A new paper from the extended Amulet group.
John A. Batsis, John A. Naslund, Alexandra B. Zagaria, David Kotz, Rachel Dokko, Stephen J. Bartels & Elizabeth Carpenter-Song. Technology for Behavioral Change in Rural Older Adults with Obesity. Journal of Nutrition in Gerontology and Geriatrics, April 2019.DOI: 10.1080/21551197.2019.1600097
The Amulet group has been developing sensors, apps, and algorithms for sensing stress, in the field. In one of the first papers to come out of that effort, presented today in a UbiComp workshop, we explore the potential for detecting stress using a single commodity wearable sensor.
Varun Mishra, Gunnar Pope, Sarah Lord, Stephanie Lewia, Byron Lowens, Kelly Caine, Sougata Sen, Ryan Halter, and David Kotz. The Case for a Commodity Hardware Solution for Stress Detection. In Workshop on Mental Health: Sensing & Intervention, pages 1717-1728, October 2018. ACM. DOI 10.1145/3267305.3267538.
Abstract: Timely detection of an individual’s stress level has the potential to expedite and improve stress management, thereby reducing the risk of adverse health consequences that may arise due to unawareness or mismanagement of stress. Recent advances in wearable sensing have resulted in multiple approaches to detect and monitor stress with varying levels of accuracy. The most accurate methods, however, rely on clinical grade sensors strapped to the user. These sensors measure physiological signals of a person and are often bulky, custom-made, expensive, and/or in limited supply, hence limiting their large-scale adoption by researchers and the general public. In this paper, we explore the viability of commercially available off-the-shelf sensors for stress monitoring. The idea is to be able to use cheap, non-clinical sensors to capture physiological signals, and make inferences about the wearer’s stress level based on that data. In this paper, we describe a system involving a popular off-the-shelf heart-rate monitor, the Polar H7; we evaluated our system in a lab setting with three well-validated stress-inducing stimuli with 26 participants. Our analysis shows that using the off-the-shelf sensor alone, we were able to detect stressful events with an F1 score of 0.81, on par with clinical-grade sensors.
Equipped with sensors that are capable of collecting physiological and environmental data continuously, wearable technologies have the potential to become a valuable component of personalized healthcare and health management. However, in addition to the potential benefits of wearable devices, the widespread and continuous use of wearables also poses many privacy challenges. In some instances, users may not be aware of the risks associated with wearable devices, while in other cases, users may be aware of the privacy-related risks, but may be unable to negotiate complicated privacy settings to meet their needs and preferences. This lack of awareness could have an adverse impact on users in the future, even becoming a “skeleton in the closet.” In this work, we conducted 32 semi-structured interviews to understand how users perceive privacy in wearable computing. Results suggest that user concerns toward wearable privacy have different levels of variety ranging from no concern to highly concerned. In addition, while user concerns and benefits are similar among participants in our study, these variablesshould be investigated more extensively for the development of privacy enhanced wearable technologies.
- Byron Lowens, Vivian G. Motti, and Kelly E. Caine. Wearable Privacy: Skeletons in the Data Closet. Proceedings of IEEE International Conference on Healthcare Informatics (ICHI). Park City, UT, 2017, pp. 295-304. DOI: 10.1109/ICHI.2017.29
Abstract: In this work, we attempt to determine whether the contextual information of a participant can be used to predict whether the participant will respond to a particular EMA trigger. We use a publicly available dataset for our work, and find that by using basic contextual features about the participant’s activity, conversation status, audio, and location, we can predict if an EMA triggered at a particular time will be answered with a precision of 0.647, which is significantly higher than a baseline precision of 0.41. Using this knowledge, the researchers conducting field studies can efficiently schedule EMAs and achieve higher response rates.
Varun Mishra, Byron Lowens, Sarah Lord, Kelly Caine, and David Kotz. Investigating Contextual Cues As Indicators for EMA Delivery. In Proceedings of the International Workshop on Smart & Ambient Notification and Attention Management (UbiTtention), pages 935-940, September 2017. ACM. DOI 10.1145/3123024.3124571.
We’ve just released a version 1.1 of the hardware, with many fixes and improvements; see our GitHub site.
- Changed from spring terminals to SPI-BI-WIRE POGO pin connector for programming both the MSP430 and nRF51822
- Repositioned the LCD screen to provide more room for the programmer ports and LEDs
- Broke out UART TX/RX lines for debugging the nRF51822
- Complete case redesign to better fit the mother-daughter boards, buttons, and LCD screen
- Replaced the 4 pin charging connector with a more sturdy USB charging port
David Harmon ’17 develops and evaluates a novel protocol for secure transfer of sensor data from an Amulet to a smartphone, in this Senior Honors Thesis released as a Dartmouth Computer Science Technical Report.
Abstract. The authenticity, confidentiality, and integrity of data streams from wearable healthcare devices are critical to patients, researchers, physicians, and others who depend on this data to measure the effectiveness of treatment plans and clinical trials. Many forms of mHealth data are highly sensitive; in the hands of unintended parties such data may reveal indicators of a patient’s disorder, disability, or identity. Furthermore, if a malicious party tampers with the data, it can affect the diagnosis or treatment of patients, or the results of a research study. Although existing network protocols leverage encryption for confidentiality and integrity, network-level encryption does not provide end-to-end security from the device, through the smartphone and database, to downstream data consumers. In this thesis we provide a new open protocol that provides end-to-end authentication, confidentiality, and integrity for healthcare data in such a pipeline.
We present and evaluate a prototype implementation to demonstrate this protocol’s feasibility on low-power wearable devices, and present a case for the system’s ability to meet critical security properties under a specific adversary model and trust assumptions.
Advisor: David Kotz.
George Boateng, M.S., reports on new Amulet research in his Master’s thesis, available as a Dartmouth Computer Science Technical Report.
Abstract. Physical activity helps reduce the risk of cardiovascular disease, hypertension and obesity. The ability to monitor a person’s daily activity level can inform self-management of physical activity and related interventions. For older adults with obesity, the importance of regular, physical activity is critical to reduce the risk of long-term disability. In this work, we present ActivityAware, an application on the Amulet wrist-worn device that monitors the daily activity levels (low, moderate and vigorous) of older adults in real-time. The app continuously collects acceleration data on the Amulet, classifies the current activity level, updates the day’s accumulated time spent at that activity level, displays the results on the screen and logs summary data for later analysis.
The app implements an activity-level detection model we developed using a Linear Support Vector Machine (SVM). We trained our model using data from a user study, where subjects performed common physical activities (sit, stand, lay down, walk and run). We obtained accuracies up to 99.2% and 98.5% with 10-fold cross validation and leave-one-subject-out (LOSO) cross-validation respectively. We ran a week-long field study to evaluate the utility, usability and battery life of the ActivityAware system where 5 older adults wore the Amulet as it monitored their activity level. The utility evaluation showed that the app was somewhat useful in achieving the daily physical activity goal. The usability feedback showed that the ActivityAware system has the potential to be used by people for monitoring their activity levels. Our energy-efficiency evaluation revealed a battery life of at least 1 week before needing to recharge. The results are promising, indicating that the app may be used for activity-level monitoring by individuals or researchers for epidemiological studies, and eventually for the development of interventions that could improve the health of older adults.
Advisors: David Kotz, Ryan Halter, John Batsis