Enriched Traffic Datasets for Madrid

-Description of the Research and Data: This work includes two datasets of traffic in Madrid, "DADAS" and "MLDAS", collected between June 2022 and February 2024. These datasets combine traffic sensor data, weather data, calendar data, road infrastructure data and localization data to facilitate detailed analysis of urban mobility and prediction of traffic patterns. -DADAS (Descriptive Analysis DAtaSet): "DADAS" is a dataset oriented towards descriptive analysis, capturing traffic intensity in 15-minute intervals from urban sensors and roads. Data processing includes meticulous cleaning and filtering to remove inconsistencies and outliers. Additionally, the k-means algorithm is used to group data from multiple sensors. -MLDAS (ML-oriented DAtaSet): "MLDAS" is designed for predictive analysis and modeling of traffic patterns. Derived from the "DADAS" dataset, this dataset has been processed to include temporal transformations and encoding of categorical and ordinal features, specifically preparing it for advanced machine learning applications. -Data usage: These datasets are crucial for infrastructure planning and sustainable traffic policies, providing valuable resources for researchers and urban planners interested in mobility studies and their environmental impact. For more details, see [Submitted to Data in Brief].

-研究与数据说明：本研究涵盖两套2022年6月至2024年2月期间采集的马德里市交通数据集，分别为"DADAS"与"MLDAS"。两类数据集整合了交通传感器数据、气象数据、日历数据、道路基础设施数据与定位数据，可支撑城市出行详细分析与交通流模式预测任务。
-DADAS（描述性分析数据集，Descriptive Analysis DAtaSet）：该数据集面向描述性分析场景，以15分钟为间隔采集城市传感器与道路的交通强度数据。数据处理环节包含精细化清洗与过滤操作，以剔除不一致性数据与异常值；此外，还采用k-means算法对多传感器采集的数据进行聚类分组。
-MLDAS（面向机器学习的数据集，ML-oriented DAtaSet）：该数据集专为交通流模式的预测分析与建模而设计，其衍生自"DADAS"数据集，经过时序转换、分类特征与有序特征编码等预处理流程，专门适配先进机器学习应用场景。
-数据用途：上述数据集对于基础设施规划与可持续交通政策制定至关重要，可为关注出行研究及其环境影响的科研人员与城市规划者提供宝贵的研究资源。更多详情请参阅[Submitted to Data in Brief]。

搜集汇总

背景与挑战

背景概述

该数据集包含两个子数据集：DADAS（描述性分析数据集）和MLDAS（机器学习导向数据集），覆盖2022年6月至2024年2月马德里的交通数据。数据集整合了交通传感器、天气、日历、道路基础设施和定位数据，支持城市交通的描述性分析和机器学习预测，适用于交通模式研究、基础设施规划和可持续政策制定。