Search Results (946)

Deep learning (DL)-based Human Activity Recognition (HAR) using wearable inertial measurement unit (IMU) sensors can revolutionize continuous health monitoring and early disease prediction. However, most DL HAR models are untested in their robustness to real-world variability, as they are trained on limited lab-controlled data. In this study, we isolated and analyzed the effects of the subject, device, position, and orientation variabilities on DL HAR models using the HARVAR and REALDISP datasets. The Maximum Mean Discrepancy (MMD) was used to quantify shifts in the data distribution caused by these variabilities, and the relationship between the distribution shifts and model performance was drawn. Our HARVAR results show that different types of variability significantly degraded the DL model performance, with an inverse relationship between the data distribution shifts and performance. The compounding effect of multiple variabilities studied using REALDISP further underscores the challenges of generalizing DL HAR models to real-world conditions. Analyzing these impacts highlights the need for more robust models that generalize effectively to real-world settings. The MMD proved valuable for explaining the performance drops, emphasizing its utility in evaluating distribution shifts in HAR data. Full article

With the rapid development of sports technology, smart wearable devices play a crucial role in athletic training and health management. Sports fatigue is a key factor affecting athletic performance. Using smart wearable devices to detect the onset of fatigue can optimize training, prevent excessive fatigue and resultant injury, and increase efficiency and safety. However, current wearable sensing devices are often uncomfortable and imprecise. Furthermore, stable methods for fatigue detection are not yet established. To address these challenges, this paper introduces 3D printing and deep learning to design a smart wearable sensing device to detect different states of sports fatigue. First, to meet the need for comfort and improved accuracy in data collection, we utilized reverse engineering and additive manufacturing technologies. Second, we designed a prototype based on the long short-term memory (LSTM) neural network to analyze the collected bioelectrical signals for the identification of sports fatigue states and the extraction of related indicators. Finally, we conducted a large number of numerical experiments. The results demonstrated that our prototype and related equipment could collect signals and mine information as well as identify indicators associated with sports fatigue in the signals, thereby improving accuracy in the classification of fatigue states. Full article

The rapid advancement of intelligent technologies, including sensing devices, artificial intelligence, and the Internet of Things, has significantly accelerated the progress in industrial technology, particularly within the medical enterprise sector. Wearable innovations for health management have introduced novel approaches to physiological monitoring and early disease detection, contributing to an improved quality of life. In the context of sustainable development, wearable devices demonstrate considerable potential for supporting long-term healthcare solutions, particularly in the post-pandemic era, where the demand for smart health solutions continues to rise. This study aims to identify critical product design indicators for wearable devices that align with sustainable health management goals. Utilizing expert questionnaires and employing a combination of the Fuzzy Delphi Method and the DEMATEL-based Analytic Network Process (ANP), this research systematically evaluates the key factors influencing wearable device design. The findings highlight three primary aspects, six criteria, and 16 design indicators, with pivotal factors including “Compatibility”, “Foresight”, “Integration”, “Comfort”, “Appearance”, “Customization”, and “Intelligence”. These indicators provide a comprehensive framework for developing wearable devices that address diverse user needs while promoting individual well-being and sustainable health management. This study offers valuable insights into the design and development of wearable devices that support sustainable healthcare practices, advance social responsibility, and strengthen preventive care initiatives. Full article

Background: Artificial Intelligence (AI) technologies are now essential as the agenda of nutrition research expands its scope to look at the intricate connection between food and health in both an individual and a community context. AI also helps in tracing and offering solutions in dietary assessment, personalized and clinical nutrition, as well as disease prediction and management, such as cardiovascular diseases, diabetes, cancer, and obesity. This review aims to investigate and assess the different applications and roles of AI in nutrition and research and understand its potential future impact. Methods: We used PubMed, Scopus, Web of Science, Google Scholar, and EBSCO databases for our search. Results: Our findings indicate that AI is reshaping the field of nutrition in ways that were previously unimaginable. By enhancing how we assess diets, customize nutrition plans, and manage complex health conditions, AI has become an essential tool. Technologies like machine learning models, wearable devices, and chatbot applications are revolutionizing the accuracy of dietary tracking, making it easier than ever to provide tailored solutions for individuals and communities. These innovations are proving invaluable in combating diet-related illnesses and encouraging healthier eating habits. One breakthrough has been in dietary assessment, where AI has significantly reduced errors that are common in traditional methods. Tools that use visual recognition, deep learning, and mobile applications have made it possible to analyze the nutrient content of meals with incredible precision. Conclusions: Moving forward, collaboration between tech developers, healthcare professionals, policymakers, and researchers will be essential. By focusing on high-quality data, addressing ethical challenges, and keeping user needs at the forefront, AI can truly revolutionize nutrition science. The potential is enormous. AI is set to make healthcare not only more effective and personalized but also more equitable and accessible for everyone. Full article

MEMS acoustic sensors are a type of physical quantity sensor based on MEMS manufacturing technology for detecting sound waves. They utilize various sensitive structures such as thin films, cantilever beams, or cilia to collect acoustic energy, and use certain transduction principles to read out the generated strain, thereby obtaining the targeted acoustic signal’s information, such as its intensity, direction, and distribution. Due to their advantages in miniaturization, low power consumption, high precision, high consistency, high repeatability, high reliability, and ease of integration, MEMS acoustic sensors are widely applied in many areas, such as consumer electronics, industrial perception, military equipment, and health monitoring. Through different sensing mechanisms, they can be used to detect sound energy density, acoustic pressure distribution, and sound wave direction. This article focuses on piezoelectric, piezoresistive, capacitive, and optical MEMS acoustic sensors, showcasing their development in recent years, as well as innovations in their structure, process, and design methods. Then, this review compares the performance of devices with similar working principles. MEMS acoustic sensors have been increasingly widely applied in various fields, including traditional advantage areas such as microphones, stethoscopes, hydrophones, and ultrasound imaging, and cutting-edge fields such as biomedical wearable and implantable devices. Full article

An origami-based tactile sensory ring utilizing multilayered conductive paper substrates presents an innovative approach to wearable health applications. By harnessing paper’s flexibility and employing origami folding, the sensors integrate structural stability and self-packaging without added encapsulation layers. Knot-shaped designs create loop-based systems that secure conductive paper strips and protect sensing layers. Demonstrating a sensitivity of 3.8 kPa⁻¹ at subtle pressures (0–0.05 kPa), the sensors detect both minimal stimuli and high-pressure inputs. Electrical modeling of various origami configurations identifies designs with optimized performance with a pentagon knot offering higher sensitivity to support high-sensitivity needs. Meanwhile a square knot provides greater precision and quicker recovery, balancing sensitivity and stability for real-time feedback devices. The enhanced elastic modulus from folds remains within human skin’s elasticity range, ensuring comfort. Applications include grip strength monitoring and pulse rate detection from the thumb, capturing pulse transit time (PTT), an essential cardiovascular biomarker. This design shows the potential of origami-based tactile sensors in creating versatile, cost-effective wearable health monitoring systems. Full article

The early monitoring of cardiovascular biomarkers is essential for the prevention and management of some cardiovascular diseases. Here, we present a novel, compact, and highly integrated skin electrode as a mechanical–electrochemical dual-model E-skin, designed for the real-time monitoring of heart rate and sweat ion concentration, two critical parameters for assessing cardiovascular health. As a pressure sensor, this E-skin is suitable for accurate heart rate monitoring, as it exhibits high sensitivity (25.2 pF·kPa⁻¹), a low detection limit of 6 Pa, and a rapid response time of ~20 ms, which is attributed to the iontronic sensing interface between the skin and the electrode. Additionally, the electrode functions as a potassium ion-selective electrode based on chemical doping, achieving an enhanced response of 11 mV·mM⁻¹. A test based on the real-time monitoring of a subject riding an indoor bike demonstrated the device’s capability to monitor heart rate and sweat potassium ion levels reliably and accurately. This advancement in wearable technology offers significant potential for enhancing patient care based on the early detection and proactive management of cardiovascular conditions. Full article

Federated learning (FL) is revolutionizing healthcare by enabling collaborative machine learning across institutions while preserving patient privacy and meeting regulatory standards. This review delves into FL’s applications within smart health systems, particularly its integration with IoT devices, wearables, and remote monitoring, which empower real-time, decentralized data processing for predictive analytics and personalized care. It addresses key challenges, including security risks like adversarial attacks, data poisoning, and model inversion. Additionally, it covers issues related to data heterogeneity, scalability, and system interoperability. Alongside these, the review highlights emerging privacy-preserving solutions, such as differential privacy and secure multiparty computation, as critical to overcoming FL’s limitations. Successfully addressing these hurdles is essential for enhancing FL’s efficiency, accuracy, and broader adoption in healthcare. Ultimately, FL offers transformative potential for secure, data-driven healthcare systems, promising improved patient outcomes, operational efficiency, and data sovereignty across the healthcare ecosystem. Full article

Wearable devices have potential applications in health monitoring and personalized healthcare due to their portability, conformability, and excellent mechanical flexibility. However, their performance is often limited by instability in acidic or basic environments. In this study, a flexible sensor with excellent stability based on a GaN nanoplate was developed through a simple and controllable fabrication process, where the linearity and stability remained at almost 99% of the original performance for 40 days in an air atmosphere. Moreover, perfect stability was also demonstrated in acid–base environments, with pH values ranging from 1 to 13. Based on its excellent stability and piezotronic performance, a flexible device for motion monitoring was developed, capable of detecting motions such as finger, knee, and wrist bending, as well as swallowing. Furthermore, gesture recognition and intelligent fall monitoring were explored based on the bending properties. In addition, an intelligent fall warning system was proposed for the personalized healthcare application of elders by applying machine learning to analyze data collected from typical activities. Our research provides a path for stable and flexible electronics and personalized healthcare applications. Full article

Emotion recognition through artificial intelligence and smart sensing of physical and physiological signals (affective computing) is achieving very interesting results in terms of accuracy, inference times, and user-independent models. In this sense, there are applications related to the safety and well-being of people (sexual assaults, gender-based violence, children and elderly abuse, mental health, etc.) that require even more improvements. Emotion detection should be done with fast, discrete, and non-luxurious systems working in real time and real life (wearable devices, wireless communications, battery-powered). Furthermore, emotional reactions to violence are not equal in all people. Then, large general models cannot be applied to a multi-user system for people protection, and health and social workers and law enforcement agents would welcome customized and lightweight AI models. These semi-personalized models will be applicable to clusters of subjects sharing similarities in their emotional reactions to external stimuli. This customization requires several steps: creating clusters of subjects with similar behaviors, creating AI models for every cluster, continually updating these models with new data, and enrolling new subjects in clusters when required. An initial approach for clustering labeled data compiled (physiological data, together with emotional labels) is presented in this work, as well as the method to ensure the enrollment of new users with unlabeled data once the AI models are generated. The idea is that this complete methodology can be exportable to any other expert systems where unlabeled data are added during in-field operation and different profiles exist in terms of data. Experimental results demonstrate an improvement of 5% in accuracy and 4% in F1 score with respect to our baseline general model, along with a 32% to 58% reduction in variability, respectively. Full article

Electroencephalography (EEG) has emerged as a pivotal tool in both research and clinical practice due to its non-invasive nature, cost-effectiveness, and ability to provide real-time monitoring of brain activity. Wearable EEG technology opens new avenues for consumer applications, such as mental health monitoring, neurofeedback training, and brain–computer interfaces. However, there is still much to verify and re-examine regarding the functionality of these devices and the quality of the signal they capture, particularly as the field evolves rapidly. In this study, we recorded the resting-state brain activity of healthy volunteers via three consumer-grade EEG devices, namely PSBD Headband Pro, PSBD Headphones Lite, and Muse S Gen 2, and compared the spectral characteristics of the signal obtained with that recorded via the research-grade Brain Product amplifier (BP) with the mirroring montages. The results showed that all devices exhibited higher mean power in the low-frequency bands, which are characteristic of dry-electrode technology. PSBD Headband proved to match BP most precisely among the other examined devices. PSBD Headphones displayed a moderate correspondence with BP and signal quality issues in the central group of electrodes. Muse demonstrated the poorest signal quality, with extremely low alignment with BP. Overall, this study underscores the importance of considering device-specific design constraints and emphasizes the need for further validation to ensure the reliability and accuracy of wearable EEG devices. Full article

An organization’s success depends on its ability to attract and retain skilled personnel. Superintendents play a critical role in overseeing project sites in the construction industry and can adapt to the increasingly complicated requirements of modern construction projects. This study examines traditional and modern personnel selection methods to determine effective tactics, essential competencies, and emerging trends regarding supervisory personnel. The research methodology follows the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) framework. First, this study examines traditional and modern selection methods used by organizations and engineering firms to provide a comprehensive overview of the topic and assist in selecting appropriate staff recruitment procedures. Second, the Web of Science, Scopus, and Google Scholar databases were reviewed to identify superintendent selection approaches and competencies, over the period January 2000 to September 2024. A total of 22 relevant papers were analyzed. Superintendent selection processes included questionnaires (57%), interviews (26%), literature reviews (14%), and data-driven AI tools (3%). Forty competency criteria were identified, with the top five being knowledge, communication skills, leadership, health and safety expertise, and commitment. As a result, novel approaches employing Industry 4.0 technologies, including virtual reality (VR), wearable sensing devices (WSDs), natural language processing (NLP), blockchain, and computer vision, are recommended. These findings support a better understanding of how best to identify the most qualified supervisory personnel and provides enhanced methods for evaluating job applicants. Full article

Background/Objectives: Sudden cardiac death (SCD) remains a major global health concern and represents one of the most common causes of mortality due to cardiovascular diseases. The wearable cardioverter–defibrillator (WCD) is an innovative, non-invasive medical device designed to provide continuous heart monitoring and immediate defibrillation in patients at risk for SCD. The study aimed to assess the efficacy of WCD usage in patients awaiting decision on therapy with implantable cardioverter–defibrillators (ICDs). Methods: We explored the clinical applications, benefits, and limitations of WCD usage within the BIA-VEST registry in Poland over the years 2021–2023. The study included 10 patients with a mean age of 49.1 ± 12.02 years. Results: All patients demonstrated good tolerance and compliance with the LifeVest WCD, wearing it for an average of 93.1 days, about 22.8 h per day (95.7% of the time). No interventions from LifeVests were recorded, and there were no effective, ineffective, or inadequate discharges. After the first follow-up echocardiography, five patients still required ICDs. Due to improved LVEF and overall condition in six out of ten patients undergoing WCD bridge therapy, ICD implantation was finally waived. Conclusions: The WCD acts as a bridge to therapy, such as ICD implantation or cardiac surgery, and may be particularly beneficial for patients with transient or evolving conditions, such as structural heart diseases and life-threatening ventricular arrhythmias. Full article

During the COVID-19 pandemic, a Canadian recreation centre launched a community-based intervention to increase physical activity (PA) and reduce sedentary behaviour (SB). The Vivo Play Scientist (VPS) program provided a free wearable device (Garmin Vivofit4) that synchronized with a customized eHealth dashboard. Aim: The study investigated the feasibility and effectiveness of the VPS program through the participants’ use and experiences of the device and dashboard using the Technology Acceptance Model (TAM). Method: We employed a concurrent mixed-methods approach of online surveys and semi-structured telephone interviews and estimated the device and dashboard’s perceived usefulness and ease of use with TAM. Results: Of the 318 participants (mean age 39.8) 87 enrolled and completed the survey at baseline-T₀, 4 wks-T₁, and 8 wks-T₂. Maximal-variation sampling was used to select 23 participants (78%, F) for interviews. We compared frequency of use, perceived usefulness and ease of use of the device and dashboard across all surveys using non-parametric statistical tests. A thematic analysis was used to analyze data. Participants had some experience using a wearable device (46%) or eHealth application (49%). A high use (≥4 d/wk.) of Vivofit4 at T₁ (93%) and T₂ (87%) occurred, but dashboard use was less frequent (≥1 d/wk. T₁ 54.0% and T₂ 47.1%). Average levels of perceived usefulness and ease of use for the Vivofit4 and dashboard remained constant from T₁ to T₂. Average daily PA scores decreased from T₁ to T₂ (4.9 to 4.5; p = 0.017). Conclusion: Participants were guarded about the value of the dashboard use and reported several challenges associated with the VPS program, but the free device and dashboard did provide PA support during the pandemic. Full article

In the growing field of personalized medicine, non-invasive wearable devices and sensors are valuable diagnostic tools for the real-time monitoring of physiological and biokinetic signals. Among all the possible multiple (bio)-entities, pH is important in defining health-related biological information, since its variations or alterations can be considered the cause or the effect of disease and disfunction within a biological system. In this work, an innovative (bio)-electrochemical flexible pH sensor was proposed by realizing three electrodes (working, reference, and counter) directly on a polyimide (Kapton) sheet through the implementation of CO₂ laser writing, which locally converts the polymeric sheet into a laser-induced graphene material (LIG electrodes), preserving inherent mechanical flexibility of Kapton. A uniform distribution of nanostructured PEDOT:PSS was deposited via ultrasonic spray coating onto an LIG working electrode as the active material for pH sensing. With a pH-sensitive PEDOT coating, this flexible sensor showed good sensitivity defined through a linear Nernstian slope of (75.6 ± 9.1) mV/pH, across a pH range from 1 to 7. We demonstrated the capability to use this flexible pH sensor during dynamic experiments, and thus concluded that this device was suitable to guarantee an immediate response and good repeatability by measuring the same OCP values in correspondence with the same pH applied. Full article