Deep-Learning Technique for Risk-Based Action Prediction Using Extremely Low-Resolution Thermopile Sensor Array

Morawski, Igor; Lie, Wen-Nung; Aing, Lee; Chiang, Jui-Chiu; Chen, Kuan-Ting

doi:10.1109/tcsvt.2022.3229059

Cited by 3 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Attaching wearable devices firmly onto the skin or integrating them into portable and daily necessary items to provide monitoring, feedback, and treatment has become a great scientific hotspot. [338][339][340][341] For example, Hua et al developed a self-powered sensor based on an ionic hydrogel to monitor the daily movements of the elderly. [340] The triboelectrical signals generated by the bending fingers corresponded to specific words.…”

Section: Elder Carementioning

confidence: 99%

Electronic Skin for Health Monitoring Systems: Properties, Functions, and Applications

Yang,

Chen,

Fan

et al. 2024

Advanced Materials

View full text Add to dashboard Cite

Electronic skin (e‐skin), a skin‐like wearable electronic device, holds great promise in the fields of telemedicine and personalized healthcare because of its good flexibility, biocompatibility, skin conformability, and sensing performance. E‐skin can monitor various health indicators of the human body in real time and over the long term, including physical indicators (exercise, respiration, blood pressure, etc.) and chemical indicators (saliva, sweat, urine, etc.). In recent years, the development of various materials, analysis, and manufacturing technologies has promoted significant development of e‐skin, laying the foundation for the application of next‐generation wearable medical technologies and devices. Herein, we discuss the properties required for e‐skin health monitoring devices to achieve long‐term and precise monitoring and summarize several detectable indicators in the health monitoring field. Subsequently, the applications of integrated e‐skin health monitoring systems are reviewed. Finally, current challenges and future development directions in this field are discussed. This review is expected to generate great interest and inspiration for the development and improvement of e‐skin and health monitoring systems.This article is protected by copyright. All rights reserved

show abstract

Section: Elder Carementioning

confidence: 99%

Electronic Skin for Health Monitoring Systems: Properties, Functions, and Applications

Yang,

Chen,

Fan

et al. 2024

Advanced Materials

View full text Add to dashboard Cite

show abstract

“…• Long-term action prediction: focus on prediction the future action based on the observed action. In other words, given a sequence of action A (which can be either completed or ongoing), the objective is to predict the subsequent action B. Risk-based action prediction, as discussed in [190], [191], is a specific type of long-term action prediction. Its aim is to forecast an action in advance, with a defined anticipation time τ a before the action takes place.…”

Section: F Fall Predictionmentioning

confidence: 99%

Advances in Skeleton-Based Fall Detection in RGB Videos: From Handcrafted to Deep Learning Approaches

Hoang,

Lee,

Piran

et al. 2023

IEEE Access

View full text Add to dashboard Cite

In the elderly population, falls are one of the leading causes of fatal and non-fatal injuries. Fall detection and early alarms play an important role in mitigating the negative effects of falls, especially given the growing proportion of the elderly population. Due to their non-intrusive nature, data availability, and low deployment costs, RGB videos have been used in many previous studies to detect falls. The RGB data, however, can be affected by background environment changes, resulting in non-recognition. To overcome these challenges, many researchers propose extracting skeleton data from RGB videos and using it for fall detection. Although there have been multiple surveys on fall detection, most of them focus on assessing fall detection systems using different kinds of sensors, and a comprehensive evaluation of skeleton-based fall detection in RGB videos is lacking. In this paper, we examine the most recent advances in skeleton-based fall detection in RGB videos, from handcrafted feature-based methods to advanced deep learning algorithms. Further, we present several skeleton-based fall detection techniques and their performance results on various benchmark datasets, along with challenges and future directions in this field.

show abstract

“…Our experiments were performed on two datasets which show that through efficient denoising steps, a competitive performance among state-of-the-art (SOTA) methods can be achieved. This technical advancement, along with the availability of commercial RGB-NIR dual-modality cameras, will broaden the applications of heart rate estimation, e.g., fitting exercise monitoring in gym, elder care [17], etc.…”

Section: Introductionmentioning

confidence: 99%

Heart Rate Estimation from Facial Image Sequences of a Dual-Modality RGB-NIR Camera

Lie

Lai

et al. 2023

Sensors

View full text Add to dashboard Cite

This paper presents an RGB-NIR (Near Infrared) dual-modality technique to analyze the remote photoplethysmogram (rPPG) signal and hence estimate the heart rate (in beats per minute), from a facial image sequence. Our main innovative contribution is the introduction of several denoising techniques such as Modified Amplitude Selective Filtering (MASF), Wavelet Decomposition (WD), and Robust Principal Component Analysis (RPCA), which take advantage of RGB and NIR band characteristics to uncover the rPPG signals effectively through this Independent Component Analysis (ICA)-based algorithm. Two datasets, of which one is the public PURE dataset and the other is the CCUHR dataset built with a popular Intel RealSense D435 RGB-D camera, are adopted in our experiments. Facial video sequences in the two datasets are diverse in nature with normal brightness, under-illumination (i.e., dark), and facial motion. Experimental results show that the proposed method has reached competitive accuracies among the state-of-the-art methods even at a shorter video length. For example, our method achieves MAE = 4.45 bpm (beats per minute) and RMSE = 6.18 bpm for RGB-NIR videos of 10 and 20 s in the CCUHR dataset and MAE = 3.24 bpm and RMSE = 4.1 bpm for RGB videos of 60-s in the PURE dataset. Our system has the advantages of accessible and affordable hardware, simple and fast computations, and wide realistic applications.

show abstract

Deep-Learning Technique for Risk-Based Action Prediction Using Extremely Low-Resolution Thermopile Sensor Array

Cited by 3 publications

References 31 publications

Electronic Skin for Health Monitoring Systems: Properties, Functions, and Applications

Electronic Skin for Health Monitoring Systems: Properties, Functions, and Applications

Advances in Skeleton-Based Fall Detection in RGB Videos: From Handcrafted to Deep Learning Approaches

Heart Rate Estimation from Facial Image Sequences of a Dual-Modality RGB-NIR Camera

Contact Info

Product

Resources

About