochemical performance of MOFs while preserving their structural integrity through functionalization with biocompatible polymers and conductive materials. The resulting MOF-based bioelectronic supercapacitors exhibit significant improvements in specific capacitance, energy density, and cycling stability. Additionally, the inclusion of bioreceptors allows for the simultaneous detection of biochemical signals alongside energy storage, thus enabling innovative applications in wearable electronics and health monitoring systems. These results suggest that MOF-based supercapacitors have the capacity to fulfill energy storage needs while also advancing bioelectronics by merging energy and sensing capabilities.

Fiber‐Shaped, Stretchable Strain Sensors with High Linearity by One‐Step Injection Molding for Structural Health Monitoring

AbstractFiber‐shaped strain sensors have attracted considerable attention due to their exceptional stretchability, conductivity, and flexibility, making them promising for applications in wearable electronics, smart textiles, and structural health monitoring. However, most reported ones based on elastic conductive fibers are fabricated by blending conductive materials with polymers, lacking effective encapsulation to resist environmental interferences such as dust and water. Inspired by the myelin sheath of nerve fibers, a fiber‐shaped, stretchable strain sensor featuring an elastic silicone tube is developed as the encapsulation layer and a conductive hybrid film as the sensing layer. The difference in rebound hysteresis capacity between the silicone tube and the hybrid film effectively enhances the sensor's recovery after stretching. Experimental results demonstrate that the sensors exhibit a linearity of up to 0.9958, a stretchability of 100% strain, and outstanding cyclic stability over 7 000 loading‐unloading cycles. Furthermore, the sensor demonstrates multi‐functionality in monitoring strain, temperature, and pressure while maintaining robust water and dust resistance. Application tests on large‐scale bridges and agricultural greenhouses have validated its effectiveness in structural health monitoring, showcasing the significant potential for use in health monitoring systems. The sensor's environmental resilience facilitates its deployment in real‐world scenarios by minimizing interference from external factors.

Analysis and prospects of the occupational pathology service in the Siberian Federal District

Introduction. At the State level, the Russian Federation pays unprecedented attention to preserving the health of the working population. One of the most important mechanisms for achieving real success is the implementation of new federal-scale national projects "Healthcare" and "Demography". A system for monitoring the health status of the working population and medical examinations in medical centers is important. The study aims to develop proposals for optimizing the occupational pathology service of the Siberian Federal District (SFD) based on the analysis of the health monitoring system for employees. Materials and methods. The researchers analyzed the structure of the occupational pathology service, the reports of the occupational pathology centers of the Siberian Federal District, and the final acts of periodic medical examinations (PME). Results. Based on the analysis of the work of the occupational pathology centers of the Siberian Federal District, specialists optimized the development system of the occupational pathology service in large industrial regions of the country and also developed programs to optimize its work for the early detection of occupational diseases and the routing of patients with occupational sensorineural hearing loss (OSHL). Conclusion. An integrated approach to the study of the frequency and structure of occupational diseases in the Siberian Federal District, the quality of periodic medical examinations in the comparative aspect of occupational pathology centers and private medical organizations (MO) has revealed the main areas of optimization of occupational pathology services in the Siberian Federal District. This will allow timely implementation of preventive and rehabilitation programs, which will ultimately reduce the rates of temporary and permanent disability, mortality, and, consequently, labor loss in working groups and increase the longevity of the working population. Limitations. Geographical specifics: the authors have carried out the analysis on the basis of data from the centers of occupational pathology at the Siberian Federal District, which may limit the applicability of the results to other regions. Ethics. This study did not require the conclusion of an Ethics committee.

Study on the Development of an Intelligent Regional Health Security Monitoring and Emergency Medical Response System in Less Developed Regions

Less developed regions face challenges such as uneven distribution of medical resources, lagging informatization, and insufficient regional synergistic capacity in response to public health emergencies and critical care treatment. Therefore, this study proposes an intelligent regional health and safety monitoring and emergency treatment system, which combines the Internet of Things, big data, cloud computing, and artificial intelligence technologies to realize cross-regional medical resource scheduling, ICU bed management, telemedicine consultation, intelligent first aid scheduling, and infectious disease early warning. This paper first provides a systematic literature review of the development of the global infectious disease early warning system (EWS) and regional collaborative treatment (RCT) model and analyzes the challenges in the construction of infectious disease prevention and control and emergency care systems in less developed regions. Subsequently, a framework for designing a regional collaborative healthcare and emergency management system adapted to the needs of less developed regions is designed for Ganzhou, Jiangxi, China, and key components and innovations are described. Finally, the feasibility of the system is analyzed from four dimensions: technology, economy, society, and policy, and a low-cost and intelligent regional medical collaboration solution is proposed. This study can provide theoretical support and practical reference for the construction of public health management and medical emergency response systems in less developed regions.

Empowering Maternal Healthcare through IoT- Driven Long-Term Monitoring: System Architecture and Assessment

During pregnancy, it is crucial to monitor maternal health to ensure the well-being of both the mother and the unborn baby. Numerous studies conducted thus far have presented a range of maternal health monitoring systems. However, these studies tend to concentrate on particular health concerns and frequently depend on limited-term data- gathering approaches like questionnaires. Furthermore, there is a lack of long-term studies evaluating the requirements and challenges of continuous monitoring. Our team has successfully developed an advanced system that utilizes cutting-edge Inter- net-of-Things (IoT) technology to continuously monitor maternal health both before and after childbirth. This cutting-edge system integrates various data collection mechanisms to precisely record crucial health metrics, including stress levels, sleep pat- terns, and physical activity. We conducted a comprehensive study with actual pregnant women from the Vadodara region of Gujarat State, India, to validate the effectiveness of our system. Our extensive research has unequivocally demonstrated the practicality, energy efficiency, and the data reliability of this system we have established. This system has been proven to be highly effective in monitoring the health of expectant mothers for the entire duration of their nine-month pregnancy. Our maternal health monitoring system, utilizing IoT technology, offers an exceptional framework for ongoing monitoring throughout both pregnancy and the postpartum period. Rest assured that our system is the ultimate solution for monitoring maternal health. It has been implemented and evaluated, providing valuable insights into its feasibility, energy efficiency, and data reliability. This positions it as a strong candidate for improving maternal care and seamless integration with existing healthcare systems.

Opportunities and Challenges in Transformer Neural Networks for Battery State Estimation: Charge, Health, Lifetime, and Safety

Opportunities and Challenges in Transformer Neural Networks for Battery State Estimation: Charge, Health, Lifetime, and Safety

IoT-Based Elderly Health Monitoring System Using Firebase Cloud Computing.

The increasing elderly population presents significant challenges for healthcare systems, necessitating innovative solutions for continuous health monitoring. This study develops and validates an IoT-based elderly monitoring system designed to enhance the quality of life for elderly people. The system features a robust Android-based user interface integrated with the Firebase cloud platform, ensuring real-time data collection and analysis. In addition, a supervised machine learning technology is implemented to conduct prediction task of the observed user whether in "stable" or "not stable" condition based on real-time parameter. The system architecture adopts the IoT layer including physical layer, network layer, and application layer. Device validation is conducted by involving six participants to measure the real-time data of heart-rate, oxygen saturation, and body temperature, then analysed by mean average percentage error (MAPE) to define error rate. A comparative experiment is conducted to define the optimal supervised machine learning model to be deployed into the system by analysing evaluation metrics. Meanwhile, the user satisfaction aspect evaluated by the terms of usability, comfort, security, and effectiveness. IoT-based elderly health monitoring system has been constructed with a MAPE of 0.90% across the parameters: heart-rate (1.68%), oxygen saturation (0.57%), and body temperature (0.44%). In machine learning experiment indicates XGBoost model has the optimal performance based on the evaluation metrics of accuracy and F1 score which generates 0.973 and 0.970, respectively. In user satisfaction aspect based on usability, comfort, security, and effectiveness achieving a high rating of 86.55%. This system offers practical applications for both elderly users and caregivers, enabling real-time monitoring of health conditions. Future enhancements may include integration with artificial intelligence technologies such as machine learning and deep learning to predict health conditions from data patterns, further improving the system's capabilities and effectiveness in elderly care.

Navigating sensor-skin coupling challenges in magnetic-based blood pressure monitoring: Innovations and clinical implications for hypertension and aortovascular disease management.

Navigating sensor-skin coupling challenges in magnetic-based blood pressure monitoring: Innovations and clinical implications for hypertension and aortovascular disease management.

Thermal radiation image detection and optical motion capture in athlete physical health monitoring system simulation: Tissue thermal effects

Thermal radiation image detection and optical motion capture in athlete physical health monitoring system simulation: Tissue thermal effects

Liquid Metal-Based Frequency and Pattern Reconfigurable Yagi Antenna for Pressure Sensing

In this work, a frequency- and pattern-reconfigurable Yagi antenna based on liquid metal (LM) switches is proposed for pressure sensing and health monitoring. The proposed antenna consists of a dipole radiator, a reflector, a director, a dielectric substrate, and four flexible LM switches. Benefitted from the switching effect of the LM switches under external pressure, the frequency and radiation pattern of the antenna can be reconfigured. When the LM switch is fully or partially turned on, the radiation directions of the antenna are bidirectionally end-shot and end-fired, respectively. The operating frequency of the antenna can be tuned from 2.28 GHz to 2.5 GHz. It is shown that a maximum gain of 6 dBi can be obtained. A sample was fabricated and measured, and the experimental results were in good agreement with the simulations. The reconfigurable antenna can be applied in wireless pressure-sensing and health-monitoring systems.

Indicators of Structural Failure: Causes, Diagnosis, and Mitigation Strategies

Abstract: This paper examines the critical factors contributing to structural failures, particularly highlighting moisture ingress, soil instability, and design deficiencies. The evaluation, based on seven case studies, illustrates how these aspects interact to compromise structural integrity. Issues related to moisture, such as sump leaks and inadequate drainage, significantly impact foundation stability and accelerate material deterioration. Soil dynamics, including weak soil profiles and uneven settlement, intensify vulnerabilities, particularly in sloped areas. The study underscores the importance of proactive slope management strategies, such as geogrid reinforcement and turfing. Furthermore, the research highlights the efficacy of Non-Destructive Testing (NDT) and Structural Health Monitoring (SHM) systems in identifying structural problems before they escalate into failures. The findings emphasize the necessity of incorporating geotechnical evaluations and advanced diagnostic tools during the design phase to enhance resilience. This paper advocates for revisions in building regulations, improved construction methodologies, and the development of innovative materials to enhance long-term structural performance and reduce the risk of future failures. The findings contribute to ongoing discussions in structural engineering by offering practical recommendations to improve infrastructure safety and sustainability

Efficient ECG Classification Based on Machine Learning and Feature Selection Algorithm for IoT-5G Enabled Health Monitoring Systems

Efficient ECG Classification Based on Machine Learning and Feature Selection Algorithm for IoT-5G Enabled Health Monitoring Systems

Designing Health Monitoring System for fault prediction in Centrifugal Pump using ML and DL algorithm

The operational dependability of centrifugal pumps holds paramount significance within industrial applications, thereby necessitating the implementation of sophisticated health monitoring systems to proactively identify potential failures. This investigation introduces an innovative Health Monitoring System (HMS) meticulously engineered for centrifugal pumps, utilizing Machine Learning (ML) and Deep Learning (DL) algorithms to augment predictive maintenance capabilities. Our framework amalgamates real-time data acquisition, rigorous feature extraction, and advanced predictive analytics to effectively evaluate pump health. By employing a comprehensive dataset that encompasses operational parameters alongside historical failure records, the research includes executing a variety of ML algorithms, which include Logistic Classifier, Decision Tree Classifier, XGB Classifier, Naïve Bayes Classifier, Random Forest, Support Vector Classifier, and Neural Network, for the classification of centrifugal pump health status. Moreover, the research accentuates the application of sophisticated deep learning techniques, particularly Artificial Neural Networks (ANN), to discern intricate patterns and temporal relationships within the data. Experimental results demonstrate that our proposed HMS markedly enhances fault detection accuracy, accomplishing classification rates that surpass 99%. This system not only enables timely maintenance interventions but also mitigates operational downtime and maintenance expenditures. The research elucidates the potential of advanced AI-driven methodologies in the formulation of intelligent monitoring solutions, ultimately contributing to the sustainability and reliability of centrifugal pump operations in industrial contexts.

Evaluation of health monitoring parameters for automotive pneumatic elastomeric system using soft pressure sensors for enhanced vehicle performance

Abstract In the rapidly evolving automotive industry, the need for reliable and efficient pneumatic elastomeric components necessitates cutting-edge health monitoring methods, given that the pneumatic components are directly connected to dampening properties, ride comfort, vehicle safety, and stability. A novel approach for pneumatic elastomeric component health monitoring utilizing ionic liquid-based soft sensor technology has been proposed, which has the promise to enable real-time health monitoring and prognostics of vehicle systems. The proposed polymer sensor leverages the distinctive characteristics of flexibility, stretchability, and high sensitivity. These properties are critical for precisely measuring load, vertical displacement, air pressure, force locations, and load frequency of the air pressure responsive rubber part. The sensors are attached to three key contact positions: two on the metal cover of the elastomeric component and one on the piston of the component to provide critical information about the rolled and unrolled rubber. These sensors continuously measure essential parameters for health monitoring. The collected data can identify potential issues such as leaks, wear, or structural weaknesses. The finding illustrates the effectiveness of the ionic liquid-based soft sensors in providing precise and reliable data for health monitoring parameters.

Design of an integrated ultrasonic guided wave structural health monitoring system based on multi-channel high-speed synchronous acquisition

Design of an integrated ultrasonic guided wave structural health monitoring system based on multi-channel high-speed synchronous acquisition

Imbalanced Power Spectral Generation for Respiratory Rate and Uncertainty Estimations Based on Photoplethysmography Signal

Respiratory rate (RR) changes in the elderly can indicate serious diseases. Thus, accurate estimation of RRs for cardiopulmonary function is essential for home health monitoring systems. However, machine learning (ML) algorithm errors embedded in health monitoring systems can be problematic in medical decision-making because some data have much larger sample sizes in the training set than others. This difference in sample size implies biosignal data imbalance. Therefore, we propose a novel methodology that combines bootstrap-based imbalanced continuous power spectral generation (IPSG) with ML approaches to estimate RRs and uncertainty to address data imbalance. The sample differences between normal breathing (12–20 breaths per minute (brpm)), dyspnea (≥20 brpm), and hypopnea (<8 brpm) show significant data imbalance, which can affect the learning of ML algorithms. Hence, the normal breathing part with a large amount of data is well-trained. In contrast, the dyspnea and hypopnea parts with relatively fewer data are not well-trained, and this data imbalance makes it difficult to estimate the reference variables of the actual dyspnea and hypopnea data parts, thus generating significant errors. Hence, we apply ML models by mixing artificial feature curves generated using a bootstrap model with the original feature curves to estimate RRs and solve this problem. As a result, the nonparametric bootstrap approach significantly increases the number of artificial feature curves. The generated artificial feature curves are selectively utilized in the highly imbalanced parts. Therefore, we confirm that IPSG is efficiently trained to predict the complex nonlinear relationship between the feature vectors obtained from the photoplethysmography signal and the reference RR. The proposed methodology shows more accurate prediction performance and uncertainty. Combining the proposed Gaussian process regression (GPR) with IPSG based on the Beth Israel Deaconess Medical Center dataset, the mean absolute error of the RR is 0.79 and 1.47 brpm. Our approach achieves high stability and accuracy by randomly mixing original and artificial feature curves. The proposed GPR-IPSG model can improve the performance of clinical home-based monitoring systems and design a reliable framework.

Gas Path Fault Diagnosis Method Under Small Samples With Interclass Imbalance

Abstract Current data-driven methods for diagnosing gas path faults in aero-engines often rely on large, costly fault sample sets and face challenges related to class imbalances. These include disparities in the quantity of normal and fault data, differences among fault types, and variations in fault severity levels. This paper proposes a novel generative model, TL-GMVAE, which integrates Gaussian mixture models (GMM) with variational auto-encoders (VAE) and incorporates a transfer learning (TL) strategy. Using a large dataset of normal operational data, the VAE learns latent feature mappings of engine behavior and establishes a joint probability distribution across sensor measurements. To account for complexity in engine operating conditions, the GMM is used as the sampling distribution of the VAE. This enhances the model’s ability to represent diverse operating scenarios. The pretrained model is then fine-tuned with a small dataset of gas path fault data, transferring knowledge to fault domains. Each fault-specific TL-GMVAE model serves as an independent generator for synthetic fault samples. The proposed approach is validated using several established classifiers. The impact of different Fault-Normal ratios and imbalances across fault categories on classification accuracy is analyzed. Additionally, the robustness of the method to individual engine variability is evaluated. Results demonstrate that the TL-GMVAE generates high-quality fault samples and significantly improves fault diagnosis accuracy. These findings highlight its potential application in aero-engine health monitoring and fault diagnosis systems.