Radar detection with the Neyman–Pearson criterion using supervised-learning-machines trained with the cross-entropy error

Jarabo-Amores, María-Pilar; Mata-Moya, David; Gil-Pita, Roberto; Rosa-Zurera, Manuel

doi:10.1186/1687-6180-2013-44

Cited by 28 publications

(16 citation statements)

References 42 publications

(57 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In these papers, learning machines trained in a supervised manner using a suitable loss function are proved to approximate the NP detector. As a representative example, in [12], a neural network is trained to implement a radar detector assuming unknown statistical models for the radar channel using supervised learning. In such case, a conventional NP detector is intractable, since the likelihood ratio cannot be computed.…”

Section: Introductionmentioning

confidence: 99%

End-to-end Learning of Waveform Generation and Detection for Radar Systems

Jiang

Haimovich

Simeone

2019

2019 53rd Asilomar Conference on Signals, Systems, and Computers

View full text Add to dashboard Cite

An end-to-end learning approach is proposed for the joint design of transmitted waveform and detector in a radar system.Detector and transmitted waveform are trained alternately: For a fixed transmitted waveform, the detector is trained using supervised learning so as to approximate the Neyman-Pearson detector; and for a fixed detector, the transmitted waveform is trained using reinforcement learning based on feedback from the receiver. No prior knowledge is assumed about the target and clutter models.Both transmitter and receiver are implemented as feedforward neural networks. Numerical results show that the proposed endto-end learning approach is able to obtain a more robust radar performance in clutter and colored noise of arbitrary probability density functions as compared to conventional methods, and to successfully adapt the transmitted waveform to environmental conditions. Index TermsRadar waveform design, radar detector design, neural network, reinforcement learning, supervised learning.

show abstract

Section: Introductionmentioning

confidence: 99%

End-to-end Learning of Waveform Generation and Detection for Radar Systems

Jiang

Haimovich

Simeone

2019

2019 53rd Asilomar Conference on Signals, Systems, and Computers

View full text Add to dashboard Cite

show abstract

“…Note that the number of samples used during the adaptation phase could be much smaller than that used during the offline training phase. The standard cross-entropy [9] is adopted as the loss function for the receiver. For any dataset D 0 = z (q) ∼ p(z|H i (q) ), i (q) ∈ {0, 1} Q0 q=1 containing Q 0 pairs of received signal z and target state indicator i, the empirical cross-entropy loss is a function of the trainable parameter vector φ, and is given by…”

Section: Two-stage Design Of Fast Adaptive Receivermentioning

confidence: 99%

“…Deep learning has been successfully applied in a variety of fields to solve problems for which reliable mathematical models are unavailable or too complex to yield feasible optimal solutions [8]. In the radar field, deep learning-based approaches have been proposed for implementing NP detectors [9]. These approaches rely on the assumption that the training and the actual operating environments have similar statistical properties.…”

Section: Introductionmentioning

confidence: 99%

“…In this work, we aim to design detectors that adapt quickly to the radar operating environment based on few data samples. Unlike the techniques in [9], the deep learning-based detector design is separated into two stages, i.e., an offline training stage and an adaptation stage. The goal of the offline training stage is to leverage prior knowledge from multiple radar environments via transfer learning or meta-learning.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fast Data-Driven Adaptation of Radar Detection via Meta-Learning

Jiang¹,

Haimovich²,

Govoni³

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper addresses the problem of fast learning of radar detectors with a limited amount of training data. In current data-driven approaches for radar detection, re-training is generally required when the operating environment changes, incurring large overhead in terms of data collection and training time.In contrast, this paper proposes two novel deep learning-based approaches that enable fast adaptation of detectors based on few data samples from a new environment. The proposed methods integrate prior knowledge regarding previously encountered radar operating environments in two different ways. One approach is based on transfer learning: it first pre-trains a detector such that it works well on data collected in previously observed environments, and then it adapts the pre-trained detector to the specific current environment. The other approach targets explicitly few-shot training via meta-learning: based on data from previous environments, it finds a common initialization that enables fast adaptation to a new environment. Numerical results validate the benefits of the proposed two approaches compared with the conventional method based on training with no prior knowledge. Furthermore, the meta-learning-based detector outperforms the transfer learning-based detector when the clutter is Gaussian.

show abstract

“…If the value in the cell C T exceeds the threshold value T, the comparator declares that an impulse is located in the cell C T . The P f a is chosen to satisfy the Neyman-Pearson theorem for detection [27]…”

Section: Burst Detection Use Enhance Constant Fault Alarm Ratementioning

confidence: 99%

Acoustic Emission Burst Extraction for Multi-Level Leakage Detection in a Pipeline

et al. 2020

View full text Add to dashboard Cite

Acoustic emission bursts are signal waveforms that include a number of consecutive imbrication transients with variable strengths and contain crucial information on the leakage phenomenon in a pipeline system. Detection and isolation of a burst against the background signal increases the ability of a pipe’s fault diagnosis system. This paper proposes a methodology using the Enhanced Constant Fault Alarm Rate (ECFAR) to detect bursts and exploit the burst phenomenon in acoustic emission. The extracted information from the burst waveform is used to distinguish several levels of leakage in a laboratory leak-off experimental testbed. The multi-class support vector machine in the one-against-all method is established as the classifier. The results are compared with those of the wavelet threshold-based method, another algorithm utilized for impulse and burst detection, which indicates that the ECFAR method gives an ameliorative classification result with an accuracy of 93% for different levels of leakage.

show abstract

Radar detection with the Neyman–Pearson criterion using supervised-learning-machines trained with the cross-entropy error

Cited by 28 publications

References 42 publications

End-to-end Learning of Waveform Generation and Detection for Radar Systems

End-to-end Learning of Waveform Generation and Detection for Radar Systems

Fast Data-Driven Adaptation of Radar Detection via Meta-Learning

Acoustic Emission Burst Extraction for Multi-Level Leakage Detection in a Pipeline

Contact Info

Product

Resources

About