Radar Gesture Recognition System in Presence of Interference using Self-Attention Neural Network

Hazra, Souvik; Santra, Avik

doi:10.1109/icmla.2019.00230

Cited by 28 publications

(17 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Windowing can also be employed to track target position across spectrograms [123]. Maximal Ration Combining (MRC) refers to the creation of mean range and velocity and range and azimuth spectrograms from a range, velocity, and azimuth cube containing magnitude values by computing a weighted mean [126]. Discontinuous range, azimuth sine, and velocity sequence values are smoothed.…”

Section: Reconstructon Denoisingmentioning

confidence: 99%

“…The border between feature extraction and analytical modeling has become blurry in recent papers on millimeter wave sensing applications. Several deep learning models contain layers designated for feature extraction [16], [46], [47], [92], [125], [126], [130], [138], [158]. Certain positioning and environment mapping algorithms resemble feature extraction methodologies [160], [184].…”

Section: Feature Extractionmentioning

confidence: 99%

“…Not adapting the learning rate, i.e., a hyperparameter that controls how much parameter update is used to change the model parameters, during training cycles can result in long execution time for model training or training instability. To combat these problems, adaptive learning rate techniques such as Adaptive Moment (ADAM) estimation [46], [47], [53], [63], [76], [92], [103], [123], [124], [126]- [128], [130], [158] or manual learning rate decay [125], [174] can be employed. c) Cross Validation: Cross validation refers to training a model and evaluating model performance multiple times on a variety of different data or feature set splits.…”

Section: E Modeling Evaluationmentioning

confidence: 99%

“…Training instability examples include the cost or reward function prematurely becoming constant, a cost function that suddenly starts to increase with continuous acceleration, etc. Batch normalization [16], [63], [92], [123], [124], [128], [138], [192], initializing the model parameters prior to training with Xavier initialization [126]- [128], [192], making changes to existing model types with for example the ResNet layer [92], [123] or LeakyRELU activation function [48], [53], [77], [138], and parameter update averaging over multiple training cycles with momentum [120], [125], [181], [193] have been proposed to solve the problem of training instability.…”

Section: Regularization Hyperparameter Tuning Cross Validation Trainimentioning

confidence: 99%

See 3 more Smart Citations

Millimeter Wave Sensing: A Review of Application Pipelines and Building Blocks

et al. 2021

View full text Add to dashboard Cite

The increasing bandwidth requirement of new wireless applications has lead to standardization of the millimeter wave spectrum for high-speed wireless communication. The millimeter wave spectrum is part of 5G and covers frequencies between 30 and 300 GHz that correspond to wavelengths ranging from 10 to 1 mm. Although millimeter wave is often considered as a communication medium, it has also proved to be an excellent 'sensor', thanks to its narrow beams, operation across a wide bandwidth, and interaction with atmospheric constituents. In this paper, which is to the best of our knowledge the first review that completely covers millimeter wave sensing application pipelines, we provide a comprehensive overview and analysis of different basic application pipeline building blocks, including hardware, algorithms, analytical models, and model evaluation techniques. The review also provides a taxonomy that highlights different millimeter wave sensing application domains. By performing a thorough analysis, complying with the systematic literature review methodology and reviewing 165 papers, we not only extend previous investigations focused only on communication aspects of the millimeter wave technology and using millimeter wave technology for active imaging, but also highlight scientific and technological challenges and trends, and provide a future perspective for applications of millimeter wave as a sensing technology.

show abstract

Section: Reconstructon Denoisingmentioning

confidence: 99%

Section: Feature Extractionmentioning

confidence: 99%

Section: E Modeling Evaluationmentioning

confidence: 99%

Section: Regularization Hyperparameter Tuning Cross Validation Trainimentioning

confidence: 99%

See 2 more Smart Citations

Millimeter Wave Sensing: A Review of Application Pipelines and Building Blocks

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Another concern of the contemporary HCI frameworks is their power [22][23][24][25][26]. The typical operation of HCI frameworks is based on the analysis of the spatial-temporal relations between consecutive frames utilizing the deep learning methods, e.g., 3D convolutional neural networks (CNN3D), long short-term memory (LSTM), and Recurrent Neural Networks (RNN) [27][28][29][30]. This analysis is a computationally complex task, which prevents deployment on resource-constrained devices [23][24][25][26][31][32][33][34][35][36][37][38][39].…”

Section: Introductionmentioning

confidence: 99%

Highly-Optimized Radar-Based Gesture Recognition System with Depthwise Expansion Module

Chmurski

Mauro

Santra

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

The increasing integration of technology in our daily lives demands the development of more convenient human–computer interaction (HCI) methods. Most of the current hand-based HCI strategies exhibit various limitations, e.g., sensibility to variable lighting conditions and limitations on the operating environment. Further, the deployment of such systems is often not performed in resource-constrained contexts. Inspired by the MobileNetV1 deep learning network, this paper presents a novel hand gesture recognition system based on frequency-modulated continuous wave (FMCW) radar, exhibiting a higher recognition accuracy in comparison to the state-of-the-art systems. First of all, the paper introduces a method to simplify radar preprocessing while preserving the main information of the performed gestures. Then, a deep neural classifier with the novel Depthwise Expansion Module based on the depthwise separable convolutions is presented. The introduced classifier is optimized and deployed on the Coral Edge TPU board. The system defines and adopts eight different hand gestures performed by five users, offering a classification accuracy of 98.13% while operating in a low-power and resource-constrained environment.

show abstract

Deep Parametric Learning

2022

Methods and Techniques in Deep Learning

View full text Add to dashboard Cite

Radar Gesture Recognition System in Presence of Interference using Self-Attention Neural Network

Cited by 28 publications

References 7 publications

Millimeter Wave Sensing: A Review of Application Pipelines and Building Blocks

Millimeter Wave Sensing: A Review of Application Pipelines and Building Blocks

Highly-Optimized Radar-Based Gesture Recognition System with Depthwise Expansion Module

Deep Parametric Learning

Contact Info

Product

Resources

About