Afsaneh Doryab

Toss 'n' turn: smartphone as sleep and sleep quality detector

The rapid adoption of smartphones along with a growing habit for using these devices as alarm clocks presents an opportunity to use this device as a sleep detector. This adds value to UbiComp and personal informatics in terms of user context and new performance data to collect and visualize, and it benefits healthcare as sleep is correlated with many health issues. To assess this opportunity, we collected one month of phone sensor and sleep diary entries from 27 people who have a variety of sleep contexts. We used this data to construct models that detect sleep and wake states, daily sleep quality, and global sleep quality. Our system classifies sleep state with 93.06% accuracy, daily sleep quality with 83.97% accuracy, and overall sleep quality with 81.48% accuracy. Individual models performed better than generally trained models, where the individual models require 3 days of ground truth data and 3 weeks of ground truth data to perform well on detecting sleep and sleep quality, respectively. Finally, the features of noise and movement were useful to infer sleep quality.

BeWell: Sensing Sleep, Physical Activities and Social Interactions to Promote Wellbeing

Smartphone sensing and persuasive feedback design is enabling a new generation of wellbeing apps capable of automatically monitoring multiple aspects of physical and mental health. In this article, we present BeWell+ the next generation of the BeWell smartphone wellbeing app, which monitors user behavior along three health dimensions, namely sleep, physical activity, and social interaction. BeWell promotes improved behavioral patterns via feedback rendered as an ambient display on the smartphone’s wallpaper. With BeWell+, we introduce new mechanisms to address key limitations of the original BeWell app; specifically, (1) community adaptive wellbeing feedback, which generalizes to diverse user communities (e.g., elderly, children) by promoting better behavior yet remains realistic to the user’s lifestyle; and, (2) wellbeing adaptive energy allocation, which prioritizes monitoring fidelity and feedback responsiveness on specific health dimensions (e.g., sleep) where the user needs additional help. We evaluate BeWell+ with a 27 person, 19 day field trial. Our findings show that not only can BeWell+ operate successfully on consumer smartphones; but also users understand feedback and respond by taking steps towards leading healthier lifestyles.

Supporting disease insight through data analysis: refinements of the monarca self-assessment system

There is a growing interest in personal health technologies that sample behavioral data from a patient and visualize this data back to the patient for increased health awareness. However, a core challenge for patients is often to understand the connection between specific behaviors and health, i.e. to go beyond health awareness to disease insight. This paper presents MONARCA 2.0, which records subjective and objective data from patients suffering from bipolar disorder, processes this, and informs both the patient and clinicians on the importance of the different data items according to the patients mood. The goal is to provide patients with a increased insight into the parameters influencing the nature of their disease. The paper describes the user-centered design and the technical implementation of the system, as well as findings from an initial field deployment.

BeWell+: multi-dimensional wellbeing monitoring with community-guided user feedback and energy optimization

Smartphone sensing and persuasive feedback design is enabling a new generation of wellbeing applications capable of automatically monitoring multiple aspects of physical and mental health. In this paper, we present BeWell+ the next generation of the BeWell smartphone health app, which continuously monitors user behavior along three distinct health dimensions, namely sleep, physical activity, and social interaction. BeWell promotes improved behavioral patterns via feedback rendered as an ambient display on the smartphones wallpaper. With BeWell+, we introduce new wellbeing mechanisms to address challenges identified during the initial deployment of the BeWell app; specifically, (i) community adaptive wellbeing feedback, which automatically generalize to diverse user communities (e.g., elderly, young adults, children) by balancing the need to promote better behavior yet remains realistic to the users goals; and, (ii) wellbeing adaptive energy allocation, which prioritizes monitoring fidelity and feedback responsiveness on specific health dimensions of wellbeing (e.g., social interaction) where the user needs most help. We evaluate the performance of these mechanisms as part of an initial deployment and user study that includes 27 people using BeWell+ over a 19 day field trial. Our findings show that not only can BeWell+ operate successfully on consumer-grade smartphones, but users understand feedback and respond by taking positive steps towards leading healthier lifestyles.

Phase recognition during surgical procedures using embedded and body-worn sensors

In Ubiquitous Computing (Ubicomp) research, substantial work has been directed towards sensor-based detection and recognition of human activity. This research has, however, mainly been focused on activities of daily living of a single person. This paper presents a sensor platform and a machine learning approach to sense and detect phases of a surgical operation. Automatic detection of the progress of work inside an operating room has several important applications, including coordination, patient safety, and context-aware information retrieval. We verify the platform during a surgical simulation. Recognition of the main phases of an operation was done with a high degree of accuracy. Through further analysis, we were able to reveal which sensors provide the most significant input. This can be used in subsequent design of systems for use during real surgeries.

Impact factor analysis: combining prediction with parameter ranking to reveal the impact of behavior on health outcome

An increasing number of healthcare systems allow people to monitor behavior and provide feedback on health and wellness. Most applications, however, only offer feedback on behavior in form of visualization and data summaries. This paper presents a different approach—called impact factor analysis—in which machine learning techniques are used to infer the progression of a primary health parameter and then apply parameter ranking to investigate which behavioral data have the highest ‘impact’ on health. We have applied this approach to improve the MONARCA personal health application for patients suffering from bipolar disorder. In the MONARCA system, patients report their daily mood score and by analyzing self-reported and automatically sensed behavioral data with this mood score, the system is able to identify the impact of different behavior on the patient’s mood. We report from a study involving ten bipolar patients, in which we were able to estimate mood values with an average mean absolute error of 0.5. This was used to rank the behavior parameters whose variations indicate changes in the mental state. The rankings acquired from our algorithms correspond to the patients’ rankings, identifying physical activity and sleep as the highest impact parameters. These results revealed the feasibility of identifying behavioral impact factors. This data analysis motivated us to design an impact factor inference engine as part of the MONARCA system. To our knowledge, this is a novel approach in monitoring and control of mental illness, and we argue that the impact factor analysis can be useful in the design of other health and wellness systems.

Designing activity-aware recommender systems for operating rooms

This paper presents research in ubiquitous computing focusing on creating context- and activity-aware systems in collaborative environments such as hospitals. These activity-aware systems are able to infer human physical actions and subsequently offer services that support the users ongoing task. The paper introduces our initial design of an activity-aware recommender system for surgical procedures in operating rooms. Based on sensor input, the system automatically detects and recognizes co-located collaborative and concurrent human actions in the operating room, and uses this to show information and recommend actions to take, which are relevant to the current situation.

'MASTerful' Matchmaking in Service Transactions: Inferred Abilities, Needs and Interests versus Activity Histories

Timebanking is a growing type of peer-to-peer service exchange, but is hampered by the effort of finding good transaction partners. We seek to reduce this effort by using a Matching Algorithm for Service Transactions (MAST). MAST matches transaction partners in terms of similarity of interests and complementarity of abilities and needs. We present an experiment involving data and participants from a real timebanking network, that evaluates the acceptability of MAST, and shows that such an algorithm can retrieve matches that are subjectively better than matches based on matching the category of peoples historical offers or requests to the category of a current transaction request.

Activity-aware recommendation for collaborative work in operating rooms

This paper presents a recommender system for teams of medical professionals working collaboratively in hospital operating rooms. The system recommends relevant virtual actions, such as retrieval of information resources and initiation of communication with professionals outside the operating rooms. Recommendations are based on the current state of the ongoing operation as recognised from sensor data using machine learning techniques. The selection and non-selection of virtual actions during operations are interpreted as implicit feedback and used to update the weight matrices that guide recommendations. A pilot user study involving medical professionals indicates that the adaptation mechanism is effective and that the system provides adequate recommendations.

Activity recognition in collaborative environments

We present an approach to learning to recognize concurrent activities based on multiple data streams. One example is recognition of concurrent activities in hospital operating rooms based on multiple wearable and embedded sensors. This problem differs from standard time series classification in that there is no natural single target dimension, as multiple activities are performed at the same time. Hence, most existing approaches fail. The key innovations that allow us to tackle this problem is (1) learning to recognize base activities from raw sensor data, (2) creating artificial joint activities from base activities using frequent pattern mining and (3) handling temporal dependency using virtual evidence boosting.