Wee-Soon Yeoh

Ambulatory monitoring of human posture and walking speed using wearable accelerometer sensors

This paper describes a new classification system for real-time monitoring of physical activity, which is able to detect body postures (lying, sitting, and standing) and walking speed with data acquired from three wearable biaxial accelerometer sensors deployed in a wireless body sensor network. One sensor is waist-mounted while the remaining two are attached to the respective thighs. Two studies were conducted for the evaluation of the system, with each study involving five human subjects. Results from the first study indicated an overall accuracy of 100% for classification of lying, sitting, standing, and walking across a series of 40 randomly chosen tasks. In our system, estimated walking speeds are used to distinguish between different types of movement activity (walking, jogging, and running), and the accuracy of its estimation was evaluated in our second study which gave an overall mean-square error (MSE) of 1.76 (km/h)2.

MobiSense: Mobile body sensor network for ambulatory monitoring

This article introduces MobiSense, a novel mobile health monitoring system for ambulatory patients. MobiSense resides in a mobile device, communicates with a set of body sensor devices attached to the wearer, and processes data from these sensors. MobiSense is able to detect body postures such as lying, sitting, and standing, and walking speed, by utilizing our rule-based heuristic activity classification scheme based on the extended Kalman (EK) Filtering algorithm. Furthermore, the proposed system is capable of controlling each of the sensor devices, and performing resource reconfiguration and management schemes (sensor sleep/wake-up mode). The architecture of MobiSense is highlighted and discussed in depth. The system has been implemented, and its prototype is showcased. We have also carried out rigorous performance measurements of the system including real-time and query latency as well as the power consumption of the sensor nodes. The accuracy of our activity classifier scheme has been evaluated by involving several human subjects, and we found promising results.

Design and evaluation of lightweight middleware for personal wireless body area network

This paper presents a lightweight middleware to be used for wireless medical body area networks. The middleware is designed to reside in mobile devices, and acts as a gateway to receive sensor data as well as to control a set of sensor devices attached to the wearer. The main essence of the middleware is to simplify and accelerate the development of wireless healthcare applications by providing highly reusable codes. The architecture of the middleware including its main functions such as data acquisition, dynamic plug-and-play capabilities, on-the-fly sensor reconfiguration, and resource management (i.e., sensor sleep/wake-up, critical self-wake) will be discussed. A security feature as a means to protect critical sensor data from malicious/unauthorized parties has also been incorporated in our proposed middleware. The prototype system of the middleware has been built and is presented in this paper together with its performance measurements.

Real-time tracking of flexion angle by using wearable accelerometer sensors

This paper presents a new algorithm for real time tracking the flexion angle from wearable accelerometer sensor data using wireless body sensor network (BSN). The proposed algorithm uses dynamic filter for tracking the flexion angles of which the human body dynamics is described by its system model. In this work, the Extended Kalman Filtering is used to demonstrate the superiority of this approach. Results from a thigh tracking experiment show that the flexion angle estimated closely followed that of the video data.

Mobile Middleware for Wireless Body Area Network

This paper presents a flexible, efficient and lightweight Wireless Body Area Network (WBAN) Middleware. The Middleware is developed to bridge the communication between mobile device as a gateway and the sensor nodes, and therefore it shields the underlying sensor and OS/protocol stack away from the WBAN application layer. The middleware is coded in the form of lightweight dynamic link library, which allows the application developer to simply incorporate the middleware resource dynamic link library into their application and call the required functions (i.e. data acquisition, resource management and configurations). A showcase of the middleware deployment is exhibited at the end of the paper.

LiteMWBAN: A lightweight middleware for wireless body area network

Healthcare is considered as one of the most important agenda to address by many countries worldwide. Thanks to the recent development in wireless sensor technology, a continuous medical monitoring of the patients under their natural physiological states has been made possible and this will certainly help to detect transient life threatening from daily activities. With the growing variety of healthcare sensor devices, it is of interest to deploy a middleware system that shields the underlying technology differences from the application layer. The aim of this paper is to propose LiteMWBAN, a lightweight middleware for wireless medical body area network. The main features of the proposed middleware include support on: (i) multiple sensors and applications, (ii) plug and play, (iii) resource management and alert, and (iv) mobile applications. The prototype of the middleware has been built and its effective uses when deployed with a mobile healthcare application are shown in this paper.

Footpaths: Fusion of mobile outdoor personal advisor for walking route and health fitness

This paper is mainly concerned with the integration of wireless body sensor network and walking route navigation system in order to provide the most suitable walking path to the wearer following the wearer’s health condition. A novel system called Footpaths is proposed. Footpaths is designed to facilitate the measurement of the user’s cardio-respiratory fitness level (CRF), through the use of a wearable wireless sensor network, in which the result is used as a key factor in determining the most suitable walking route. The CRF is assessed based on the maximal oxygen uptake or VO2max through field performance tests (i.e. Rockport 1-mile test). The prototype of Footpaths and showcase of its effective uses are exhibited in the paper.

SLIM: A secured lightweight interactive middleware for wireless body area network

Advances in wireless sensor technology have introduced a new dimension in healthcare computing. With miniaturized sensor devices, continuous medical monitoring of patients to detect transient life threatening conditions from daily activities has been made possible. This phenomenon will certainly improve the quality of life for a majority of people. However, the growing variety of sensor devices in the market, has made application developments very challenging. In light of this view, we are proposing SLIM, a lightweight middleware that shields the underlying differences in sensor technology from the application layer. SLIM is designed to simplify/accelerate application development while not simply providing common middleware functions (i.e. data acquisition and plug-and-play capability) but also others like security and interactive features. To support both indoor and outdoor activities, SLIM is built to reside on mobile devices. At the end of the paper, we will show the prototype of the proposed middleware including its functionalities when used with a mobile application.

Motion-based wake-up scheme for ambulatory monitoring in wireless body sensor networks

Given that wearable sensors that are attached on patients for the purpose of continuous real-time medical monitoring typically need to remain operational for periods of up to 24 hours before a battery change or recharge, power preservation schemes play a critical role in minimizing any possible disruption to a patients daily activities. In this paper, we propose a motion-based wake-up scheme, a feature which combines motion detection with existing power preservation schemes in order to achieve a balance between energy saving and data timeliness, particularly in critical situations. As a showcase, we have integrated this feature with a healthcare application and demonstrate the capability of the scheme to deal with critical events, e.g., when a patient falls down from the bed. This showcase affirms the effective uses of our proposed motion-based wake-up scheme.

Modeling and Identification of practical ultrasound transducers in ultrasound imaging systems

This paper provides linear analysis for a practical ultrasound imaging system with single-element transducers. A proper eighth-order linear ARMA model with inputs and outputs of voltage traces is given to present the transfer characteristics of such a practical system, so that echo signals containing tissue information can be collected and analyzed more properly