NUMOSIM: A Synthetic Mobility Dataset with Anomaly Detection Benchmarks
Authors:
- Chris StanfordCSChris Stanford
- Suman AdariSASuman Adari
- Xishun LiaoXLXishun Liao
- Yueshuai HeYHYueshuai He
- Qinhua JiangQJQinhua Jiang
- Chenchen KuaiCKChenchen Kuai
- Jiaqi MaJMJiaqi Ma
- Emmanuel TungETEmmanuel Tung
- Yinlong QianYQYinlong Qian
- Lingyi ZhaoLZLingyi Zhao
- Zihao ZhouZZZihao Zhou
- Zeeshan RasheedZRZeeshan Rasheed
Preprint
Abstract
Collecting real-world mobility data is challenging. It is often fraught with privacy concerns, logistical difficulties, and inherent biases. Moreover, accurately annotating anomalies in large-scale data is nearly impossible, as it demands meticulous effort to distinguish subtle and complex patterns. These challenges significantly impede progress in geospatial anomaly detection research by restricting access to reliable data and complicating the rigorous evaluation, comparison, and benchmarking of methodologies. To address these limitations, we introduce a synthetic mobility dataset, NUMOSIM, that provides a controlled, ethical, and diverse environment for benchmarking anomaly detection techniques. NUMOSIM simulates a wide array of realistic mobility scenarios, encompassing both typical and anomalous behaviours, generated through advanced deep learning models trained on real mobility data. This approach allows NUMOSIM to accurately replicate the complexities of real-world movement patterns while strategically injecting anomalies to challenge and evaluate detection algorithms based on how effectively they capture the interplay between demographic, geospatial, and temporal factors. Our goal is to advance geospatial mobility analysis by offering a realistic benchmark for improving anomaly detection and mobility modeling techniques. To support this, we provide open access to the NUMOSIM dataset, along with comprehensive documentation, evaluation metrics, and benchmark results.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- MetaPoL: Immersive VR based Indoor Patterns of Life (PoL) and Anomalies Data Generation for Insider Threat Modeling in Nuclear Security2024
- HumoNet: A Framework for Realistic Modeling and Simulation of Human Mobility Network2024
- YJMob100K: City-scale and longitudinal dataset of anonymized human mobility trajectoriesScientific Data, 2024
- Learning GPS Point Representations to Detect Anomalous Bus TrajectoriesIEEE Access, 2020
- Online Anomalous Trajectory Detection with Deep Generative Sequence Modeling2020
- Word2VecNatural Language Engineering, 2016
- Opportunistic communication in smart city: Experimental insight with small-scale taxi fleets as data carriersAd Hoc Networks, 2016
- Returners and explorers dichotomy in human mobilityNature Communications, 2015
- Unravelling daily human mobility motifsJournal of The Royal Society Interface, 2013
- Understanding individual human mobility patternsNature, 2008