Deep Learning Techniques for Radar-Based Continuous Human Activity Recognition

Human capability to perform routine tasks declines with age and age-related problems. Remote human activity recognition (HAR) is beneficial for regular monitoring of the elderly population. This paper addresses the problem of the continuous detection of daily human activities using a mm-wave Doppler...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Machine learning and knowledge extraction Ročník 5; číslo 4; s. 1493 - 1518
Hlavní autoři: Mehta, Ruchita, Sharifzadeh, Sara, Palade, Vasile, Tan, Bo, Daneshkhah, Alireza, Karayaneva, Yordanka
Médium: Journal Article
Jazyk:angličtina
Vydáno: Basel MDPI AG 01.12.2023
Témata:
Activities of daily living
Algorithms
Annotations
Artificial neural networks
Coding
convolutional variational autoencoder (CVAE)
Data analysis
Data collection
Deep learning
deep neural networks (DNNs)
Doppler radar
dynamic time warping (DTW)
Equalization
Feature extraction
Frames (data processing)
Human activity recognition
human activity recognition (HAR)
Machine learning
Millimeter waves
mm-wave radar sensor
Neural networks
Object recognition (Computers)
Older people
Pattern recognition
Principal components analysis
Privacy
Radar systems
Sensors
Wearable computers
United Kingdom
ISSN:2504-4990, 2504-4990
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Human capability to perform routine tasks declines with age and age-related problems. Remote human activity recognition (HAR) is beneficial for regular monitoring of the elderly population. This paper addresses the problem of the continuous detection of daily human activities using a mm-wave Doppler radar. In this study, two strategies have been employed: the first method uses un-equalized series of activities, whereas the second method utilizes a gradient-based strategy for equalization of the series of activities. The dynamic time warping (DTW) algorithm and Long Short-term Memory (LSTM) techniques have been implemented for the classification of un-equalized and equalized series of activities, respectively. The input for DTW was provided using three strategies. The first approach uses the pixel-level data of frames (UnSup-PLevel). In the other two strategies, a convolutional variational autoencoder (CVAE) is used to extract Un-Supervised Encoded features (UnSup-EnLevel) and Supervised Encoded features (Sup-EnLevel) from the series of Doppler frames. The second approach for equalized data series involves the application of four distinct feature extraction methods: i.e., convolutional neural networks (CNN), supervised and unsupervised CVAE, and principal component Analysis (PCA). The extracted features were considered as an input to the LSTM. This paper presents a comparative analysis of a novel supervised feature extraction pipeline, employing Sup-ENLevel-DTW and Sup-EnLevel-LSTM, against several state-of-the-art unsupervised methods, including UnSUp-EnLevel-DTW, UnSup-EnLevel-LSTM, CNN-LSTM, and PCA-LSTM. The results demonstrate the superiority of the Sup-EnLevel-LSTM strategy. However, the UnSup-PLevel strategy worked surprisingly well without using annotations and frame equalization.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2504-4990
2504-4990
DOI:10.3390/make5040075