Soft Computing Healthcare Intelligence through Multisensory Activity Recognition

Abstract

Remote patient monitoring through telemedicine has become very usual nowadays. Sensor are attached to the patient's body and they monitor the during various activity, the data acquires from sensor is given as input to genetic algorithm based activity recognition system. If any deviations are vital signs during any activity, it is informed to the physician. Simulation was performed by taking 10 sample patients and some activities. Results prove the efficiency of the algorithm. INTRODUCTION: Telemedicine plays a very important role in patient management and have been effectively used for intra hospital transport of patients. Live monitoring of patients from both the hospitals creates new challenges. Similarly issues arise as how to process the data captured in real time. Sensors can overcome some of the challenges faced in telemedicine (Gaynor et al 2004). Advances in Micro Electro Mechanical Systems (MEMS) and Nano technology have enabled design of low powers sensor nodes capable of sensing different vital signs in our body. These nodes can communicate with each other to aggregate data and transmit vital parameters to a Base Station. The data collected in the base station can be used to monitor health in real time. The patient wearing sensors m be mobile leading to aggregation of data from different BS for processing. Processing real time data is compute intensive and telemedicine facilities may not have appropriate hardware to process the real time data effectively. Hence we propose a genetic algorithm based activity recognition which monitors the patient activity and send message to the doctor @ IJTSRD |