Preventing Infectious Disease in Dynamic Populations Under Uncertainty
Authors: Bryan Wilder, Sze-Chuan Suen, Milind Tambe
AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate our algorithm on two instances where this distribution is inferred from real world data: tuberculosis in India and gonorrhea in the United States. Our algorithm produces a policy which is predicted to avert an average of least 8,000 person-years of tuberculosis and 20,000 personyears of gonorrhea annually compared to current policy. |
| Researcher Affiliation | Academia | Department of Computer Science 2Department of Industrial and Systems Engineering 3Center for Artificial Intelligence in Society University of Southern California {bwilder, ssuen, tambe}@usc.edu |
| Pseudocode | Yes | Algorithm 1 DOMO |
| Open Source Code | No | The paper does not contain any explicit statement about releasing source code for the methodology or provide a link to a code repository. |
| Open Datasets | Yes | We instantiate MCF-SIS in two domains using empirical data which takes into account behavioral, demographic, and epidemic trends: first, TB spread in India, and second, gonorrhea in the United States. ... We estimate prevalence (the initial infected vector I0 and new arrivals I) using agestratified data provided by the Indian government for the years 1993-2005 (IIPS 2014), see Table 1. |
| Dataset Splits | No | The paper describes using sampled instances and refers to data, but it does not specify explicit training, validation, and test dataset splits (e.g., 80/10/10 percentages or specific sample counts for each split). |
| Hardware Specification | No | The paper mentions that 'all algorithms, implemented in Python, run in under 10 minutes' but does not specify any particular hardware (e.g., CPU, GPU models, memory). |
| Software Dependencies | No | The paper states that the algorithms were 'implemented in Python', but it does not provide specific version numbers for Python or any libraries/frameworks used. |
| Experiment Setup | Yes | DOMO is run with R = 100 iterations and r = 100 samples. We start with TB. ... We set U = 1.05 νSQ. ... For each sample, we find the ˆβ that minimizes the mean squared error between the observed I and that predicted by MCF-SIS. |