SMRT: Multi-Resident Tracking in Smart Homes With Sensor Vectorization.
Ontology highlight
ABSTRACT:
SUBMITTER: Wang T
PROVIDER: S-EPMC7423766 | biostudies-literature | 2021 Aug
REPOSITORIES: biostudies-literature
Publications
sMRT: Multi-Resident Tracking in Smart Homes With Sensor Vectorization.
Wang Tinghui T Cook Diane J DJ
IEEE transactions on pattern analysis and machine intelligence 20210701 8
Smart homes equipped with anonymous binary sensors offer a low-cost, unobtrusive solution that powers activity-aware applications, such as building automation, health monitoring, behavioral intervention, and home security. However, when multiple residents are living in a smart home, associating sensor events with the corresponding residents can pose a major challenge. Previous approaches to multi-resident tracking in smart homes rely on extra information, such as sensor layouts, floor plans, and ...[more]
Similar Datasets
Project description:A dataset of sensor measurements is presented. Our dataset contains discrete measurements of 8 IoT devices located in various places in a research lab at the University of Bristol. Nordic nRF52840 DK IoT devices periodically collects environmental data, such as temperature, humidity, pressure, gas, room light intensity, accelerometer; including also a measurement quality indicator. The measurements were taken every 10 seconds over a six-month period between February and September 2022. In addition, we provide Received Signal Strength Indicator (RSSI) of the IoT devices. The data files are formatted as CSV files. There are various software libraries available to access and read this file format. We provide "README.txt" file which explains the repository and how to use dataset. Each data file is named according to its creation date and, once it reaches a size of 1MB, it is compressed and archived. A new folder is created every week to store all the data files from that week automatically. The dataset can be used for drift detection such as malicious or anomaly detection algorithms. It can also be used for smart building applications like occupation detection. The dataset can be found at https://data.bris.ac.uk/data/dataset/fwlmb11wni392kodtyljkw4n2.
| S-EPMC10375552 | biostudies-literature
Project description:Wearing masks has been a recommended protective measure due to the risks of coronavirus disease 2019 (COVID-19) even in its coming endemic phase. Therefore, deploying a "smart mask" to monitor human physiological signals is highly beneficial for personal and public health. This work presents a smart mask integrating an ultrathin nanocomposite sponge structure-based soundwave sensor (≈400 µm), which allows the high sensitivity in a wide-bandwidth dynamic pressure range, i.e., capable of detecting various respiratory sounds of breathing, speaking, and coughing. Thirty-one subjects test the smart mask in recording their respiratory activities. Machine/deep learning methods, i.e., support vector machine and convolutional neural networks, are used to recognize these activities, which show average macro-recalls of ≈95% in both individual and generalized models. With rich high-frequency (≈4000 Hz) information recorded, the two-/tri-phase coughs can be mapped while speaking words can be identified, demonstrating that the smart mask can be applicable as a daily wearable Internet of Things (IoT) device for respiratory disease identification, voice interaction tool, etc. in the future. This work bridges the technological gap between ultra-lightweight but high-frequency response sensor material fabrication, signal transduction and processing, and machining/deep learning to demonstrate a wearable device for potential applications in continual health monitoring in daily life.
| S-EPMC9631096 | biostudies-literature
Project description:Drowning is considered amongst the top 10 causes of unintentional death, according to the World Health Organization (WHO). Therefore, anti-drowning systems that can save lives by preventing and detecting drowning are much needed. This paper proposes a robust and waterproof sensor-based device to detect distress in swimmers at varying depths and different types of water environments. The proposed device comprises four main components, including heart rate, blood oxygen level, movement, and depth sensors. Although these sensors were designed to work together to boost the system's capability as an anti-drowning device, each could operate independently. The sensors were able to determine the heart rate to an accuracy of 1 beat per minute (BPM), 1% SpO2, the acceleration with adjustable sensitivities of ±2 g, ±4 g, ±8 g, and ±16 g, and the depth up to 12.8 m. The data obtained from the sensors were sent to a microcontroller that compared the input data to adjustable threshold values to detect dangerous situations. Being in hazardous situations for more than a specific time activated the alarming system. Based on the comparison made in the program and measuring the time of submersion, a message indicating drowning or safe was sent to a lifeguard to continuously monitor the swimmer' condition via Wi-Fi to an IP address reachable by a mobile phone or laptop. It is also possible to continuously monitor the sensor outputs on the device's display or the connected mobile phone or laptop. The threshold values could be adjusted based on biometric parameters such as swimming conditions (swimming pool, beach, depth, etc.) and swimmers health and conditions. The functionality of the proposed device was thoroughly tested over a wide range of parameters and under different conditions, both in air and underwater. It was demonstrated that the device could detect a range of potentially hazardous aquatic situations. This work will pave the way for developing an effective drowning sensing system that could save tens of thousands of lives across the globe every year.
| S-EPMC8839118 | biostudies-literature
Project description:BackgroundOne of the main challenges of health monitoring systems is the support of older persons in living independently in their homes and with relatives. Smart homes equipped with internet of things devices can allow older persons to live longer in their homes. Previous surveys used to identify sensor-based data sets in human activity recognition systems have been limited by the use of public data set characteristics, data collected in a controlled environment, and a limited number of older participants.ObjectiveThe objective of our study is to build a model that can learn the daily routines of older persons, detect deviations in daily living behavior, and notify these anomalies in near real-time to relatives.MethodsWe extracted features from large-scale sensor data by calculating the time duration and frequency of visits. Anomalies were detected using a parametric statistical approach, unusually short or long durations being detected by estimating the mean (μ) and standard deviation (σ) over hourly time windows (80 to 355 days) for different apartments. The confidence level is at least 75% of the tested values within two (σ) from the mean. An anomaly was triggered where the actual duration was outside the limits of 2 standard deviations (μ-2σ, μ+2σ), activity nonoccurrence, or absence of activity.ResultsThe patterns detected from sensor data matched the routines self-reported by users. Our system observed approximately 1000 meals and bathroom activities and notifications sent to 9 apartments between July and August 2020. A service evaluation of received notifications showed a positive user experience, an average score of 4 being received on a 1 to 5 Likert-like scale. One was poor, two fair, three good, four very good, and five excellent. Our approach considered more than 75% of the observed meal activities were normal. This figure, in reality, was 93%, normal observed meal activities of all participants falling within 2 standard deviations of the mean.ConclusionsIn this research, we developed, implemented, and evaluated a real-time monitoring system of older participants in an uncontrolled environment, with off-the-shelf sensors and internet of things devices being used in the homes of older persons. We also developed an SMS-based notification service and conducted user evaluations. This service acts as an extension of the health/social care services operated by the municipality of Skellefteå provided to older persons and relatives.
| S-EPMC9039812 | biostudies-literature
Project description:Time series data acquired from sensors deployed in smart homes present valuable information for intelligent systems to learn activity patterns of occupants. With the increasing need to enable people to age in place independently, the availability of such data is key to the development of home monitoring solutions. In this article we describe an unlabelled dataset of measurements collected from multiple environmental sensors placed in a smart home to capture human activities of daily living. Various sensors were used including passive infrared, force sensing resistors, reed switches, mini photocell light sensors, temperature and humidity, and smart plugs. The sensors record data from the user's interactions with the environment, such as indoor movements, pressure applied on the bed, or current consumption when using electrical appliances. Millions of raw sensor data samples were collected continuously at a frequency of 1 Hz over a period of six months between 26 February 2020 and 26 August 2020. The dataset can be useful in the analysis of different methods, including data-driven algorithms for activity or habit recognition. In particular, the research community might be interested in investigating the performance of algorithms when applied on unlabelled datasets and not necessarily on annotated datasets. Furthermore, by applying artificial intelligence (AI) algorithms on such data collected over long periods, it is possible to extract patterns that reveal the user's habits as well as detect changes in the habits. This can benefit in detecting deviations in order to provide timely interventions for patients, e.g., people with dementia.
| S-EPMC7758366 | biostudies-literature
Project description:This article presents the Resident VIEW (Voicing Importance, Experience, and Well-Being), a measure designed to learn directly from long-term care residents the extent to which they experience support that matters most to them. The Resident VIEW contains 63 items across eight domains developed through cognitive interviews with residents in different types of residential settings (e.g., nursing homes, assisted living, and adult foster care). Residents rate items on both importance and their experience. In total, 258 nursing home residents living in 32 Oregon nursing homes were selected through a two-stage random sampling design and participated in the study. Results demonstrate that what matters most to residents varies, emphasizing the value of asking residents directly about their preferences. The relationship between importance and experience differed by item. Residents who experienced support rated very important within some domains, reported better quality of life and reported lower levels of depressive symptoms than those who did not experience these things. The interaction between importance and experience, however, did not reach statistical significance, suggesting that positive experiences may provide benefit even in some areas that are not perceived as important by residents. Results underscore the value of incorporating the resident perspective into measure development in long-term care.
| S-EPMC6764029 | biostudies-literature
Project description:BackgroundResident-to-resident elder mistreatment (R-REM) in nursing homes can cause physical and psychological injury and death, yet its prevalence remains unknown.ObjectiveTo estimate the prevalence of physical, verbal, and sexual R-REM in nursing home residents and subgroups.Design1-month observational prevalence study.Setting5 urban and 5 suburban New York state nursing homes.Participants2011 residents in 10 facilities randomly selected on the basis of size and location; 83% of facilities and 84% of eligible residents participated.MeasurementsR-REM was identified through resident interviews, staff interviews, shift coupons, observation, chart review, and accident or incident reports.Results407 of 2011 residents experienced at least 1 R-REM event; the total 1-month prevalence was 20.2% (95% CI, 18.1% to 22.5%). The most common forms were verbal (9.1% [CI, 7.7% to 10.8%]), other (such as invasion of privacy or menacing gestures) (5.3% [CI, 4.4% to 6.4%]), physical (5.2% [CI, 4.1% to 6.5%]), and sexual (0.6% [CI, 0.3% to 1.1%]). Several clinical and contextual factors (for example, lower vs. severe levels of cognitive impairment, residing on a dementia unit, and higher nurse aide caseload) were associated with higher estimated rates of R-REM.LimitationsMost facilities were relatively large. All R-REM cases may not have been detected; resident and staff reporting may be subject to recall bias.ConclusionR-REM in nursing homes is highly prevalent. Verbal R-REM is most common, but physical mistreatment also occurs frequently. Because R-REM can cause injury or death, strategies are urgently needed to better understand its causes so that prevention strategies can be developed.Primary funding sourceNational Institute on Aging.
| S-EPMC6366619 | biostudies-literature
Project description:BackgroundCare problems such as decubitus and fall incidents are prevalent in nursing homes. Yet, research regarding explanatory factors on these care problems is scarce. The aim of this study is twofold: (1) to identify the degree to which a diverse set of resident-related factors (e.g., care dependency levels) are associated with the sum of six care problems (pressure ulcers, incontinence, malnutrition, falls, freedom restriction, and pain), and (2) to investigate which resident-related factors are associated with each of these six care problems individually.MethodsData were collected (2016-2023) using the International Prevalence Measurements of Care Quality (LPZ). Factors such as age, number of diagnoses, and length of stay were included. While respecting nested data within eight organizations, the associations between thirteen resident-related factors and the six care problems were determined using multilevel analyses.ResultsA total of 3043 residents were included (mean age 81.9; SD: 10.5). The most prevalent care problem was incontinence (n = 1834; 60.3%). Nurse proxy-rated confusion (r = 0.227; p < 0.001) and aggression (r = 0.285; p = 0.001) were associated strongest with the sum of the six care problems; and higher after correcting for the residents' care dependency levels (respectively r = 0.504; 0.584 - both p < 0.001). Pre-admission risk assessments for pressure ulcers (OR 7.03), malnutrition (OR 3.57), and falls (OR 3.93) were strongest associated with individual care problems such as pressure ulcers, and falls.ConclusionsThis study shows the association between several resident-related factors and care problems such as gender, years since admission, and care dependency level. Factors such as proxy-rated aggression and confusion were strongest associated with the presence of care problems, while pre-admission risk assessments were strongest associated with several individual care problems. The findings underscore the importance of prioritizing early pre-assessments, as they empower care professionals to take into account resident-specific factors and their influence on the emergence of care problems.
| S-EPMC11577899 | biostudies-literature
Project description:This article describes an educational program to inform nursing and care staff of the management of resident-to-resident elder mistreatment (R-REM) in nursing homes, using the SEARCH (Support, Evaluate, Act, Report, Care plan, and Help to avoid) approach. Although relatively little research has been conducted on this form of abuse, there is mounting interest in R-REM because such aggression has been found to be extensive and can have both physical and psychological consequences for residents and staff. The goal of the SEARCH approach is to support staff in the identification and recognition of R-REM as well as to suggest recommendations for management. The educational program and the SEARCH approach are described. Three case studies from the research project are presented, illustrating how nurses and care staff can use the SEARCH approach to manage R-REM in nursing homes. Resident and staff safety and well-being can be enhanced by the use of the evidence-based SEARCH approach.
| S-EPMC4178932 | biostudies-literature
Project description:Studying how humans eat in the context of a meal is important to understanding basic mechanisms of food intake regulation and can help develop new interventions for the promotion of healthy eating and prevention of obesity and eating disorders. While there are a number of methodologies available for behavioral evaluation of a meal, there is a need for new tools that can simplify data collection through automatic and online analysis. Also, there are currently no methods that leverage technology to add a dimension of interactivity to the meal table. In this study, we examined the feasibility of a new technology for automatic detection and classification of bites during a laboratory meal. We used a SUR40 multi-touch tabletop computer, powered by an infrared camera behind the screen. Tags were attached to three plates, allowing their positions to be tracked, and the saturation (a measure of the infrared intensity) in the surrounding region was measured. A Kinect camera was used to record the meals for manual verification and provide gesture detection for when the bites were taken. Bite detections triggered classification of the source plate by the SUR40 based on saturation flux in the preceding time window. Five healthy subjects (aged 20-40 years, one female) were tested, providing a total sample of 320 bites. Sensitivity, defined as the number of correctly detected bites out of the number of actual bites, was 67.5%. Classification accuracy, defined as the number of correctly classified bites out of those detected, was 82.4%. Due to the poor sensitivity, a second experiment was designed using a single plate and a Myo armband containing a nine-axis accelerometer as an alternative method for bite detection. The same subjects were tested (sample: 195 bites). Using a simple threshold on the pitch reading of the magnetometer, the Myo data achieved 86.1% sensitivity vs. 60.5% with the Kinect. Further, the precision of positive predictive value was 72.1% for the Myo vs. 42.8% for the Kinect. We conclude that the SUR40 + Myo combination is feasible for automatic detection and classification of bites with adequate accuracy for a range of applications.
| S-EPMC4749696 | biostudies-literature