A Novel Micro-Doppler Coherence Loss for Deep Learning Radar Applications

• URL: http://arxiv.org/abs/2404.15346v1
• Date: Fri, 12 Apr 2024 08:11:07 GMT
• Title: A Novel Micro-Doppler Coherence Loss for Deep Learning Radar Applications
• Authors: Mikolaj Czerkawski, Christos Ilioudis, Carmine Clemente, Craig Michie, Ivan Andonovic, Christos Tachtatzis,
• Abstract summary: This paper introduces a micro-Doppler coherence loss, minimized when the normalized power of micro-Doppler oscillatory components between input and output is matched. Experiments conducted on real data show that the application of the introduced loss results in models more resilient to noise.
• Score: 1.099532646524593
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep learning techniques are subject to increasing adoption for a wide range of micro-Doppler applications, where predictions need to be made based on time-frequency signal representations. Most, if not all, of the reported applications focus on translating an existing deep learning framework to this new domain with no adjustment made to the objective function. This practice results in a missed opportunity to encourage the model to prioritize features that are particularly relevant for micro-Doppler applications. Thus the paper introduces a micro-Doppler coherence loss, minimized when the normalized power of micro-Doppler oscillatory components between input and output is matched. The experiments conducted on real data show that the application of the introduced loss results in models more resilient to noise.

Related papers

• Generalizable Indoor Human Activity Recognition Method Based on Micro-Doppler Corner Point Cloud and Dynamic Graph Learning [12.032590125621155]
  Through-the-wall radar (TWR) human activity recognition can be achieved by fusing micro-Doppler signature extraction and intelligent decision-making algorithms. This paper proposes a generalizable indoor human activity recognition method based on micro-Doppler corner point cloud and dynamic graph learning.
  arXiv  Detail & Related papers  (2024-10-10T02:24:07Z)
• Dynamical quantum maps for single-qubit gates under universal non-Markovian noise [0.0]
  Noise in quantum devices is ubiquitous and generally deleterious in settings where precision is required. Here we derive a compact microscopic error model for single-qubit gates that only requires a single experimental input. We find that experimental estimates of average gate errors measured through randomized benchmarking and reconstructed via quantum process tomography are tightly lower-bounded by our analytical estimates.
  arXiv  Detail & Related papers  (2024-02-22T13:24:03Z)
• Enhancing Lightweight Neural Networks for Small Object Detection in IoT Applications [1.6932009464531739]
  The paper proposes a novel adaptive tiling method that can be used on top of any existing object detector. Our experimental results show that the proposed tiling method can boost the F1-score by up to 225% while reducing the average object count error by up to 76%.
  arXiv  Detail & Related papers  (2023-11-13T08:58:34Z)
• Attention-Refined Unrolling for Sparse Sequential micro-Doppler Reconstruction [1.1356542363919058]
  STAR is a neural network that reconstructs micro-Doppler sequences of human movement even from highly incomplete channel measurements. It substantially outperforms state-of-the-art techniques in terms of the reconstructed micro-Doppler quality.
  arXiv  Detail & Related papers  (2023-06-25T12:50:17Z)
• Amplitude-Varying Perturbation for Balancing Privacy and Utility in Federated Learning [86.08285033925597]
  This paper presents a new DP perturbation mechanism with a time-varying noise amplitude to protect the privacy of federated learning. We derive an online refinement of the series to prevent FL from premature convergence resulting from excessive perturbation noise. The contribution of the new DP mechanism to the convergence and accuracy of privacy-preserving FL is corroborated, compared to the state-of-the-art Gaussian noise mechanism with a persistent noise amplitude.
  arXiv  Detail & Related papers  (2023-03-07T22:52:40Z)
• MDPose: Human Skeletal Motion Reconstruction Using WiFi Micro-Doppler Signatures [4.92674421365689]
  We propose MDPose, a novel framework for human skeletal motion reconstruction based on WiFi micro-Doppler signatures. It provides an effective solution to track human activities by reconstructing a skeleton model with 17 key points. MDPose outperforms state-of-the-art RF-based pose estimation systems.
  arXiv  Detail & Related papers  (2022-01-11T21:46:28Z)
• Adaptive Low-Pass Filtering using Sliding Window Gaussian Processes [71.23286211775084]
  We propose an adaptive low-pass filter based on Gaussian process regression. We show that the estimation error of the proposed method is uniformly bounded.
  arXiv  Detail & Related papers  (2021-11-05T17:06:59Z)
• Unit-Modulus Wireless Federated Learning Via Penalty Alternating Minimization [64.76619508293966]
  Wireless federated learning (FL) is an emerging machine learning paradigm that trains a global parametric model from distributed datasets via wireless communications. This paper proposes a wireless FL framework, which uploads local model parameters and computes global model parameters via wireless communications.
  arXiv  Detail & Related papers  (2021-08-31T08:19:54Z)
• Neural Network-based Virtual Microphone Estimator [111.79608275698274]
  We propose a neural network-based virtual microphone estimator (NN-VME) The NN-VME estimates virtual microphone signals directly in the time domain, by utilizing the precise estimation capability of the recent time-domain neural networks. Experiments on the CHiME-4 corpus show that the proposed NN-VME achieves high virtual microphone estimation performance even for real recordings.
  arXiv  Detail & Related papers  (2021-01-12T06:30:24Z)
• Delay Minimization for Federated Learning Over Wireless Communication Networks [172.42768672943365]
  The problem of delay computation for federated learning (FL) over wireless communication networks is investigated. A bisection search algorithm is proposed to obtain the optimal solution. Simulation results show that the proposed algorithm can reduce delay by up to 27.3% compared to conventional FL methods.
  arXiv  Detail & Related papers  (2020-07-05T19:00:07Z)
• Temporal-Spatial Neural Filter: Direction Informed End-to-End Multi-channel Target Speech Separation [66.46123655365113]
  Target speech separation refers to extracting the target speaker's speech from mixed signals. Two main challenges are the complex acoustic environment and the real-time processing requirement. We propose a temporal-spatial neural filter, which directly estimates the target speech waveform from multi-speaker mixture.
  arXiv  Detail & Related papers  (2020-01-02T11:12:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.