Pub Date : 2023-05-01DOI: 10.1109/RadarConf2351548.2023.10149573
D. Ciuonzo, Apoorva Chawla, P. Rossi
In this study, we address the challenge of non-cooperative target detection by federating two wireless sensor networks. The objective is to capitalize on the diversity achievable from both sensing and reporting phases. The target's presence results in an unknown signal that is influenced by unknown distances between the sensors and target, as well as by symmetrical and single-peaked noise. The fusion center, responsible for making more accurate decisions, receives quantized sensor observations through error-prone binary symmetric channels. This leads to a two-sided testing problem with nuisance parameters (the target position) only present under the alternative hypothesis. To tackle this challenge, we present a generalized likelihood ratio test and design a fusion rule based on a generalized Rao test to reduce the computational complexity. Our results demonstrate the efficacy of the Rao test in terms of detection/false-alarm rate and computational simplicity, highlighting the advantage of designing the system using federation.
{"title":"Non-cooperative Distributed Detection via Federated Sensor Networks","authors":"D. Ciuonzo, Apoorva Chawla, P. Rossi","doi":"10.1109/RadarConf2351548.2023.10149573","DOIUrl":"https://doi.org/10.1109/RadarConf2351548.2023.10149573","url":null,"abstract":"In this study, we address the challenge of non-cooperative target detection by federating two wireless sensor networks. The objective is to capitalize on the diversity achievable from both sensing and reporting phases. The target's presence results in an unknown signal that is influenced by unknown distances between the sensors and target, as well as by symmetrical and single-peaked noise. The fusion center, responsible for making more accurate decisions, receives quantized sensor observations through error-prone binary symmetric channels. This leads to a two-sided testing problem with nuisance parameters (the target position) only present under the alternative hypothesis. To tackle this challenge, we present a generalized likelihood ratio test and design a fusion rule based on a generalized Rao test to reduce the computational complexity. Our results demonstrate the efficacy of the Rao test in terms of detection/false-alarm rate and computational simplicity, highlighting the advantage of designing the system using federation.","PeriodicalId":168311,"journal":{"name":"2023 IEEE Radar Conference (RadarConf23)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134484930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/RadarConf2351548.2023.10149778
K. Kolodziej, G. Brigham, M. Harger, B. Janice, Adrienne I. Sands, R. Teal, Louis Turek, Pierre-Francois W. Wolfe, J. Doane, B. Perry
Phased array systems can straightforwardly support integrated sensing and communication (ISAC) as well as other functions simultaneously by incorporating in-band full-duplex (IBFD) technology. Digitally-controlled self-interference cancellation techniques have been shown to create isolation between transmit and receive sub arrays within a single aperture for limited numbers of elements. This paper discusses the key components of a scalable panel-based IBFD array system, including the aperture and backplane assemblies as well as a cold plate structure for thermal management. The array is designed to operate from 2.7 to 3.5 GHz, and will provide the opportunity to demonstrate ISAC capability in a fashion that is scalable for many different deployment locations and/or platforms.
{"title":"Phased Array Architecture Enabling Scalable Integrated Sensing and Communication","authors":"K. Kolodziej, G. Brigham, M. Harger, B. Janice, Adrienne I. Sands, R. Teal, Louis Turek, Pierre-Francois W. Wolfe, J. Doane, B. Perry","doi":"10.1109/RadarConf2351548.2023.10149778","DOIUrl":"https://doi.org/10.1109/RadarConf2351548.2023.10149778","url":null,"abstract":"Phased array systems can straightforwardly support integrated sensing and communication (ISAC) as well as other functions simultaneously by incorporating in-band full-duplex (IBFD) technology. Digitally-controlled self-interference cancellation techniques have been shown to create isolation between transmit and receive sub arrays within a single aperture for limited numbers of elements. This paper discusses the key components of a scalable panel-based IBFD array system, including the aperture and backplane assemblies as well as a cold plate structure for thermal management. The array is designed to operate from 2.7 to 3.5 GHz, and will provide the opportunity to demonstrate ISAC capability in a fashion that is scalable for many different deployment locations and/or platforms.","PeriodicalId":168311,"journal":{"name":"2023 IEEE Radar Conference (RadarConf23)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133310746","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/RadarConf2351548.2023.10149608
Xue-lian Yu, Sen Liu, H. Ren, L. Zou, Yun Zhou, Xue-gang Wang
In recent years, synthetic aperture radar (SAR) automatic target recognition (ATR) methods driven by huge training samples have achieved remarkable results. However, in real SAR application scenarios, it is extremely difficult to provide enough training samples. This paper proposes a novel method, named transductive prototypical attention network (TPAN), to solve the few-shot target recognition problem in SAR ATR. The proposed method consists of three parts in total, i.e., region awareness-based feature extraction model, cross-feature spatial attention module and transductive prototype reasoning algorithm. Specifically, we build a region awareness-based feature extraction model, which can effectively focus on target regions of interest by embedding direction-aware and position-sensitive information. Next, a cross-feature spatial attention module is used to enhance the discriminativeness of identifying sample features. Finally, we propose a novel class inference algorithm, named transductive prototype reasoning algorithm, which iteratively updates class prototypes by mixing training samples with high-confidence test samples to achieve better class representation ability. Experimental results on moving and stationary target acquisition and recognition (MSTAR) dataset show that TPAN is effective and superior to some state-of-the-arts methods in few-shot SAR target recognition tasks.
{"title":"Transductive Prototypical Attention Network for Few-shot SAR Target Recognition","authors":"Xue-lian Yu, Sen Liu, H. Ren, L. Zou, Yun Zhou, Xue-gang Wang","doi":"10.1109/RadarConf2351548.2023.10149608","DOIUrl":"https://doi.org/10.1109/RadarConf2351548.2023.10149608","url":null,"abstract":"In recent years, synthetic aperture radar (SAR) automatic target recognition (ATR) methods driven by huge training samples have achieved remarkable results. However, in real SAR application scenarios, it is extremely difficult to provide enough training samples. This paper proposes a novel method, named transductive prototypical attention network (TPAN), to solve the few-shot target recognition problem in SAR ATR. The proposed method consists of three parts in total, i.e., region awareness-based feature extraction model, cross-feature spatial attention module and transductive prototype reasoning algorithm. Specifically, we build a region awareness-based feature extraction model, which can effectively focus on target regions of interest by embedding direction-aware and position-sensitive information. Next, a cross-feature spatial attention module is used to enhance the discriminativeness of identifying sample features. Finally, we propose a novel class inference algorithm, named transductive prototype reasoning algorithm, which iteratively updates class prototypes by mixing training samples with high-confidence test samples to achieve better class representation ability. Experimental results on moving and stationary target acquisition and recognition (MSTAR) dataset show that TPAN is effective and superior to some state-of-the-arts methods in few-shot SAR target recognition tasks.","PeriodicalId":168311,"journal":{"name":"2023 IEEE Radar Conference (RadarConf23)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133612814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/RadarConf2351548.2023.10149549
R. McKilliam, I. Clarkson, Troy A. Kilpatrick
This paper analyzes the centre-frequency estimator proposed by Lank, Reed, and Pollon [1]. This estimator is popular in practical applications due to its robustness and computational simplicity. The estimator's behaviour when applied to sinusoidal signals has previously been studied. The behaviour for non-sinusoidal signals is analysed here. Under general conditions the estimator is shown to be statistically consistent and asymptotically normally distributed as the number of samples of the signal grows. The asymptotic variance is shown to depend upon the spectrum of the underlying signal, and in particular its band-width. Sinusoidal signals are shown to minimise this variance and so represent the best-case behaviour. Under a bandwidth constraint, the worst-case behaviour is shown to occur when the underlying signal consists of two sinusoids separated by the bandwidth. This worst-case behaviour provides upper bounds on the error and corresponding confidence intervals when the underlying signal is unknown. The upper bounds are useful in applications such as electronic support where the specific form of received signals may not be known.
{"title":"Worst-case centre-frequency estimation","authors":"R. McKilliam, I. Clarkson, Troy A. Kilpatrick","doi":"10.1109/RadarConf2351548.2023.10149549","DOIUrl":"https://doi.org/10.1109/RadarConf2351548.2023.10149549","url":null,"abstract":"This paper analyzes the centre-frequency estimator proposed by Lank, Reed, and Pollon [1]. This estimator is popular in practical applications due to its robustness and computational simplicity. The estimator's behaviour when applied to sinusoidal signals has previously been studied. The behaviour for non-sinusoidal signals is analysed here. Under general conditions the estimator is shown to be statistically consistent and asymptotically normally distributed as the number of samples of the signal grows. The asymptotic variance is shown to depend upon the spectrum of the underlying signal, and in particular its band-width. Sinusoidal signals are shown to minimise this variance and so represent the best-case behaviour. Under a bandwidth constraint, the worst-case behaviour is shown to occur when the underlying signal consists of two sinusoids separated by the bandwidth. This worst-case behaviour provides upper bounds on the error and corresponding confidence intervals when the underlying signal is unknown. The upper bounds are useful in applications such as electronic support where the specific form of received signals may not be known.","PeriodicalId":168311,"journal":{"name":"2023 IEEE Radar Conference (RadarConf23)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133868651","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/RadarConf2351548.2023.10149756
David G. Felton, Christian C. Jones, D. B. Herr, Lumumba A. Harnett, S. Blunt, Chris Allen
The single pulse imaging (SPI) algorithm was developed as a means to generalize adaptive pulse compression (APC) by incorporating fast-time Doppler, thereby enhancing separability of scatterers in both range and Doppler. Here, we modify this model-based method by introducing dynamic beamspoiling to provide additional robustness. Open-air experimental results for this robust instantiation of SPI are then shown using an ultrasonic testbed at a center frequency of 47.5 kHz, which is analogous to an RF center frequency of 41.25 GHz. The low propagation velocity and associated wavelength of sound permits meaningful emulation of the high speeds that introduce fast-time Doppler effects for RF operation.
{"title":"Experimental Demonstration of Single Pulse Imaging (SPI)","authors":"David G. Felton, Christian C. Jones, D. B. Herr, Lumumba A. Harnett, S. Blunt, Chris Allen","doi":"10.1109/RadarConf2351548.2023.10149756","DOIUrl":"https://doi.org/10.1109/RadarConf2351548.2023.10149756","url":null,"abstract":"The single pulse imaging (SPI) algorithm was developed as a means to generalize adaptive pulse compression (APC) by incorporating fast-time Doppler, thereby enhancing separability of scatterers in both range and Doppler. Here, we modify this model-based method by introducing dynamic beamspoiling to provide additional robustness. Open-air experimental results for this robust instantiation of SPI are then shown using an ultrasonic testbed at a center frequency of 47.5 kHz, which is analogous to an RF center frequency of 41.25 GHz. The low propagation velocity and associated wavelength of sound permits meaningful emulation of the high speeds that introduce fast-time Doppler effects for RF operation.","PeriodicalId":168311,"journal":{"name":"2023 IEEE Radar Conference (RadarConf23)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134060467","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/RadarConf2351548.2023.10149701
Yuanhang Wu, Chenyu Zhang, Yiru Lin, Xiaoxi Ma, Wei Yi
Traditional clutter suppression and target detection methods have limitations in that they must satisfy specific statistical models. In this paper, we propose a unified deep learning model for complex-valued self-attention generative adversarial networks (CV-SAGAN) for clutter suppression and target detection. In the complex-valued framework, we first use a generator module to learn the clutter distribution and perform clutter suppression. Then, a self-attention module is used for the first time to perform corrective detection of sparse targets. Finally, a discriminator is used to judge between the real data and the network output results, improving the robustness of the model. We verified that the CV-SAGAN model has a better detection rate and robustness than the conventional cell-average constant false alarm rate (CA-CFAR), real-valued GAN, and real-valued SAGAN on three clutter distributions and achieved better detection results on the publicly available IPIX real-world dataset.
{"title":"CV-SAGAN: Complex-valued Self-attention GAN on Radar Clutter Suppression and Target Detection","authors":"Yuanhang Wu, Chenyu Zhang, Yiru Lin, Xiaoxi Ma, Wei Yi","doi":"10.1109/RadarConf2351548.2023.10149701","DOIUrl":"https://doi.org/10.1109/RadarConf2351548.2023.10149701","url":null,"abstract":"Traditional clutter suppression and target detection methods have limitations in that they must satisfy specific statistical models. In this paper, we propose a unified deep learning model for complex-valued self-attention generative adversarial networks (CV-SAGAN) for clutter suppression and target detection. In the complex-valued framework, we first use a generator module to learn the clutter distribution and perform clutter suppression. Then, a self-attention module is used for the first time to perform corrective detection of sparse targets. Finally, a discriminator is used to judge between the real data and the network output results, improving the robustness of the model. We verified that the CV-SAGAN model has a better detection rate and robustness than the conventional cell-average constant false alarm rate (CA-CFAR), real-valued GAN, and real-valued SAGAN on three clutter distributions and achieved better detection results on the publicly available IPIX real-world dataset.","PeriodicalId":168311,"journal":{"name":"2023 IEEE Radar Conference (RadarConf23)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134529502","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/RadarConf2351548.2023.10149555
Cengcang Zeng, Fangzhou Wang, Hongbin Li, M. Govoni
This paper considers target detection in distributed multi-input multi-output (MIMO) radar with non-orthogonal waveforms in non-homogenous clutter. We first present a general signal model for distributed MIMO radar in cluttered environments. To cope with the non-homogenous clutter and possible clutter bandwidth mismatch, the covariance matrix of the disturbance (clutter and noise) signal is modeled as a random matrix following an inverse complex Wishart distribution. Then, we propose three Bayesian detectors, including a non-coherent detector, a coherent detector, and a hybrid detector. The latter is a compromise of the former two, as it forsakes phase estimation needed by the coherent detector, but requires the samples within a coherent processing interval (CPI) to maintain phase coherence that is unnecessary for the non-coherent detector. Simulation results are presented to illustrate the performance of these Bayesian detectors and their non-Bayesian counterparts in non-homogeneous clutter when the clutter bandwidth is known exactly and, respectively, with uncertainty.
{"title":"Bayesian Detection for Distributed MIMO Radar with Non-Orthogonal Waveforms in Non-Homogeneous Clutter","authors":"Cengcang Zeng, Fangzhou Wang, Hongbin Li, M. Govoni","doi":"10.1109/RadarConf2351548.2023.10149555","DOIUrl":"https://doi.org/10.1109/RadarConf2351548.2023.10149555","url":null,"abstract":"This paper considers target detection in distributed multi-input multi-output (MIMO) radar with non-orthogonal waveforms in non-homogenous clutter. We first present a general signal model for distributed MIMO radar in cluttered environments. To cope with the non-homogenous clutter and possible clutter bandwidth mismatch, the covariance matrix of the disturbance (clutter and noise) signal is modeled as a random matrix following an inverse complex Wishart distribution. Then, we propose three Bayesian detectors, including a non-coherent detector, a coherent detector, and a hybrid detector. The latter is a compromise of the former two, as it forsakes phase estimation needed by the coherent detector, but requires the samples within a coherent processing interval (CPI) to maintain phase coherence that is unnecessary for the non-coherent detector. Simulation results are presented to illustrate the performance of these Bayesian detectors and their non-Bayesian counterparts in non-homogeneous clutter when the clutter bandwidth is known exactly and, respectively, with uncertainty.","PeriodicalId":168311,"journal":{"name":"2023 IEEE Radar Conference (RadarConf23)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133518577","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Multi-function radar (MFR) plays an important role in modern battlefield, and the cognitive jamming decision-makingmethod for MFR is the key technology to effectively interfere MFR, which is ofgreat research significance. In order to effectively interfere MFR, a cognitivejamming decision-making method based on threat assessment is proposed in thispaper. Firstly, the problem of jamming decision-making is modeled as a Markovdecision process with reward. Creatively, rewards will be given by atrack-based threat assessment model, by which the jamming strategies are ableto fit the real-time requirements of electronic countermeasures. Finally, the Q-Learningalgorithm is used to solve the problem and derive the optimal jamming strategy.Experiment results show that the proposed jamming strategy is more effective inreducing the threat of MFR to the target. Compared with the present methods,the proposed approach has advantages in real-time performance and effectivenessof jamming decision-making, and has more practical value.
{"title":"A Cognitive Jamming Decision-making Method for Multi-functional Radar Based on Threat Assessment","authors":"Gengchen Xu, Yujie Zhang, Weibo Huo, Jifang Pei, Yin Zhang, Haiguang Yang","doi":"10.1109/RadarConf2351548.2023.10149674","DOIUrl":"https://doi.org/10.1109/RadarConf2351548.2023.10149674","url":null,"abstract":"Multi-function radar (MFR) plays an important role in modern battlefield, and the cognitive jamming decision-makingmethod for MFR is the key technology to effectively interfere MFR, which is ofgreat research significance. In order to effectively interfere MFR, a cognitivejamming decision-making method based on threat assessment is proposed in thispaper. Firstly, the problem of jamming decision-making is modeled as a Markovdecision process with reward. Creatively, rewards will be given by atrack-based threat assessment model, by which the jamming strategies are ableto fit the real-time requirements of electronic countermeasures. Finally, the Q-Learningalgorithm is used to solve the problem and derive the optimal jamming strategy.Experiment results show that the proposed jamming strategy is more effective inreducing the threat of MFR to the target. Compared with the present methods,the proposed approach has advantages in real-time performance and effectivenessof jamming decision-making, and has more practical value.","PeriodicalId":168311,"journal":{"name":"2023 IEEE Radar Conference (RadarConf23)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133139476","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/RadarConf2351548.2023.10149646
J. Akhtar
Matched filtering plays an important role in radar systems as the established pulse compression technique. This article puts forwards an alternative machine learning based technique for the matched filtering process assuming the incoming signal is oversampled. The aim is to replace the convolutional operation with a small fully connected feedforwarding neural network and attain an additional increase in the range resolution. The paper demonstrates how such a neural network design can be constructed and a practical training approach is presented. The results are compared against traditional matched filtering and target detection methods showing a clear advantage of trained neural networks for the pulse compression procedure and as a mean to construct inventive mismatched filters.
{"title":"Neural Network LFM Pulse Compression","authors":"J. Akhtar","doi":"10.1109/RadarConf2351548.2023.10149646","DOIUrl":"https://doi.org/10.1109/RadarConf2351548.2023.10149646","url":null,"abstract":"Matched filtering plays an important role in radar systems as the established pulse compression technique. This article puts forwards an alternative machine learning based technique for the matched filtering process assuming the incoming signal is oversampled. The aim is to replace the convolutional operation with a small fully connected feedforwarding neural network and attain an additional increase in the range resolution. The paper demonstrates how such a neural network design can be constructed and a practical training approach is presented. The results are compared against traditional matched filtering and target detection methods showing a clear advantage of trained neural networks for the pulse compression procedure and as a mean to construct inventive mismatched filters.","PeriodicalId":168311,"journal":{"name":"2023 IEEE Radar Conference (RadarConf23)","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116550057","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/RadarConf2351548.2023.10149668
Ahmad Alkasimi, Anh-Vu Pham, Christopher S. Gardner, B. Funsten
We demonstrate the improvement of theradar-based human activity recognition using the combination of four datadomains: time-frequency, time-range, range-Doppler and, for the first time,time-angle domain. Six different activities are observed from nine subjectsusing frequency-modulated continuous-wave millimeter-wave radar. Each domainoffers additional information to the classification process. The classificationresults of four deep convolutional neural networks are then combined using theJoint Probability Mass Function method to achieve a combined classificationaccuracy of 100%. The proposed system also demonstrates similar performance inrecognizing activities from participants not involved in training the network.To the best of our knowledge, this is the first work that demonstrates theutilization of four data domains to address the radar-based human activityrecognition problem.
{"title":"Human Activity Recognition Based on 4-Domain Radar Deep Transfer Learning","authors":"Ahmad Alkasimi, Anh-Vu Pham, Christopher S. Gardner, B. Funsten","doi":"10.1109/RadarConf2351548.2023.10149668","DOIUrl":"https://doi.org/10.1109/RadarConf2351548.2023.10149668","url":null,"abstract":"We demonstrate the improvement of theradar-based human activity recognition using the combination of four datadomains: time-frequency, time-range, range-Doppler and, for the first time,time-angle domain. Six different activities are observed from nine subjectsusing frequency-modulated continuous-wave millimeter-wave radar. Each domainoffers additional information to the classification process. The classificationresults of four deep convolutional neural networks are then combined using theJoint Probability Mass Function method to achieve a combined classificationaccuracy of 100%. The proposed system also demonstrates similar performance inrecognizing activities from participants not involved in training the network.To the best of our knowledge, this is the first work that demonstrates theutilization of four data domains to address the radar-based human activityrecognition problem.","PeriodicalId":168311,"journal":{"name":"2023 IEEE Radar Conference (RadarConf23)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125696442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：