Adversary models account for imperfect crime data: Forecasting and planning against real-world poachers

Simple item page
dc.contributor.authorGholami, Shahrzad
dc.contributor.authorMc Carthy, Sara
dc.contributor.authorDilkina, Bistra
dc.contributor.authorPlumptre, Andrew
dc.contributor.authorTambe, Milind
dc.contributor.authorDriciru, Margaret
dc.contributor.authorWanyama, Fred
dc.contributor.authorRwetsiba, Aggrey
dc.contributor.authorNsubaga, Mustapha
dc.contributor.authorMabonga, Joshua
dc.contributor.authorOkello, Tom
dc.contributor.authorEnyel, Eric
dc.date.accessioned2022-12-26T16:41:12Z
dc.date.available2022-12-26T16:41:12Z
dc.date.issued2018
dc.description.abstractPoachers are engaged in extinction level wholesale slaughter, so it is critical to harness historical data for predicting poachers’ behavior. However, in these domains, data collected about adversarial actions are remarkably imperfect, where reported negative instances of crime may be mislabeled or uncertain. Unfortunately, past attempts to develop predictive and prescriptive models to address this problem suffer from shortcomings from a modeling perspective as well as in the implementability of their techniques. Most notably these models i) neglect the uncertainty in crime data, leading to inaccurate and biased predictions of adversary behavior, ii) use coarse-grained crime analysis and iii) do not provide a convincing evaluation as they only look at a single protected area. Additionally, they iv) proposed time-consuming techniques which cannot be directly integrated into low resource outposts. In this innovative application paper, we (I) introduce iWare-E a novel imperfect-observation aWare Ensemble (iWare-E) technique, which is designed to handle the uncertainty in crime information efficiently. This approach leads to superior accuracy and efficiency for adversary behavior prediction compared to the previous stateof- the-art. We also demonstrate the country-wide efficiency of the models and are the first to (II) evaluate our adversary behavioral model across different protected areas in Uganda, i.e., Murchison Fall and Queen Elizabeth National Park, (totaling about 7500 km2) as well as (III) on fine-grained temporal resolutions. Lastly, (IV) we provide a scalable planning algorithm to design fine-grained patrol routes for the rangers, which achieves up to 150% improvement in number of predicted attacks detected.en_US
dc.identifier.citationGholami, S., Mc Carthy, S., Dilkina, B., Plumptre, A., Tambe, M., Driciru, M., ... & Enyel, T. O. E. (2018). Adversary models account for imperfect crime data: Forecasting and planning against real-world poachers (Corrected Version). In 17th International Conference on Autonomous Agents and Multiagent Systems.en_US
dc.identifier.urihttps://teamcore.seas.harvard.edu/files/teamcore/files/2018_28_teamcore_sgholami_aamas18.pdf
dc.identifier.urihttps://nru.uncst.go.ug/handle/123456789/6580
dc.language.isoenen_US
dc.publisherInternational Conference on Autonomous Agents and Multiagent Systemsen_US
dc.subjectPredictive modelsen_US
dc.subjectWildlife poachingen_US
dc.subjectEnsemble techniquesen_US
dc.subjectField test evaluationen_US
dc.subjectWildlife protectionen_US
dc.titleAdversary models account for imperfect crime data: Forecasting and planning against real-world poachersen_US
dc.typeOtheren_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Adversary models account for imperfect crime data.pdf
Size:
1.2 MB
Format:
Adobe Portable Document Format
Description:
Conference Paper
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Natural Sciences