Preventing HIV spread in homeless populations using PSINET

Amulya Yadav, L. Marcolino, E. Rice, R. Petering, H. Winetrobe, H. Rhoades, M. Tambe, H. Carmichael

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

Homeless youth are prone to Human Immunodeficiency Virus (HIV) due to their engagement in high risk behavior such as unprotected sex, sex under influence of drugs, etc. Many non-profit agencies conduct interventions to educate and train a select group of homeless youth about HIV prevention and treatment practices and rely on word-of-mouth spread of information through their social network. Previous work in strategic selection of intervention participants does not handle un-certainties in the social network's structure and evolving network state, potentially causing significant shortcomings in spread of information. Thus, we developed PSINET, a decision support system to aid the agencies in this task. PSINET includes the following key novelties: (i) it handles uncertainties in network structure and evolving network state; (ii) it addresses these uncertainties by using POMDPs in influence maximization; and (iii) it provides algorithmic advances to allow high quality approximate solutions for such POMDPs. Simulations show that PSINET achieves more information spread over the current state-of-the-art. PSINET was developed in collaboration with My Friend's Place (a drop-in agency serving homeless youth in Los Angeles) and is currently being reviewed by their officials.

Original languageEnglish (US)
Title of host publicationPlanning, Search, and Optimization - Papers Presented at the 29th AAAI Conference on Artificial Intelligence, Technical Report
PublisherAI Access Foundation
Pages92-99
Number of pages8
ISBN (Electronic)9781577357230
StatePublished - Jan 1 2015
Event29th AAAI Conference on Artificial Intelligence, AAAI 2015 - Austin, United States
Duration: Jan 25 2015Jan 30 2015

Publication series

NameAAAI Workshop - Technical Report
VolumeWS-15-12

Conference

Conference29th AAAI Conference on Artificial Intelligence, AAAI 2015
CountryUnited States
CityAustin
Period1/25/151/30/15

Fingerprint

Viruses
Decision support systems
Uncertainty

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Yadav, A., Marcolino, L., Rice, E., Petering, R., Winetrobe, H., Rhoades, H., ... Carmichael, H. (2015). Preventing HIV spread in homeless populations using PSINET. In Planning, Search, and Optimization - Papers Presented at the 29th AAAI Conference on Artificial Intelligence, Technical Report (pp. 92-99). (AAAI Workshop - Technical Report; Vol. WS-15-12). AI Access Foundation.
Yadav, Amulya ; Marcolino, L. ; Rice, E. ; Petering, R. ; Winetrobe, H. ; Rhoades, H. ; Tambe, M. ; Carmichael, H. / Preventing HIV spread in homeless populations using PSINET. Planning, Search, and Optimization - Papers Presented at the 29th AAAI Conference on Artificial Intelligence, Technical Report. AI Access Foundation, 2015. pp. 92-99 (AAAI Workshop - Technical Report).
@inproceedings{3680f8642cac4bcb998c76548ab64af6,
title = "Preventing HIV spread in homeless populations using PSINET",
abstract = "Homeless youth are prone to Human Immunodeficiency Virus (HIV) due to their engagement in high risk behavior such as unprotected sex, sex under influence of drugs, etc. Many non-profit agencies conduct interventions to educate and train a select group of homeless youth about HIV prevention and treatment practices and rely on word-of-mouth spread of information through their social network. Previous work in strategic selection of intervention participants does not handle un-certainties in the social network's structure and evolving network state, potentially causing significant shortcomings in spread of information. Thus, we developed PSINET, a decision support system to aid the agencies in this task. PSINET includes the following key novelties: (i) it handles uncertainties in network structure and evolving network state; (ii) it addresses these uncertainties by using POMDPs in influence maximization; and (iii) it provides algorithmic advances to allow high quality approximate solutions for such POMDPs. Simulations show that PSINET achieves more information spread over the current state-of-the-art. PSINET was developed in collaboration with My Friend's Place (a drop-in agency serving homeless youth in Los Angeles) and is currently being reviewed by their officials.",
author = "Amulya Yadav and L. Marcolino and E. Rice and R. Petering and H. Winetrobe and H. Rhoades and M. Tambe and H. Carmichael",
year = "2015",
month = "1",
day = "1",
language = "English (US)",
series = "AAAI Workshop - Technical Report",
publisher = "AI Access Foundation",
pages = "92--99",
booktitle = "Planning, Search, and Optimization - Papers Presented at the 29th AAAI Conference on Artificial Intelligence, Technical Report",
address = "United States",

}

Yadav, A, Marcolino, L, Rice, E, Petering, R, Winetrobe, H, Rhoades, H, Tambe, M & Carmichael, H 2015, Preventing HIV spread in homeless populations using PSINET. in Planning, Search, and Optimization - Papers Presented at the 29th AAAI Conference on Artificial Intelligence, Technical Report. AAAI Workshop - Technical Report, vol. WS-15-12, AI Access Foundation, pp. 92-99, 29th AAAI Conference on Artificial Intelligence, AAAI 2015, Austin, United States, 1/25/15.

Preventing HIV spread in homeless populations using PSINET. / Yadav, Amulya; Marcolino, L.; Rice, E.; Petering, R.; Winetrobe, H.; Rhoades, H.; Tambe, M.; Carmichael, H.

Planning, Search, and Optimization - Papers Presented at the 29th AAAI Conference on Artificial Intelligence, Technical Report. AI Access Foundation, 2015. p. 92-99 (AAAI Workshop - Technical Report; Vol. WS-15-12).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Preventing HIV spread in homeless populations using PSINET

AU - Yadav, Amulya

AU - Marcolino, L.

AU - Rice, E.

AU - Petering, R.

AU - Winetrobe, H.

AU - Rhoades, H.

AU - Tambe, M.

AU - Carmichael, H.

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Homeless youth are prone to Human Immunodeficiency Virus (HIV) due to their engagement in high risk behavior such as unprotected sex, sex under influence of drugs, etc. Many non-profit agencies conduct interventions to educate and train a select group of homeless youth about HIV prevention and treatment practices and rely on word-of-mouth spread of information through their social network. Previous work in strategic selection of intervention participants does not handle un-certainties in the social network's structure and evolving network state, potentially causing significant shortcomings in spread of information. Thus, we developed PSINET, a decision support system to aid the agencies in this task. PSINET includes the following key novelties: (i) it handles uncertainties in network structure and evolving network state; (ii) it addresses these uncertainties by using POMDPs in influence maximization; and (iii) it provides algorithmic advances to allow high quality approximate solutions for such POMDPs. Simulations show that PSINET achieves more information spread over the current state-of-the-art. PSINET was developed in collaboration with My Friend's Place (a drop-in agency serving homeless youth in Los Angeles) and is currently being reviewed by their officials.

AB - Homeless youth are prone to Human Immunodeficiency Virus (HIV) due to their engagement in high risk behavior such as unprotected sex, sex under influence of drugs, etc. Many non-profit agencies conduct interventions to educate and train a select group of homeless youth about HIV prevention and treatment practices and rely on word-of-mouth spread of information through their social network. Previous work in strategic selection of intervention participants does not handle un-certainties in the social network's structure and evolving network state, potentially causing significant shortcomings in spread of information. Thus, we developed PSINET, a decision support system to aid the agencies in this task. PSINET includes the following key novelties: (i) it handles uncertainties in network structure and evolving network state; (ii) it addresses these uncertainties by using POMDPs in influence maximization; and (iii) it provides algorithmic advances to allow high quality approximate solutions for such POMDPs. Simulations show that PSINET achieves more information spread over the current state-of-the-art. PSINET was developed in collaboration with My Friend's Place (a drop-in agency serving homeless youth in Los Angeles) and is currently being reviewed by their officials.

UR - http://www.scopus.com/inward/record.url?scp=84964624183&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964624183&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84964624183

T3 - AAAI Workshop - Technical Report

SP - 92

EP - 99

BT - Planning, Search, and Optimization - Papers Presented at the 29th AAAI Conference on Artificial Intelligence, Technical Report

PB - AI Access Foundation

ER -

Yadav A, Marcolino L, Rice E, Petering R, Winetrobe H, Rhoades H et al. Preventing HIV spread in homeless populations using PSINET. In Planning, Search, and Optimization - Papers Presented at the 29th AAAI Conference on Artificial Intelligence, Technical Report. AI Access Foundation. 2015. p. 92-99. (AAAI Workshop - Technical Report).