Nhu Khue Vuong

Feasibility study of a real-time wandering detection algorithm for dementia patients

In this paper, we present a new algorithm that automatically classifies wandering patterns (or behaviors) of patients with Alzheimers disease and other different types of dementia. Experimental results on a real-life dataset show that this algorithm can provide a robust and credible assistive technology for monitoring patients with dementia (PWD) who are prone to wandering. Combined with indoor and outdoor location technologies using ubiquitous devices such as smart phones, we also demonstrate the feasibility of a remote mobile healthcare monitoring solution that is capable of reasoning about wandering behaviors of PWD and real-time detection of abnormalities that require timely intervention from caregivers.

mHealth Sensors, Techniques, and Applications for Managing Wandering Behavior of People with Dementia: A Review

Managing wandering behavior of people with dementia (PWD) has become increasingly imperative for these reasons: its high prevalence (60%) among PWD, its negative outcomes such as falls or elopement, and its burden on caregivers. In this chapter, we discuss the emergence of sensors, techniques, and applications for managing wandering behavior of PWD. First, we briefly present the 5Ws1H (WHO, WHAT, WHERE, WHEN, WHY, HOW) conceptual map of wandering science including stakeholders (WHO), measurements of wandering (WHAT), environments in which wandering takes place (WHERE), detection of wandering (WHEN), causes of wandering (WHY), interventions of wandering (HOW). Second, we introduce a framework that identifies specific groups of mHealth and eHealth assistive technologies for managing dementia-related wandering. Third, we review existing technological works that address these 4 domains in the 5Ws1H conceptual map: WHAT-WHERE-WHY-HOW. In particular, we explore mHealth sensors to geo-fence and prevent elopement, mHealth devices to track and locate PWD who wander, information services to assist caregivers, eHealth tools to measure dimensions of dementia-related wandering, and mHealth tools that analyze proximal factors as well as study background factors. Based on this review, we further discuss research and design issues, human factors, ethics, security and privacy that need to be considered when implementing mHealth applications for wandering management. We conclude the chapter by highlighting the future research work in this area.

A mobile-health application to detect wandering patterns of elderly people in home environment

Wandering is a common and risky behavior in people with dementia (PWD). In this paper, we present a mobile healthcare application to detect wandering patterns in indoor settings. The application harnesses consumer electronics devices including WiFi access points and mobile phones and has been tested successfully in a home environment. Experimental results show that the mobile-health application is able to detect wandering patterns including lapping, pacing and random in real-time. Once wandering is detected, an alert message is sent using SMS (Short Message Service) to attending caregivers or physicians for further examination and timely interventions.

A predictive location-aware algorithm for dementia care

Some mentally impaired but otherwise physically healthy individuals may have a tendency of wandering or difficulties using public transportation. Intelligent assistive technologies which are able to learn the individuals travel behavior and prompt anomalous events such as when the person deviates from expected destinations would greatly enhance the independence and safety of the individual and also reduce the stress on family members and caregivers. This paper presents the design and preliminary evaluation of a prediction model that is a critical component of a mobile and personal wellness management system for patients with dementia. We define a generic architecture of assurance systems aiming to ensure the safety and well-being of such patients and also develop an enhanced class of state predictor for location-aware applications catering to dementia care. With our new scheme, the prediction accuracy has reached up to 90% compared to the average 76% to 81% accuracy achieved by Markov, Bayesian network, Multilayer Perceptron, Elman net or the original state predictor with confidence estimator. Considerations for the development of future dementia care systems are also addressed.

Classification of pH levels using a mobile phone

We present a novel and automated system for estimating pH levels from non-calibrated camera phone images. Experimental results show that pH levels reported by the software are consistent with the ground truth estimation.

pH Levels Classification by Color Quantization on a Camera Phone

In this paper, we present a mobile healthcare application that applies color quantization technique in analysis of color images taken by a camera phone to automate pH classification of medical tests. Experimental results and comparative study have demonstrated the advantages of this new approach in terms of efficiency, accuracy, and robustness over the solution developed earlier based on edge detectors.

Preliminary results of using inertial sensors to detect dementia- related wandering patterns

We present a solution for detecting dementia-related travel patterns using only inertial sensors. The results and lessons learnt from the experiments on dementia and non-dementia subjects are reported.