Janet Light

Monitoring of Human Movements for Fall Detection and Activities Recognition in Elderly Care Using Wireless Sensor Network: a Survey

The problem with accidental falls among elderly people has massive social and economic impacts. Falls in elderly people are the main cause of admission and extended period of stay in a hospital. It is the sixth cause of death for people over the age of 65, the second for people between 65 and 75, and the first for people over 75. Among people affected by Alzheimer’s Disease, the probability of a fall increases by a factor of three. Elderly care can be improved by using sensors that monitor the vital signs and activities of patients, and remotely communicate this information to their doctors and caregivers. For example, sensors installed in homes can alert caregivers when a patient falls. Research teams in universities and industries are developing monitoring technologies for in-home elderly care. They make use of a network of sensors including pressure sensors on chairs, cameras, and RFID tags embedded throughout the home of the elderly people as well as in furniture and clothing, which communicate with tag readers in floor mats, shelves, and walls. A fall can occur not only when a person is standing, but also while sitting on a chair or lying on a bed during sleep. The consequences of a fall can vary from scrapes to fractures and in some cases lead to death. Even if there are no immediate consequences, the long-wait on the floor for help increases the probability of death from the accident. This underlines the importance of real-time monitoring and detection of a fall to enable first-aid by relatives, paramedics or caregivers as soon as possible. Monitoring the activities of daily living (ADL) is often related to the fall problem and requires a non-intrusive technology such as a wireless sensor network. An elderly with risk of fall can be instrumented with (preferably) one wireless sensing device to capture and analyze the 1

Recognition of false alarms in fall detection systems

Falls are a major cause of hospitalization and injury-related deaths among the elderly population. The detrimental effects of falls, as well as the negative impact on health services costs, have led to a great interest on fall detection systems by the health-care industry. The most promising approaches are those based on a wearable device that monitors the movements of the patient, recognizes a fall and triggers an alarm. Unfortunately such techniques suffer from the problem of false alarms: some activities of daily living are erroneously reported as falls, thus reducing the confidence of the user. This paper presents a novel approach for improving the detection accuracy which is based on the idea of identifying specific movement patterns into the acceleration data. Using a single accelerometer, our system can recognize these patterns and use them to distinguish activities of daily living from real falls; thus the number of false alarms is reduced.

Non-intrusive Patient Monitoring of Alzheimer's Disease Subjects Using Wireless Sensor Networks

On aging there is a decrease in the cognitive functions of the brain which can result in behavioral anomalies such as wandering and susceptibility to fall, typical of patients with Alzheimers disease. In order to learn how to manage patients with cognitive impairment it is necessary to non-intrusively monitor brain activity in conjunction with body movements. To facilitate the translation of insights derived through wireless monitoring into robust strategies for crisis prevention and management, we provide a preliminary assessment of a patient monitoring infrastructure, and we discuss related issues and challenges.

MIMS: A Minimally Invasive Monitoring Sensor Platform

This paper describes a minimally invasive sensor platform for active and passive monitoring of human movements and physiological signals. Such a system is needed in cases where 24 × 7 monitoring is required, as in older adults with cognitive impairment, dementia and Alzheimers disease. The passive monitoring systems used today are useful only in detecting events after they happen; the accuracy and speed of detection is questionable. The noninvasive nature of such systems does not bring trade off benefits to early detection and prevention of emergency incidents. We compare some existing sensor platforms and present our monitoring approach using minimally invasive wearable sensor device(s). With a Minimally Invasive Monitoring Sensor (MIMS), using advanced intelligent systems, we analyze the physiological signal data preceding potential emergency events in order to predict them quickly. The Virtual Hub is the core component of MIMS, which acts as a gateway between a monitored person and her/his caregivers, as well as a shared access point between active and passive sensing devices. Some preliminary results are presented here from our sleep-related fall study using two heterogeneous sensor systems.

Usability study of a wireless monitoring system among alzheimer's disease elderly population

Healthcare technologies are slowly entering into our daily lives, replacing old devices and techniques with newer intelligent ones. Although they are meant to help people, the reaction and willingness to use such new devices by the people can be unexpected, especially among the elderly. We conducted a usability study of a fall monitoring system in a long-term nursing home. The subjects were the elderly with advanced Alzheimers disease. The study presented here highlights some of the challenges faced in the use of wearable devices and the lessons learned. The results gave us useful insights, leading to ergonomics and aesthetics modifications to our wearable systems that significantly improved their usability and acceptance. New evaluating metrics were designed for the performance evaluation of usability and acceptability.

Data association in remote health monitoring systems

Pervasive healthcare using remote health monitoring offers solutions to many of todays healthcare challenges, including chronic diseases and an ageing population. Reliability of such remote medical monitoring systems depends on reliable data association. This article first identifies and characterizes the data association problem, it sets the requirements for correct data association, and it presents a taxonomy for the problem.

Agent-Based Mobile Middleware Architecture (AMMA) for Patient-Care Clinical Data Messaging Using Wireless Networks

Mobile messaging in healthcare environment is asynchronous based on real-time events, set of contextual elements such as location of service, resource availability, and guaranteed message delivery. Due to the critical nature of the healthcare delivery system, the mobile messaging has two key issues: reliability of message passing and synchronization of message delivery. AMMA provides solution for reliable asynchronous message passing by implementing an event-based context-centric agent communication protocol, and Mobile Message Passing Protocol with synchronized message delivery using global checkpoint method. In this demo the AMMA, a mobile agent system for reliable clinical data mobile messaging is presented. HL7 clinical document architecture is used for defining agents. AMMA is designed as part of the electronic patient call report (e-PCR) project for the 911- emergency medical services. The demo also includes the e-PCR data capturing tool, the wireless communication protocol and the middleware.

Mobile Agent Based Messaging Mechanism for Emergency Medical Data Transmission Over Cellular Networks

Healthcare environment integrate several health care services through a high degree of mutual work, mobility and information access from many devices and artifacts. Sharing of information through a fast and reliable transmission media among the services will have a significant impact. The rapid developments in mobile communication technologies and new generations of mobile devices allow users access to stored data even when they travel. This capability has elicited emergency medical data transmission over cellular network. In this paper, we have proposed a message framework for emergency medical data transmission and an agent based implementation mechanism. The HL7 messaging format, a standard adopted for medical data transmission is discussed. The messaging mechanism is used in AMMA; an agent based mobile middleware architecture for reliable transmission of patient data from the ambulance to the hospital over code division multiple access (CDMA) cellular network.

Context-Aware Data Association and Authenticity in Pervasive Healthcare

This paper briefly explains the data association and security issues in pervasive health-care and proposes a context aware security approach to overcome these issues. Our algorithm gathers vital physiological, environmental and personal data to generate user context and uses that information to authenticate a specific patient.

Monitoring Winter Ice Conditions Using Thermal Imaging Cameras Equipped with Infrared Microbolometer Sensors

Abstract Snow cover duration and thickness affects the permafrost thermal state, the depth and timing of seasonal soil freeze/thaw/break-up, and melting of on land and sea ice. Monitoring the ice conditions in lakes and rivers during a winter season is critical for the safety of people living in those regions. Infrared cameras equipped with microbolometer sensors, placed near lakes and rivers during winter, captures and send those thermal images wirelessly to a server, where image processing and analysis algorithms measure the ice conditions in real-time. This study presents results from an ice classification system using captured ice images.