SearcharxivSearch

arXiv subjects

Jaymar Soriano

Publications and source records attributed to Jaymar Soriano.

2 recordsLinked to original sources

Cascading Effects of the COVID-19 Pandemic on Barangays in the Philippines

The COVID-19 pandemic disrupted socio-economic and healthcare systems in the Philippines, significantly affecting barangays. This study analyzes the cascading effects of the COVID-19 pandemic on key aspects of a barangay, namely mobility, accessibility of public services, economic and financial health, food security, educational engagement, and physical health. It focuses on data from 2,122 Filipino households collected during May to June 2021 as part of the World Bank COVID-19 Households Survey. A Bayesian network model was constructed to programmatically map the conditional dependencies among these variables, utilizing Python libraries. Survey responses were grouped into common variables based on shared characteristics and standardized through z-score normalization to serve as nodes in the Bayesian network. By extending the Bayesian network into an influence diagram, the results will help identify interventions to guide local government units (LGUs) and policymakers in crafting tailored recovery programs and strategies that address impacts on physical health, economic and financial health, food security, public service access, mobility, and educational engagement. These efforts ultimately aim to enhance barangay resilience and preparedness for future public health crises. The results indicate that interventions aimed at boosting food production, stabilizing market prices, and expanding income opportunities are the most effective in improving community outcomes. This highlights the vital role of targeted economic and food security measures in mitigating the socio-economic impacts of the pandemic and offers valuable insights for shaping future response and recovery efforts.

econ.GN

A Hierarchical Mixture Density Network

The relationship among three correlated variables could be very sophisticated, as a result, we may not be able to find their hidden causality and model their relationship explicitly. However, we still can make our best guess for possible mappings among these variables, based on the observed relationship. One of the complicated relationships among three correlated variables could be a two-layer hierarchical many-to-many mapping. In this paper, we proposed a Hierarchical Mixture Density Network (HMDN) to model the two-layer hierarchical many-to-many mapping. We apply HMDN on an indoor positioning problem and show its benefit.

cs.CV