Data assimilation with Long Short-Term Memory Networks based on Attention for Highway Traffic Flow Prediction

NCU Institutional Repository > 理學院 > 數學研究所 > 博碩士論文 > Item 987654321/81528

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://ir.lib.ncu.edu.tw/handle/987654321/81528

题名:	Data assimilation with Long Short-Term Memory Networks based on Attention for Highway Traffic Flow Prediction
作者:	張家銘;Chang, Chia-Ming
贡献者:	數學系
关键词:	交通流;機器學習;卡爾曼濾波;Traffic flow;LSTM;Kalman Filter
日期:	2019-08-21
上传时间:	2019-09-03 16:00:24 (UTC+8)
出版者:	國立中央大學
摘要:	交通流量預測是交通工程中一個活躍的研究課題。大致上，交通流量預測模型可以分為三種，第一種是有母數方法，第二種是無母數方法，最後一種是基於PDE的模擬。另外還有有母數方法和無母數方法的混合方法。在這項工作中，我們建議將數據驅動的仿真技術與機器學習工具相結合，以減少預測誤差，並使用卡爾曼濾波器（KF）實現數據同化。 KF包括兩個步驟：預測和校正。在預測步驟中，我們使用EX方法來離散LWR模型，其中MacNicholas模型作為速度和密度之間的基本關係。由於預測未來需要邊界點，因此我們使用具有注意力機制的LSTM獲得的預測值來設置邊界條件，在更新步驟中，我們使用具有注意力機制的LSTM獲得的預測值來當作觀測值，它用來跟我們的預測值進行權重並得到更新後的預測值。在本研究中，我們使用SARIMA和具有注意力機制的LSTM作為基線方法。自回歸整合移動平均線（ARIMA）是用於單變量時間序列數據預測的最廣泛使用的預測方法之一。SARIMA是ARIMA的延伸，有季節性的成分。長短期記憶網絡(LSTM NN)是一種可以學習長期依賴關係的特殊RNN。此外，加入注意機制可以幫助我們更好的預測未來。我們將它們與我們提出的方法比較，實驗結果表明，該方法優於SARIMA和具有注意機制的LSTM。;Traffic flow prediction an active research topic in transportation engineering. In general, the traffic flow prediction model can be divided into three categories, one is PDE-based simulation, another one is parametric approaches, and the other is non-parametric approaches. There are further hybrid approaches to parametric approaches and non-parametric approaches. In this work, we propose combining the data-driven simulation technique with machine learning tools to decrease prediction error, and use the Kalman Filter (KF) on this basis to achieve the effect of data assimilation. The KF consists of two steps: prediction and correction. In the prediction step, we use the EX method to discretize the LWR model where the MacNicholas model is used as the fundamental relation between the velocity and density. Since the data at the boundary points in the future period are not available. The predicted values obtained by using LSTM with the attention mechanism are used for setting the boundary condition. In the correction step, we use the predicted value obtained by the LSTM with attention mechanism as the observation value, which is used to weight our predicted value and get the correction predicted value. In this study, we use SARIMA and the LSTM Attention as the baseline methods. Autoregressive Integrated Moving Average (ARIMA) is one of the most widely used methods of prediction for university time series data prediction. SARIMA is an extension of ARIMA with seasonal components. Long Short Term Memory networks (LSTMs) is a special kind of RNN that can learn long-term dependencies better than RNN. In addition, adding attention mechanisms can help us better predict the future. We compare them with our proposed method. The experimental results demonstrate that our method outperforms SARIMA and LSTM Attention.
显示于类别:	[數學研究所] 博碩士論文

文件中的档案:

档案	描述	大小	格式	浏览次数
index.html		0Kb	HTML	264	检视/开启

在NCUIR中所有的数据项都受到原著作权保护.

社群 sharing

数据加载中.....