國道五號的擁塞現象一直是交通管理單位關心的課題，藉由大數據分析進行模式辨識，並整合天氣資訊、網路輿論等資料庫建構交通流量預警機制是近年來最受矚目的應用趨勢，可惜目前有關大數據分析在交通管理的應用多半忽略用路人的選擇與決策行為。由於部分用路人交通旅次的出發時間是具有彈性且可以視情況需要進行調整，因此若能讓第三方移動應用軟體 (Application; APP)整合國道五號交通資訊並提供介面讓用路人根據交通狀況事先調整出發時間，將有助於改善國道五號交通每逢假日必定壅塞的現象。本計劃首先以電腦程式撰寫模擬產生APP所需要的交通流量，其次撰寫APP提供用路人根據交通資訊來規劃(或預約)旅行出發時間，最後則是建構劇變模型來分析用路人使用APP來進行旅行出發時間的決策行為。本計畫之研究結果將有助於交通主管機關研擬相關交通控制策略的參考依據。
The research aiming to alleviate traf?c jams of freeway No. 5. Growing attention is being paid to the use of big data techniques for gathering and analyzing data. Bid data and data mining are the critical method for traf?c management to build strategies/policies to reduce the traffic jams. The purpose of this research is to analyze one possible force which makes a significant contribution to explaining the decision behavior of travelers to re-arrange their departure time. Departing from the traditional utility maximization theory, this model focuses on the decisionmaking process based on imperfect information, bounded and distinctive rationalities. In the modeling framework, we developed an agent-based model for travelers’ choices of mode and departure time. Second, we use the butterfly catastrophe model and cusp catastrophe model to analysis the choice behavior of travelers for use the APP to decide whether or not to switch to the new departure time. The findings of this research could strengthen the contribution of professionals to traffic management goals.
