查詢結果分析
來源資料
相關文獻
- 基於經驗模態分解法之遞迴式赫米特類神經網路預測模型--以短時交通流量預測為例
- 經驗模態分解法於信號分解之研究
- 專科生英語成就的累積機率邏輯模型之建立
- 臺灣股票市場水泥產業上市公司益本比預測模型研究
- 國內新上市股、跌破承銷價預測模型與各式期間報酬率
- 預測方法之比較--以臺灣電力負載預測為例
- 長期發電燃料價格預測模式與方法分析
- The Information Loss of the Binary Logit in the Study of Financial Statements: A Comparison of Three Probability Models
- 統計方法在總統選舉預測的應用
- GM(1,1)模型誤差分析之研究
頁籤選單縮合
題名 | 基於經驗模態分解法之遞迴式赫米特類神經網路預測模型--以短時交通流量預測為例=An EMD based Recurrent Hermite Neural Network Prediction Model--A Case Study of Short Term Traffic Flow Prediction |
---|---|
作者 | 陳瑄易; Chen, Syuan-yi; |
期刊 | 電腦與通訊 |
出版日期 | 20111200 |
卷期 | 142 2011.12[民100.12] |
頁次 | 頁98-105 |
分類號 | 448.6 |
語文 | chi |
關鍵詞 | 預測模型; 遞迴式赫米特類神經網路; 經驗模態分解法; 內建模態函數; 短時交通流量預測; Prediction model; Recurrent hermite neural network; RHNN; Empirical mode decomposition; EMD; Intrinsic mode function; IMF; Short-term traffic flow prediction; |
中文摘要 | 近年來,預測模型(Prediction Model)被廣泛且成功地應用在各種領域之中,藉由建立與使用系統之預測模型,可預先掌握系統之未來趨勢。而隨著建模對象越趨複雜,傳統以類神經網路(NeuralNetwork;NN)建立之預測模型其預測準確度已無法令人滿意。有鑑於此,本研究提出一新的基於經驗模態分解法之遞迴式赫米特類神經網路(Empirical Mode Decomposition based Recurrent Hermite Neural Network;ERHNN)預測模型,該模型整合了Hermite多項式之非線性訊號近似、EMD之非線性訊號分析與過濾、RNN之非線性系統建模與學習能力,對於非線性與非穩態訊號有優異之建模與預測效果。本研究以美國加州高速高路I-80W所記錄之短時交通流量進行預測驗證,最後經模擬證實,相較於NN預測模型,本研究所提出之ERHNN預測模型確實具有更佳之預測準確度。 |
英文摘要 | In recent years, prediction model has been widely and successfully applied in various kinds of fields. According to the development and employment of prediction models, the trends of the system can be predicted in advance. However, the performance of the pure neural network (NN) based prediction model is not favorable in terms of the complication of modeling system. For this reason, an empirical mode decomposition based recurrent Hermite neural network (ERHNN) prediction model is proposed in this study which comprises good analysis ability for the non-linear and non-stationary signals through the combination of the merits of Hermit polynomial, empirical mode decomposition and recurrent Hermite neural network. The validity of the ERHNN prediction model is verified using all day short-term traffic flow data on route I-80W in California. Simulation results show that the proposed ERHMM prediction model is with superior performance compared with the pure NN one. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。