Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
563
result(s) for
"Cook, Diane"
Sort by:
A survey of methods for time series change point detection
Change points are abrupt variations in time series data. Such abrupt changes may represent transitions that occur between states. Detection of change points is useful in modelling and prediction of time series and is found in application areas such as medical condition monitoring, climate change detection, speech and image analysis, and human activity analysis. This survey article enumerates, categorizes, and compares many of the methods that have been proposed to detect change points in time series. The methods examined include both supervised and unsupervised algorithms that have been introduced and evaluated. We introduce several criteria to compare the algorithms. Finally, we present some grand challenges for the community to consider.
Journal Article
SynSys: A Synthetic Data Generation System for Healthcare Applications
Creation of realistic synthetic behavior-based sensor data is an important aspect of testing machine learning techniques for healthcare applications. Many of the existing approaches for generating synthetic data are often limited in terms of complexity and realism. We introduce SynSys, a machine learning-based synthetic data generation method, to improve upon these limitations. We use this method to generate synthetic time series data that is composed of nested sequences using hidden Markov models and regression models which are initially trained on real datasets. We test our synthetic data generation technique on a real annotated smart home dataset. We use time series distance measures as a baseline to determine how realistic the generated data is compared to real data and demonstrate that SynSys produces more realistic data in terms of distance compared to random data generation, data from another home, and data from another time period. Finally, we apply our synthetic data generation technique to the problem of generating data when only a small amount of ground truth data is available. Using semi-supervised learning we demonstrate that SynSys is able to improve activity recognition accuracy compared to using the small amount of real data alone.
Journal Article
Activity learning : discovering, recognizing, and predicting human behavior from sensor data
Defines the notion of an activity model learned from sensor data and presents key algorithms that form the core of the field
Activity Learning: Discovering, Recognizing and Predicting Human Behavior from Sensor Data provides an in-depth look at computational approaches to activity learning from sensor data. Each chapter is constructed to provide practical, step-by-step information on how to analyze and process sensor data. The book discusses techniques for activity learning that include the following:
* Discovering activity patterns that emerge from behavior-based sensor data
* Recognizing occurrences of predefined or discovered activities in real time
* Predicting the occurrences of activities
The techniques covered can be applied to numerous fields, including security, telecommunications, healthcare, smart grids, and home automation. An online companion site enables readers to experiment with the techniques described in the book, and to adapt or enhance the techniques for their own use. With an emphasis on computational approaches, Activity Learning: Discovering, Recognizing, and Predicting Human Behavior from Sensor Data provides graduate students and researchers with an algorithmic perspective to activity learning.
eBook
How Smart Is Your Home?
Technical advances are bringing intelligent homes that respond to residents' needs and wishes within reach. Individuals spend most of their time in their home or workplace; for many, these places are their sanctuaries. Over the course of the 20th century, technological advances have helped to enhance the comfort and shelter provided by our homes. Insights gained from capturing and modeling behavior in these places may be useful in making our environments more intelligent and responsive to our needs. Recent advances are bringing such “ambient intelligence” in the home closer to reality.
Journal Article
Dementia Care Research and Psychosocial Factors
Understanding the relationship between behavior, environment, and dementia risk is critical for assessing well-being and designing interventions. Smartwatch sensor data can provide objective insights into these relationships. This study examines digital markers associated with EMA responses in a cohort from rural Florida.
Data were collected for 17 participants who wore Apple Watches daily. The watches used an in-house app that queried participants 4x/day about physical activity, anxiety, air quality, and smoke exposure, rated on a scale from 1 (not at all) to 5 (very much). Each day, participants reported time spent with friends/family and neighbors. They also completed our custom 45-second smartwatch-based n-back shape test to measure cognition. Home was defined as the most frequent location each morning, and social isolation was estimated as the percent time spent at home. We analyzed EMA responses, n-back scores, and their correlations with social isolation.
Participants wore watches for Mean = 356.78 hours (SD = 189.45) and responded to Mean = 89.18 prompts (SD = 51.36). Response distributions were active: M = 2.91, SD = 1.22; anxious: M = 1.59, SD = 0.86; air: M = 3.36, SD = 1.39; smoke: M = 1.18, SD = 0.60; friends/family: M = 2.66, SD = 1.29; neighbors: M = 2.20, SD = 1.30. N-back scores were M = 19.71 (SD = 4.84). Small correlations were observed between n-back scores and activity level (r = -0.34), anxiety (r = 0.30), and time with friends/family (r = 0.18). Activity was correlated with neighbor time (r = 0.39). Additionally, friend/family time correlated positively with neighbor time (r = 0.53) and negatively with time spent at home (r = -0.11), while neighbor time correlated positively with time spent at home (r = 0.14). The negative correlation between n-back score and time spent at home was very small (r = -0.04).
Smartwatch data that include a real-time measure of cognition offer valuable insights into the relationship between self-reported states, behavior, and air quality. Larger, more diverse samples are needed to enhance the generalizability of these findings.
Journal Article