Shahrzad Gholami

Taking It for a Test Drive: A Hybrid Spatio-Temporal Model for Wildlife Poaching Prediction Evaluated Through a Controlled Field Test

Worldwide, conservation agencies employ rangers to protect conservation areas from poachers. However, agencies lack the manpower to have rangers effectively patrol these vast areas frequently. While past work has modeled poachers’ behavior so as to aid rangers in planning future patrols, those models’ predictions were not validated by extensive field tests. In this paper, we present a hybrid spatio-temporal model that predicts poaching threat levels and results from a five-month field test of our model in Uganda’s Queen Elizabeth Protected Area (QEPA). To our knowledge, this is the first time that a predictive model has been evaluated through such an extensive field test in this domain. We present two major contributions. First, our hybrid model consists of two components: (i) an ensemble model which can work with the limited data common to this domain and (ii) a spatio-temporal model to boost the ensemble’s predictions when sufficient data are available. When evaluated on real-world historical data from QEPA, our hybrid model achieves significantly better performance than previous approaches with either temporally-aware dynamic Bayesian networks or an ensemble of spatially-aware models. Second, in collaboration with the Wildlife Conservation Society and Uganda Wildlife Authority, we present results from a five-month controlled experiment where rangers patrolled over 450 sq km across QEPA. We demonstrate that our model successfully predicted (1) where snaring activity would occur and (2) where it would not occur; in areas where we predicted a high rate of snaring activity, rangers found more snares and snared animals than in areas of lower predicted activity. These findings demonstrate that (1) our model’s predictions are selective, (2) our model’s superior laboratory performance extends to the real world, and (3) these predictive models can aid rangers in focusing their efforts to prevent wildlife poaching and save animals.

Keeping Pace with Criminals: An Extended Study of Designing Patrol Allocation against Adaptive Opportunistic Criminals

Police patrols are used ubiquitously to deter crimes in urban areas. A distinctive feature of urban crimes is that criminals react opportunistically to patrol officers assignments. Compared to strategic attackers (such as terrorists) with a well-laid out plan, opportunistic criminals are less strategic in planning attacks and more flexible in executing them. In this paper, our goal is to recommend optimal police patrolling strategy against such opportunistic criminals. We first build a game-theoretic model that captures the interaction between officers and opportunistic criminals. However, while different models of adversary behavior have been proposed, their exact form remains uncertain. Rather than simply hypothesizing a model as done in previous work, one key contribution of this paper is to learn the model from real-world criminal activity data. To that end, we represent the criminal behavior and the interaction with the patrol officers as parameters of a Dynamic Bayesian Network (DBN), enabling application of standard algorithms such as EM to learn the parameters. Our second contribution is a sequence of modifications to the DBN representation, that allows for a compact representation of the model resulting in better learning accuracy and increased speed of learning of the EM algorithm when used for the modified DBN. These modifications use marginalization approaches and exploit the structure of this problem. Finally, our third contribution is an iterative learning and planning mechanism that keeps updating the adversary model periodically. We demonstrate the efficiency of our learning algorithm by applying it to a real data set of criminal activity obtained from the police department of University of Southern California (USC) situated in Los Angeles, USA. We project a significant reduction in crime rate using our planning strategy as opposed to the actual strategy deployed by the police department. We also demonstrate the improvement in crime prevention in simulations when we use our iterative planning and learning mechanism compared to just learning once and planing. This work was done in collaboration with the police department of USC.

Divide to Defend: Collusive Security Games

Research on security games has focused on settings where the defender must protect against either a single adversary or multiple, independent adversaries. However, there are a variety of real-world security domains where adversaries may benefit from colluding in their actions against the defender, e.g., wildlife poaching, urban crime and drug trafficking. Given such adversary collusion may be more detrimental for the defender, she has an incentive to break up collusion by playing off the self-interest of individual adversaries. As we show in this paper, breaking up such collusion is difficult given bounded rationality of human adversaries; we therefore investigate algorithms for the defender assuming both rational and boundedly rational adversaries. The contributions of this paper include i collusive security games COSGs, a model for security games involving potential collusion among adversaries, ii SPECTRE-R, an algorithm to solve COSGs and break collusion assuming rational adversaries, iii observations and analyses of adversary behavior and the underlying factors including bounded rationality, imbalanced- resource-allocation effect, coverage perception, and individualism/collectivism attitudes within COSGs with data from 700 human subjects, iv a learned human behavioral model that incorporates these factors to predict when collusion will occur, v SPECTRE-BR, an enhanced algorithm which optimizes against the learned behavior model to provide demonstrably better performing defender strategies against human subjects compared to SPECTRE-R.

ON THE CONTROL OF TUMOR GROWTH VIA TYPE-1 AND INTERVAL TYPE-2 FUZZY LOGIC

This paper deals with growth control of cancer cells population using type-1 and interval type-2 fuzzy logic. A type-1 fuzzy controller is designed in order to reduce the population of cancer cells, adjust the drug dosage in a manner that allows normal cells re-grow in treatment period and maintain the maximum drug delivery rate and plasma concentration of drug in an appropriate range. Two different approaches are studied. One deals with reducing the number of cancer cells without any concern about the rate of decreasing, and the other takes the rate of malignant cells damage into consideration. Due to the fact that uncertainty is an inherent part of real systems and affects controller efficacy, employing new methods of design such as interval type-2 fuzzy logic systems for handling uncertainties may be efficacious. Influence of noise on the system is investigated and the effect of altering free parameters of design is studied. Using an interval type-2 controller can diminish the effects of incomplete and uncertain information about the system, environmental noises, instrumentation errors, etc. Simulation results confirm the effectiveness of the proposed methods on tumor growth control.

Predicting poaching for wildlife Protection

Wildlife species such as tigers and elephants are under the threat of poaching. To combat poaching, conservation agencies (“defenders”) need to 1) anticipate where the poachers are likely to poach and 2) plan effective patrols. We propose an anti-poaching tool CAPTURE (Comprehensive Anti-Poaching tool with Temporal and observation Uncertainty REasoning), which helps the defenders achieve both goals. CAPTURE builds a novel hierarchical model for poacher-patroller interaction. It considers the patrollers imperfect detection of signs of poaching, the complex temporal dependencies in the poachers behaviors, and the defenders lack of knowledge of the number of poachers. Further, CAPTURE uses a new game-theoretic algorithm to compute the optimal patrolling strategies and plan effective patrols. This paper investigates the computational challenges that CAPTURE faces. First, we present a detailed analysis of parameter separation and cell abstraction, two novel approaches used by CAPTURE to efficiently learn the parameters in the hierarchical model. Second, we propose two heuristics—piecewise linear approximation and greedy planning—to speed up the computation of the optimal patrolling strategies. In this paper, we discuss the lessons learned from using CAPTURE to analyze real-world poaching data collected over 12 years in Queen Elizabeth National Park in Uganda.

Observer based feedback control of a biodynamical model of tumor growth with sampled measurements

This paper deals with the cancer treatment scheduling via observer-based feedback control of a tumor growth biodynamical model. An experimental nonlinear model is utilized to design a feedback controller. This model was validated by a pharmacological study on xenograft models obtained by transplantation of colon carcinoma cell lines in athymic mice. Input-output feedback linearization approach is used to linearize the nonlinear model of the system and design a control law. It is assumed that tumor weight can be measured in definite intervals. So a continuous-discrete observer is designed to estimate states of the system based on discrete sampled data which are tumor weight in this case. To investigate the effect of the drug on the normal cells, a body weight toxicity model is considered to be checked during the simulation. Finally, a discrete chemotherapy dose schedule is proposed. Simulation results show the effectiveness of the proposed observer-controller algorithms.