By the same authors

Protecting wildlife under imperfect observation

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

Standard

Protecting wildlife under imperfect observation. / Nguyen, Thanh H.; Sinha, Arunesh; Gholami, Shahrzad; Plumptre, Andrew; Joppa, Lucas; Tambe, Milind; Driciru, Margaret; Wanyama, Fred; Rwetsiba, Aggrey; Critchlow, Rob; Beale, Colin.

The Workshops of the Thirtieth AAAI Conference on Artificial Intelligence. Vol. WS-16-01 - WS-16-15 AI Access Foundation, 2017. p. 371-377 (AAAI Workshop Series Technical Reports).

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

Harvard

Nguyen, TH, Sinha, A, Gholami, S, Plumptre, A, Joppa, L, Tambe, M, Driciru, M, Wanyama, F, Rwetsiba, A, Critchlow, R & Beale, C 2017, Protecting wildlife under imperfect observation. in The Workshops of the Thirtieth AAAI Conference on Artificial Intelligence. vol. WS-16-01 - WS-16-15, AAAI Workshop Series Technical Reports, AI Access Foundation, pp. 371-377, 30th AAAI Conference on Artificial Intelligence, AAAI 2016, Phoenix, United States, 12/02/16. <https://aaai.org/Press/Reports/Workshops/ws-16-aaai.php>

APA

Nguyen, T. H., Sinha, A., Gholami, S., Plumptre, A., Joppa, L., Tambe, M., Driciru, M., Wanyama, F., Rwetsiba, A., Critchlow, R., & Beale, C. (2017). Protecting wildlife under imperfect observation. In The Workshops of the Thirtieth AAAI Conference on Artificial Intelligence (Vol. WS-16-01 - WS-16-15, pp. 371-377). (AAAI Workshop Series Technical Reports). AI Access Foundation. https://aaai.org/Press/Reports/Workshops/ws-16-aaai.php

Vancouver

Nguyen TH, Sinha A, Gholami S, Plumptre A, Joppa L, Tambe M et al. Protecting wildlife under imperfect observation. In The Workshops of the Thirtieth AAAI Conference on Artificial Intelligence. Vol. WS-16-01 - WS-16-15. AI Access Foundation. 2017. p. 371-377. (AAAI Workshop Series Technical Reports).

Author

Nguyen, Thanh H. ; Sinha, Arunesh ; Gholami, Shahrzad ; Plumptre, Andrew ; Joppa, Lucas ; Tambe, Milind ; Driciru, Margaret ; Wanyama, Fred ; Rwetsiba, Aggrey ; Critchlow, Rob ; Beale, Colin. / Protecting wildlife under imperfect observation. The Workshops of the Thirtieth AAAI Conference on Artificial Intelligence. Vol. WS-16-01 - WS-16-15 AI Access Foundation, 2017. pp. 371-377 (AAAI Workshop Series Technical Reports).

Bibtex - Download

@inproceedings{f4fca78ed6fd4e49bd7a61ed1c9a2a72,
title = "Protecting wildlife under imperfect observation",
abstract = "Wildlife poaching presents a serious extinction threat to many animal species. In order to save wildlife in designated wildlife parks, park rangers conduct patrols over the park area to combat such illegal activities. An important aspect of the patrolling activity of the rangers is to anticipate where the poachers are likely to catch animals and then respond accordingly. Previous work has applied defender-attacker Stackel-berg Security Games (SSGs) to solve the problem of wildlife protection, wherein attacker behavioral models are used to predict the behaviors of the poachers. However, these behavioral models have several limitations which limit their accuracy in predicting poachers' behavior. First, existing models fail to account for the rangers' imperfect observations w.r.t poaching activities (due to the limited capability of rangers to patrol thoroughly over a vast geographical area). Second, these models are built upon discrete choice models that assume a single agent choosing targets, while it is infeasible to obtain information about every single attacker in wildlife protection. Third, these models do not consider the etfect of past poachers' actions on the current poachers' activities, one of the key factors affecting the poachers' behaviors. In this work, we attempt to address these limitations while providing three main contributions. First, we propose a novel hierarchical behavioral model, HiBRID, to predict the poachers' behaviors wherein the rangers' imperfect detection of poaching signs is taken into account - a significant advance towards existing behavioral models in security games. Furthermore, HiBRID incorporates the temporal effect on the poachers' behaviors. The model also does not require a known number of attackers. Second, we provide two new heuristics: parameter separation and target abstraction to reduce the computational complexity in learning the model parameters. Finally, we use the real-world data collected in Queen Elizabeth National Park (QENP) in Uganda over 12 years to evaluate the prediction accuracy of our new model.",
author = "Nguyen, {Thanh H.} and Arunesh Sinha and Shahrzad Gholami and Andrew Plumptre and Lucas Joppa and Milind Tambe and Margaret Driciru and Fred Wanyama and Aggrey Rwetsiba and Rob Critchlow and Colin Beale",
year = "2017",
month = feb,
day = "24",
language = "English",
volume = "WS-16-01 - WS-16-15",
series = "AAAI Workshop Series Technical Reports",
publisher = "AI Access Foundation",
pages = "371--377",
booktitle = "The Workshops of the Thirtieth AAAI Conference on Artificial Intelligence",
note = "30th AAAI Conference on Artificial Intelligence, AAAI 2016 ; Conference date: 12-02-2016 Through 13-02-2016",

}

RIS (suitable for import to EndNote) - Download

TY - GEN

T1 - Protecting wildlife under imperfect observation

AU - Nguyen, Thanh H.

AU - Sinha, Arunesh

AU - Gholami, Shahrzad

AU - Plumptre, Andrew

AU - Joppa, Lucas

AU - Tambe, Milind

AU - Driciru, Margaret

AU - Wanyama, Fred

AU - Rwetsiba, Aggrey

AU - Critchlow, Rob

AU - Beale, Colin

PY - 2017/2/24

Y1 - 2017/2/24

N2 - Wildlife poaching presents a serious extinction threat to many animal species. In order to save wildlife in designated wildlife parks, park rangers conduct patrols over the park area to combat such illegal activities. An important aspect of the patrolling activity of the rangers is to anticipate where the poachers are likely to catch animals and then respond accordingly. Previous work has applied defender-attacker Stackel-berg Security Games (SSGs) to solve the problem of wildlife protection, wherein attacker behavioral models are used to predict the behaviors of the poachers. However, these behavioral models have several limitations which limit their accuracy in predicting poachers' behavior. First, existing models fail to account for the rangers' imperfect observations w.r.t poaching activities (due to the limited capability of rangers to patrol thoroughly over a vast geographical area). Second, these models are built upon discrete choice models that assume a single agent choosing targets, while it is infeasible to obtain information about every single attacker in wildlife protection. Third, these models do not consider the etfect of past poachers' actions on the current poachers' activities, one of the key factors affecting the poachers' behaviors. In this work, we attempt to address these limitations while providing three main contributions. First, we propose a novel hierarchical behavioral model, HiBRID, to predict the poachers' behaviors wherein the rangers' imperfect detection of poaching signs is taken into account - a significant advance towards existing behavioral models in security games. Furthermore, HiBRID incorporates the temporal effect on the poachers' behaviors. The model also does not require a known number of attackers. Second, we provide two new heuristics: parameter separation and target abstraction to reduce the computational complexity in learning the model parameters. Finally, we use the real-world data collected in Queen Elizabeth National Park (QENP) in Uganda over 12 years to evaluate the prediction accuracy of our new model.

AB - Wildlife poaching presents a serious extinction threat to many animal species. In order to save wildlife in designated wildlife parks, park rangers conduct patrols over the park area to combat such illegal activities. An important aspect of the patrolling activity of the rangers is to anticipate where the poachers are likely to catch animals and then respond accordingly. Previous work has applied defender-attacker Stackel-berg Security Games (SSGs) to solve the problem of wildlife protection, wherein attacker behavioral models are used to predict the behaviors of the poachers. However, these behavioral models have several limitations which limit their accuracy in predicting poachers' behavior. First, existing models fail to account for the rangers' imperfect observations w.r.t poaching activities (due to the limited capability of rangers to patrol thoroughly over a vast geographical area). Second, these models are built upon discrete choice models that assume a single agent choosing targets, while it is infeasible to obtain information about every single attacker in wildlife protection. Third, these models do not consider the etfect of past poachers' actions on the current poachers' activities, one of the key factors affecting the poachers' behaviors. In this work, we attempt to address these limitations while providing three main contributions. First, we propose a novel hierarchical behavioral model, HiBRID, to predict the poachers' behaviors wherein the rangers' imperfect detection of poaching signs is taken into account - a significant advance towards existing behavioral models in security games. Furthermore, HiBRID incorporates the temporal effect on the poachers' behaviors. The model also does not require a known number of attackers. Second, we provide two new heuristics: parameter separation and target abstraction to reduce the computational complexity in learning the model parameters. Finally, we use the real-world data collected in Queen Elizabeth National Park (QENP) in Uganda over 12 years to evaluate the prediction accuracy of our new model.

UR - http://www.scopus.com/inward/record.url?scp=85021906409&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85021906409

VL - WS-16-01 - WS-16-15

T3 - AAAI Workshop Series Technical Reports

SP - 371

EP - 377

BT - The Workshops of the Thirtieth AAAI Conference on Artificial Intelligence

PB - AI Access Foundation

T2 - 30th AAAI Conference on Artificial Intelligence, AAAI 2016

Y2 - 12 February 2016 through 13 February 2016

ER -