- مبلغ: ۸۶,۰۰۰ تومان
- مبلغ: ۹۱,۰۰۰ تومان
This paper presents a health condition monitoring solution that detects an elderly accidental fall occurrence. The fall detection algorithm implements both accelerometer-based and sound-based detections for the possible occurrence of a valid fall. The accelerometer-based fall detection is instrumental in the detection of a valid fall occurrence. However, it has been shown that by using accelerometer alone is insufficient to accurately detect a fall, as the accelerometer also misinterprets some daily motion activities and classified them as valid falls. The sound sensor can be used to detect the sound pressure generated from a resultant fall, but sound pressure cannot by itself be used as a reliable indicator of a fall. Thus, a fuzzy logic-based fall detection algorithm is developed to process the output signals from the accelerometer and sound sensor, where a valid fall activity detected by the accelerometer, coupled with a detected sound pressure from the resultant fall can infer an occurrence of a valid fall. This paper demonstrates the fuzzy logic algorithm to improve the accuracy of detecting a valid fall as compared to the accelerometer only fall detection algorithm and it can be demonstrated that the algorithm is capable of minimizing false fall detections per day from high of 1.37 to low of 0.06.
In this paper, a non-intrusive fall detection monitoring system (e-HealthCM) for the elderly based on fuzzy logic has been proposed, designed and successfully implemented. The proposed fall detection monitoring system consists of three main components i.e., a base station module (e-BS) where fall alerts and 505 caregiver notification are being handled when a fall is detected, sound sensor modules (e-SS) for continuous monitoring of potential falls based on detected sound, and finally an accelerometer-based wearable module (e-WM) for real time motion activities monitoring. Extensive research have shown that using accelerometer alone for fall detection monitoring is insufficient to provide a re510 liable system, as the accelerometer itself is easily prone to false fall detections resulted from daily motion activities. In order to increase the valid fall detection accuracy, a microphone-based sound sensor module is introduced into this proposed monitoring system. These e-SS modules are installed at strategic locations within a senior citizen’s home to provide an additional sound based 515 fall detection function. Fuzzy logic algorithm is developed to fuse and process the accelerometer and sound data, resulting in a highly accurate fall detection solution. Experiments are carried out to verify the effectiveness of the proposed fall detection solution and comparison between the purely accelerometer-based and fuzzy logic-based algorithm are documented in this paper. Five volunteers 520 are engaged to emulate elderly physical behaviors in performing common daily activities in the experiment. Based on the experiment results, the purely accelerometer-based fall detection system has the maximum false fall detection of 20%, whereas the proposed fuzzy logic-based algorithm has the false fall detection rate reduced to ≤ 2.5%.