The Neurocomputing Approximation for Waiting Time between Cross-System Services

以類神經演算法推估跨系統服務之使用者等候時間

許春霖(Spring C. Hsu)

《中華技術學院學報》 36期 (2007/06) Pp. 85-98

https://doi.org/10.7095/JCIT.200706.0085

摘要

本研究以類神經網路方法進行城際大眾運輸之跨系統服務使用者等候時間估算。在此之前，已有相關的研究對於此一城際大眾運輸跨系統使用者之等候時間進行精確的數學模式建構，然而這些模式化的方法計算過程耗時且繁瑣，使用上極為不便。有鑑於此缺點，本研究依據先前相關研究所建立之數學模式加以改進，以使用上較為方便快速之類神經網路進行學習訓練，而獲致十分接近於原模式所精算之答案。本研究結果不論對於後續更深入的理論分析或實務運輸管理人員進行服務績效之衡量應用均具有相當之助益。

關鍵字

類神經網路 ； 等候時間 ； 可靠度 ； 跨系統服務

並列摘要

This paper aims to develop a neural network model for analyzing the users waiting time of an intercity transit station with feeder bus services. The behaviors of users for intercity transit systems are significantly different from those of urban bus systems. If the urban bus system is always considered as a major feeder mode of the intercity transit, users waiting time and relevant behaviors for the intercity transit system should be influenced by the reliabilities of the feeder bus services. A precise mathematical model of the users waiting time for an intercity transit system has been developed by earlier studies, however, it is somehow difficult to employ. Therefore, a user-friendly neural network model which is trained according to the original mathematical model is proposed in this paper.

並列關鍵字

neural network ； waiting time ； reliability ； cross-system services