Falling is a major cause of serious injury or even death for the elderly population. To improve the safety of elderly people, a wide range of wearable fall detection devices have been developed over recent years, such as smart watches, waistbands and other wearable fall detectors. However, most of these fall detection devices are threshold-based and have a high rate of false alarm. This paper presents a novel fuzzy logic fall detection algorithm used in smart wristbands to reduce false alarms and achieve accurate fall detection. Experiments have been conducted in our laboratory and the results show that the proposed algorithm can accurately distinguish fall events from non-fall daily activities such as walking, jumping, clapping, and so forth. It shows good potential for commercial applications.

The consumer electronics market is already saturated with wearable devices that intend to be used to detect falls and request help from carers or family members. However, these products have a high rate of false alarms which affect their reliable performance. To provide the high accuracy and high precision of fall detection for the elderly, this paper presents a machine learning approach to improve the fall detection accuracy and reduce the false alarms. Three machine learning algorithms are deployed in this research, namely the K-Means, Perceptron Neural Network (PNN), and Convolutional Neural Network (CNN) algorithms. A development board with a 9-axis inertial sensor unit is used as a prototype of wristband to collect data and identify falls from seven daily activities. These data is then used to train and test machine learning algorithms. Experimental results show that the CNN algorithm achieves the highest accuracy comparing with K-mean, PNN and the algorithm used in the existing wristbands.