Back to Bayesics: Uncovering Human Mobility Distributions and Anomalies with an Integrated Statistical and Neural Framework

TL;DR

DeepBayesic combines Bayesian principles with neural networks to effectively model complex, heterogeneous mobility data, enabling personalized and accurate anomaly detection in spatiotemporal sequences.

Contribution

The paper introduces DeepBayesic, a novel integrated framework that models multivariate mobility distributions and detects anomalies using personalized neural density estimators.

Findings

Significant improvement over existing anomaly detection methods.

Effective handling of heterogeneous and high-dimensional mobility data.

Enhanced detection of subtle and complex anomalies.

Abstract

Existing methods for anomaly detection often fall short due to their inability to handle the complexity, heterogeneity, and high dimensionality inherent in real-world mobility data. In this paper, we propose DeepBayesic, a novel framework that integrates Bayesian principles with deep neural networks to model the underlying multivariate distributions from sparse and complex datasets. Unlike traditional models, DeepBayesic is designed to manage heterogeneous inputs, accommodating both continuous and categorical data to provide a more comprehensive understanding of mobility patterns. The framework features customized neural density estimators and hybrid architectures, allowing for flexibility in modeling diverse feature distributions and enabling the use of specialized neural networks tailored to different data types. Our approach also leverages agent embeddings for personalized anomaly detection, enhancing its ability to distinguish between normal and anomalous behaviors for individual agents. We evaluate our approach on several mobility datasets, demonstrating significant improvements over state-of-the-art anomaly detection methods. Our results indicate that incorporating personalization and advanced sequence modeling techniques can substantially enhance the ability to detect subtle and complex anomalies in spatiotemporal event sequences.