Health Monitoring Research Articles

Egocentric Behavior Analysis Based on Object Relationship Extraction with Graph Transfer Learning for Cognitive Rehabilitation Support

Recognizing human behavior is essential for early interventions in cognitive rehabilitation, particularly for older adults. Traditional methods often focus on improving third-person vision but overlook the importance of human visual attention during object interactions. This study introduces an egocentric behavior analysis (EBA) framework that uses transfer learning to analyze object relationships. Egocentric vision is used to extract features from hand movements, object detection, and visual attention. These features are then used to validate hand-object interactions (HOI) and describe human activities involving multiple objects. The proposed method employs graph attention networks (GATs) with transfer learning, achieving 97% accuracy in categorizing various activities while reducing computation time. These findings suggest that integrating the EBA with advanced machine learning methods could revolutionize cognitive rehabilitation by offering more personalized and efficient interventions. Future research can explore real-world applications of this approach, potentially improving the quality of life for older adults through better cognitive health monitoring.

Performance Assessment of a Permeable Reactive Barrier on Reducing Groundwater Transport of Nitrate from an Onsite Wastewater Treatment System

Elevated concentrations of nitrate in potable water supplies have been linked to negative health outcomes such as methemoglobinemia and various cancers. Groundwater can become contaminated with nitrate from sources including onsite wastewater treatment systems (OWTSs). A groundwater well down-gradient from an OWTS serving an elementary school in Eastern North Carolina USA had 15 consecutive water samples collected over a 5-year period that exceeded the maximum contaminant level of 10 mg/L for nitrate. Corrective actions were required. A permeable reactive barrier (PRB) filled with woodchips was installed between the OWTS drainfield and the contaminated well. The concentration of nitrate in groundwater from the well steadily decreased after the PRB was installed, and a significant (p = 0.001) inverse correlation (−0.859) was observed between the mean annual nitrate concentration and years after the PRB. The nitrate concentration in groundwater from the well has been below 10 mg/L for the last 17 consecutive sampling events. The median nitrate concentration in the well was significantly lower (p = 0.007) post (6.93 mg/L) relative to pre (12.66 mg/L) PRB. The PRB has not required any maintenance over the past 10 years. The implemented PRB directly influences the sampling results from a monitoring well, but it is not necessarily confirmed that it intercepts the entire groundwater flow or fully prevents aquifer contamination. To confirm this, additional monitoring wells would need to be installed. This research has shown that PRBs can be an effective, low-maintenance, best-management practice to reduce the groundwater transport of nitrate.

Thermoelectric porous laser-induced graphene-based strain-temperature decoupling and self-powered sensing

Despite rapid developments of wearable self-powered sensors, it is still elusive to decouple the simultaneously applied multiple input signals. Herein, we report the design and demonstration of stretchable thermoelectric porous graphene foam-based materials via facile laser scribing for self-powered decoupled strain and temperature sensing. The resulting sensor can accurately detect temperature with a resolution of 0.5°C and strain with a gauge factor of 1401.5. The design of the nanocomposites also explores the synergistic effect between the porous graphene and thermoelectric components to greatly enhance the Seebeck coefficient by almost four times (from 9.703 to 37.33 μV/°C). Combined with the stretchability of 45%, the self-powered sensor platform allows for early fire detection in remote settings and accurate and decoupled monitoring of temperature and strain during the wound healing process in situ. The design concepts from this study could also be leveraged to prepare multimodal sensors with decoupled sensing capability for accurate multi-parameter detection towards health monitoring.

High-performance solid-state proton gating membranes based on two-dimensional hydrogen-bonded organic framework composites

Biological ion channels exhibit strong gating effects due to their zero-current closed states. However, the gating capabilities of artificial nanochannels have typically fallen short of biological channels, primarily owing to the larger nanopores that fail to completely block ion transport in the off-states. Here, we demonstrate solid-state hydrogen-bonded organic frameworks-based membranes to achieve high-performance ambient humidity-controlled proton gating, accomplished by switching the proton transport pathway instead of relying on conventional ion blockage/activation effects. Density functional theory calculations reveal that the reversible formation and disruption of humidity-induced water bridges within the frameworks facilitates the switching of proton transport mode from the adsorption site hopping to the Grotthuss mechanism. This transition, coupled with the introduction of bacterial cellulose to enhance desorption/adsorption of water clusters, enables us to achieve a superior proton gating ratio of up to 5740, surpassing state-of-the-art solid-state gating devices. Moreover, the developed membrane operates entirely on solid-state principles, rendering it highly versatile for a myriad of applications from environmental detection to human health monitoring. This study offers perspectives for the design of efficient proton gating systems.

Transfer Learning-Based Health Monitoring of Robotic Rotate Vector Reducer Under Variable Working Conditions

Due to their precision, compact size, and high torque transfer, Rotate vector (RV) reducers are becoming more popular in industrial robots. However, repetitive operations and varying speed conditions mean that these components are prone to mechanical failure. Therefore, it is important to develop effective health monitoring (HM) strategies. Traditional approaches for HM, including those using vibration and acoustic emission sensors, encounter such challenges as noise interference, data inconsistency, and high computational costs. Deep learning-based techniques, which use current electrical data embedded within industrial robots, address these issues, offering a more efficient solution. This research provides transfer learning (TL) models for the HM of RV reducers, which eliminate the need to train models from scratch. Fine-tuning pre-trained architectures on operational data for the three different reducers of health conditions, which are healthy, faulty, and faulty aged, improves fault classification across different motion profiles and variable speed conditions. Four TL models, EfficientNet, MobileNet, GoogleNet, and ResNET50v2, are considered. The classification accuracy and generalization capabilities of the suggested models were assessed across diverse circumstances, including low speed, high speed, and speed fluctuations. Compared to the other models, the proposed EfficientNet model showed the most promising results, achieving a testing accuracy and an F1-score of 98.33% each, which makes it best suited for the HM of robotic reducers.

Dome-Structure Array from Pre-Strained Extendable Mesh for Tactile Sensing Without Crosstalk and Lateral Strain Interference.

Flexible tactile sensors have received significant attention for use in wearable applications such as robotics, human-machine interfaces, and health monitoring. However, conventional tactile sensors face challenges in accurately measuring pressure because vertical deformation is induced by Poisson's ratio in situations where lateral strain is applied. This study shows a strain-insensitive flexible tactile sensor array without the crosstalk effect using a highly stretchable mesh. This sensor is fabricated by assembling a sensing layer in which sensing cells form in each hole of an elastomer mesh and liquid-metal-based stretchable electrode layers. Stretching deforms the soft mesh layer with little effect on the rigid sensing cell array, which results in the sensor being insensitive to uniaxial strain. In addition, each sensing cell is formed in a dome shape, which resulted in a sensor exhibiting high sensitivity (7.80 kPa-1) over a wide sensing range (<160 kPa). The proposed design also allows each sensing cell to be electrically separated, enabling the pressure measurements without cell-to-cell crosstalk. Based on these characteristics, strain-insensitive pressure monitoring is demonstrated to prevent carpal/cubital tunnel syndrome by attaching the device to the joints, which suggests its potential application in healthcare.

Nonalcoholic Fatty Liver Disease Increases the Risk of Lung Abscess: Findings from a Nationwide Cohort Study

Objectives: This study aimed to investigate the association between nonalcoholic fatty liver disease (NAFLD), assessed by the Fatty Liver Index (FLI), and the occurrence of lung abscess within a large population-based cohort. Method: We conducted a nationwide retrospective study using data from 367,930 subjects who underwent National Health check-ups between 2009 and 2018. Cox proportional hazards regression was performed to evaluate the association between the FLI and the incidence of lung abscess and community-acquired pneumonia (CAP) after adjusting for age, sex, and relevant covariates. Results: Among the study population, 455 (0.12%) and 44,934 (12.2%) patients were diagnosed with lung abscesses and CAP, respectively. The cumulative incidence of lung abscess was higher in individuals with elevated FLI values (FLI &lt; 30, 0.10%; 30 ≤ FLI &lt; 60, 0.16%; FLI ≥ 60, 0.18%; p &lt; 0.001), whereas the incidence of CAP decreased across FLI groups (FLI &lt; 30, 12.4%; 30 ≤ FLI &lt; 60, 12.3%; FLI ≥ 60, 11.0%; p &lt; 0.001). After adjusting for covariates, the risk of lung abscess significantly increased in the 30 ≤ FLI &lt; 60 (Hazard ratio (HR) = 1.26; 95% confidence interval (CI), 0.95–1.68; p = 0.115) and the FLI ≥ 60 (HR = 1.67; 95% CI, 1.37–2.29; p &lt; 0.001) groups, although the risk of CAP was relatively small in both groups (30 ≤ FLI &lt; 60; HR = 1.06; 95% CI, 1.03–1.09; p &lt; 0.001) (FLI ≥ 60; HR = 1.13; 95% CI, 1.08–1.12; p &lt; 0.001). Conclusions: Our study provides compelling evidence supporting a potential link between NAFLD, as measured by FLI, and the incidence of lung abscess. These findings suggest the importance of vigilant monitoring of respiratory health in patients with NAFLD and emphasise the need for early detection of possible complications.

Dimension Reduction of MUSIC Database for Tailored Clustering Using Lasso

The tailored clustering enabled regionalization (TCER) framework has shown that the prediction error of design parameters at a target site can be reduced by constructing a transformation model from a cluster that only contains sites with geotechnical properties similar to the target site. These sites are retrieved from a global/regional database. However, the similarity between any two sites will reduce when the number of properties increases. TCER will be ineffective if too many properties are included in the database (e.g., structural health monitoring and remote sensing databases). The current study presents a least absolute shrinkage and selection operator for databases with incomplete records (denoted by HMLasso; a dimension reduction method) to improve the performance of TCER in high dimensional databases. HMLasso is utilized to construct a dimensionally reduced database, which includes only the properties relevant to the design parameters, from a high-dimensional database. TCER is then adopted to retrieve a cluster from the dimensionally reduced database for inferring the design parameters at a target site. The capability of HMLasso to enhance the performance of TCER in terms of identifying clusters similar to the target site and reducing the prediction error of design parameters are demonstrated using real-world geotechnical databases.

Technological Evolution of Architecture, Engineering, Construction, and Structural Health Monitoring of Bridges in Peru: History, Challenges, and Opportunities

Technological Evolution of Architecture, Engineering, Construction, and Structural Health Monitoring of Bridges in Peru: History, Challenges, and Opportunities

Coplanar Pattern and Temperature Transient Control in Intelligent Wearable Multi‐Color Alternating Current Electroluminescence Devices

AbstractFlexible alternating current electroluminescence (ACEL) devices integrated into textiles are gaining significant attention for their potential in lighting displays and health monitoring applications. Traditional challenges include high‐voltage “breakdown” and limited color output due to the inherent properties of ZnS:Cu. This study introduces a novel multi‐color ACEL device featuring a fluorescent dye color conversion layer alongside a robust protective layer designed to enhance device stability. The optimal ratio of dielectric layer concentration and protective layer thickness is systematically investigated to mitigate the risk of “breakdown”. Utilizing the principles of photoluminescence and electroluminescence, luminous electronic textile devices is successfully developed that exhibit both purple and green luminescence. Additionally, integration with a temperature sensor enables the device to serve as a health‐monitoring tool by signaling changes in body temperature. This research delineates the protective capabilities of the protective layer and the efficacy of the color conversion mechanism in maintaining consistent brightness under various conditions. The findings suggest a viable pathway for broadening applications and potentially accelerating the commercialization of wearable electroluminescent technologies.

Robotics in Elderly Healthcare: A Qualitative Analysis of 20 Recent European Research Projects

Studies foresee a dramatic increase in the elderly population of Western Europe over the next decades, putting pressure on healthcare systems. Healthcare robots are developed to facilitate independent living for elderly people. This paper aims to provide a qualitative analysis of recent projects in healthcare robotics (2008-2024) and proposes new research directions for healthcare robots for older adults. We provide an overview of current research and a roadmap for upcoming research. Our study began with a literature search using four databases. Searches were performed for articles from research projects containing the words “elderly care”, “assisted aging”, “health monitoring”, or “elderly health”. Additional exclusion criteria were used to focus on elderly healthcare and utilization of commercial robotic systems. Resulting from this endeavor, 20 recent research projects are described and categorized in this paper. Then, these projects were analyzed using thematic analysis. Our findings are summarized in common themes: most projects have a strong bias towards care robots’ functionalities; robots are often seen as outsiders in care settings; there is an emphasis on robots as commercial products; and there is some limited attention to the design and ethical aspects of care robots, but very little attention to their legal aspects. The paper concludes with key points representing a roadmap for future research addressing robotics for the elderly.

Preserving History: Assessments and Climate Adaptations at the House of the Seven Gables in Salem, Massachusetts, USA

Salem, Massachusetts, is one of the oldest cities in the United States (1629) and its coastal location on the Atlantic helped create one of the wealthiest cities in America during the late 18th century, but today its coastal location threatens many of its buildings due to sea level rise and increased storm activity. The House of the Seven Gables, a National Historic Landmark District, consists of five important historic buildings, the most famous being The Turner Ingersoll Mansion (1668), more commonly known as The House of the Seven Gables. Considered one of the most important houses in America, it is also one of the most threatened historic buildings due to its location on Salem’s harbor. The House of the Seven Gables conducted a two-year study funded by Massachusetts Coastal Zone Management to evaluate the risks posed by climate change. This process included the use of data from groundwater monitoring wells and a tidal gauge installed on-site, along with soil samples and a detailed survey base plan including topography and subsurface infrastructure. The project team then used the Massachusetts Coastal Flood Risk Model (MC-FRM) to assess climate change impacts on the site in 2030, 2050, and 2070, and then created a plan for adaptations that should be implemented before those risks materialize. Strategies for adapting to storm surges, increasing groundwater, and intense surface water runoff were evaluated for their effectiveness and appropriateness for the historic site. The conclusion of the study resulted in a five-phase plan ending in the managed retreat of the historic buildings to higher ground on the existing site. This article goes beyond other research that suggests coastal retreats by demonstrating how to quantitatively evaluate current and future coastal issues with predictive models and how to set viable dates for adaptive solutions and a managed retreat.

An Over-Actuated Hexacopter Tilt-Rotor UAV Prototype for Agriculture of Precision: Modeling and Control

This paper focuses on the modeling, control, and simulation of an over-actuated htr. This configuration implies that two of the six actuators are independently tilted using servomotors, which provide high maneuverability and reliability. This approach is predicted to maintain zero pitch throughout the trajectory and is expected to improve the aircraft’s steering accuracy. This arrangement is particularly beneficial for pa applications where accurate monitoring and management of crops are critical. The enhanced maneuverability allows for precise navigation in complex vineyard environments, enabling the uav to perform tasks such as aerial imaging and crop health monitoring. The employed control architecture consists of cascaded p-pid controllers using the slc method on the five controlled dof. Simulated results using Gazebo demonstrate that the htr achieves stability and maneuverability throughout the flight path, significantly improving precision agriculture practices. Furthermore, a comparison of the htr with a traditional hexacopter validates the proposed approach.

Deep guided wave convolution neural network committee-based multi-path fusion diagnosis method for fatigue corner crack

Accurate diagnosis of crack size is a critical task for guided wave (GW)-based structural health monitoring (SHM). However, fatigue cracks would have complex morphology due to complex structural geometries and loading conditions, in which multiple dimension characteristics, like crack length, depth, and angle are involved. It is challenging to quantitatively evaluate these characteristics with GW signals from a single excitation-sensing path. This paper proposes a novel deep guided wave convolution neural network (CNN) committee-based multi-path GW fusion diagnosis method, aiming at quantitative evaluation of dimension characteristics of the complex fatigue damage. GW signals from multiple excitation-sensing paths are synthesized as a high-dimension input image to enhance the effects of the fatigue crack. Besides, the deep GW-CNN committee is developed for damage quantification, in which each GW-CNN is trained with a portion of the training dataset to reduce the impact of small sample size. The proposed method is validated on fatigue tests of landing gear beam specimens under variable amplitude loading, which is designed referring to the critical region of a real aircraft and its fatigue crack presents as a corner crack. The leave-one-out validation results show the effectiveness of the proposed method, especially improvements in the diagnosis of small cracks.

Simultaneous vibration and soil moisture sensing using a single mode fiber for structural health monitoring applications

A dual-purpose single mode optical fiber sensor was developed for simultaneous soil moisture and structural health monitoring. Unmodified G655 SMF with polarization coupled phase components was used to detect environmental changes due to ground movement and moisture content variations. Spectral distribution profiles of the baseband frequencies below 10 Hz were analyzed for structural health monitoring, while resonant peak frequencies higher than 110 Hz had notable dependence on the damping effect of moisture on the spectral peak intensity of the detected acoustic waves. Using these peaks, moisture content was measured within a root mean square error value of +/−0.04. The sensor demonstrates a critical resource optimization tool for distributed sensing applications and monitoring in PON systems.

Non-Stationary Wind Loading Identification for Large Transmission Tower Based on Dynamic Finite-Element Model Updating

An effective approach to deal with the structural failures of transmission towers in tornadic events is to develop good structural health monitoring (SHM) systems for them. However, the strategy for SHM of transmission towers against tornados should be different from the conventional atmospheric boundary layer (ABL) winds oriented ones, as the non-stationary nature of the tornados significantly differentiates them from the ABL winds. To satisfy the need of obtaining the highly time-varying whole-field stress on the structure in the course of the tornadic event for effective SHM, an innovative transient tornadic load distribution identification method is proposed for use, which is based on the field structural mode shape measurement and dynamic finite-element (FE) model updating. Via a numerical case study, it is noted that good effectiveness is achieved for the new load distribution identification method. Employing the Modal Assurance Criteria based FE model updating technique, the new method has the advantage of being easily embraced in practical SHM systems. It is found that when the transient tornadic velocity profile to be identified is noticeably different from the mode shape of the structure without undertaking external loads, the identified load pattern is very accurate for the new approach.

Guided Waves in Composite Overwrapped Pressure Vessels and Considerations for Sensor Placement Towards Structural Health Monitoring – An Experimental Study

Abstract The utilization of composite overwrapped pressure vessels (COPVs) to store hydrogen, especially at high pressures, is gaining more popularity due to their lightweight design and high storage density, offering significant economic advantages. However, the presence of material defects or fatigue can lead to critical failures, requiring an innovative and robust approach to ensure safe operation and system integrity. Developing a continuous structural health monitoring (SHM) system for COPVs can provide comprehensive real-time information about their condition, facilitating a shift away from periodic inspections. This study scrutinizes the behavior of guided waves (GWs) within COPVs to design a sensor network for damage detection and localization. First, the dispersive and multimodal propagation behavior of GWs is experimentally investigated. Subsequently, important parameters for the network design are derived and finally a sensor network consisting of fifteen piezoelectric transducers is designed to cover the entire cylindrical area. The effectiveness is then evaluated experimentally by placing artificial defects on the surface of the COPV. The multi-layered dataset of GW signals was analyzed using both commonly used ultrasonic features (e.g., amplitude, frequency, time of flight) as well as statistical features (kurtosis, skewness, variance, etc.). These features were utilized to compute a damage index, and the effectiveness of the detection performance was assessed using receiver operating characteristic curves. It can be seen that some features are more sensitive and robust under varying experimental conditions. The results show that ultrasonic GW SHM system is a promising solution for damage detection and localization in COPVs.

Research Advanced in Speech Emotion Recognition based on Deep Learning

Speech Emotion Recognition (SER)s burgeoning significance within intelligent systems is underscored by its transformative impact across various fields, from human-computer interaction, and virtual assistants to mental health monitoring. Over the rapid development of this technology in the past two decades, studies have continuously confronted and overcome kinds of real-world challenges, such as data scarcity, environmental noise, and cross-language differences. This survey focuses on recent innovations in SER, particularly deep learning architectures, and synthetic data augmentation, and addresses recent developments in cross-domain and multimodal SER techniques, which have expanded the applicability of SER to more diverse datasets.

Design and Application of Uniaxially Sensitive Stress Sensor

Current stress sensors for microsystems face integration challenges and complex signal decoding. This paper proposes a real-time uniaxially sensitive stress sensor. It is obtained by simple combinations of bar resistors using their sensitivity differences in different axes. With the aid of a Wheatstone bridge, the sensor can measure the uniaxial stress magnitude by simple calibration of the stress against the output voltage and detect the bidirectional stress magnitude and direction in a micro-zone by simple rotation. The theoretical sensitivity obtained from simulation is 0.087 mV/V·MPa when the X-bridge is stressed in the X-direction under 1 V of excitation, and the test sensitivity of the X-bridge prepared in this paper is 0.1 mV/V·MPa. The design is structurally and procedurally simple, exhibits better temperature stability, and reduces interface requirements, making it suitable for the health monitoring of multi-chip microsystem chips.

A novel wearable device integrating ECG and PCG for cardiac health monitoring

The alarming prevalence and mortality rates associated with cardiovascular diseases have emphasized the urgency for innovative detection solutions. Traditional methods, often costly, bulky, and prone to subjectivity, fall short of meeting the need for daily monitoring. Digital and portable wearable monitoring devices have emerged as a promising research frontier. This study introduces a wearable system that integrates electrocardiogram (ECG) and phonocardiogram (PCG) detection. By ingeniously pairing a contact-type PZT heart sound sensing structure with ECG electrodes, the system achieves the acquisition of high-quality ECG and PCG signals. Notably, the signal-to-noise ratios (SNR) for ECG and PCG signals were measured at 44.13 dB and 30.04 dB, respectively, demonstrating the system’s remarkable stability across varying conditions. These collected signals were subsequently utilized to derive crucial feature values, including electromechanical delay (EMD), left ventricular ejection time (LVET), and pre-ejection period (PEP). Furthermore, we collected a dataset comprising 40 cases of ECG and PCG signals, enabling a comparative analysis of these three feature parameters between healthy individuals and coronary heart disease patients. This research endeavor presents a significant step forward in the realm of early, non-invasive, and intelligent monitoring of cardiovascular diseases, offering hope for earlier detection and more effective management of these life-threatening conditions.