Towards a mobile airbag system using MEMS sensors and embedded intelligence

This paper introduces the development of a mobile human airbag system designed for fall protection for the elderly. A Micro Inertial Measurement Unit (μIMU) that is 66 mm × 20 mm × 20 mm in size is built. This unit consists of three dimensional MEMS accelerometers, gyroscopes, MCU, and a Bluetooth module. It records human motion information, and, with a Support Vector Machine (SVM) training process, it can be used to classify falls and other normal motions successfully with an SVM filter. Based on the SVM filter, an embedded DSP (Digital Signal Processing) system is developed for real-time fall detection. Also, a smart mechanical airbag deployment system is finalized. This system weighs 253.5 grams (including a 42.5 g compressed CO₂ cylinder) with dimensions of 190 mm length, 57 mm width and 30 mm height. The response time of the mechanical trigger is 0.133 seconds, which has been proven in our lab to allow enough time for compressed air release before a person falls down to the ground. The integrated system is tested, and the feasibility of the airbag system for real-time fall protection is demonstrated. © 2008 IEEE.