A neural network-based fall detection method for the elderly

Abstract

The invention discloses a method for detecting falls of the elderly based on a neural network, comprising the following steps: S1. Preprocessing depth image data to obtain a binary image; S2. Using a particle swarm optimization algorithm to obtain optimal ELM mapping parameters to obtain The optimized ELM neural network model; S3, sample the binary image, add labels to the samples, and input the samples into the optimized ELM neural network model for training to obtain feature vectors; S4, input the feature vectors into the convolutional neural network The network model is used to obtain the probability that the elderly are in a falling state; S5, according to the probability that the elderly are in a falling state, determine whether the elderly have fallen behavior. The present invention solves the fall detection based on traditional machine learning, the input layer weight and the hidden layer The deviation is randomly generated, which will lead to the problem of excessive consumption of neurons and poor stability of feature extraction results.

Description

technical field [0001] The invention belongs to the technical field of human body recognition, and in particular relates to a neural network-based fall detection method for the elderly. Background technique [0002] At present, my country's aging process is accelerating. With age, body function and balance control decline, leading to an increased risk of falls. Falls in the elderly can easily cause physical injury and affect daily life. Fall detection is the basis for implementing fall protection and supports fall injury assessment and timely rescue. Fall behavior detection mainly senses human behavior data through sensors, performs preprocessing and feature extraction on the data, and finally performs fall recognition. Sensors used for fall detection can be divided into wearable sensors and environmental perception sensors. Wearable sensors need to be worn with you and are suitable for daytime outdoor places. Environmental perception sensors include video, infrared, an...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the above-mentioned deficiencies in the prior art, a neural network-based fall detection method for the elderly provided by the present invention solves the fall detection based on traditional machine learning, and the input layer weights and hidden layer deviations are randomly generated, which will cause consumption The number of neurons is too large, and the stability of the feature extraction results is poor

Images