The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Bunyi kilauan tidak pegun sering diperhatikan dalam sistem pengesanan radar. Taburan hingar glint bukan Gaussian dan heavy-tailed. Algoritma pengenalan rekursif konvensional menggunakan kaedah penghampiran stokastik (SA). Walau bagaimanapun, kaedah SA menumpu secara perlahan dan tidak sah untuk hingar tidak pegun. Makalah ini mencadangkan algoritma penyesuaian, yang menggunakan kaedah keturunan kecerunan stokastik (SGD), untuk mengatasi masalah ini. Kaedah SGD mengekalkan struktur ringkas kaedah SA dan sesuai untuk pelaksanaan dunia sebenar. Tingkah laku penumpuan kaedah SGD dianalisis dan ungkapan bentuk tertutup untuk had saiz langkah yang mencukupi diperoleh. Memandangkan data hingar biasanya tidak tersedia dalam amalan, kami kemudian mencadangkan skim pengekstrakan hingar. Menggabungkan kaedah SGD, kami boleh melakukan pengenalpastian hingar adaptif dalam talian terus daripada pengukuran radar. Keputusan simulasi menunjukkan bahawa prestasi kaedah SGD adalah setanding dengan kaedah kemungkinan maksimum (ML). Selain itu, skim pengekstrakan hingar berkesan kerana hasil pengenalpastian daripada ukuran radar adalah hampir dengan hasil daripada data hingar kilat tulen.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Wen-Rong WU, Kuo-Guan WU, "Adaptive Identification of Non-Gaussian/Non-stationary Glint Noise" in IEICE TRANSACTIONS on Fundamentals,
vol. E82-A, no. 12, pp. 2783-2792, December 1999, doi: .
Abstract: Non-stationary glint noise is often observed in a radar tracking system. The distribution of glint noise is non-Gaussian and heavy-tailed. Conventional recursive identification algorithms use the stochastic approximation (SA) method. However, the SA method converges slowly and is invalid for non-stationary noise. This paper proposes an adaptive algorithm, which uses the stochastic gradient descent (SGD) method, to overcome these problems. The SGD method retains the simple structure of the SA method and is suitable for real-world implementation. Convergence behavior of the SGD method is analyzed and closed-form expressions for sufficient step size bounds are derived. Since noise data are usually not available in practice, we then propose a noise extraction scheme. Combining the SGD method, we can perform on-line adaptive noise identification directly from radar measurements. Simulation results show that the performance of the SGD method is comparable to that of the maximum-likelihood (ML) method. Also, the noise extraction scheme is effective that the identification results from the radar measurements are close to those from pure glint noise data.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e82-a_12_2783/_p
Salinan
@ARTICLE{e82-a_12_2783,
author={Wen-Rong WU, Kuo-Guan WU, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Adaptive Identification of Non-Gaussian/Non-stationary Glint Noise},
year={1999},
volume={E82-A},
number={12},
pages={2783-2792},
abstract={Non-stationary glint noise is often observed in a radar tracking system. The distribution of glint noise is non-Gaussian and heavy-tailed. Conventional recursive identification algorithms use the stochastic approximation (SA) method. However, the SA method converges slowly and is invalid for non-stationary noise. This paper proposes an adaptive algorithm, which uses the stochastic gradient descent (SGD) method, to overcome these problems. The SGD method retains the simple structure of the SA method and is suitable for real-world implementation. Convergence behavior of the SGD method is analyzed and closed-form expressions for sufficient step size bounds are derived. Since noise data are usually not available in practice, we then propose a noise extraction scheme. Combining the SGD method, we can perform on-line adaptive noise identification directly from radar measurements. Simulation results show that the performance of the SGD method is comparable to that of the maximum-likelihood (ML) method. Also, the noise extraction scheme is effective that the identification results from the radar measurements are close to those from pure glint noise data.},
keywords={},
doi={},
ISSN={},
month={December},}
Salinan
TY - JOUR
TI - Adaptive Identification of Non-Gaussian/Non-stationary Glint Noise
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2783
EP - 2792
AU - Wen-Rong WU
AU - Kuo-Guan WU
PY - 1999
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E82-A
IS - 12
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - December 1999
AB - Non-stationary glint noise is often observed in a radar tracking system. The distribution of glint noise is non-Gaussian and heavy-tailed. Conventional recursive identification algorithms use the stochastic approximation (SA) method. However, the SA method converges slowly and is invalid for non-stationary noise. This paper proposes an adaptive algorithm, which uses the stochastic gradient descent (SGD) method, to overcome these problems. The SGD method retains the simple structure of the SA method and is suitable for real-world implementation. Convergence behavior of the SGD method is analyzed and closed-form expressions for sufficient step size bounds are derived. Since noise data are usually not available in practice, we then propose a noise extraction scheme. Combining the SGD method, we can perform on-line adaptive noise identification directly from radar measurements. Simulation results show that the performance of the SGD method is comparable to that of the maximum-likelihood (ML) method. Also, the noise extraction scheme is effective that the identification results from the radar measurements are close to those from pure glint noise data.
ER -