DIAT-μ RadHAR (Micro-Doppler Signature Dataset) &amp; μ RadNet (A Lightweight DCNN)—For Human Suspicious Activity Recognition

Chakraborty, Mainak; Kumawat, Harish Chandra; Dhavale, Sunita Vikrant; Raj, A. Arockia Bazil

doi:10.1109/jsen.2022.3151943

Cited by 32 publications

(8 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Ref. Year Reference Equipment Radar Type Radar Frequency Methodology Scenarios Trial Number Data Format Proposed 2023 Lidar UWB 5.3 GHz, 7.5 GHz, 8.8 GHz FFT Biomedical and Ambient-Assistant Living 8 .mat [20] 2022 ECG and respiratory belts Continuous Wave 24 GHz FFT Biomedical 1 .csv (5) 2022 – FMCW 5.8 GHz, 400 MHz Bandwidth FFT and classification algorithms Human Activity Recognition Up to 3 .dat [21] 2022 – Continuous Wave Human Activity Recognition FFT, STFT and classification algorithms Human Activity Recognition – .jpg, .mat [22] 2020 PPG, ECG, PCG, radar, respiration sensor Continuos Wave 24 GHz R peaks and T-wave end detection, STFT Biomedical Up to 30 .mat and .csv [23] 2022 Kinect sensor, Wifi Channel State Information UWB 6.5 GHz Convolutional neurol network based classifier Human Activity Recognition Up to 6 .mat and .csv [24] 2021 – UWB 500 MHz FFT, STFT, EEMD, LTS Convolutional neural network Human Activity Recognition – .jpg [25] 2021 – UWB Biomedical research Co...…”

Section: Methodsmentioning

confidence: 99%

Radar human breathing dataset for applications of ambient assisted living and search and rescue operations

Eren,

Karamzadeh,

Kartal

2023

Data in Brief

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Radar human breathing dataset for applications of ambient assisted living and search and rescue operations

Eren,

Karamzadeh,

Kartal

2023

Data in Brief

View full text Add to dashboard Cite

“…To validate our network, an open-source dataset, DIAT-µRadHAR [30], was selected, which contained samples of six human activities: army crawling, army jogging, jumping while holding a gun, army marching, boxing, and stone-pelting/grenades-throwing. When configuring the network, the optimizer was set to Adam with a learning rate of 0.0001, and a total of 100 epochs were trained.…”

Section: Open-source Dataset Comparisonmentioning

confidence: 99%

Pedestrian Pose Recognition Based on Frequency-Modulated Continuous-Wave Radar with Meta-Learning

Shi,

Zhang,

Shi

et al. 2024

Sensors

View full text Add to dashboard Cite

With the continuous advancement of autonomous driving and monitoring technologies, there is increasing attention on non-intrusive target monitoring and recognition. This paper proposes an ArcFace SE-attention model-agnostic meta-learning approach (AS-MAML) by integrating attention mechanisms into residual networks for pedestrian gait recognition using frequency-modulated continuous-wave (FMCW) millimeter-wave radar through meta-learning. We enhance the feature extraction capability of the base network using channel attention mechanisms and integrate the additive angular margin loss function (ArcFace loss) into the inner loop of MAML to constrain inner loop optimization and improve radar discrimination. Then, this network is used to classify small-sample micro-Doppler images obtained from millimeter-wave radar as the data source for pose recognition. Experimental tests were conducted on pose estimation and image classification tasks. The results demonstrate significant detection and recognition performance, with an accuracy of 94.5%, accompanied by a 95% confidence interval. Additionally, on the open-source dataset DIAT-μRadHAR, which is specially processed to increase classification difficulty, the network achieves a classification accuracy of 85.9%.

show abstract

“…Despite these drawbacks, contactless sensing systems have attracted a lot of attention from researchers. Cameras, microphones, and radar systems are the most prevalent types of contactless sensors [3]. When it comes to lighting and blind spots, cameras aren't perfect.…”

Section: Introductionmentioning

confidence: 99%

Micro-Doppler based Human Activity Recognition using ABOA based Dual Spatial Convolution with Gated Recurrent Unit

Yarramsetti,

et al. 2024

JMC

View full text Add to dashboard Cite

The through-wall capability, device-free detection of radar-based human activity recognition are drawing a lot of interest from both academics and industry. The majority of radar-based systems do not yet combine signal analysis and feature extraction in the frequency domain and the time domain. Applications like smart homes, assisted living, and monitoring rely on human identification and activity recognition (HIAR). Radar has a number of advantages over other sensing modalities, such as the ability to shield users' privacy and conduct contactless sensing. The article introduces a new human tracking system that uses radar and a classifier called Dual Spatial Convolution Gated Recurrent Unit (DSC-GRU) to identify the subject and their behavior. The system follows the person and identifies the type of motion whenever it detects movement. One important feature is the integration of the GRU with the DSC unit, which allows the model to simultaneously capture the spatiotemporal dependence. Present prediction models just take into account spatial features that are immediately adjacent to each other, disregarding or just superimposing global spatial features when taking spatial correlation into account. A new dependency graph is created by calculating the correlation among nodes using the correlation coefficient; this graph represents the global spatial dependence, while the classic static graph represents the neighboring spatial dependence in the DSC unit. The DSC unit goes a step further by using a modified gated mechanism to quantify the various contributions of both local and global spatial correlation. While previous models performed worse, the suggested model outperformed them with an accuracy of 99.45 percent and a precision of 97.15 percent.

show abstract

DIAT-μ RadHAR (Micro-Doppler Signature Dataset) & μ RadNet (A Lightweight DCNN)—For Human Suspicious Activity Recognition

Cited by 32 publications

References 30 publications

Radar human breathing dataset for applications of ambient assisted living and search and rescue operations

Radar human breathing dataset for applications of ambient assisted living and search and rescue operations

Pedestrian Pose Recognition Based on Frequency-Modulated Continuous-Wave Radar with Meta-Learning

Micro-Doppler based Human Activity Recognition using ABOA based Dual Spatial Convolution with Gated Recurrent Unit

Contact Info

Product

Resources

About