ReAD: A Regional Anomaly Detection Framework Based on Dynamic Partition

TL;DR

ReAD introduces a novel unsupervised framework for detecting arbitrary-shaped abnormal regions in urban data by dynamically partitioning regions to address data sparsity and heterogeneity issues.

Contribution

The paper presents a dynamic region partition method combined with an anomaly detection framework that effectively identifies irregular regions in urban data, overcoming limitations of previous grid-based approaches.

Findings

Effective detection of irregular abnormal regions demonstrated on real-world data.

Addresses data sparsity and heterogeneity issues in urban anomaly detection.

Framework outperforms traditional grid-based methods in accuracy and flexibility.

Abstract

The detection of the abnormal area from urban data is a significant research problem. However, to the best of our knowledge, previous methods designed on spatio-temporal anomalies are road-based or grid-based, which usually causes the data sparsity problem and affects the detection results. In this paper, we proposed a dynamic region partition method to address the above issues. Besides, we proposed an unsupervised REgional Anomaly Detection framework (ReAD) to detect abnormal regions with arbitrary shapes by jointly considering spatial and temporal properties. Specifically, the proposed framework first generate regions via a dynamic region partition method. It keeps that observations in the same region have adjacent locations and similar non-spatial attribute readings, and could alleviate data sparsity and heterogeneity compared with the grid-based approach. Then, an anomaly metric will be calculated for each region by a regional divergence calculation method. The abnormal regions could be finally detected by a weighted approach or a wavy approach according to the different scenario. Experiments on both the simulated dataset and real-world applications demonstrate the effectiveness and practicability of the proposed framework.