Cargando…

Comparative Analysis of Audio Processing Techniques on Doppler Radar Signature of Human Walking Motion Using CNN Models

Artificial intelligence (AI) radar technology offers several advantages over other technologies, including low cost, privacy assurance, high accuracy, and environmental resilience. One challenge faced by AI radar technology is the high cost of equipment and the lack of radar datasets for deep-learni...

Descripción completa

Detalles Bibliográficos
Autores principales: Ha, Minh-Khue, Phan, Thien-Luan, Nguyen, Duc Hoang Ha, Quan, Nguyen Hoang, Ha-Phan, Ngoc-Quan, Ching, Congo Tak Shing, Hieu, Nguyen Van
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10650032/
https://www.ncbi.nlm.nih.gov/pubmed/37960447
http://dx.doi.org/10.3390/s23218743
_version_ 1785135686329827328
author Ha, Minh-Khue
Phan, Thien-Luan
Nguyen, Duc Hoang Ha
Quan, Nguyen Hoang
Ha-Phan, Ngoc-Quan
Ching, Congo Tak Shing
Hieu, Nguyen Van
author_facet Ha, Minh-Khue
Phan, Thien-Luan
Nguyen, Duc Hoang Ha
Quan, Nguyen Hoang
Ha-Phan, Ngoc-Quan
Ching, Congo Tak Shing
Hieu, Nguyen Van
author_sort Ha, Minh-Khue
collection PubMed
description Artificial intelligence (AI) radar technology offers several advantages over other technologies, including low cost, privacy assurance, high accuracy, and environmental resilience. One challenge faced by AI radar technology is the high cost of equipment and the lack of radar datasets for deep-learning model training. Moreover, conventional radar signal processing methods have the obstacles of poor resolution or complex computation. Therefore, this paper discusses an innovative approach in the integration of radar technology and machine learning for effective surveillance systems that can surpass the aforementioned limitations. This approach is detailed into three steps: signal acquisition, signal processing, and feature-based classification. A hardware prototype of the signal acquisition circuitry was designed for a Continuous Wave (CW) K-24 GHz frequency band radar sensor. The collected radar motion data was categorized into non-human motion, human walking, and human walking without arm swing. Three signal processing techniques, namely short-time Fourier transform (STFT), mel spectrogram, and mel frequency cepstral coefficients (MFCCs), were employed. The latter two are typically used for audio processing, but in this study, they were proposed to obtain micro-Doppler spectrograms for all motion data. The obtained micro-Doppler spectrograms were then fed to a simplified 2D convolutional neural networks (CNNs) architecture for feature extraction and classification. Additionally, artificial neural networks (ANNs) and 1D CNN models were implemented for comparative analysis on various aspects. The experimental results demonstrated that the 2D CNN model trained on the MFCC feature outperformed the other two methods. The accuracy rate of the object classification models trained on micro-Doppler features was 97.93%, indicating the effectiveness of the proposed approach.
format Online
Article
Text
id pubmed-10650032
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-106500322023-10-26 Comparative Analysis of Audio Processing Techniques on Doppler Radar Signature of Human Walking Motion Using CNN Models Ha, Minh-Khue Phan, Thien-Luan Nguyen, Duc Hoang Ha Quan, Nguyen Hoang Ha-Phan, Ngoc-Quan Ching, Congo Tak Shing Hieu, Nguyen Van Sensors (Basel) Article Artificial intelligence (AI) radar technology offers several advantages over other technologies, including low cost, privacy assurance, high accuracy, and environmental resilience. One challenge faced by AI radar technology is the high cost of equipment and the lack of radar datasets for deep-learning model training. Moreover, conventional radar signal processing methods have the obstacles of poor resolution or complex computation. Therefore, this paper discusses an innovative approach in the integration of radar technology and machine learning for effective surveillance systems that can surpass the aforementioned limitations. This approach is detailed into three steps: signal acquisition, signal processing, and feature-based classification. A hardware prototype of the signal acquisition circuitry was designed for a Continuous Wave (CW) K-24 GHz frequency band radar sensor. The collected radar motion data was categorized into non-human motion, human walking, and human walking without arm swing. Three signal processing techniques, namely short-time Fourier transform (STFT), mel spectrogram, and mel frequency cepstral coefficients (MFCCs), were employed. The latter two are typically used for audio processing, but in this study, they were proposed to obtain micro-Doppler spectrograms for all motion data. The obtained micro-Doppler spectrograms were then fed to a simplified 2D convolutional neural networks (CNNs) architecture for feature extraction and classification. Additionally, artificial neural networks (ANNs) and 1D CNN models were implemented for comparative analysis on various aspects. The experimental results demonstrated that the 2D CNN model trained on the MFCC feature outperformed the other two methods. The accuracy rate of the object classification models trained on micro-Doppler features was 97.93%, indicating the effectiveness of the proposed approach. MDPI 2023-10-26 /pmc/articles/PMC10650032/ /pubmed/37960447 http://dx.doi.org/10.3390/s23218743 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Ha, Minh-Khue
Phan, Thien-Luan
Nguyen, Duc Hoang Ha
Quan, Nguyen Hoang
Ha-Phan, Ngoc-Quan
Ching, Congo Tak Shing
Hieu, Nguyen Van
Comparative Analysis of Audio Processing Techniques on Doppler Radar Signature of Human Walking Motion Using CNN Models
title Comparative Analysis of Audio Processing Techniques on Doppler Radar Signature of Human Walking Motion Using CNN Models
title_full Comparative Analysis of Audio Processing Techniques on Doppler Radar Signature of Human Walking Motion Using CNN Models
title_fullStr Comparative Analysis of Audio Processing Techniques on Doppler Radar Signature of Human Walking Motion Using CNN Models
title_full_unstemmed Comparative Analysis of Audio Processing Techniques on Doppler Radar Signature of Human Walking Motion Using CNN Models
title_short Comparative Analysis of Audio Processing Techniques on Doppler Radar Signature of Human Walking Motion Using CNN Models
title_sort comparative analysis of audio processing techniques on doppler radar signature of human walking motion using cnn models
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10650032/
https://www.ncbi.nlm.nih.gov/pubmed/37960447
http://dx.doi.org/10.3390/s23218743
work_keys_str_mv AT haminhkhue comparativeanalysisofaudioprocessingtechniquesondopplerradarsignatureofhumanwalkingmotionusingcnnmodels
AT phanthienluan comparativeanalysisofaudioprocessingtechniquesondopplerradarsignatureofhumanwalkingmotionusingcnnmodels
AT nguyenduchoangha comparativeanalysisofaudioprocessingtechniquesondopplerradarsignatureofhumanwalkingmotionusingcnnmodels
AT quannguyenhoang comparativeanalysisofaudioprocessingtechniquesondopplerradarsignatureofhumanwalkingmotionusingcnnmodels
AT haphanngocquan comparativeanalysisofaudioprocessingtechniquesondopplerradarsignatureofhumanwalkingmotionusingcnnmodels
AT chingcongotakshing comparativeanalysisofaudioprocessingtechniquesondopplerradarsignatureofhumanwalkingmotionusingcnnmodels
AT hieunguyenvan comparativeanalysisofaudioprocessingtechniquesondopplerradarsignatureofhumanwalkingmotionusingcnnmodels