Real-time low-energy fall detection algorithm with a Programmable Truncated MAC

The ability to discriminate between falls and activities of daily living (ADL) has been investigated by using tri-axial accelerometer sensors, mounted on the trunk and using simulated falls performed by young healthy subjects under supervised conditions and ADL performed by elderly subjects. In this paper we propose a power-aware real-time fall detection integrated circuit (IC) that can distinguish Falls from ADL by processing the accelerations measured during 240 falls and 240 ADL. In the proposed fixed point custom DSP architecture, a threshold algorithm was implemented to analyze the effectiveness of Programmable Truncated Multiplication regarding power reduction while maintaining a high output accuracy. The presented system runs a real time implementation of the algorithm on a low power architecture that allows up to 23% power savings through its digital blocks when compared to a standard implementation, without any accuracy loss.