Human Activity Recognition for AI-Enabled Healthcare Using Low-Resolution Infrared Sensor Data

Abstract

This paper explores the feasibility of using low-resolution infrared (LRIR) image streams for human activity recognition (HAR) with potential application in e-healthcare. Two datasets based on synchronized multichannel LRIR sensors systems are considered for a comprehensive study about optimal data acquisition. A novel noise reduction technique is proposed for alleviating the effects of horizontal and vertical periodic noise in the 2D spatiotemporal activity profiles created by vectorizing and concatenating the LRIR frames. Two main analysis strategies are explored for HAR, including (1) manual feature extraction using texture-based and orthogonal-transformation-based techniques, followed by classification using support vector machine (SVM), random forest (RF), k-nearest neighbor (k-NN), and logistic regression (LR), and (2) deep neural network (DNN) strategy based on a convolutional long short-term memory (LSTM). The proposed periodic noise reduction technique showcases an increase of up to 14.15% using different models. In addition, for the first time, the optimum number of sensors, sensor layout, and distance to subjects are studied, indicating the optimum results based on a single side sensor at a close distance. Reasonable accuracies are achieved in the case of sensor displacement and robustness in detection of multiple subjects. Furthermore, the models show suitability for data collected in different environments.

A Low-Resolution Infrared Array for Unobtrusive Human Activity Recognition That Preserves Privacy

“…They focused on spotting falls and lying down and obtained high scores: around 97% accuracy overall. Study [14] addressed human activity recognition using low-resolution IR sensors in various settings. They introduced a new dataset, Coventry-2018, for use with Infra-ADL2018 analysis.…”

“…The study emphasizes the significance of context-aware monitoring and demonstrates the efficacy of this fusion for enhancing the precision of human activity detection within home environments. Karayaneva et al (2023) delve into the realm of AI-enabled healthcare, focusing on the utilization of low-resolution infrared sensor data for human activity recognition. Their work showcases the potential of these sensors in healthcare settings and provides a foundation for advanced patient monitoring systems [14].…”

“…Karayaneva et al (2023) delve into the realm of AI-enabled healthcare, focusing on the utilization of low-resolution infrared sensor data for human activity recognition. Their work showcases the potential of these sensors in healthcare settings and provides a foundation for advanced patient monitoring systems [14]. Yuan et al contribute to the field with a focus on interpretability in passive multi-modal sensor fusion for human identification and activity recognition.…”

Smart Healthcare Activity Recognition Using Statistical Regression and Intelligent Learning

“…But the analyzing time was not addressed. A novel supervised denoising algorithm was proposed [12] for elevating the horizontal and vertical periodic noise from the 2D spatiotemporal images. The proposed approach augments the activity classification accuracy but, it failed to focus on the occurring performance overhead.…”

Ambient assisted living for frail people through human activity recognition: state-of-the-art, challenges and future directions

“…In recent years, low-cost devices integrating RGB and depth sensors, such as Kinect and Intel RealSense systems, have been employed as environmental sensors in AAL systems. Another alternative, IR array cameras, measure thermal energy emitted by the human body or other objects ( Mashiyama et al, 2015 ; Spasova et al, 2016 ; Karayaneva et al, 2023 ). These low-resolution IR arrays offer advantages such as privacy preservation, low power consumption, insensitivity to ambient lighting variations, operation in complete darkness, fast response time, easy deployment, and straightforward image processing.…”