NC-BSI: TASK 3.5: Reduction of False Alarm Rates from Fused Data Problem Statement/Objectives Research Objectives Intelligent fusing of data from hybrid.

Slides:



Advertisements
Similar presentations
Some Reflections on Augmented Cognition Eric Horvitz ISAT & Microsoft Research November 2000 Some Reflections on Augmented Cognition Eric Horvitz ISAT.
Advertisements

Department of Electronic Engineering Challenges & Proposals INFSO Information Day Research Networking Test-beds 26/27 May 2005,
Ergonomics and Information Systems RESEARCH INSTITUTE FOR COMMUNICATION, INFORMATION PROCESSING, AND ERGONOMICS FGAN A Knowledge-based Human-Machine Interface.
Online Filtering, Smoothing & Probabilistic Modeling of Streaming Data In short, Applying probabilistic models to Streams Bhargav Kanagal & Amol Deshpande.
DFF 2014 February 24, Self-adapting Sensor Networks for Semi- automated Threat Detection in a Controlled Area By Jorge Buenfil US ARMY RDECOM ARDEC.
Data Mining Methodology 1. Why have a Methodology  Don’t want to learn things that aren’t true May not represent any underlying reality ○ Spurious correlation.
Bayesian Biosurveillance Gregory F. Cooper Center for Biomedical Informatics University of Pittsburgh The research described in this.
Tru-Alarm: Trustworthiness Analysis of Sensor Network in Cyber Physical Systems Lu-An Tang, Xiao Yu, Sangkyum Kim, Jiawei Han, Chih-Chieh Hung, Wen-Chih.
1 CISR-consultancy Challenges “Customer ask us what to do next” Keywords: “Customer ask us what to do next” From Policy to Practise The world is going.
1 SAFIRE Project DHS Update – July 15, 2009 Introductions  Update since last teleconference Demo Video - Fire Incident Command Board (FICB) SAFIRE Streams.
Report on Intrusion Detection and Data Fusion By Ganesh Godavari.
© Franz Kurfess Project Topics 1 Topics for Master’s Projects and Theses -- Winter Franz J. Kurfess Computer Science Department Cal Poly.
Unlock Your Data Rich connectivity Robust data integration Enterprise-class manageability Deliver Relevant Information Intuitive design environment.
Software Process and Product Metrics
Computer Science Universiteit Maastricht Institute for Knowledge and Agent Technology Data mining and the knowledge discovery process Summer Course 2005.
Intrusion and Anomaly Detection in Network Traffic Streams: Checking and Machine Learning Approaches ONR MURI area: High Confidence Real-Time Misuse and.
AGENDA Welcome and introductions Brief introduction to PSI Mobile Technical Overview Demonstration Q and A Next Actions.
Kansas State University Department of Computing and Information Sciences CIS 830: Advanced Topics in Artificial Intelligence From Data Mining To Knowledge.
Information Fusion in Continuous Assurance Johan Perols University of San Diego Uday Murthy University of South Florida UWCISA Symposium October 2, 2009.
Tennessee Technological University1 The Scientific Importance of Big Data Xia Li Tennessee Technological University.
By Manuel C. Salas Advisor: Dr. Bernard P. Zeigler University of Arizona 2008.
Jay F. Nunamaker, Jr. – Director Elyse Golob – Executive Director Challenges and Solutions at the Northern Border Thursday, February 26, 2009 Meydenbauer.
CSIAC is a DoD Information Analysis Center (IAC) sponsored by the Defense Technical Information Center (DTIC) Presentation to: Insider Threat SOAR Workshop.
Computer Science Open Research Questions Adversary models –Define/Formalize adversary models Need to incorporate characteristics of new technologies and.
NC-BSI 2.3: Smart Border Systems for Localization and Tracking Problem Statement/Objectives Develop methods which will allow accurately, robustly and ubiquitously.
David S. Ebert David S. Ebert Visual Analytics to Enable Discovery and Decision Making: Potential, Challenges, and.
Robust GW summary statistics & robust GW regression are used to investigate spatial variation and relationships in a freshwater acidification critical.
Recognizing Activities of Daily Living from Sensor Data Henry Kautz Department of Computer Science University of Rochester.
Report on Intrusion Detection and Data Fusion By Ganesh Godavari.
NC-BSI: 3.3 Data Fusion for Decision Support Problem Statement/Objectives: Problem - Accurate situation awareness requires rapid integration of heterogeneous.
Chengjie Sun,Lei Lin, Yuan Chen, Bingquan Liu Harbin Institute of Technology School of Computer Science and Technology 1 19/11/ :09 PM.
Interviewing and Deception Detection Techniques for Rapid Screening and Credibility Assessment Dr. Jay F. Nunamaker, Jr. Dr. Judee K. Burgoon.
Subtask 1.8 WWW Networked Knowledge Bases August 19, 2003 AcademicsAir force Arvind BansalScott Pollock Cheng Chang Lu (away)Hyatt Rick ParentMark (SAIC)
© 2010 IBM Corporation IBM Research - Ireland © 2014 IBM Corporation xStream Data Fusion for Transport Smarter Cities Technology Centre IBM Research.
Developing a 21st-Century Organization CHAPTER 20 McGraw-Hill/Irwin Copyright © 2013 by The McGraw-Hill Companies, Inc. All rights reserved.
Adapted from the original presentation made by the authors Reputation-based Framework for High Integrity Sensor Networks.
Responding to the Unexpected Yigal Arens Paul Rosenbloom Information Sciences Institute University of Southern California.
Department of Electronic Engineering Challenges & Proposals INFSO Information Day e-Infrastructure Grid Initiatives 26/27 May.
Kansas State University Department of Computing and Information Sciences CIS 830: Advanced Topics in Artificial Intelligence Wednesday, January 24, 2001.
Robust GW summary statistics & robust GW regression are used to investigate a freshwater acidification data set. Results show that data relationships can.
Kansas State University Department of Computing and Information Sciences CIS 798: Intelligent Systems and Machine Learning Tuesday, December 7, 1999 William.
Mining Weather Data for Decision Support Roy George Army High Performance Computing Research Center Clark Atlanta University Atlanta, GA
Kansas State University Department of Computing and Information Sciences CIS 730: Introduction to Artificial Intelligence Friday, 14 November 2003 William.
Artificial Intelligence Center,
ISCTSC Workshop A7 Best Practices in Data Fusion.
Data Management Support for Life Sciences or What can we do for the Life Sciences? Mourad Ouzzani
Identifying “Best Bet” Web Search Results by Mining Past User Behavior Author: Eugene Agichtein, Zijian Zheng (Microsoft Research) Source: KDD2006 Reporter:
Control-Theoretic Approaches for Dynamic Information Assurance George Vachtsevanos Georgia Tech Working Meeting U. C. Berkeley February 5, 2003.
Introduction to Software Engineering 1. Software Engineering Failures – Complexity – Change 2. What is Software Engineering? – Using engineering approaches.
The article written by Boyarshinova Vera Scientific adviser: Eltyshev Denis THE USE OF NEURO-FUZZY MODELS FOR INTEGRATED ASSESSMENT OF THE CONDITIONS OF.
1. ABSTRACT Information access through Internet provides intruders various ways of attacking a computer system. Establishment of a safe and strong network.
Data Mining Techniques Applied in Advanced Manufacturing PRESENT BY WEI SUN.
Resource Optimization for Publisher/Subscriber-based Avionics Systems Institute for Software Integrated Systems Vanderbilt University Nashville, Tennessee.
Cognos BI. What is Cognos? Cognos (Cognos Incorporated) was an Ottawa, Ontario-based company that makes Business Intelligence (BI) and Performance Management.
Monitoreo y Administración de Infraestructura Fisica (DCIM). StruxureWare for Data Centers 2.0 Arturo Maqueo Business Development Data Centers LAM.
National Institute of Standards and Technology (NIST) Advanced Manufacturing Technology Consortia (AMTech) Program Award Number: 70NANB14H056 Development.
Testbed for Medical Cyber-Physical Systems
WSRec: A Collaborative Filtering Based Web Service Recommender System
Optimal CyberSecurity Analyst Staffing Plan
Problem Statement/Objectives
Tailor slide to customer industry/pain points
Multi-Step Attack Defense Operating Point Estimation via Bayesian Modeling under Parameter Uncertainty Peng Liu, Jun Dai, Xiaoyan Sun, Robert Cole Penn.
Fusing A Heterogeneous Alert Stream Into Scenarios
Technology Planning.
Module Description: This course intends to introduce special topics of current trends in information technology. Topics covered in this course should be.
CIPSEC architecture CIPSEC workshop Frankfurt 16/10/2018
View Inter-Prediction GAN: Unsupervised Representation Learning for 3D Shapes by Learning Global Shape Memories to Support Local View Predictions 1,2 1.
Big DATA.
{Project Name} Organizational Chart, Roles and Responsibilities
Presentation transcript:

NC-BSI: TASK 3.5: Reduction of False Alarm Rates from Fused Data Problem Statement/Objectives Research Objectives Intelligent fusing of data from hybrid sensors Minimize false alarms when detecting changes and anomalies to improve reliability Extending the solutions to current and new border security data applications Methodology (A) Cliques of neighboring sensors will be formed to discover reliable local patterns via data fusion, cross validation, and level-0 Bayesian network inference. (B) Clique outputs will be integrated at the next level with level-i Bayesian network inference about global patterns for intelligent monitoring. (C) Tools and techniques will be developed to select complements by minimizing the number and considering features from different sources based on canonical correlation analysis. Benefits to DHS Sensors and state-of-the-art video technology have been deployed and generate enormous quantities of data. Inability to identify meaningful patterns and relationships within this mass of data results in false alarms, real alerts lost in background data, inability to identify “big picture” relationships and duplication of effort. More effective tools and techniques to find meaning in the large, heterogeneous datasets will improve efficiency of human responses, increase agent confidence and provide more effective tactical and strategic information to guide operations. Deliverables and Timelines Year 1 – Identify user population and identify current sources, uses of sensor data and examples of false alarms Obtain sample data sets, apply existing algorithms and identify (or insert) false alarms as ground truth for testing during development Develop initial cliques of neighborhood sensors and begin to develop/refine algorithms. Year 2 - Conduct feature-level data fusion study for a hybrid data fusion system using cliques of neighboring sensors. 1

NC-BSI: TASK 3.5: Reduction of False Alarm Rates from Fused Data Elevator speech We will use efficient feature-level data fusion techniques to represent the massive, hybrid sensor data in reconfigurable sub-graphs at different levels and apply techniques to accurately and efficiently discover and verify critical patterns, detecting deceptive variants, and predicting new trends. Ongoing/leveraged research Data Mining and Information Fusion Hierarchical Bayesian reasoning about uncertainty with noisy information Canonical correlation analysis Feature level data fusion Costs and Special Equipment Personnel Travel Total project funding : $70,588 Investigators The Arizona State University Task 3.5 Team Huan Liu George Runger Jeremy Rowe 2

Presentation and use of the models and simulations Collaborative Research core of Computer Science/Informatics, Data Mining, Modeling and Analysis to inform scenarios, planning and policy Data Description and Management Physical Technology Infrastructure Data Foundation Schematic Representation NC-BSI: TASK 3.5: Reduction of False Alarm Rates from Fused Data

Embedded Intelligence, DataMining Detail Evaluator of baseline Hierarchical system with neighborhood, complementary and surrogate features Sensors … Hierarchical Bayesian integration, complementary and surrogate features False Alarm Filters, Detection Ensembles Context and Environment Information Clique neighborhoods and zooms: Level 0 Clique neighborhoods and zooms: Level 1 Evaluator: Baseline System and Simulator Retrieval and Analysis NC-BSI: TASK 3.5: Reduction of False Alarm Rates from Fused Data