Presenter : Hyotaek Shim A wireless body area network of intelligent motion sensors for computer assisted physical rehabilitation Emil Jovanov, Aleksandar Milenkovic, Chris Otto and Piet C de Groen Presenter : Hyotaek Shim
Telemedicine System Wearable health monitoring systems integrated into a telemedicine system continuous monitoring as a part of a diagnostic procedure to support early detection of abnormal conditions and prevention of its serious consequences during supervised recovery from an acute event or surgical procedure
Holter monitors Traditional personal medical monitoring systems only to collect data for off-line processing Wires may limit the patient’s activity and level of comfort negatively influence the measured results
Continuous monitoring Important limitation for wider acceptance of the existing systems for continuous monitoring unwieldy wires between sensors and a processing unit lack of system integration of individual sensors interference on a wireless communication channel shared by multiple devices nonexistent support for massive data collection and knowledge discovery
Integrated research databases Records from individual monitoring sessions are rarely integrated into research databases support for data mining and knowledge discovery relevant to specific conditions and patient categories
Wireless Body Area Network preprocessing & synchronization
Data flow in an WBAN Sensor level Personal Server Level Medical Service Level
Sensor Level (1/2) ECG(electrocardiogram) sensor for monitoring heart activity EMB(electromyography) sensor for monitoring muscle activity EEG(electroencephalography) sensor for monitoring brain electrical activity A blood pressure sensor A tilt sensor for monitoring trunk position movement sensors used to estimate user’s activity A “smart sock” sensor or a sensor equipped shoe insole to delineate phases of individual steps
Sensor Level (2/2) Minimal weight Low-power operation to permit prolonged continuous monitoring Seamless integration into a WBAN standard-based interface protocols Patient-specific calibration, tuning and customization continuously collect and process raw information, store them locally, and send them to the personal server
Bluetooth Disadvantages transfer raw data from sensors to the monitoring station limitation for prolonged wearable monitoring too complex power demanding prone to interference
Zigbee wireless protocol High level communication protocols using small, low-power digital radios based IEEE 802.15.4 standard for wireless personal area networks (WPANs) targeted at RF applications that require a low data rate, long battery life, and secure networking
Personal server level Initialization, configuration and synchronization of WBAN nodes Control and monitor operation of WBAN nodes Collection of sensor readings from physiological sensors An audio and graphical user-interface early warnings or guidance Secure communication with remote healthcare provider servers Internet-enabled PDA 3G cell phone A home personal computer
Medical Services An emergency service If the received data are out of range or indicate an imminent medical condition The exact location of the patient If the personal server is equipped with GPS sensor monitoring the activity of the patient By medical professionals Issue altered guidance based on the new information
ActiS : Activity Sensor ISPM Telos ADXL202 Accelerometer TI MSP430F1232 TI MSP430F149 CC2420 (ZigBee) ADXL202 Accelerometer Flash ECG Signal Conditioning USB Interface ECG electrodes The Telos platform 8MHz MSP430F1611 microcontroller 10KB RAM and 48KB Flash Memory UART(Universal Asynchronous Receiver Transmitter) ISPM MSP430F1232 microcontroller 10-bit ADC and UART
ActiS : Motion Sensor ActiS sensor as Motion Sensor Vertical Plane Θ = Ax Ay g q ActiS sensor as Motion Sensor Vertical Plane Θ = to detection of gait phases
ActiS : Signal Processing
Conclusion Continuous monitoring in the ambulatory setting early detection of abnormal conditions increased level of confidence improve quality of life supervised rehabilitation potential knowledge discovery through data mining of all gathered information