Human Activity Classification With Radar: Optimization and Noise Robustness With Iterative Convolutional Neural Networks Followed With Random Forests
Open accessThe DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.
Abstract
The accurate classification of activity patterns based on radar signatures is still an open problem and is a key to detect anomalous behavior for security and health applications. This paper presents a novel iterative convolutional neural network strategy with an autocorrelation pre-processing instead of the traditional micro-Doppler image pre-processing to classify activities or subjects accurately. The proposed strategy uses an iterative deep learning framework for the automatic definition and extraction of features. This is followed by a traditional supervised learning classifier to label different activities. Using three human subjects and their real motion captured data, 12 000 radar signatures were simulated by varying additive white Gaussian noise. In addition, 6720 experimental radar signatures were captured with a frequency-modulated continuous radar at 5.8 GHz with 400 MHz of instantaneous bandwidth from seven activities using one subject and 4800 signatures from five subjects while walking. The simulated and experimental data were both used to validate our proposed method, with signal-noise ratio varying from -20 to 20 dB and with 88.74% average accuracy at -10 dB and 100% peak accuracy at 15 dB. The proposed iterative convolutional neural networks followed with random forests not only outperform the feature-based methods using micro-Doppler images but also outperform the classification methods using other types of supervised classifiers after our proposed iterative convolutional neural network.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“When collecting human activity data in natural environments, imbalances often occur [37].”
From LSTM-CNN Architecture for Human Activity Recognition (2020) · cites this paper as [37]
Citations
Cites
Boyd, S., & Vandenberghe, L. (2004) · doi:10.1017/cbo9780511804441 · Cited by 56,601
Micro-doppler effect in radar: phenomenon, model, and simulation study
Chen, V. C., Li, F., Ho, S.-S., & Wechsler, H. (2006) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2006.1603402 · Cited by 1,684
Time-Frequency Transforms for Radar Imaging and Signal Analysis
Chen, V. C., & Ling, H. (2002) · Cited by 887
Chan, J. C.-W., & Paelinckx, D. (2008) · Remote Sensing of Environment · doi:10.1016/j.rse.2008.02.011 · Cited by 858
The Micro-Doppler Effect in Radar
Chen, V. C. (2010) · Cited by 717
Kim, Y., & Moon, T. (2016) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2015.2491329 · Cited by 647
Notes on Convolutional Neural NetworksPreprint
Bouvrie, J. (2006) · CogPrints (University of Southampton) · Cited by 571
A global human walking model with real-time kinematic personification
Boulic, R., Thalmann, N. M., & Thalmann, D. (1990) · The Visual Computer · doi:10.1007/bf01901021 · Cited by 502
Documentation Mocap Database HDM05
Müller, M., Röder, T., Clausen, M. V., Eberhardt, B., Krüger, B., & Weber⋆, A. (2007) · Cited by 378
Hand Gesture Recognition Using Micro-Doppler Signatures With Convolutional Neural Network
Kim, Y., & Toomajian, B. (2016) · IEEE Access · doi:10.1109/access.2016.2617282 · Cited by 378
Fall Detection Using Deep Learning in Range-Doppler Radars
Jokanovic, B., & Amin, M. (2018) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2017.2740098 · Cited by 260
Analysis of radar micro-Doppler with time-frequency transform
Chen, V. C. (2002) · Proceedings of the Tenth IEEE Workshop on Statistical Signal and Array Processing (Cat. No.00TH8496) · doi:10.1109/ssap.2000.870167 · Cited by 249
Drone Classification Using Convolutional Neural Networks With Merged Doppler Images
Kim, B. K., Kang, H.-S., & Park, S.-O. (2017) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2016.2624820 · Cited by 234
Radar and RGB-Depth Sensors for Fall Detection: A Review
Cippitelli, E., Fioranelli, F., Gambi, E., & Spinsante, S. (2017) · IEEE Sensors Journal · doi:10.1109/jsen.2017.2697077 · Cited by 198
Self-citationSensitivity and specificity of classification systems for fatness in adolescents
Neovius, M., Linne, Y. M., Barkeling, B., & Rössner, S. (2004) · American Journal of Clinical Nutrition · doi:10.1093/ajcn/80.3.597 · Cited by 179
Introduction to Statistical Machine Learning
杉山, 将. (2016) · Elsevier eBooks · doi:10.1016/c2014-0-01992-2 · Cited by 164
Deep learning based doppler radar for micro UAS detection and classification
Mendis, G. J., Randeny, T., Wei, J., & Madanayake, A. (2016) · MILCOM 2016 - 2016 IEEE Military Communications Conference · doi:10.1109/milcom.2016.7795448 · Cited by 97
A kinect-based human micro-doppler simulator
Erol, B., & Gürbüz, S. Z. (2015) · IEEE Aerospace and Electronic Systems Magazine · doi:10.1109/maes.2015.7119820 · Cited by 88
Knowledge Exploitation for Human Micro-Doppler Classification
Karabacak, C., Gürbüz, S. Z., Gürbüz, A. C., Guldogan, M. B., Hendeby, G., & Gustafsson, F. (2015) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2015.2452311 · Cited by 81
Operational assessment and adaptive selection of micro‐Doppler features
Gürbüz, S. Z., Erol, B., Çağlıyan, B., & Tekeli, B. (2015) · IET Radar Sonar & Navigation · doi:10.1049/iet-rsn.2015.0144 · Cited by 77
Multistatic human micro‐Doppler classification of armed/unarmed personnel
Fioranelli, F., Ritchie, M., & Griffiths, H. (2015) · IET Radar Sonar & Navigation · doi:10.1049/iet-rsn.2014.0360 · Cited by 76
Self-citationFioranelli, F., Ritchie, M., & Griffiths, H. (2016) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2016.2539386 · Cited by 65
Self-citationDeep learning of micro-Doppler features for aided and unaided gait recognition
Seyfioğlu, M. S., Gürbüz, S. Z., Özbayoğlu, A. M., & Yüksel, M. (2017) · IEEE Radar Conference (RadarConf) · doi:10.1109/radar.2017.7944373 · Cited by 61
Introduction to Machine Learning
Tiwari, A. K. (2017) · Advances in computational intelligence and robotics book series · doi:10.4018/978-1-5225-2545-5.ch001 · Cited by 46
Feature diversity for fall detection and human indoor activities classification using radar systems
Shrestha, A., Kernec, J. L., Fioranelli, F., Cippitelli, E., Gambi, E., & Spinsante, S. (2017) · IET International Conference on Radar Systems (RADAR) · doi:10.1049/cp.2017.0381 · Cited by 44
Self-citationDiversified radar micro-Doppler simulations as training data for deep residual neural networks
Seyfioğlu, M. S., Erol, B., Gürbüz, S. Z., & Amin, M. G. (2018) · IEEE Radar Conference (RadarConf) · doi:10.1109/radar.2018.8378629 · Cited by 41
Lin, Y., & Kernec, J. L. (2017) · International Conference on Computational Intelligence and Security (CIS) · doi:10.1109/cis.2017.00111 · Cited by 37
Self-citationActivity recognition with cooperative radar systems at C and K band
Shrestha, A., Li, H., Fioranelli, F., & Kernec, J. L. (2019) · The Journal of Engineering · doi:10.1049/joe.2019.0559 · Cited by 8
Self-citationAutomatic human activity classification using radar
Karabacak, C., Gürbüz, S. Z., & Gürbüz, A. C. (2014) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2014.6830413 · Cited by 2
Deflection characterisation of rotary systems using ground‐based radar
Ochieng, F. X., Jiang, H., Hancock, C. M., Roberts, G. W., Kernec, J. L., Tang, X., & de Ligt, H. (2019) · The Journal of Engineering · doi:10.1049/joe.2019.0503 · Cited by 2
Research works printed but not linked: 2
- zhu, 2010, Sensitivity, Specificity, Accuracy, Associated Confidence Interval and ROC Analysis with Practical SAS Implementations, NESUG Health Care and Life Sciences, 67
- o’neill, 2006, Neural Network for Recognition of Handwritten Digits
Cited by
LSTM-CNN Architecture for Human Activity Recognition
Xia, K., Huang, J., & Wang, H. (2020) · IEEE Access · doi:10.1109/access.2020.2982225 · Cited by 851
“[26] presented a novel iterative CNN strategy with autocorrelation pre-processing capability, instead of traditional micro-Doppler image pre-processing, which can accurately classify seven activities or five subjects.”
BackgroundHuman Action Recognition From Various Data Modalities: A Review
Sun, Z., Ke, Q., Rahmani, H., Bennamoun, M., Wang, G., & Liu, J. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3183112 · Cited by 601
A Survey of Deep Learning-Based Human Activity Recognition in Radar
Li, X., He, Y., & Jing, X. (2019) · Remote Sensing · doi:10.3390/rs11091068 · Cited by 290
Ding, C., Hong, H., Zou, Y., Chu, H., Zhu, X., Fioranelli, F., Le Kernec, J., & Li, C. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2908758 · Cited by 183
Self-citationCRN: Camera Radar Net for Accurate, Robust, Efficient 3D Perception
Kim, Y., Shin, J., Kim, S., Lee, I.-J., Choi, J. W., & Kum, D. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01615 · Cited by 155
“For training and evaluating long-range models, we increase the ‘class range’ in nuScenes [1] twice to filter the ground truth and predictions.”
Method
Metadata
- Authors
- Lin, Y., Le Kernec, J., Yang, S., Fioranelli, F., Romain, O., & Zhao, Z.
- Affiliations
- University of Electronic Science and Technology of China (CN)
- University of Glasgow (GB)
- Equipes Traitement de l'Information et Systèmes (FR)
- Venue
- IEEE Sensors Journal
- Published
- 2018-12-01
- Volume
- 18
- Issue
- 23
- Pages
- 9669-9681
- ISSN
- 1530-437X (ISSN-L)
- 1558-1748
- 2379-9153
- OpenAlex
- W2893047521
- Cited by
- 81
- References
- 30
- Citations by year
- 2025: 4 · 2024: 11 · 2023: 17 · 2022: 11 · 2021: 22 · 2020: 9 · 2019: 6 · 2018: 1
- FWCI
- 7.72
- Type
- journal article
- Language
- en
- Open access
- green
- eprints.gla.ac.uk
- Locations
- IEEE Sensors Journal (publishedVersion)
- ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam) (acceptedVersion, cc-by-sa)
- Research Output (Edinburgh Napier University) (submittedVersion)
- Edinburgh Napier Research Repository (Edinburgh Napier University) (submittedVersion)
- Funders
- National Natural Science Foundation of China (61571086, 61601103)
- Engineering and Physical Sciences Research Council (EP/R041679/1)
- China Scholarship Council (201806070002)
- Topics
- Physical Sciences › Engineering › Aerospace Engineering › Advanced SAR Imaging Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Engineering › Biomedical Engineering › Non-Invasive Vital Sign Monitoring
- Keywords
- human activity classification, radar signature, random forest, noise robustness, signal-to-noise ratio, abnormal behavior detection, feature extraction
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.