Design of a Compressive Sensing Based Fall detection System for Elderly Using WSN

Recent researches have pointed out that one third persons are aged 65 and above requires special health care. As the number of elderly person is increasing, home monitoring for healthcare applications is playing a vital role in our daily life. Falls are one of the unpredicted but hazardous events. A sudden fall has to be informed to the caretaker immediately and wireless sensor networks are capable of sensing these falls. In this framework, fall frames are identified from a monitored video and transmitted using wireless sensor nodes. Since the multimedia data requires high bandwidth, there is a need for efficient compression. In this paper, compressed sensing based fall detection system for elderly using WSN (CSFDS) is proposed. A quantization with entropy coding is incorporated in this new fall detection framework for achievement of the efficient video compression. Performance evaluation is done using parameters like peak signal to noise ratio, structural similarity index, transmission energy, delay and packet loss. Simulation results show the CSFDS framework outperforming the raw frame transmission by achieving 83.4% reduction in transmission energy and time. An average PSNR and SSIM value of 34.67 dB and 0.9706 respectively is achieved.