No abstract

Falls are currently a leading cause of death from injury in the elderly. The usage of the conventional assistive cane devices is critical in reducing the risk of falls and is relied upon by over 4 million patients in the U.S.. While canes provide physical support as well as supplementary sensing feedback to patients, at the same time, these conventional aids also exhibit serious adverse effects that contribute to falls. The falls due to the improper usage of the canes are particularly acute in the elderly and disabled where reduced cognitive capacity accompanied by the burden of managing cane motion leads to increased risk. This paper describes the development of the SmartCane assistive system that encompasses broad engineering challenges that will impact general development of individualized, robust assistive and prosthetic devices. The SmartCane system combines advances in signal processing, embedded computing, and wireless networking technology to provide capabilities for remote monitoring, local signal processing, and real-time feedback on the cane usage. This system aims to reduce risks of injuries and falls by enabling training and guidance of patients in proper usage of assistive devices.

Fall-induced injury has become a leading cause of death for the elderly. Many elderly people rely on canes as an assistive device to overcome problems such as balance disorder and leg weakness, which are believed to have led to many incidents of falling. In this paper, we present the design and the implementation of SmartFall, an automatic fall detection system for the SmartCane system we have developed previously. SmartFall employs subsequence matching, which differs fundamentally from most existing fall detection systems based on multi-stage thresholding. The SmartFall system achieves a near perfect fall detection rate for the four types of fall conducted in the experiments. After augmenting the algorithm with an assessment on the peak impact force, we have successfully reduced the false-positive rate of the system to close to zero for all six non-falling activities performed in the experiment.

No abstract

Energy efficiency presents a critical design challenge in wireless, wearable sensor technology, mainly because of the associated diagnostic objectives required in each monitoring application. In order to maximize the operating lifetime during real-life monitoring and maintain sufficient classification accuracy, the wearable sensors require hardware support that allows dynamic power control on the sensors and wireless interfaces as well as monitoring algorithms to control these components intelligently. This paper introduces a context-aware sensing technique known as episodic sampling – a method of performing context classification only at specific time instances. Based on Additive-Increase/Multiplicative-Decrease (AIMD), episodic sampling demonstrates an energy reduction of 85 percent with a loss of only 5 percent in classification accuracy in our experiment.