Abstract The rapid advancements in sensor technologies has resulted in the increased use of Automatic Vehicle Location (AVL) systems for traffic data collection. Global Position System (GPS) sensors are the most commonly used AVL system, majorly because of it being a time-tested technology and being relatively cheap. Also, many of the transportation agencies have their vehicles equipped with GPS sensors. One of the interesting challenges in the field of Intelligent Transportation Systems (ITS) is to effectively mine useful information from such large-scale database accumulated over time. The current study analyses travel time data obtained from buses fitted with GPS devices in Chennai, India to understand its variation over time and space to find the spatial and temporal points of criticality. For this, Cumulative Frequency Distribution (CFD) curves, bar charts and boxplots were used. Inter-Quartile Range (IQR) was used as a measure to quantify the variations in travel time. Analysis showed that both travel time and its variation increased approximately 10% and 40%, respectively, from 2014 to 2016. This increase was observed to be primarily concentrated in six critical intersections during morning and evening peak hours. The findings from the study were further used in demonstrating possible user applications that can improve the efficiency of public transportation systems. As part of this, a real-time bus travel time prediction method was developed using a deep learning approach, Long and Short-Term Memory (LSTM) networks. Along with this, a robust fleet management system was also developed to check the adequacy of buses along the study corridor for different time of the day.

中文翻译：

---

基于全球定位系统的公交出行时间数据分析及其在先进公共交通系统应用中的应用

摘要 传感器技术的快速进步导致车辆自动定位 (AVL) 系统越来越多地用于交通数据收集。全球定位系统 (GPS) 传感器是最常用的 AVL 系统，主要是因为它是一种经过时间考验的技术并且相对便宜。此外，许多运输机构的车辆都配备了 GPS 传感器。智能交通系统 (ITS) 领域的有趣挑战之一是从长期积累的大规模数据库中有效挖掘有用信息。当前的研究分析了从印度钦奈装有 GPS 设备的公共汽车上获得的旅行时间数据，以了解其随时间和空间的变化，从而找到空间和时间的临界点。为了这，使用了累积频率分布 (CFD) 曲线、条形图和箱线图。四分位距 (IQR) 被用作量化旅行时间变化的度量。分析表明，从 2014 年到 2016 年，出行时间及其变化分别增加了约 10% 和 40%。据观察，这种增加主要集中在早晚高峰时段的六个关键路口。该研究的结果进一步用于展示可以提高公共交通系统效率的可能的用户应用程序。作为其中的一部分，使用深度学习方法、长短期记忆 (LSTM) 网络开发了一种实时公交车行程时间预测方法。与此同时，