Advanced Sensing and Human Activity Recognition in Early Intervention and Rehabilitation of Elderly People

Abstract

Ageing is associated with a decline in physical activity and a decrease in the ability to perform activities of daily living, affecting physical and mental health. Elderly people or patients could be supported by a human activity recognition (HAR) system that monitors their activity patterns and intervenes in case of change in behavior or a critical event has occurred. A HAR system could enable these people to have a more independent life. In our approach, we apply machine learning methods from the field of human activity recognition (HAR) to detect human activities. These algorithmic methods need a large database with structured datasets that contain human activities. Compared to existing data recording procedures for creating HAR datasets, we present a novel approach, since our target group comprises of elderly and diseased people, who do not possess the same physical condition as young and healthy persons. Since our targeted HAR system aims at supporting elderly and diseased people, we focus on daily activities, especially those to which clinical relevance in attributed, like hygiene activities, nutritional activities or lying positions. Therefore, we propose a methodology for capturing data with elderly and diseased people within a hospital under realistic conditions using wearable and ambient sensors. We describe how this approach is first tested with healthy people in a laboratory environment and then transferred to elderly people and patients in a hospital environment. We also describe the implementation of an activity recognition chain (ARC) that is commonly used to analyse human activity data by means of machine learning methods and aims to detect activity patterns. Finally, the results obtained so far are presented and discussed as well as remaining problems that should be addressed in future research.

Deep Sensing: Inertial and Ambient Sensing for Activity Context Recognition Using Deep Convolutional Neural Networks

“…For inertial sensing, they achieved 91.98% compared to the work presented in this article, achieved 93.6% accuracy, whereas combination inertial and ambient sensing achieved 98.9% accuracy. Another recent work is the one by Schrader et al [ 32 ]. They used an accelerometer as an inertial sensor combined with a camera and body pressure measurement system.…”

“…In this process, the input data is split into data segments of fixed intervals of samples called “windows”. Each window contains a small part of the sensor signal [ 3 , 32 ]. As illustrated by Figure 10 , each window is 50% “ overlapped ” to form the next window, preserving a proportion of the previously sampled signal data overlapping the start of the next sample [ 3 , 27 , 35 ].…”

“…One of the latest reports is the one conducted by Cruciani et al [ 13 ], in which they used audio and inertial datasets to pre-train a DCNN model for automatic human activity recognition. Another recent work is presented by Schrader et al [ 32 ], which uses audio signals and cameras as ambient sensors in addition to other sensors to recognize elderly people’s activities for rehabilitation and early intervention. We proposed a combination of 3 inertial sensors, namely accelerometer, gyroscope, and magnetometer.…”

Deep Sensing: Inertia and Ambient Sensing for Activity Context Recognition Using Deep Convolutional Neural Networks

“…al [11] in which they have used audio and inertial datasets to pre-train a DCNN model for automatic human activity recognition. Another recent work is presented by Schrader et al [25], which uses audio signals and cameras as ambient sensors in addition to other sensors to recognize elderly people's activities for rehabilitation and early intervention. We have proposed a combination of 3 inertia sensors namely: accelerometer, gyroscope, and magnetometer.…”

Modeling Two-Person Segmentation and Locomotion for Stereoscopic Action Identification: A Sustainable Video Surveillance System

“…If these data are compromised by inadequate processing, the reliability and efficiency of the whole system and its outcomes will be compromised. [22]. Many methods are used to acquire data.…”