Machine Learning-Based Classification of Human Behaviors and Falls in Restroom via Dual Doppler Radar Measurements

Abstract

This study presents a radar-based remote measurement system for classification of human behaviors and falls in restrooms without privacy invasion. Our system uses a dual Doppler radar mounted onto a restroom ceiling and wall. Machine learning methods, including the convolutional neural network (CNN), long short-term memory, support vector machine, and random forest methods, are applied to the Doppler radar data to verify the model’s efficiency and features. Experimental results from 21 participants demonstrated the accurate classification of eight realistic behaviors, including falling. Using the Doppler spectrograms (time–velocity distribution) as the inputs, CNN showed the best results with an overall classification accuracy of 95.6% and 100% fall classification accuracy. We confirmed that these accuracies were better than those achieved by conventional restroom monitoring techniques using thermal sensors and radars. Furthermore, the comparison results of various machine learning methods and cases using each radar’s data show that the higher-order derivative parameters of acceleration and jerk, and the motion information in the horizontal direction are the efficient features for behavior classification in a restroom. These findings indicate that daily restroom monitoring using the proposed radar system accurately recognizes human behaviors and allows early detection of fall accidents.

A Deep Convolutional Neural Network-XGB for Direction and Severity Aware Fall Detection and Activity Recognition

“…This allows CNNs to develop a deeper understanding of the provided input compared to typical multilayer perceptron models. CNNs have revolutionized the field of computer vision where they have been used for a variety of tasks such as classification, object detection, segmentation, and object counting [ 43 , 44 ] and they have also successfully been used for applications within the speech and other time series signal application domain [ 45 , 46 , 47 ]. In this paper, rather then using hand crafted features, a CNN has been used to perform feature extraction in order to take advantage of the spatial and temporal dependency capturing capabilities of CNNs.…”

DeepHAR: a deep feed-forward neural network algorithm for smart insole-based human activity recognition

“…Human activity recognition (HAR) can be used to monitor user's behaviours, analyse them, and consequently assist the user in his/her daily life or provide histories on the activities to specialists for evaluation. The applications of HAR include health monitoring [1,2], rehabilitation [3], fitness [4], home automation [5], and safety [6].…”

Identifying Sensors-based Parameters Associated with Fall Risk in Community-Dwelling Older Adults: An Investigation and Interpretation of Discriminatory Parameters

“…Among these methods, nearable (environmental perception) and wearable sensors are widely employed due to their high e cacy. Typical examples of environmental perception sensors are infrared sensors, Doppler radar, depth camera systems, and force platforms [12][13][14][15] which facilitate accurate and precise monitoring, detection, and analysis of various environmental parameters. Typical examples of wearable sensors are pressure insoles and inertial measurement units (IMUs) [16,17] which can monitor human activities in real-time and provide kinematic data for subsequent analysis.…”