Recognizing Personal Contexts from Egocentric Images

In recent years, owing to the significant applications of health monitoring, wearable electronic devices such as smart watches, smart glass and wearable cameras have been growing rapidly. Gas sensor is an important part of wearable electronic devices for detecting pollutant, toxic, and combustible gases. However, in order to apply to wearable electronic devices, the gas sensor needs flexible, transparent, and working at room temperature, which are not available for traditional gas sensors. Here, we for the first time fabricate a light-controlling, flexible, transparentand working at room-temperature ethanol gas sensor by using commercial ZnO nanoparticles. The fabricated sensor not only exhibits fast and excellent photoresponse, but also shows high sensing response to ethanol under UV irradiation. Meanwhile, its transmittance exceeds 62% in the visible spectral range, and the sensing performance keeps the same even bent it at a curvature angle of 90o. Additionally, using commercial ZnO nanoparticles provides a facile and low-cost route to fabricate wearable electronic devices.

There has been a proliferation of smartphones, smart watches, and wearable sensors, making them ubiquitous in our daily lives. Mobile sensors have found widespread use due to their ever-decreasing cost, ease of deployment, and ability to provide continuous monitoring as opposed to sensors installed at fixed locations. Various techniques have been proposed for fall detection, gait analysis, activity monitoring, and heart rate and sleep sensing by wearable sensors and mobile phones. Compared to works that use inertial measurement unit (IMU) data or static cameras installed in the environment, there has been relatively less work using egocentric videos, meaning providing the first-person view from wearable cameras. Moreover, most of the existing studies on egocentric videos are based on only one sensor modality, namely the camera. There have been even fewer approaches that combine egocentric video data with IMU data. In this chapter, we will describe three different applications using wearable cameras together with IMU data. First, we will present an overview of a fall detection system using wearable devices, e.g., smartphones and tablets, equipped with cameras and accelerometers. Since the portable device is worn by the subject, monitoring is not limited to confined areas, and extends to wherever the subject may travel, as opposed to static sensors installed in certain rooms. Second, we will present an autonomous and robust method for counting footsteps, and tracking and calculating stride length by using both accelerometer and camera data from smartphones or Google™ glass. To provide higher precision, instead of using a preset stride length, the proposed method calculates the distance traveled with each step by using the camera data. This method is compared with the commercially available accelerometer-based step counter apps. The results show that the proposed method provides a significant increase in accuracy, and has the lowest average error rate both in number of steps taken and the distance traveled. Finally, we will provide an overview of a robust and autonomous method to detect activities with more details and context by using accelerometer and egocentric video data obtained from a smartphone.

BackgroundBlood pressure (BP) is an important modifiable cardiovascular risk factor, yet its long-term monitoring remains problematic. Wearable cuffless devices enable the capture of multiple BP measures during everyday activities and could improve BP monitoring, but little is known about their validity or acceptability.ObjectiveThis study aimed to validate a wrist-worn cuffless wearable BP device (Model T2; TMART Technologies Limited) and assess its acceptability among users and health care professionals.MethodsA mixed methods study was conducted to examine the validity and comparability of a wearable cuffless BP device against ambulatory and home devices. BP was measured simultaneously over 24 hours using wearable and ambulatory devices and over 7 days using wearable and home devices. Pearson correlation coefficients compared the degree of association between the measures, and limits of agreement (LOA; Bland-Altman plots) were generated to assess measurement bias. Semistructured interviews were conducted with users and 10 health care professionals to assess acceptability, facilitators, and barriers to using the wearable device. Interviews were audio recorded, transcribed, and analyzed.ResultsA total of 9090 BP measurements were collected from 20 healthy volunteers (mean 20.3 years, SD 5.4; N=10 females). Mean (SD) systolic BP (SBP)/diastolic BP (DBP) measured using the ambulatory (24 hours), home (7 days), and wearable (7 days) devices were 126 (SD 10)/75 (SD 6) mm Hg, 112 (SD 10)/71 (SD 9) mm Hg and 125 (SD 4)/77 (SD 3) mm Hg, respectively. Mean (LOA) biases and precision between the wearable and ambulatory devices over 24 hours were 0.5 (−10.1 to 11.1) mm Hg for SBP and 2.24 (−17.6 to 13.1) mm Hg for DBP. The mean biases (LOA) and precision between the wearable and home device over 7 days were −12.7 (−28.7 to 3.4) mm Hg for SBP and −5.6 (−20.5 to 9.2) mm Hg for DBP. The wearable BP device was well accepted by participants who found the device easy to wear and use. Both participants and health care providers agreed that the wearable cuffless devices were easy to use and that they could be used to improve BP monitoring.ConclusionsWearable BP measures compared well against a gold-standard ambulatory device, indicating potential for this user-friendly method to augment BP management, particularly by enabling long-term monitoring that could improve treatment titration and increase understanding of users’ BP response during daily activity and stressors.

Association of number of bites and eating speed with energy intake: Wearable technology results under free-living conditions

Wearable physiological parameter monitoring devices play an increasingly important role in daily health monitoring and disease diagnosis/treatment due to their continuous dynamic and low physiological/psychological load characteristics. After decades of development, wearable technologies have gradually matured, and research has expanded to clinical applications. This paper reviews the research progress of wearable physiological parameter monitoring technology and its clinical applications. Firstly, it introduces wearable physiological monitoring technology's research progress in terms of sensing technology and data processing and analysis. Then, it analyzes the monitoring physiological parameters and principles of current medical-grade wearable devices and proposes three specific directions of clinical application research: 1) real-time monitoring and predictive warning, 2) disease assessment and differential diagnosis, and 3) rehabilitation training and precision medicine. Finally, the challenges and response strategies of wearable physiological monitoring technology in the biomedical field are discussed, highlighting its clinical application value and clinical application mode to provide helpful reference information for the research of wearable technology-related fields.

Stress is a universal experience impacting mental and physical health. However, no precise, objective wearable tool exists for continuous, long-term stress monitoring, which is essential for understanding stress-related health outcomes. To address this gap, we introduce SQC-SAS, a multimodal wearable device that simultaneously and continuously measures multiple physiological and molecularstress biomarkers for quantitative stress assessment and sub-classification. This device features exceptional environmental stability, reusability, and fully wireless data and power operation. Machine learning enables data-driven stress assessment and classification across multiple stress states, allowing biomarker profiles to be correlated with each state. Its wristband-like design enables continuous stress monitoring and real-time visualization. We envision our wearable will greatly advance precise, objective stress assessment and monitoring, offering unprecedented capabilities and laying the foundation for personalized interventions and a deeper understanding of stress-related outcomes.

Cardiovascular diseases kill 18 million people each year. Currently, a patient’s health is assessed only during clinical visits, which are often infrequent and provide little information on the person’s health during daily life. Advances in mobile health technologies have allowed for the continuous monitoring of indicators of health and mobility during daily life by wearable and other devices. The ability to obtain such longitudinal, clinically relevant measurements could enhance the prevention, detection and treatment of cardiovascular diseases. This review discusses the advantages and disadvantages of various methods for monitoring patients with cardiovascular disease during daily life using wearable devices. We specifically discuss three distinct monitoring domains: physical activity monitoring, indoor home monitoring and physiological parameter monitoring.

Introduction Screen time is an integral part of children’s evening activities. However its impact on sleep, an essential component of healthy development, remains unclear with most research limited to school-age children and parent/self-report of screens. Aim To describe pre-bedtime screen use in pre-schoolers using novel wearable video camera technology and examine associations with sleep. Methods Seventy children aged 3-4 years (51.4% female, 18.6% indigenous Māori) without significant sleep disturbance participated. Sleep was measured using 7-day actigraphy and chest-worn GoPro cameras captured pre-bedtime screen use up to 5 nights. Videos were coded for screen duration, type, and content. Eight actigraphy variables captured timing, duration and quality. Bedtime was based on video and/or parent report. Mixed-effects regression models assessed associations between screen use and same-night sleep. Results Of 358 nights recorded, 284 (79.3%) involved screens in the 2 hours before bed, including TVs (56.2%), phones (22.9%), computers (11.2%), tablets (10.9%) and other devices (2.2%). In the 30 min before bed, 49.7% of 340 nights with data involved screens. Screen time had no relationship with actigraphy-derived sleep. The only significant finding was that on nights when pre-schoolers went to bed earlier they had more screen time 30 minutes before bedtime (p=.028). Conclusions Why screen use near bedtime was linked to earlier bedtime is unknown, but may reflect continued use in bed as part of settling. Screen use did not affect other sleep outcomes. Findings suggest recommendations to restrict evening screen use in the 1-2 h before bed for healthy sleep lack objective support.

ABSTRACTThe growing demand for self‐powered wearable electronic devices in healthcare, fitness, and entertainment has driven significant advancements in energy harvesting technologies. This review explores the latest progress in energy harvesting mechanisms that enable sustainable and autonomous wearable devices, with a particular emphasis on the role of polymers in their development. Polymers offer a unique combination of mechanical flexibility, biocompatibility, and lightweight properties, making them ideal for wearable applications. The review systematically categorizes the major energy harvesting technologies into three primary mechanisms: thermoelectric generators (TEGs), piezoelectric energy harvesters (PEHs), and triboelectric nanogenerators (TENGs). Each section provides an in‐depth discussion of the working principles, material innovations, fabrication techniques, and applications of these energy harvesting technologies in wearable systems. Beyond the fundamental mechanisms, the review discusses hybrid energy harvesting systems that integrate multiple energy sources to maximize power generation and ensure continuous device operation. The role of energy storage technologies, such as flexible supercapacitors and micro‐batteries, is also highlighted to address the intermittency challenges of ambient energy sources. Despite significant progress, challenges remain in improving energy conversion efficiency, enhancing device durability, and optimizing system integration for real‐world applications. The review identifies key research directions for overcoming these challenges, including advanced materials engineering, miniaturization techniques, and artificial intelligence‐driven energy management strategies. The findings presented in this review provide valuable insights into the development of next‐generation self‐powered wearable devices, paving the way for sustainable and efficient wearable electronics that seamlessly integrate into daily life.

Despite the increasing popularity of ambulatory assessment, the reliability and validity of psychophysiological signals from wearable devices is unproven in daily life settings. We evaluated the reliability and validity of physiological signals (electrocardiogram, ECG; photoplethysmography, PPG; electrodermal activity, EDA) collected from two wearable devices (Movisens EcgMove4 and Empatica E4) in the lab (N = 67) and daily life (N = 20) among adults aged 18-64 with Mindware as the laboratory gold standard. Results revealed that both wearable devices' valid data rates in daily life were lower than in the laboratory (Movisens ECG 82.94 vs. 93.10%, Empatica PPG 8.79 vs. 26.14%, and Empatica EDA 41.16 vs. 42.67%, respectively). The poor valid data rates of Empatica PPG signals in the laboratory could be partially attributed to participants' hand movements (r = - .27, p = .03). In laboratory settings, heart rate (HR) derived from both wearable devices exhibited higher concurrent validity than heart rate variability (HRV) metrics (ICCs 0.98-1.00 vs. 0.75-0.97). The number of skin conductance responses (SCRs) derived from Empatica showed higher concurrent validity than skin conductance level (SCL, ICCs 0.38 vs. 0.09). Movisens EcgMove4 provided more reliable and valid HRV measurements than Empatica E4 in both laboratory (split-half reliability: 0.95-0.99 vs. 0.85-0.98; concurrent validity: 0.95-1.00 vs. 0.75-0.98; valid data rate: 93.10 vs. 26.14%) and ambulatory settings (split-half reliability: 0.99-1.00 vs. 0.89-0.98; valid data rate: 82.94 vs. 8.79%). Although the reliability and validity of wearable devices are improving, findings suggest researchers should select devices that yield consistently robust and valid data for their measures of interest.

BackgroundEarly diagnosis of mild cognitive impairment (MCI) is essential for timely treatment planning. With recent advances in the wearable technology, interest has increasingly shifted toward computer-aided self-diagnosis of MCI using wearable electroencephalography (EEG) devices in daily life. However, no study so far has investigated the optimal electrode configurations for the efficient diagnosis of MCI while considering the design factors of wearable EEG devices. In this study, we aimed to determine the optimal channel configurations of wearable EEG devices for the computer-aided diagnosis of MCI.MethodWe employed an EEG dataset collected from 21 patients with MCI and 21 healthy control subjects. After evaluating the classification accuracies for all possible electrode configurations for the two-, four-, six-, and eight-electrode conditions using a support vector machine, the optimal electrode configurations that provide the highest diagnostic accuracy were suggested for each electrode condition.ResultsThe highest classification accuracies of 74.04% ± 4.82, 82.43% ± 6.14, 86.28% ± 2.81, and 86.85% ± 4.97 were achieved for the optimal two-, four-, six-, and eight-electrode configurations, respectively, which demonstrated the possibility of precise machine-learning-based diagnosis of MCI with a limited number of EEG electrodes. Additionally, further simulations with the EEG dataset revealed that the optimal electrode configurations had significantly higher classification accuracies than commercial EEG devices with the same number of electrodes, which suggested the importance of electrode configuration optimization for wearable EEG devices based on clinical EEG datasets.ConclusionsThis study highlighted that the optimization of the electrode configuration, assuming the wearable EEG devices can potentially be utilized for daily life monitoring of MCI, is necessary to enhance the performance and portability.

This study addresses the gap in understanding how personal context influences students' numeracy skills, particularly in the context of the Minimum Competency Assessment (MCA) in Indonesia. The research problem centers on the challenge of engaging students with numeracy tasks that are not only mathematically relevant but also relatable to their personal experiences. While the MCA assesses mathematical reasoning and problem-solving, students often struggle to apply these skills to real-world scenarios, particularly when the context of the problems is unfamiliar or disconnected from their daily lives. This study aims to analyze the numeracy skills of eighth-grade students in solving problems with a personal context within the Minimum Competency Assessment (MCA). The study employed a mixed-methods design, integrating both quantitative and qualitative data. Quantitative data were analyzed using content validity analysis (Aiken's V) and inter-rater reliability (Cohen's Kappa) to assess the validity and consistency of the MCA questions. Descriptive statistics were used to analyze the students' numeracy scores. For qualitative analysis, semi-structured interviews were conducted to explore students' reasoning and problem-solving strategies. The triangulation of data from the MCA tests and interviews provided a comprehensive understanding of how students engaged with mathematical problems and applied their numeracy skills in real-world contexts. A total of 17 eighth-grade students were selected, and three students from each numeracy category; high, medium, and low were chosen using a categorization method based on standard deviation. Results showed that students with high numeracy abilities demonstrated effective problem-solving and reasoning skills, while students with medium and low numeracy abilities struggled with complex problems and real-world applications. The study suggests that while personal context can enhance student engagement, its effectiveness depends on a solid foundation in numeracy skills. The findings recommend a balanced approach in teaching, strengthening foundational skills alongside contextualized learning. In conclusion, while the personal context in MCA increases student engagement and relevance, particularly among high-performing students, its effectiveness is contingent on a solid foundation in basic numeracy skills. A balanced approach that strengthens basic numeracy skills while incorporating personal contexts is necessary to foster critical thinking and effective application of mathematics across all ability levels.

To develop a new method of evaluating swallowing behaviour. Sixty-nine healthy participants were divided into a younger (16 males and 16 females, mean age 39.09 ± 12.16 years) and older (18 males and 19 females, mean age 71.43 ± 5.50 years) group. The participants ingested water and yoghurt twice (directed and free swallowing) at rest and after performing simple daily life tasks (calculation and exercise). To measure swallowing frequency, we employed a smartphone-based, portable and neck-worn swallowing-sound-monitoring device. This device monitors swallowing behaviour continuously by collecting biological sounds from the neck without imposing behavioural restrictions. A neural network model of swallowing sound identification by deep learning was used for the subsequent evaluation. This device was used to obtain two types of saliva-swallowing sounds associated with different ingestants, at rest and after performing a stimulating task. Furthermore, we assessed the associated subjective psychological states. The younger group showed a higher directed swallowing frequency (for both water and yoghurt) than the older group did. Regarding the type of ingestant, the swallowing frequency for yoghurt was higher during free swallowing in both the young and the older groups. 'Feeling calm' was reported significantly more often in the older group after swallowing yoghurt following exercise. Swallowing status in daily life was measured non-invasively using a wearable mobile device. It is important to consider the type of ingestant, daily living activities, and age when assessing swallowing.

Flexible capacitive pressure sensors with a simple structure and low power consumption are attracting attention, owing to their wide range of applications in wearable electronic devices. However, it is difficult to manufacture pressure sensors with high sensitivity, wide detection range, and low detection limits. We developed a highly sensitive and flexible capacitive pressure sensor based on the porous Ecoflex, which has an aligned airgap structure and can be manufactured by simply using a mold and a micro-needle. The existence of precisely aligned airgap structures significantly improved the sensor sensitivity compared to other dielectric structures without airgaps. The proposed capacitive pressure sensor with an alignment airgap structure supports a wide range of working pressures (20–100 kPa), quick response time (≈100 ms), high operational stability, and low-pressure detection limit (20 Pa). Moreover, we also studied the application of pulse wave monitoring in wearable sensors, exhibiting excellent performance in wearable devices that detect pulse waves before and after exercise. The proposed pressure sensor is applicable in electronic skin and wearable medical assistive devices owing to its excellent functional features.

PURPOSE: Higher physical activity (PA) in daily life is associated with a decrease in the risk of all-cause mortality and in prevalence of non-communicable diseases (NCDs). Thus, accurate estimation of PA is important for increasing PA and promoting the NCDs prevention. This study was performed to examine the validity of PA energy expenditure (PAEE) and PA level (PAL) estimated using twelve wearable devices under free-living conditions. METHODS: Nineteen healthy adults (9 men and 10 women) aged 21-50 years wore 12 wearable devices simultaneously (five wearable devices on the waist, five on the wrist and two in the pocket including those for the consumer and the research) for consecutive 15 days in a free-living condition. PAEEs were calculated by subtracting the basal metabolic rate (BMR) from the total energy expenditure (TEE) obtained from each device application. PALs were calculated by dividing the TEE by BMR. Because some devices did not show BMR in device applications, TEE values in a day when the devices were stationary were used as BMRs. The reference PAEE and PAL were calculated by using the TEE measured by doubly labeled water (DLW) method during 15 days worn 12 wearable devices and the BMR estimated on the sleeping metabolic rate (SMR) by the metabolic chamber method on a different day. RESULTS: The mean value of reference PAEE and PAL for 15 days were 1064 ± 196 kcal/d (696 to 1541 kcal/d) and 1.88 ± 0.21 (1.51 to 2.23), respectively. Spearman’s rank correlation coefficients between the reference PAEE and the estimated PAEE were significant in four wearable devices (r=0.498-0.579, p < 0.05), those for PAL were significant in neither wearable devices. CONCLUSIONS: The accurate ranking among individuals based on PAEE and PAL seems difficult. These results suggest that the estimation of PA using wearable devices needs to be cautiously considered.This research was supported by the Japan Agency for Medical Research and Development (AMED).