Modeling Patterns of Activities using Activity Curves

Application of artificial intelligence in active assisted living for aging population in real-world setting with commercial devices - A scoping review

BACKGROUND

The aging population is steadily increasing, posing new challenges and opportunities for healthcare systems worldwide. Technological advancements, particularly in commercially available Active Assisted Living devices, offer a promising alternative. These readily accessible products, ranging from smartwatches to home automation systems, are often equipped with Artificial Intelligence capabilities that can monitor health metrics, predict adverse events, and facilitate a safer living environment. However, there is no review exploring how Artificial Intelligence has been integrated into commercially available Active Assisted Living technologies, and how these devices monitor health metrics and provide healthcare solutions in a real-world environment for healthy aging. This review is essential because it fills a knowledge gap in understanding AI's integration in Active Assisted Living technologies in promoting healthy aging in real-world settings, identifying key issues that require to be addressed in future studies.

OBJECTIVE

The aim of this overview is to outline current understanding, identify potential research opportunities, and highlight research gaps from published studies regarding the use of Artificial Intelligence in commercially available Active Assisted Living technologies that assists older individuals aging at home.

METHODS

A comprehensive search was conducted in six databases-PubMed, CINAHL, IEEE Xplore, Scopus, ACM Digital Library, and Web of Science-to identify relevant studies published over the past decade from 2013 to 2024. Our methodology adhered to the PRISMA extension for scoping reviews to ensure rigor and transparency throughout the review process. After applying predefined inclusion and exclusion criteria on 825 retrieved articles, a total of 64 papers were included for analysis and synthesis.

RESULTS

Several trends emerged from our analysis of the 64 selected papers. A majority of the work (39/64, 61%) was published after the year 2020. Geographically, most of the studies originated from East Asia and North America (36/64, 56%). The primary application goal of Artificial Intelligence in the reviewed literature was focused on activity recognition (34/64, 53%), followed by daily monitoring (10/64, 16%). Methodologically, tree-based and neural network-based approaches were the most prevalent Artificial Intelligence algorithms used in studies (32/64, 50% and 31/64, 48% respectively). A notable proportion of the studies (32/64, 50%) carried out their research using specially designed smart home testbeds that simulate the conditions in real-world. Moreover, ambient technology was a common thread (49/64, 77%), with occupancy-related data (such as motion and electrical appliance usage logs) and environmental sensors (indicators like temperature and humidity) being the most frequently used.

CONCLUSION

Our results suggest that Artificial Intelligence has been increasingly deployed in the real-world Active Assisted Living context over the past decade, offering a variety of applications aimed at healthy aging and facilitating independent living for the older adults. A wide range of smart home indicators were leveraged for comprehensive data analysis, exploring and enhancing the potentials and effectiveness of solutions. However, our review has identified multiple research gaps that need further investigation. First, most research has been conducted in controlled testbed environments, leaving a lack of real-world applications that could validate the technologies' efficacy and scalability. Second, there is a noticeable absence of research leveraging cloud technology, an essential tool for large-scale deployment and standardized data collection and management. Future work should prioritize these areas to maximize the potential benefits of Artificial Intelligence in Active Assisted Living settings.

Utilizing activity sensors to identify the behavioural activity patterns of elderly home care clients

PURPOSE

The behavioural activity pattern is a behavioural and biological 24-hour rhythm. Ageing, diseases and memory disorders can change this pattern. Home care staff can utilize knowledge about the behavioural activity pattern of elderly home care clients in many ways. The purpose of this study was to evaluate whether home care staff could identify the behavioural activity pattern of elderly home care clients using activity sensors, namely, actigraphs and motion sensors, could identify the behavioural activity rhythms.

MATERIALS AND METHODS

A total of four elderly home care clients and one elderly home rehabilitation client took part in the study. The participants wore actigraphs on their wrist and motion sensors were installed in their apartment. In addition to sensor data, home care staff answered one open-ended question during each home care visit. The data collection period was two weeks. Both quantitative and qualitative methods were used in the analysis.

RESULTS

The behavioural activity pattern was easy to identify from the motion sensor data, whereas actigraph data were difficult to interpret. The home care staff members' answers to open-ended questions reinforced the reliability of motion sensor data.

CONCLUSIONS

Motion sensors are relatively cheap, unobtrusive and reliable way to identify and detect changes in the behavioural activity patterns of elderly home care clients.Implications for rehabilitationMotion sensors are cheap, user-friendly and highly accepted technology for identifying and monitoring behavioural activity rhythm.Home care staff members can use the data about elderly home care client's behavioural activity rhythm to monitor deviations to the rhythm and detect changes in client's health.The information about behavioural activity rhythm can also be utilized in planning home care visits and interventions.

Codevelopment and Deployment of a System for the Telemonitoring of Activities of Daily Living Among Older Adults Receiving Home Care Services: Protocol for an Action Design Research Study

BACKGROUND

Telemonitoring of activities of daily living (ADLs) offers significant potential for gaining a deeper insight into the home care needs of older adults experiencing cognitive decline, particularly those living alone. In 2016, our team and a health care institution in Montreal, Quebec, Canada, sought to test this technology to enhance the support provided by home care clinical teams for older adults residing alone and facing cognitive deficits. The Support for Seniors' Autonomy program (SAPA [Soutien à l'autonomie des personnes âgées]) project was initiated within this context, embracing an innovative research approach that combines action research and design science.

OBJECTIVE

This paper presents the research protocol for the SAPA project, with the aim of facilitating the replication of similar initiatives in the future. The primary objectives of the SAPA project were to (1) codevelop an ADL telemonitoring system aligned with the requirements of key stakeholders, (2) deploy the system in a real clinical environment to identify specific use cases, and (3) identify factors conducive to its sustained use in a real-world setting. Given the context of the SAPA project, the adoption of an action design research (ADR) approach was deemed crucial. ADR is a framework for crafting practical solutions to intricate problems encountered in a specific organizational context.

METHODS

This project consisted of 2 cycles of development (alpha and beta) that involved cyclical repetitions of stages 2 and 3 to develop a telemonitoring system for ADLs. Stakeholders, such as health care managers, clinicians, older adults, and their families, were included in each codevelopment cycle. Qualitative and quantitative data were collected throughout this project.

RESULTS

The first iterative cycle, the alpha cycle, took place from early 2016 to mid 2018. The first prototype of an ADL telemonitoring system was deployed in the homes of 4 individuals receiving home care services through a public health institution. The prototype was used to collect data about care recipients' ADL routines. Clinicians used the data to support their home care intervention plan, and the results are presented here. The prototype was successfully deployed and perceived as useful, although obstacles were encountered. Similarly, a second codevelopment cycle (beta cycle) took place in 3 public health institutions from late 2018 to late 2022. The telemonitoring system was installed in 31 care recipients' homes, and detailed results will be presented in future papers.

CONCLUSIONS

To our knowledge, this is the first reported ADR project in ADL telemonitoring research that includes 2 iterative cycles of codevelopment and deployment embedded in the real-world clinical settings of a public health system. We discuss the artifacts, generalization of learning, and dissemination generated by this protocol in the hope of providing a concrete and replicable example of research partnerships in the field of digital health in cognitive aging.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

RR1-10.2196/52284.

Multimodal Fusion of Smart Home and Text-based Behavior Markers for Clinical Assessment Prediction

New modes of technology are offering unprecedented opportunities to unobtrusively collect data about people's behavior. While there are many use cases for such information, we explore its utility for predicting multiple clinical assessment scores. Because clinical assessments are typically used as screening tools for impairment and disease, such as mild cognitive impairment (MCI), automatically mapping behavioral data to assessment scores can help detect changes in health and behavior across time. In this paper, we aim to extract behavior markers from two modalities, a smart home environment and a custom digital memory notebook app, for mapping to ten clinical assessments that are relevant for monitoring MCI onset and changes in cognitive health. Smart home-based behavior markers reflect hourly, daily, and weekly activity patterns, while app-based behavior markers reflect app usage and writing content/style derived from free-form journal entries. We describe machine learning techniques for fusing these multimodal behavior markers and utilizing joint prediction. We evaluate our approach using three regression algorithms and data from 14 participants with MCI living in a smart home environment. We observed moderate to large correlations between predicted and ground-truth assessment scores, ranging from r = 0.601 to r = 0.871 for each clinical assessment.

Detecting Smartwatch-based Behavior Change in Response to a Multi-domain Brain Health Intervention

In this study, we introduce and validate a computational method to detect lifestyle change that occurs in response to a multi-domain healthy brain aging intervention. To detect behavior change, digital behavior markers (DM) are extracted from smartwatch sensor data and a Permutation-based Change Detection (PCD) algorithm quantifies the change in marker-based behavior from a pre-intervention, one-week baseline. To validate the method, we verify that changes are successfully detected from synthetic data with known pattern differences. Next, we employ this method to detect overall behavior change for n=28 BHI subjects and n=17 age-matched control subjects. For these individuals, we observe a monotonic increase in behavior change from the baseline week with a slope of 0.7460 for the intervention group and a slope of 0.0230 for the control group. Finally, we utilize a random forest algorithm to perform leave-one-subject-out prediction of intervention versus control subjects based on digital marker delta values. The random forest predicts whether the subject is in the intervention or control group with an accuracy of 0.87. This work has implications for capturing objective, continuous data to inform our understanding of intervention adoption and impact.

Ageing Safely in the Digital Era: A New Unobtrusive Activity Monitoring Framework Leveraging on Daily Interactions with Hand-Operated Appliances

Supporting the elderly to maintain their independence, safety, and well-being through Active Assisted Living (AAL) technologies, is gaining increasing momentum. Recently, Non-intrusive Load Monitoring (NILM) approaches have become the focus of these technologies due to their non-intrusiveness and reduced price. Whilst some research has been carried out in this respect; it still is challenging to design systems considering the heterogeneity and complexity of daily routines. Furthermore, scholars gave little attention to evaluating recent deep NILM models in AAL applications. We suggest a new interactive framework for activity monitoring based on custom user-profiles and deep NILM models to address these gaps. During evaluation, we consider four different deep NILM models. The proposed contribution is further assessed on two households from the REFIT dataset for a period of one year, including the influence of NILM on activity monitoring. To the best of our knowledge, the current study is the first to quantify the error propagated by a NILM model on the performance of an AAL solution. The results achieved are promising, particularly when considering the UNET-NILM model, a multi-task convolutional neural network for load disaggregation, that revealed a deterioration of only 10% in the f1-measure of the framework's overall performance.

Indoor Location Data for Tracking Human Behaviours: A Scoping Review

Real-time location systems (RTLS) record locations of individuals over time and are valuable sources of spatiotemporal data that can be used to understand patterns of human behaviour. Location data are used in a wide breadth of applications, from locating individuals to contact tracing or monitoring health markers. To support the use of RTLS in many applications, the varied ways location data can describe patterns of human behaviour should be examined. The objective of this review is to investigate behaviours described using indoor location data, and particularly the types of features extracted from RTLS data to describe behaviours. Four major applications were identified: health status monitoring, consumer behaviours, developmental behaviour, and workplace safety/efficiency. RTLS data features used to analyse behaviours were categorized into four groups: dwell time, activity level, trajectory, and proximity. Passive sensors that provide non-uniform data streams and features with lower complexity were common. Few studies analysed social behaviours between more than one individual at once. Less than half the health status monitoring studies examined clinical validity against gold-standard measures. Overall, spatiotemporal data from RTLS technologies are useful to identify behaviour patterns, provided there is sufficient richness in location data, the behaviour of interest is well-characterized, and a detailed feature analysis is undertaken.

Identifying and Monitoring the Daily Routine of Seniors Living at Home

As the population in the Western world is rapidly aging, the remote monitoring solutions integrated into the living environment of seniors have the potential to reduce the care burden helping them to self-manage problems associated with old age. The daily routine is considered a useful tool for addressing age-related problems having additional benefits for seniors like reduced stress and anxiety, increased feeling of safety and security. In this paper, we propose a solution for identifying the daily routines of seniors using the monitored activities of daily living and for inferring deviations from the routines that may require caregivers’ interventions. A Markov model-based method is defined to identify the daily routines, while entropy rate and cosine functions are used to measure and assess the similarity between the daily monitored activities in a day and the inferred routine. A distributed monitoring system was developed that uses Beacons and trilateration techniques for monitoring the activities of older adults. The results are promising, the proposed techniques can identify the daily routines with confidence concerning the activity duration of 0.98 and the sequence of activities in the interval of [0.0794, 0.0829]. Regarding deviation identification, our method obtains 0.88 as the best sensitivity value with an average precision of 0.95.

Behavioral Differences Between Subject Groups Identified Using Smart Homes and Change Point Detection

With the arrival of the internet of things, smart environments are becoming increasingly ubiquitous in our everyday lives. Sensor data collected from smart home environments can provide unobtrusive, longitudinal time series data that are representative of the smart home resident's routine behavior and how this behavior changes over time. When longitudinal behavioral data are available from multiple smart home residents, differences between groups of subjects can be investigated. Group-level discrepancies may help isolate behaviors that manifest in daily routines due to a health concern or major lifestyle change. To acquire such insights, we propose an algorithmic framework based on change point detection called Behavior Change Detection for Groups (BCD-G). We hypothesize that, using BCD-G, we can quantify and characterize differences in behavior between groups of individual smart home residents. We evaluate our BCD-G framework using one month of continuous sensor data for each of fourteen smart home residents, divided into two groups. All subjects in the first group are diagnosed with cognitive impairment. The second group consists of cognitively healthy, age-matched controls. Using BCD-G, we identify differences between these two groups, such as how impairment affects patterns of performing activities of daily living and how clinically-relevant behavioral features, such as in-home walking speed, differ for cognitively-impaired individuals. With the unobtrusive monitoring of smart home environments, clinicians can use BCD-G for remote identification of behavior changes that are early indicators of health concerns.

Technology Used to Recognize Activities of Daily Living in Community-Dwelling Older Adults

The use of technology has been suggested as a means of allowing continued autonomous living for older adults, while reducing the burden on caregivers and aiding decision-making relating to healthcare. However, more clarity is needed relating to the Activities of Daily Living (ADL) recognised, and the types of technology included within current monitoring approaches. This review aims to identify these differences and highlight the current gaps in these systems. A scoping review was conducted in accordance with PRISMA-ScR, drawing on PubMed, Scopus, and Google Scholar. Articles and commercially available systems were selected if they focused on ADL recognition of older adults within their home environment. Thirty-nine ADL recognition systems were identified, nine of which were commercially available. One system incorporated environmental and wearable technology, two used only wearable technology, and 34 used only environmental technologies. Overall, 14 ADL were identified but there was variation in the specific ADL recognised by each system. Although the use of technology to monitor ADL of older adults is becoming more prevalent, there is a large variation in the ADL recognised, how ADL are defined, and the types of technology used within monitoring systems. Key stakeholders, such as older adults and healthcare workers, should be consulted in future work to ensure that future developments are functional and useable.

Using Ambient Assisted Living to Monitor Older Adults With Alzheimer Disease: Single-Case Study to Validate the Monitoring Report

BACKGROUND

Many older adults choose to live independently in their homes for as long as possible, despite psychosocial and medical conditions that compromise their independence in daily living and safety. Faced with unprecedented challenges in allocating resources, home care administrators are increasingly open to using monitoring technologies known as ambient assisted living (AAL) to better support care recipients. To be effective, these technologies should be able to report clinically relevant changes to support decision making at an individual level.

OBJECTIVE

The aim of this study is to examine the concurrent validity of AAL monitoring reports and information gathered by care professionals using triangulation.

METHODS

This longitudinal single-case study spans over 490 days of monitoring a 90-year-old woman with Alzheimer disease receiving support from local health care services. A clinical nurse in charge of her health and social care was interviewed 3 times during the project. Linear mixed models for repeated measures were used to analyze each daily activity (ie, sleep, outing activities, periods of low mobility, cooking-related activities, hygiene-related activities). Significant changes observed in data from monitoring reports were compared with information gathered by the care professional to explore concurrent validity.

RESULTS

Over time, the monitoring reports showed evolving trends in the care recipient's daily activities. Significant activity changes occurred over time regarding sleep, outings, cooking, mobility, and hygiene-related activities. Although the nurse observed some trends, the monitoring reports highlighted information that the nurse had not yet identified. Most trends detected in the monitoring reports were consistent with the clinical information gathered by the nurse. In addition, the AAL system detected changes in daily trends following an intervention specific to meal preparation.

CONCLUSIONS

Overall, trends identified by AAL monitoring are consistent with clinical reports. They help answer the nurse's questions and help the nurse develop interventions to maintain the care recipient at home. These findings suggest the vast potential of AAL technologies to support health care services and aging in place by providing valid and clinically relevant information over time regarding activities of daily living. Such data are essential when other sources yield incomplete information for decision making.

Linguistic summarization of in-home sensor data

INTRODUCTION

With the increase in the population of older adults around the world, a significant amount of work has been done on in-home sensor technology to aid the elderly age independently. However, due to the large amounts of data generated by the sensors, it takes a lot of effort and time for the clinicians to makes sense of this data. In this work, we develop a system to help make this data more useful by presenting it in the form of natural language.

METHODS

We start by identifying important attributes in the sensor data that are relevant to the health of the elderly. We then develop algorithms to extract these important health related features from the sensor parameters and summarize them in natural language. We focus on making the natural language summaries to be informative, accurate and concise.

RESULTS

We designed multiple surveys using real and synthetic data to validate the summaries produced by our algorithms. We show that the algorithms produce meaningful results comparable to human subjects. We also implemented our linguistic summarization system to produce summaries of data leading to health alerts derived from the sensor data. The system is running live in 110 apartments currently. By the means of retrospective case studies, we illustrate that the linguistic summaries are able to make the connection between changes in the sensor data and the health of the elderly.

CONCLUSIONS

We present a system that extracts important clinically relevant features from in-home sensor data generated in the apartments of the elderly and summarize those features in natural language. The preliminary testing of our summarization system shows that it has the potential to help the clinicians utilize this data effectively.

Iterative Design of Visual Analytics for a Clinician-in-the-Loop Smart Home

In order to meet the health needs of the coming "age wave," technology needs to be designed that supports remote health monitoring and assessment. In this study we design clinician in the loop (CIL), a clinician-in-the-loop visual interface, that provides clinicians with patient behavior patterns, derived from smart home data. A total of 60 experienced nurses participated in an iterative design of an interactive graphical interface for remote behavior monitoring. Results of the study indicate that usability of the system improves over multiple iterations of participatory design. In addition, the resulting interface is useful for identifying behavior patterns that are indicative of chronic health conditions and unexpected health events. This technology offers the potential to support self-management and chronic conditions, even for individuals living in remote locations.

Robot-Enabled Support of Daily Activities in Smart Home Environments

Smart environments offer valuable technologies for activity monitoring and health assessment. Here, we describe an integration of robots into smart environments to provide more interactive support of individuals with functional limitations. RAS, our Robot Activity Support system, partners smart environment sensing, object detection and mapping, and robot interaction to detect and assist with activity errors that may occur in everyday settings. We describe the components of the RAS system and demonstrate its use in a smart home testbed. To evaluate the usability of RAS, we also collected and analyzed feedback from participants who received assistance from RAS in a smart home setting as they performed routine activities.

Windows Into Human Health Through Wearables Data Analytics

Background

Wearable sensors (wearables) have been commonly integrated into a wide variety of commercial products and are increasingly being used to collect and process raw physiological parameters into salient digital health information. The data collected by wearables are currently being investigated across a broad set of clinical domains and patient populations. There is significant research occurring in the domain of algorithm development, with the aim of translating raw sensor data into fitness- or health-related outcomes of interest for users, patients, and health care providers.

Objectives

The aim of this review is to highlight a selected group of fitness- and health-related indicators from wearables data and to describe several algorithmic approaches used to generate these higher order indicators.

Methods

A systematic search of the Pubmed database was performed with the following search terms (number of records in parentheses): Fitbit algorithm (18), Apple Watch algorithm (3), Garmin algorithm (5), Microsoft Band algorithm (8), Samsung Gear algorithm (2), Xiaomi MiBand algorithm (1), Huawei Band (Watch) algorithm (2), photoplethysmography algorithm (465), accelerometry algorithm (966), ECG algorithm (8287), continuous glucose monitor algorithm (343). The search terms chosen for this review are focused on algorithms for wearable devices that dominated the commercial wearables market between 2014-2017 and that were highly represented in the biomedical literature. A second set of search terms included categories of algorithms for fitness-related and health-related indicators that are commonly used in wearable devices (e.g. accelerometry, PPG, ECG). These papers covered the following domain areas: fitness; exercise; movement; physical activity; step count; walking; running; swimming; energy expenditure; atrial fibrillation; arrhythmia; cardiovascular; autonomic nervous system; neuropathy; heart rate variability; fall detection; trauma; behavior change; diet; eating; stress detection; serum glucose monitoring; continuous glucose monitoring; diabetes mellitus type 1; diabetes mellitus type 2. All studies uncovered through this search on commercially available device algorithms and pivotal studies on sensor algorithm development were summarized, and a summary table was constructed using references generated by the literature review as described (Table 1).

Conclusions

Wearable health technologies aim to collect and process raw physiological or environmental parameters into salient digital health information. Much of the current and future utility of wearables lies in the signal processing steps and algorithms used to analyze large volumes of data. Continued algorithmic development and advances in machine learning techniques will further increase analytic capabilities. In the context of these advances, our review aims to highlight a range of advances in fitness- and other health-related indicators provided by current wearable technologies.

Analyzing Sensor-Based Time Series Data to Track Changes in Physical Activity during Inpatient Rehabilitation

Time series data collected from sensors can be analyzed to monitor changes in physical activity as an individual makes a substantial lifestyle change, such as recovering from an injury or illness. In an inpatient rehabilitation setting, approaches to detect and explain changes in longitudinal physical activity data collected from wearable sensors can provide value as a monitoring, research, and motivating tool. We adapt and expand our Physical Activity Change Detection (PACD) approach to analyze changes in patient activity in such a setting. We use Fitbit Charge Heart Rate devices with two separate populations to continuously record data to evaluate PACD, nine participants in a hospitalized inpatient rehabilitation group and eight in a healthy control group. We apply PACD to minute-by-minute Fitbit data to quantify changes within and between the groups. The inpatient rehabilitation group exhibited greater variability in change throughout inpatient rehabilitation for both step count and heart rate, with the greatest change occurring at the end of the inpatient hospital stay, which exceeded day-to-day changes of the control group. Our additions to PACD support effective change analysis of wearable sensor data collected in an inpatient rehabilitation setting and provide insight to patients, clinicians, and researchers.

Smart Secure Homes: A Survey of Smart Home Technologies that Sense, Assess, and Respond to Security Threats

Smart home design has undergone a metamorphosis in recent years. The field has evolved from designing theoretical smart home frameworks and performing scripted tasks in laboratories. Instead, we now find robust smart home technologies that are commonly used by large segments of the population in a variety of settings. Recent smart home applications are focused on activity recognition, health monitoring, and automation. In this paper, we take a look at another important role for smart homes: security. We first explore the numerous ways smart homes can and do provide protection for their residents. Next, we provide a comparative analysis of the alternative tools and research that has been developed for this purpose. We investigate not only existing commercial products that have been introduced but also discuss the numerous research that has been focused on detecting and identifying potential threats. Finally, we close with open challenges and ideas for future research that will keep individuals secure and healthy while in their own homes.

Assessing Human Activity in Elderly People Using Non-Intrusive Load Monitoring

The ageing of the population, and their increasing wish of living independently, are motivating the development of welfare and healthcare models. Existing approaches based on the direct heath-monitoring using body sensor networks (BSN) are precise and accurate. Nonetheless, their intrusiveness causes non-acceptance. New approaches seek the indirect monitoring through monitoring activities of daily living (ADLs), which proves to be a suitable solution. ADL monitoring systems use many heterogeneous sensors, are less intrusive, and are less expensive than BSN, however, the deployment and maintenance of wireless sensor networks (WSN) prevent them from a widespread acceptance. In this work, a novel technique to monitor the human activity, based on non-intrusive load monitoring (NILM), is presented. The proposal uses only smart meter data, which leads to minimum intrusiveness and a potential massive deployment at minimal cost. This could be the key to develop sustainable healthcare models for smart homes, capable of complying with the elderly people' demands. This study also uses the Dempster-Shafer theory to provide a daily score of normality with regard to the regular behavior. This approach has been evaluated using real datasets and, additionally, a benchmarking against a Gaussian mixture model approach is presented.

Forecasting behavior in smart homes based on sleep and wake patterns

BACKGROUND

The goal of this research is to use smart home technology to assist people who are recovering from injuries or coping with disabilities to live independently.

OBJECTIVE

We introduce an algorithm to model and forecast wake and sleep behaviors that are exhibited by the participant. Furthermore, we propose that sleep behavior is impacted by and can be modeled from wake behavior, and vice versa.

METHODS

This paper describes the Behavior Forecasting (BF) algorithm. BF consists of 1) defining numeric values that reflect sleep and wake behavior, 2) forecasting wake and sleep values from past behavior, 3) analyzing the effect of wake behavior on sleep and vice versa, and 4) improving prediction performance by using both wake and sleep scores.

RESULTS

The BF method was evaluated with data collected from 20 smart homes. We found that regardless of the forecasting method utilized, wake behavior and sleep behavior can be modeled with a minimum accuracy of 84%. Additionally, normalizing the wake and sleep scores drastically improves the accuracy to 99%.

CONCLUSIONS

The results show that we can effectively model wake and sleep behaviors in a smart environment. Furthermore, wake behaviors can be predicted from sleep behaviors and vice versa.

Unsupervised detection and analysis of changes in everyday physical activity data

Sensor-based time series data can be utilized to monitor changes in human behavior as a person makes a significant lifestyle change, such as progress toward a fitness goal. Recently, wearable sensors have increased in popularity as people aspire to be more conscientious of their physical health. Automatically detecting and tracking behavior changes from wearable sensor-collected physical activity data can provide a valuable monitoring and motivating tool. In this paper, we formalize the problem of unsupervised physical activity change detection and address the problem with our Physical Activity Change Detection (PACD) approach. PACD is a framework that detects changes between time periods, determines significance of the detected changes, and analyzes the nature of the changes. We compare the abilities of three change detection algorithms from the literature and one proposed algorithm to capture different types of changes as part of PACD. We illustrate and evaluate PACD on synthetic data and using Fitbit data collected from older adults who participated in a health intervention study. Results indicate PACD detects several changes in both datasets. The proposed change algorithms and analysis methods are useful data mining techniques for unsupervised, window-based change detection with potential to track users' physical activity and motivate progress toward their health goals.