.png){kind=icon}
Return
A Lightweight DCNN Algorithm for Radar-Based Suspicious Human Activities Classification With Data Augmentation Techniques
.png){kind=icon}
PRE
AI
DOI：10.1109/MAES.2025.3581164.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Recent research on deep convolutional neural networks (DCNNs) for classifying micro-Doppler (m-D) signatures faces a significant challenge due to the limited and costly acquisition of data. This constraint restricts the depth and performance of DCNN models that can be effectively implemented. Moreover, most DCNN models are inherently complex and computationally expensive, which exacerbates issues of overfitting in scenarios with limited data availability. Using pretrained models poses disadvantages when applied to small-scale datasets of m-D signatures. Pretrained models, trained on unrelated data, such as images, often fail to capture the unique characteristics of radar m-D signatures, resulting in suboptimal performance. In this study, we address these challenges by introducing augmentation methods tailored for radar m-D signatures. Techniques, such as time shift, frequency disturbance, and frequency shift, are utilized to generate diverse datasets, thereby enriching the training data and enhancing model generalization. Furthermore, we propose a lightweight DIAT-DSCNN-HARNet model specifically designed for this task. Our experiments demonstrate that this model outperforms both pretrained and scratch DCNN models in terms of classification accuracy for augmented data. Specifically, our approach shows superior performance compared to images generated by generative adversarial networks. Our findings highlight the effectiveness of augmentation strategies and specialized model design in improving m-D signature classification.
Keywords:
Deep separable convolutional neural network
suspicious human activities
frequency shift
frequency disturbance
time shift
Journal
IF:
3.8
Papers:
2.1K
Citations:
2.5K
Organization
Cited Papers
ShareSaveA survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications.png)
JOURNAL OF BIG DATA
OAAI
JOURNAL OF BIG DATAIF6.4
OAAIShareSaveShareSaveShareSave
ShareSaveHuman Activity Recognition Based on WRGAN-GP-Synthesized Micro-Doppler SpectrogramsIEEE SENSORS JOURNAL
IEEE SENSORS JOURNALIF4.5
PREAI
ShareSaveUnsupervised Domain Adaptation for Micro-Doppler Human Motion Classification via Feature Fusion
PREAI
ShareSave
View more