An Adaptive Fusion Risk-Zone Detection Network and its Application

Abstract

COVID-19 has caused a pandemic and adverse effects in many fields on a global scale. The city scale quarantine has demonstrated its effectiveness in controlling the epidemic. Conversely, it is costly and risky in inducing economic and social challenges. A compromised solution is to place quarantine measures at high-risk zones on a local scale. Therefore, it is important to investigate risk zones for conducting cost insensitive precautionary measures. The urban data depict the characteristics of different city zones, which offers an opportunity for detecting the high-risk zones. Yet, the high noise-to-signal ratio requires an efficient procedure to rule out irrelevant information in the informative raw urban data and adapt to the risk detection task. In this paper, we propose an Adaptive Fusion Risk-zone Detection Network (AFRDN), which fuses the static and dynamic multi-sourced urban data in an adaptive manner. Specifically, AFRDN first extracts diverse information-rich features from raw urban data with various encoders in the embedding learning module. Then, the AFRDN takes a hierarchical late fusion strategy by fusing the static embedding and the attentive hidden state of dynamic features in the deep latent space. To capture the most relevant information for risk-zone detection, the AFRDN adapts each dimension in the fused embedding with multi-head self-attention blocks. We have collected a real-world dataset including six Chinese cities and conducted extensive experiments to evaluate our framework. Simulation experiments and comparative analysis results show that the AFRDN is effective and feasible for early detection of infectious diseases high-risk zones.