查詢結果分析
來源資料
相關文獻
- Radar Target Detection Using Neural Fuzzy Network
- 快速傅立葉轉換在雷達信號處理之應用
- 配對搜尋摺積運算於磁振影像左心室目標之自動搜尋
- 極值分配中母數的加權最小平方估計
- 以多變量的預測模式輔助選取最適之臺指選擇權投資策略
- 臺電系統負載特性調查分析研究第三期計畫
- 以修正之非線性加權最小平方法估計三參數之極值分配
- 臺指選擇權最適單一部位交易策略之選取
- Analysis of an Automatic Sinusoidal Detector with FFT and Cell-Averaging Processor
- Dynamic Estimation of the Number of Goals Scored by a Team in a Football Match
頁籤選單縮合
題 名 | Radar Target Detection Using Neural Fuzzy Network=類神經模糊網路應用於雷達目標之偵測 |
---|---|
作 者 | 杜峯賓; | 書刊名 | 新新科技年刊 |
卷 期 | 11 2015.01[民104.01] |
頁 次 | 頁177-193 |
分類號 | 448.81 |
關鍵詞 | 固定偽警率; 單元平均; 類神經模糊網路; 次序統計; 雷達信號處理; 目標偵測; Constant false-alarm rate; Cell averaging; Neural fuzzy network; Order statistics; Radar signal processing; Target detection; |
語 文 | 英文(English) |
中文摘要 | 目標偵測為雷達系統之基本功能,其程序為將所接收之信號振幅與臨界值相比較。為求固定偽警率所採用之適應臨界值須隨鄰近區中之雜波作調適。許多固定偽警率應用技術已在雷達文獻提出,用於處理雷達應用之不同場景,包括具穩定的、非穩定雜波及多目標。然而,傳統固定偽警率技術,如單元平均、選大、選小及次序統計,對各種情形之處理皆未能獲得好結果。本文提出一種類神經模糊網路目標偵測,稱為類神經模糊網路-固定偽警率,其為六層自我組織類神經模糊網路所建構之智慧型技術,具適應性之類神經-模糊推論系統,能提供有效的固定偽警率偵測。由模擬結果顯示類神經模糊網路-固定偽警率技術,於不同目標場景及高度雜波環境中,較傳統技術有較佳之性能。 |
英文摘要 | Target detection is a primary function in radar systems. Radar detection procedures involve the comparison of the received signal amplitude to a threshold value. In order to obtain a constant false-alarm rate (CFAR), an adaptive threshold must be applied reflecting the local clutter situation. Several algorithms of the CFAR have been proposed in the radar literature to deal with different scenarios in radar applications, including uniform (stationary), nonuniform (clutter edges) clutter and multiple targets within the CFAR processing. However, the conventional CFAR algorithms, such as CA-, GO-, SO-, and OS- CFARs, do not produce good results for all situations. This paper proposes a neural fuzzy network for target detection, called NFN-CFAR, which is an intelligent algorithm and carried out by a six-layer self-constructing neural fuzzy inference network (SONFIN) to provide an effective approach based on adaptive neuro-fuzzy inference system to the solution of CFAR detection. Simulation results show that this NFN-CFAR algorithm has significant advantages of performance in different target situations and in highly complex clutter environments, which is superior to the conventional algorithms. |
本系統中英文摘要資訊取自各篇刊載內容。