一個以行動網路訊號分析為基礎之交通速度估計機制

Abstract

近年來隨著經濟的快速發展，傳統的交通系統面臨了許多嚴峻的挑戰。為了解決日益嚴重的交通問題，許多國家寄望能夠透過資訊與通訊科技的協助，讓交通資源能夠更有效的運用。這正是智慧型運輸系統(Intelligent Transportation System, ITS) 發展的目的。然而ITS成功的關鍵在於獲得正確且即時的交通資訊，以利後續的決策分析與運用。近年來，利用追蹤手機位置來蒐集交通資訊的機制越來越受到注意，這個機制不需要花費龐大的金額來架設及維護額外的偵測裝置，由於幾乎每個人都有手機，因此以追蹤手機位置所得到的交通資訊是非常全面的。本研究提出一個以行動網路訊號分析為基礎之交通速度估計機制，透過分析通訊中手機所回傳的訊號測量報告，以指紋辨識定位演算法(Fingerprint Positioning Algorithm, FPA)來進行手機的匿名定位與測速。在實驗中以快速道路66號路段進行實際路測，其指紋辨識定位演算法位置估計的平均誤差可達36.11公尺，車速評估的平均誤差可達3.39%，提供較第三代合作夥伴計劃(3rd Generation Partnership Project, 3GPP)於標準中所定義之Cell ID定位方法更為準確的位置和車速估計。此外，本研究採用MapReduce架構進行平行處理，可有效改善指紋辨識定位演算法需要大量運算的限制，以提供即時且可靠的交通資訊，予以用路人參考。

In recent years, fast economic growth and rapid technology advance have led to significant impact of the quality of traditional transport system. Intelligent Transportation System (ITS), which aims to improve the transport system, has therefore become more and more popular. In order for an ITS to be viable, it is essential to establish and promote effective real-time traffic information systems. Compared to other traditional traffic information collecting methods, the traffic information estimations from cellular network data are more immediately, cost-effective, and easy to deploy and maintain. In this paper, we propose a novel speed estimation method based on the signals of cellular network. We analyze the measurement reports sent by active phone in the cellular networks and adopt the k-nearest-neighbors based fingerprint positioning algorithm (kNN-based FPA) to obtain the location and speed information of cell phones. In the experiments, we compare the estimated positioning information and speed information with the real information obtained from Global Position System (GPS) receiver. The results show that the average error of location determination by using FPA is 36.11 meters. For speed estimation, the average error ratio by using FPA is 3.39%. Finally, we adopt the MapReduce algorithm and a modified columnar data model to accelerate the processing of FPA. The result shows this approach will be feasible to estimate the overall speed information for ITS improvement.