查詢結果分析
來源資料
相關文獻
- 類神經網路訊號追蹤之研究
- 灰模糊控制的訊號追蹤器設計
- Neural Network Procedures for Taguchi's Dynamic Problems
- A Fast and Efficient Competitive Learning Design Algorithm Based on Weight Vector Training in Transform Domain
- 專家系統振動訊號圖型判別之研究
- 反傳遞模糊類神經網路於流量推估之應用
- 類神經網路(Neural Networks)的種類及其在影像處理上的應用
- C++Fuzzy類神經網路物件導向發展系統之建立
- 臺灣汽保費率之估計--對數線性費率模式與類神經網路之比較
- 運用類神經網路於股價指數之套利--以日經225指數為例
頁籤選單縮合
題 名 | 類神經網路訊號追蹤之研究 |
---|---|
作 者 | 胡永柟; 周寶華; 黃信富; 李明諒; 陳茂林; 卓峰斌; | 書刊名 | 南開學報 |
卷 期 | 7(上) 民91.06 |
頁 次 | 頁495-506 |
分類號 | 448.6 |
關鍵詞 | 訊號追蹤; 壓電元件; 類神經網路; Signal trace; Piezoelectric element; Neural networking; |
語 文 | 中文(Chinese) |
中文摘要 | 本研究之主要目的,在於將類神經網路訊號追蹤之理論與實務相結合。訊號源的辨識在數位訊號處理中,是一項重要的研究領域,必須就特徵參數、識別系統兩大方向進行。 本研究包括兩大部分,一是利用壓電元件,製成一組接收四個方位的吸音感測器,對訊號來源的方位作吸音取樣分析及數位訊號處理,來取得特徵參數,利用類神經網路訓練,而取得辨識系統輸入之樣本特徵參數;二是應用倒傳遞類神經網路辨識系統架構的建立。研究過程並進一步對此二部分進行整合以完成訊號來源的辨識,判別訊號源接收方向。 |
英文摘要 | This article study and research to stress theory and fact design control integrate. Signal sources recognition is a very important study area in digital signal processes, there exist two important issues that are characteristic of parameters of the signal and how to recognize it exactly. So, how to get the parameters of the signal and to recognize the signal exactly and accurately is the main purpose of this research. First, We use the piezoelectric elements to construct a sound sensor to get different direction signal of the sound, then, by digital signal processing analysis and neural training to get the characteristic of parameters patent. Secondly, we use back-propagation neural network to construct the recognition system. Finally we combine the first part and the second part in order to construct a source of signal recognition system. After this design, we expect that we can recognize all kinds of signal from different direction very accurately. |
本系統中英文摘要資訊取自各篇刊載內容。