Aung Aung Phyo Wai

Health and wellness monitoring through wearable and ambient sensors: exemplars from home-based care of elderly with mild dementia

Monitoring and timely intervention are extremely important in the continuous management of health and wellness among all segments of the population, but particularly among those with mild dementia. In relation to this, we prescribe three design principles for the construction of services and applications. These are ambient intelligence, service continuity, and micro-context. In this paper, we provide three exemplars from our research and development activities that illustrate the use of these design principles in the construction of services and applications. All the applications are drawn from the field of care for mild dementia patients in their living quarters.

Multimodal Sleeping Posture Classification

Sleeping posture reveals important information for eldercare and patient care, especially for bed ridden patients. Traditionally, some works address the problem from either pressure sensor or video image. This paper presents a multimodal approach to sleeping posture classification. Features from pressure sensor map and video image have been proposed in order to characterize the posture patterns. The spatiotemporal registration of the two modalities has been considered in the design, and the joint feature extraction and data fusion is presented. Using multi-class SVM, experiment results demonstrate that the multimodal approach achieves better performance than the approaches using single modal sensing.

Smart mote-based medical system for monitoring and handling medication among persons with dementia

This paper presents a novel smart mote-based portable medical system which automatically monitors and handles medication among persons with dementia based on wireless multimodal sensors, actuators and mobile phone or PDA (Personal Digital Assistance) technology. In particular, we present the subtle design, implementation and deployment issues of monitoring the patients behavior and providing adaptive assistive intervention such as prompts or reminders in the form of visual, audio or text cues to the patient for medical compliance. In addition, we develop mobile phone or PDA applications to provide a number of novel services to the caregivers that facilitate them in care-giving and to doctors for clinical assessment of dementia patients in a context enlightened fashion.

Smart Wireless Continence Management System for Persons with Dementia

Incontinence is highly prevalent in the elderly population, especially in nursing home residents with dementia. It is a distressing and costly health problem that affects not only the patients but also the caregivers. Effective continence management is required to provide quality care, and to eliminate high labor costs and annoyances to the caregivers resulting from episodes of incontinence. This paper presents the design, development, and preliminary deployment of a smart wireless continence management system for dementia-impaired elderly or patients in institutional care settings such as nursing homes and hospitals. Specifically, the mote wireless platform was used to support the deployment of potentially large quantities of wetness sensors with wider coverage and with dramatically less complexity and cost. It consists of an intelligent signal relay mechanism so that the residents are free to move about in the nursing home or hospital and allows personalized continence management service. Preliminary results from a trial in a local nursing home are promising and can significantly improve the quality of care for patients.

Application of ultrasonic sensors in a smart environment

A key application of sensor networks in smart environments is in monitoring activities of people. We develop several scenarios in which ultrasonic sensors are used for monitoring of patients and the elderly. In each scenario, we apply different algorithms for data fusion and sensor selection using quality-based or time division approaches. We have devised trajectory-matching algorithms to classify trajectories of movement of people in indoor environments. The trajectories are divided into several routine classes and the current trajectory is compared against the known routine trajectories. The initial results are quite promising, and show the potential usability of ultrasonic sensors in monitoring indoor movements of people, and in capturing and classifying trajectories.

Improving the accuracy of erroneous-plan recognition system for Activities of Daily Living

Using ambient intelligence to assist people with dementia in carrying out their Activities of Daily Living (ADLs) independently in smart home environment is an important research area, due to the projected increasing number of people with dementia. We present herein, a system and algorithms for the automated recognition of ADLs; the ADLs are in terms of plans made up encoded sequences of micro-context information gathered by sensors in a smart home. Previously, the Erroneous-Plan Recognition (EPR) system was developed to specifically handle the wide spectrum of micro contexts from multiple sensing modalities. The EPR system monitors the person with dementia and determines if he has executed a correct or erroneous ADL. However, due to the noisy readings of the sensing modalities, the EPR system has problems in accurately detecting the erroneous ADLs. We propose to improve the accuracy of the EPR system by two new key components. First, we model the smart home environment as a Markov decision process (MDP), with the EPR system built upon it. Simple referencing of this model allows us to filter erroneous readings of the sensing modalities. Second, we use the reinforcement learning concept of probability and reward to infer erroneous readings that are not filtered by the first key component.We conducted extensive experiments and showed that the accuracy of the new EPR system is 26.2% higher than the previous system, and is therefore a better system for ambient assistive living applications.

Automated Recognition of Complex Agitation Behavior of Dementia Patients Using Video Camera

This paper presents a framework and techniques for recognition and automated rating of complex agitation behavior for patients with dementia using video camera. In particular, we present an approach using hierarchical descriptors for video feature extraction for understanding, modeling and recognizing complex agitation behavior in patients.

A measurement study and implication for architecture design in wireless body area networks

Reliability and energy efficiency are two key performance metrics in wireless body area network (WBAN) to meet the requirement of healthcare applications. The network architecture of WBAN has significant impact on transmission performance. In this paper, we investigate the network architecture through the measurement study of WBANs. In particular, we measure the performance achieved for star and multihop IEEE 802.15.4 WBANs in terms of packet reception ratio (PRR), collection delay, energy consumption, and energy balancing. The experimental results show that in the star architecture network, only 40% of on-body nodes are able to achieve required PRR performance (0.95) when transmitting at the maximum power. This indicates the demand of multihop transmissions. In the multihop experiment, we use a customized collection tree protocol (CTP) to formulate multihop networks. Our multihop measurement results show that the link quality based routing achieves good performance in terms of PRR (>;0.96) and collection delay (<;150 ms for 95% of nodes). We further suggest the choice of the optimal transmission power level by inspecting the average number of transmissions per packet, network energy consumption and average cost per hop.

Experimental study on adaptive power control based routing in multi-hop Wireless Body Area Networks

Data transmission reliability and energy efficiency are most crucial for Wireless Body Area Network (WBAN) to perform healthcare monitoring. In this paper, we jointly consider adaptive power control and routing in multi-hop WBANs, and develop a low overhead energy-efficient routing scheme (EERS). The proposed EERS can establish an energy-efficient end-to-end path as well as adaptively choose transmission power for sensor nodes. We conduct extensive experiments on a MicaZ platform to compare the performance of the proposed EERS and the collection tree protocol (CTP) in terms of packet reception ratio (PRR), collection delay, energy consumption, and energy balancing. Experimental results show that EERS outperforms CTP in terms of reliability, delay and energy consumption. In particular, EERS reduces nearly 30% mean delay as compared to CTP, and saves 10% energy consumed by CTP at the default power (0dBm) while achieving at least 0.95 PRR.

A low overhead tree-based energy-efficient routing scheme for multi-hop wireless body area networks

Reliability and energy efficiency are key performance metrics for meeting the requirements of long-term and continuous health monitoring in Wireless Body Area Networks (WBANs). In this paper, we explore energy-efficient routing mechanisms for WBANs. We first present experimental results showing that wireless link quality changes rapidly in WBANs due to body shadowing, and a fixed transmission power results in either wasted energy or low reliability. Moreover, in multi-hop WBANs, as various vital signs are collected from sensors on different body parts, the traffic load among sensor nodes could be severely unbalanced, leading to uneven energy consumption. In this paper, we propose a scheme, we term the tree-based energy-efficient routing scheme (EERS), with low overhead to jointly address adaptive power control and routing in multi-hop WBANs. The proposed scheme can establish an energy-efficient end-to-end path as well as adaptively choose transmission power for sensor nodes. We conduct extensive experiments on a MicaZ WBAN testbed to compare the performance of EERS with the Collection Tree Protocol (CTP) in terms of packet reception ratio (PRR), collection delay, energy consumption, and energy balancing. Experimental results show that EERS outperforms CTP in terms of reliability, delay and energy consumption. In particular, EERS exhibits a mean delay 30% lower than the mean delay of CTP and an energy consumption 10% lower than CTP, while achieving at least 0.95 PRR.