The NetMob25 Dataset: A High-resolution Multi-layered View of Individual Mobility in Greater Paris Region
High-quality mobility data remains scarce despite growing interest from researchers and urban stakeholders in understanding individual-level movement patterns. The Netmob25 Data Challenge addresses this gap by releasing a unique GPS-based mobility dataset derived from the EMG 2023 GNSS-based mobility survey conducted in the Ile-de-France region (Greater Paris area), France. This dataset captures detailed daily mobility over a full week for 3,337 volunteer residents aged 16 to 80, collected between October 2022 and May 2023. Each participant was equipped with a dedicated GPS tracking device configured to record location points every 2-3 seconds and was asked to maintain a digital or paper logbook of their trips. All inferred mobility traces were algorithmically processed and validated through follow-up phone interviews. The dataset includes three components: (i) an Individuals database describing demographic, socioeconomic, and household characteristics; (ii) a Trips database with over 80,000 annotated displacements including timestamps, transport modes, and trip purposes; and (iii) a Raw GPS Traces database comprising about 500 million high-frequency points. A statistical weighting mechanism is provided to support population-level estimates. An extensive anonymization pipeline was applied to the GPS traces to ensure GDPR compliance while preserving analytical value. Access to the dataset requires acceptance of the challenge's Terms and Conditions and signing a Non-Disclosure Agreement. This paper describes the survey design, collection protocol, processing methodology, and characteristics of the released dataset.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Modelling daily mobility using mobile data traffic at fine spatiotemporal scale
We applied a data-driven approach that explores the usability of the NetMob 2023 dataset in modelling mobility patterns within an urban context. We combined the data with a highly suitable external source, the ENACT data…
Layered Diffusion Model for One-Shot High Resolution Text-to-Image Synthesis
We present a one-shot text-to-image diffusion model that can generate high-resolution images from natural language descriptions. Our model employs a layered U-Net architecture that simultaneously synthesizes images at mu…
Image GenerationSuper-ResolutionLearning 3D Shapes as Multi-Layered Height-maps using 2D Convolutional Networks
We present a novel global representation of 3D shapes, suitable for the application of 2D CNNs. We represent 3D shapes as multi-layered height-maps (MLH) where at each grid location, we store multiple instances of height…
3D Object ClassificationGeneral ClassificationLightweight Convolutional Neural Networks for Retinal Disease Classification
Retinal diseases such as Diabetic Retinopathy (DR) and Macular Hole (MH) significantly impact vision and affect millions worldwide. Early detection is crucial, as DR, a complication of diabetes, damages retinal blood ves…
ClassificationData AugmentationTransfer LearningLightweight Weighted Average Ensemble Model for Pneumonia Detection in Chest X-Ray Images
Pneumonia is a leading cause of illness and death in children, underscoring the need for early and accurate detection. In this study, we propose a novel lightweight ensemble model for detecting pneumonia in children usin…
Computational EfficiencyPneumonia Detection