skip to main content

Title: HAWAD: Hand Washing Detection using Wrist Wearable Inertial Sensors
Hand hygiene is crucial in preventing the spread of infections and diseases. Lack of hand hygiene is one of the major reasons for healthcare associated infections (HAIs) in hospitals. Adherence to hand hygiene compliance by the workers in the food business is very important for preventing food-borne illness. In addition to healthcare settings and food businesses, hand washing is also vital for personal well-being. Despite the importance of hand hygiene, people often do not wash hands when necessary. Automatic detection of hand washing activity can facilitate justin-time alerts when a person forgets to wash hands. Monitoring hand washing practices is also essential in ensuring accountability and providing personalized feedback, particularly in hospitals and food businesses. Inertial sensors available in smart wrist devices can capture hand movements, and so it is feasible to detect hand washing using these devices. However, it is challenging to detect hand washing using wrist wearable sensors since hand movements are associated with a wide range of activities. In this paper, we present HAWAD, a robust solution for hand washing detection using wrist wearable inertial sensors. We leverage the distribution of penultimate layer output of a neural network to detect hand washing from a wide range of activities. Our method reduces false positives by 77% and improves F1-score by 30% compared to the baseline method.
Award ID(s):
Publication Date:
Journal Name:
International Conference on Distributed Computing in Sensor Systems and workshops
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract Background Unified Parkinson Disease Rating Scale-part III (UPDRS III) is part of the standard clinical examination performed to track the severity of Parkinson’s disease (PD) motor complications. Wearable technologies could be used to reduce the need for on-site clinical examinations of people with Parkinson’s disease (PwP) and provide a reliable and continuous estimation of the severity of PD at home. The reported estimation can be used to successfully adjust the dose and interval of PD medications. Methods We developed a novel algorithm for unobtrusive and continuous UPDRS-III estimation at home using two wearable inertial sensors mounted on the wrist and ankle. We used the ensemble of three deep-learning models to detect UPDRS-III-related patterns from a combination of hand-crafted features, raw temporal signals, and their time–frequency representation. Specifically, we used a dual-channel, Long Short-Term Memory (LSTM) for hand-crafted features, 1D Convolutional Neural Network (CNN)-LSTM for raw signals, and 2D CNN-LSTM for time–frequency data. We utilized transfer learning from activity recognition data and proposed a two-stage training for the CNN-LSTM networks to cope with the limited amount of data. Results The algorithm was evaluated on gyroscope data from 24 PwP as they performed different daily living activities. The estimated UPDRS-III scoresmore »had a correlation of $$0.79\, (\textit{p}<0.0001)$$ 0.79 ( p < 0.0001 ) and a mean absolute error of 5.95 with the clinical examination scores without requiring the patients to perform any specific tasks. Conclusion Our analysis demonstrates the potential of our algorithm for estimating PD severity scores unobtrusively at home. Such an algorithm could provide the required motor-complication measurements without unnecessary clinical visits and help the treating physician provide effective management of the disease.« less
  2. Background Research has shown the feasibility of human activity recognition using wearable accelerometer devices. Different studies have used varying numbers and placements for data collection using sensors. Objective This study aims to compare accuracy performance between multiple and variable placements of accelerometer devices in categorizing the type of physical activity and corresponding energy expenditure in older adults. Methods In total, 93 participants (mean age 72.2 years, SD 7.1) completed a total of 32 activities of daily life in a laboratory setting. Activities were classified as sedentary versus nonsedentary, locomotion versus nonlocomotion, and lifestyle versus nonlifestyle activities (eg, leisure walk vs computer work). A portable metabolic unit was worn during each activity to measure metabolic equivalents (METs). Accelerometers were placed on 5 different body positions: wrist, hip, ankle, upper arm, and thigh. Accelerometer data from each body position and combinations of positions were used to develop random forest models to assess activity category recognition accuracy and MET estimation. Results Model performance for both MET estimation and activity category recognition were strengthened with the use of additional accelerometer devices. However, a single accelerometer on the ankle, upper arm, hip, thigh, or wrist had only a 0.03-0.09 MET increase in prediction error comparedmore »with wearing all 5 devices. Balanced accuracy showed similar trends with slight decreases in balanced accuracy for the detection of locomotion (balanced accuracy decrease range 0-0.01), sedentary (balanced accuracy decrease range 0.05-0.13), and lifestyle activities (balanced accuracy decrease range 0.04-0.08) compared with all 5 placements. The accuracy of recognizing activity categories increased with additional placements (accuracy decrease range 0.15-0.29). Notably, the hip was the best single body position for MET estimation and activity category recognition. Conclusions Additional accelerometer devices slightly enhance activity recognition accuracy and MET estimation in older adults. However, given the extra burden of wearing additional devices, single accelerometers with appropriate placement appear to be sufficient for estimating energy expenditure and activity category recognition in older adults.« less
  3. Ensuring that all the teeth surfaces are adequately covered during daily brushing can reduce the risk of several oral diseases. In this paper, we propose the mTeeth model to detect teeth surfaces being brushed with a manual toothbrush in the natural free-living environment using wrist-worn inertial sensors. To unambiguously label sensor data corresponding to different surfaces and capture all transitions that last only milliseconds, we present a lightweight method to detect the micro-event of brushing strokes that cleanly demarcates transitions among brushing surfaces. Using features extracted from brushing strokes, we propose a Bayesian Ensemble method that leverages the natural hierarchy among teeth surfaces and patterns of transition among them. For training and testing, we enrich a publicly-available wrist-worn inertial sensor dataset collected from the natural environment with time-synchronized precise labels of brushing surface timings and moments of transition. We annotate 10,230 instances of brushing on different surfaces from 114 episodes and evaluate the impact of wide between-person and within-person between-episode variability on machine learning model's performance for brushing surface detection.
  4. Stress increases the risk of several mental and physical health problems like anxiety, hypertension, and cardiovascular diseases. Better guidance and interventions towards mitigating the impact of stress can be provided if stress can be monitored continuously. The recent proliferation of wearable devices and their capability in measuring several physiological signals related to stress have created the opportunity to measure stress continuously in the wild. Wearable devices used to measure physiological signals are mostly placed on the wrist and the chest. Though currently chest sensors, with/without wrist sensors, provide better results in detecting stress than using wrist sensors only, chest devices are not as convenient and prevalent as wrist devices, particularly in the free-living context. In this paper, we present a solution to detect stress using wrist sensors that emulate the gold standard chest sensors. Data from wrist sensors are translated into the data from chest sensors, and the translated data is used for stress detection without requiring the users to wear any device on the chest. We evaluated our solution using a public dataset, and results show that our solution detects stress with accuracy comparable to the gold standard chest devices which are impractical for daily use
  5. Surgical site infections (SSIs) are a leading cause of morbidity and mortality and a significant expense to the healthcare system and hospitals. The majority of these infections are preventable; however, increasing bacterial resistance, biofilm persistence, and human error contribute to the occurrence of these healthcare-associated infections. We present a flexible antimicrobial blue-light emitting bandage designed for use on postoperative incisions and wounds. The photonic device is designed to inactivate bacteria present on the skin and prevent bacterial colonization of the site, thus reducing the occurrence of SSIs. This antimicrobial light emitting bandage uses blue light’s proven abilities to inactivate a wide range of clinical pathogens regardless of their resistance to antibiotics, inactivate bacteria without harming mammalian cells, improve wound healing, and inactivate bacteria in biofilms. The antimicrobial bandage consists of a thin 2”x2” silicone sheet with an array of 77 LEDs embedded in multiple layers of the material for thermal management. The 405 nm center wavelength LED array is designed to be a wearable device that integrates with standard hospital infection prevention protocols. The device was characterized for irradiance of 44.5 mW/cm2. Methicillin-resistant Staphylococcus aureus seeded in a petri dish was used to evaluate bacterial inactivation in vitro. Starting withmore »a concentration of 2.16 x 107 colony forming units (CFU)/mL, 45% of the bacteria was inactivated within 15 minutes, 65% had been inactivated by 30 minutes, 99% was inactivated by 60 minutes, and a 7 log reduction and complete sterilization was achieved within 120 minutes.« less