Automated Detection of Activity Transitions for Prompting

ClaSP: parameter-free time series segmentation

The study of natural and human-made processes often results in long sequences of temporally-ordered values, aka time series (TS). Such processes often consist of multiple states, e.g. operating modes of a machine, such that state changes in the observed processes result in changes in the distribution of shape of the measured values. Time series segmentation (TSS) tries to find such changes in TS post-hoc to deduce changes in the data-generating process. TSS is typically approached as an unsupervised learning problem aiming at the identification of segments distinguishable by some statistical property. Current algorithms for TSS require domain-dependent hyper-parameters to be set by the user, make assumptions about the TS value distribution or the types of detectable changes which limits their applicability. Common hyper-parameters are the measure of segment homogeneity and the number of change points, which are particularly hard to tune for each data set. We present ClaSP, a novel, highly accurate, hyper-parameter-free and domain-agnostic method for TSS. ClaSP hierarchically splits a TS into two parts. A change point is determined by training a binary TS classifier for each possible split point and selecting the one split that is best at identifying subsequences to be from either of the partitions. ClaSP learns its main two model-parameters from the data using two novel bespoke algorithms. In our experimental evaluation using a benchmark of 107 data sets, we show that ClaSP outperforms the state of the art in terms of accuracy and is fast and scalable. Furthermore, we highlight properties of ClaSP using several real-world case studies.

Are Smart Homes Adequate for Older Adults with Dementia?

Smart home technologies can enable older adults, including those with dementia, to live more independently in their homes for a longer time. Activity recognition, in combination with anomaly detection, has shown the potential to recognise users’ daily activities and detect deviations. However, activity recognition and anomaly detection are not sufficient, as they lack the capacity to capture the progression of patients’ habits across the different stages of dementia. To achieve this, smart homes should be enabled to recognise patients’ habits and changes in habits, including the loss of some habits. In this study, we first present an overview of the stages that characterise dementia, alongside real-world personas that depict users’ behaviours at each stage. Then, we survey the state of the art on activity recognition in smart homes for older adults with dementia, including the literature that combines activity recognition and anomaly detection. We categorise the literature based on goals, stages of dementia, and targeted users. Finally, we justify the necessity for habit recognition in smart homes for older adults with dementia, and we discuss the research challenges related to its implementation.

Partnering a Compensatory Application with Activity-Aware Prompting to Improve Use in Individuals with Amnestic Mild Cognitive Impairment: A Randomized Controlled Pilot Clinical Trial

BACKGROUND

Compensatory aids can help mitigate the impact of progressive cognitive impairment on daily living.

OBJECTIVE

We evaluate whether the learning and sustained use of an Electronic Memory and Management Aid (EMMA) application can be augmented through a partnership with real-time, activity-aware transition-based prompting delivered by a smart home.

METHODS

Thirty-two adults who met criteria for amnestic mild cognitive impairment (aMCI) were randomized to learn to use the EMMA app on its own (N = 17) or when partnered with smart home prompting (N = 15). The four-week, five-session manualized EMMA training was conducted individually in participant homes by trained clinicians. Monthly questionnaires were completed by phone with trained personnel blind to study hypotheses. EMMA data metrics were collected continuously for four months. For the partnered condition, activity-aware prompting was on during training and post-training months 1 and 3, and off during post-training month 2.

RESULTS

The analyzed aMCI sample included 15 EMMA-only and 14 partnered. Compared to the EMMA-only condition, by week four of training, participants in the partnered condition were engaging with EMMA more times daily and using more basic and advanced features. These advantages were maintained throughout the post-training phase with less loss of EMMA app use over time. There was little differential impact of the intervention on self-report primary (everyday functioning, quality of life) and secondary (coping, satisfaction with life) outcomes.

CONCLUSION

Activity-aware prompting technology enhanced acquisition, habit formation and long-term use of a digital device by individuals with aMCI. (ClinicalTrials.gov NCT03453554).

An entropy-based approach to the study of human mobility and behavior in private homes

Understanding human mobility in outdoor environments is critical for many applications including traffic modeling, urban planning, and epidemic modeling. Using data collected from mobile devices, researchers have studied human mobility in outdoor environments and found that human mobility is highly regular and predictable. In this study, we focus on human mobility in private homes. Understanding this type of human mobility is essential as smart-homes and their assistive applications become ubiquitous. We model the movement of a resident using ambient motion sensor data and construct a chronological symbol sequence that represents the resident's movement trajectory. Entropy rate is used to quantify the regularity of the resident's mobility patterns, and an upper bound of predictability is estimated. However, the presence of visitors and malfunctioning sensors result in data that is not representative of the resident's mobility patterns. We apply a change-point detection algorithm based on penalized contrast function to detect these changes, and to identify the time periods when the data do not completely reflect the resident's activities. Experimental results using the data collected from 10 private homes over periods of 178 to 713 days show that human mobility at home is also highly predictable in the range of 70% independent of variations in floor plans and individual daily routines.

Evaluating the Performance of Sensor-based Bout Detection Algorithms: The Transition Pairing Method

Bout detection algorithms are used to segment data from wearable sensors, but it is challenging to assess segmentation correctness.

Purpose

To present and demonstrate the Transition Pairing Method (TPM), a new method for evaluating the performance of bout detection algorithms.

Methods

The TPM compares predicted transitions to a criterion measure in terms of number and timing. A true positive is defined as a predicted transition that corresponds with one criterion transition in a mutually exclusive pair. The pairs are established using an extended Gale-Shapley algorithm, and the user specifies a maximum allowable within-pair time lag, above which pairs cannot be formed. Unpaired predictions and criteria are false positives and false negatives, respectively. The demonstration used raw acceleration data from 88 youth who wore ActiGraph GT9X monitors (right hip and non-dominant wrist) during simulated free-living. Youth Sojourn bout detection algorithms were applied (one for each attachment site), and the TPM was used to compare predicted bout transitions to the criterion measure (direct observation). Performance metrics were calculated for each participant, and hip-versus-wrist means were compared using paired T-tests (α = 0.05).

Results

When the maximum allowable lag was 1-s, both algorithms had recall <20% (2.4% difference from one another, p<0.01) and precision <10% (1.4% difference from one another, p<0.001). That is, >80% of criterion transitions were undetected, and >90% of predicted transitions were false positives.

Conclusion

The TPM improves on conventional analyses by providing specific information about bout detection in a standardized way that applies to any bout detection algorithm.

Cook D. Easing Power Consumption of Wearable Activity Monitoring with Change Point Detection

Continuous monitoring of complex activities is valuable for understanding human behavior and providing activity-aware services. At the same time, recognizing these activities requires both movement and location information that can quickly drain batteries on wearable devices. In this paper, we introduce Change Point-based Activity Monitoring (CPAM), an energy-efficient strategy for recognizing and monitoring a range of simple and complex activities in real time. CPAM employs unsupervised change point detection to detect likely activity transition times. By adapting the sampling rate at each change point, CPAM reduces energy consumption by 74.64% while retaining the activity recognition performance of continuous sampling. We validate our approach using smartwatch data collected and labeled by 66 subjects. Results indicate that change point detection techniques can be effective for reducing the energy footprint of sensor-based mobile applications and that automated activity labels can be used to estimate sensor values between sampling periods.

Real-Time Change Point Detection with application to Smart Home Time Series Data

Change Point Detection (CPD) is the problem of discovering time points at which the behavior of a time series changes abruptly. In this paper, we present a novel real-time nonparametric change point detection algorithm called SEP, which uses Separation distance as a divergence measure to detect change points in high-dimensional time series. Through experiments on artificial and real-world datasets, we demonstrate the usefulness of the proposed method in comparison with existing methods.

An Integrative Analysis of Time-varying Regulatory Networks From High-dimensional Data

Directed networks have been widely used to describe many biological processes and functions. Understanding the structure of biological networks, especially regulatory networks, could help discover the mechanisms underlying important biological processes and pathogenesis of diseases. Most network inference methods assume the network structure is time-invariant or stationary. However, in some processes, the network structure is non-stationary or time-varying. The stationary network inference methods might not be able to directly used to reconstruct time-varying networks. Some non-stationary network learning methods have been proposed to infer the networks, but, the inferred networks are not regulatory networks which require activation and inhibition information. This work proposes an integrative approach, which combines the changepoint estimation, weighted network learning and searching, and model checking technique, to reconstruct time varying regulatory networks from high-dimensional time series data. We illustrate this approach to study the structure changes of Drosophila's regulatory networks in its life cycle.

Learning Activity Predictors from Sensor Data: Algorithms, Evaluation, and Applications

Recent progress in Internet of Things (IoT) platforms has allowed us to collect large amounts of sensing data. However, there are significant challenges in converting this large-scale sensing data into decisions for real-world applications. Motivated by applications like health monitoring and intervention and home automation we consider a novel problem called Activity Prediction, where the goal is to predict future activity occurrence times from sensor data. In this paper, we make three main contributions. First, we formulate and solve the activity prediction problem in the framework of imitation learning and reduce it to a simple regression learning problem. This approach allows us to leverage powerful regression learners that can reason about the relational structure of the problem with negligible computational overhead. Second, we present several metrics to evaluate activity predictors in the context of real-world applications. Third, we evaluate our approach using real sensor data collected from 24 smart home testbeds. We also embed the learned predictor into a mobile-device-based activity prompter and evaluate the app for 9 participants living in smart homes. Our results indicate that our activity predictor performs better than the baseline methods, and offers a simple approach for predicting activities from sensor data.

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.

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.

A Genetic Algorithm Approach to Motion Sensor Placement in Smart Environments

Smart environments and ubiquitous computing technologies hold great promise for a wide range of real world applications. The medical community is particularly interested in high quality measurement of activities of daily living. With accurate computer modeling of older adults, decision support tools may be built to assist care providers. One aspect of effectively deploying these technologies is determining where the sensors should be placed in the home to effectively support these end goals. This work introduces and evaluates a set of approaches for generating sensor layouts in the home. These approaches range from the gold standard of human intuition-based placement to more advanced search algorithms, including Hill Climbing and Genetic Algorithms. The generated layouts are evaluated based on their ability to detect activities while minimizing the number of needed sensors. Sensor-rich environments can provide valuable insights about adults as they go about their lives. These sensors, once in place, provide information on daily behavior that can facilitate an aging-in-place approach to health care.

Dynamic detection of window starting positions and its implementation within an activity recognition framework

Activity recognition is an intrinsic component of many pervasive computing and ambient intelligent solutions. This has been facilitated by an explosion of technological developments in the area of wireless sensor network, wearable and mobile computing. Yet, delivering robust activity recognition, which could be deployed at scale in a real world environment, still remains an active research challenge. Much of the existing literature to date has focused on applying machine learning techniques to pre-segmented data collected in controlled laboratory environments. Whilst this approach can provide valuable ground truth information from which to build recognition models, these techniques often do not function well when implemented in near real time applications. This paper presents the application of a multivariate online change detection algorithm to dynamically detect the starting position of windows for the purposes of activity recognition.

Prompting technologies: A comparison of time-based and context-aware transition-based prompting

BACKGROUND

While advancements in technology have encouraged the development of novel prompting systems to support cognitive interventions, little research has evaluated the best time to deliver prompts, which may impact the effectiveness of these interventions.

OBJECTIVE

This study examined whether transition-based context prompting (prompting an individual during task transitions) is more effective than traditional fixed time-based prompting.

METHODS

Participants were 42 healthy adults who completed 12 different everyday activities, each lasting 1-7 minutes, in an experimental smart home testbed and received prompts to record the completed activities from an electronic memory notebook. Half of the participants were delivered prompts during activity transitions, while the other half received prompts every 5 minutes. Participants also completed Likert-scale ratings regarding their perceptions of the prompting system.

RESULTS

Results revealed that participants in the transition-based context prompting condition responded to the first prompt more frequently and rated the system as more convenient, natural, and appropriate compared to participants in the time-based condition.

CONCLUSIONS

Our findings suggest that prompting during activity transitions produces higher adherence to the first prompt and more positive perceptions of the prompting system. This is an important finding given the benefits of prompting technology and the possibility of improving cognitive interventions by using context-aware transition prompting.