Improving the Timeliness and Response to an Aerosolizedanthrax Attack in the Metropolitan Washington, D.C. Region

Our research was conducted to improve the timeliness, coordination, and communication during the detection, investigation and decision-making phases of the response to an aerosolized anthrax attack in the metropolitan Washington, DC, area with the goal of reducing casualties. Our research gathered information of the current response protocols through an extensive literature review and interviews with relevant officials and experts in order to identify potential problems that may exist in various steps of the detection, investigation, and response. Interviewing officials from private and government sector agencies allowed the development of a set of models of interactions and a communication network to identify discrepancies and redundancies that would elongate the delay time in initiating a public health response. In addition, we created a computer simulation designed to model an aerosol spread using weather patterns and population density to identify an estimated population of infected individuals within a target region depending on the virulence and dimensions of the weaponized spores. We developed conceptual models in order to design recommendations that would be presented to our collaborating contacts and agencies that would use such policy and analysis interventions to improve upon the overall response to an aerosolized anthrax attack, primarily through changes to emergency protocol functions and suggestions of technological detection and monitoring response to an aerosolized anthrax attack.

Generating Discriminative Objective Proposals via Submodular Ranking

Object recognition has long been a core problem in computer vision. To improve object spatial support and speed up object localization for object recognition, generating high-quality category-independent object proposals as the input for object recognition system has drawn attention recently. Given an image, we generate a limited number of high-quality and category-independent object proposals in advance and used as inputs for many computer vision tasks. We present an efficient dictionary-based model for image classification task. We further extend the work to a discriminative dictionary learning method for tensor sparse coding. In the first part, a multi-scale greedy-based object proposal generation approach is presented. Based on the multi-scale nature of objects in images, our approach is built on top of a hierarchical segmentation. We first identify the representative and diverse exemplar clusters within each scale. Object proposals are obtained by selecting a subset from the multi-scale segment pool via maximizing a submodular objective function, which consists of a weighted coverage term, a single-scale diversity term and a multi-scale reward term. The weighted coverage term forces the selected set of object proposals to be representative and compact; the single-scale diversity term encourages choosing segments from different exemplar clusters so that they will cover as many object patterns as possible; the multi-scale reward term encourages the selected proposals to be discriminative and selected from multiple layers generated by the hierarchical image segmentation. The experimental results on the Berkeley Segmentation Dataset and PASCAL VOC2012 segmentation dataset demonstrate the accuracy and efficiency of our object proposal model. Additionally, we validate our object proposals in simultaneous segmentation and detection and outperform the state-of-art performance. To classify the object in the image, we design a discriminative, structural low-rank framework for image classification. We use a supervised learning method to construct a discriminative and reconstructive dictionary. By introducing an ideal regularization term, we perform low-rank matrix recovery for contaminated training data from all categories simultaneously without losing structural information. A discriminative low-rank representation for images with respect to the constructed dictionary is obtained. With semantic structure information and strong identification capability, this representation is good for classification tasks even using a simple linear multi-classifier.