Skip to Main Content
The independence and safety of the elderly population is supported by new technologies, such as automated fall detectors, knowing that the fall related injuries are a central problem for this population. Accelerometry based approach has been used in various automated fall detection systems to objectively monitor a range of human movement. This paper presents a wireless reconfigurable system for automatic detection of falls using three-axis-accelerometer signals. The proposed connected health system for falls detection is based on a wireless sensor and field programmable gate arrays (FPGA) platforms. The 3D accelerometer data is processed by robust and efficient algorithm on FPGA to detect falls. Furthermore, best compromise algorithm between effectiveness and complexity to compute patient's orientation is proposed. The developed architecture is capable of monitoring up to 96 three-axis-accelerometer data simultaneously, and our performance evaluations indicate that a speedup of around 284X can be achieved over an optimized software implementation running on a 2.4GHz Dual-core processor. The proposed falls detection system has been proven to distinguish among falls and activities of daily living, and the accuracy has been evaluated in terms of specificity and sensitivity and has shown an excellent results.