Abstract:
This study introduces an innovative algorithm for classifying transportation modes. It categorizes modes such as walking, biking, tram, bus, taxi, and private vehicles based on data collected through sensors embedded in smartphones. The data include date, time, latitude, longitude, altitude, and speed, gathered using a mobile application specifically designed for this project. These data were collected through the smartphone\'s GPS to enhance the accuracy of the analysis. The stopping times of each transport mode, as well as the distance traveled and average speed, are analyzed to identify patterns and distinctive features. Conducted in Cuenca, Ecuador, the study aims to develop and validate an algorithm to enhance urban planning. It extracts significant features from mobility patterns, including speed, acceleration, and over-acceleration, and applies longitudinal dynamics to train the classification model. The classification algorithm relies on a decision tree model, achieving a high accuracy of 94.6% in validation and 94.9% in testing, demonstrating the effectiveness of the proposed approach. Additionally, the precision metric of 0.8938 signifies the model\'s ability to make correct positive predictions, with nearly 90% of positive instances correctly identified. Furthermore, the recall metric at 0.83084 highlights the model\'s capability to identify real positive instances within the dataset, capturing over 80% of positive instances. The calculated F1-score of 0.86117 indicates a harmonious balance between precision and recall, showcasing the models robust and well-rounded performance in classifying transport modes effectively. The study discusses the potential applications of this method in urban planning, transport management, public transport route optimization, and urban traffic monitoring. This research represents a preliminary stage in generating an origin-destination (OD) matrix to better understand how people move within the city.
摘要:
本研究引入了一种创新的运输方式分类算法。它对步行等模式进行分类,骑自行车,电车,公共汽车,出租车,和私人车辆基于通过嵌入在智能手机中的传感器收集的数据。数据包括日期,时间,纬度,经度,高度,和速度,使用专门为此项目设计的移动应用程序收集。这些数据是通过智能手机的GPS收集的,以提高分析的准确性。每种运输方式的停止时间,以及行驶的距离和平均速度,进行分析,以识别模式和独特的特征。在昆卡进行,厄瓜多尔,该研究旨在开发和验证一种增强城市规划的算法。它从移动模式中提取重要特征,包括速度,加速度,和过度加速,并应用纵向动力学来训练分类模型。分类算法依赖于决策树模型,在验证和测试中达到94.6%的高精度,证明了所提出方法的有效性。此外,精度指标0.8938表示模型做出正确正预测的能力,近90%的阳性病例被正确识别。此外,0.83084的召回指标突出了模型识别数据集中真正积极实例的能力,捕获超过80%的积极实例。计算出的F1分数为0.86117,表明准确率和召回率之间达到了和谐的平衡,展示了模型在有效分类运输方式方面的稳健和全面的性能。该研究讨论了该方法在城市规划中的潜在应用,运输管理,公共交通路线优化,和城市交通监控。这项研究代表了生成起点-目的地(OD)矩阵的初步阶段,以更好地了解人们如何在城市中移动。