Sluzek 142/MAPLD 20051 Development of a Reconfigurable Sensor Network for Intrusion Detection Andrzej Sluzek & Palaniappan Annamalai Intelligent Systems.

Slides:



Advertisements
Similar presentations
HARDWARE Rashedul Hasan..
Advertisements

ZXM10 EISU Training.
EECE499 Computers and Nuclear Energy Electrical and Computer Eng Howard University Dr. Charles Kim Fall 2013 Webpage:
A Distributed Security Framework for Heterogeneous Wireless Sensor Networks Presented by Drew Wichmann Paper by Himali Saxena, Chunyu Ai, Marco Valero,
A Mobile Ad hoc Biosensor Network Muzammil KP S7,ECE Govt. Engg. College, Wayanad.
Sensor network Routing protocol A study on LEACH protocol and how to improve it.
ABSTRACT Annually, heart disease causes over 17 million deaths worldwide. One of the best ways of getting preventive prognoses is to use electrocardiograms.
CLOUD COMPUTING FOR MOBILE USERS: CAN OFFLOADING COMPUTATION SAVE ENERGY? Purdue University.
Network Coding Testbed Using Software-Defined Radio Abstract In current generation networks, network nodes operate by replicating and forwarding the packets.
COMMMONWEALTH OF AUSTRALIA Do not remove this notice.
Wireless Sensor Networks: Perimeter Security By Jeremy Prince, Brad Klein, Brian Wang, & Kaustubh Jain.
1 On Handling QoS Traffic in Wireless Sensor Networks 吳勇慶.
Mica: A Wireless Platform for Deeply Embedded Networks Jason Hill and David Culler Presented by Arsalan Tavakoli.
Automatic Control & Systems Engineering Autonomous Systems Research Mini-UAV for Urban Environments Autonomous Control of Multi-UAV Platforms Future uninhabited.
A New Household Security Robot System Based on Wireless Sensor Network Reporter :Wei-Qin Du.
Flatiron Mobile Device Security Monitor Thomas Horacek Lucas Greve.
A Smart Sensor to Detect the Falls of the Elderly.
August 7, 2003 Sensor Network Modeling and Simulation in Ptolemy II Philip Baldwin University of Virginia Motivation With.
TelosCAM: Identifying Burglar Through Networked Sensor-Camera Mates with Privacy Protection Presented by Qixin Wang Shaojie Tang, Xiang-Yang Li, Haitao.
Remote Surveillance Vehicle Design Review By: Bill Burgdorf Tom Fisher Eleni Binopolus-Rumayor.
Cross Strait Quad-Regional Radio Science and Wireless Technology Conference, Vol. 2, p.p. 980 – 984, July 2011 Cross Strait Quad-Regional Radio Science.
Lecture 11 Intrusion Detection (cont)
Intrusion Detection System Marmagna Desai [ 520 Presentation]
Jason Li Jeremy Fowers Ground Target Following for Unmanned Aerial Vehicles.
1 Energy Efficient Communication in Wireless Sensor Networks Yingyue Xu 8/14/2015.
David Rogers, Stu Andrzejewski, Kelly Desmond, Brad Garrod.
Routing Algorithm for Large Data Sensor Networks Raghul Gunasekaran Group Meeting Spring 2006.
Enhancing the Capabilities of a Wireless Holter Monitor Senan Garry 4 th ECE.
Advanced Occupancy System Mitch Williams Adam Winter Shane Woolwine.
 Chasis / System cabinet  A plastic enclosure that contains most of the components of a computer (usually excluding the display, keyboard and mouse)
Ambulation : a tool for monitoring mobility over time using mobile phones Computational Science and Engineering, CSE '09. International Conference.
MICA: A Wireless Platform for Deeply Embedded Networks
Intelligent Shipping Container Project IMPACT & INTEL.
Tufts Wireless Laboratory School Of Engineering Tufts University “Network QoS Management in Cyber-Physical Systems” Nicole Ng 9/16/20151 by Feng Xia, Longhua.
Performance analysis and prediction of physically mobile systems Point view: Computational devices including Mobile phones are expanding. Different infrastructure.
Ruslan Masinjila Aida Militaru.  Nature of the Problem  Our Solution: The Roaming Security Robot  Functionalities  General System View  System Design.
WSN Done By: 3bdulRa7man Al7arthi Mo7mad AlHudaib Moh7amad Ba7emed Wireless Sensors Network.
A Review by Raghu Rangan WPI CS525 September 19, 2012 An Early Warning System Based on Reputation for Energy Control Systems.
Sensor Database System Sultan Alhazmi
Chapter 6 – Connectivity Devices
Embedded Runtime Reconfigurable Nodes for wireless sensor networks applications Chris Morales Kaz Onishi 1.
SENSOR NETWORKS BY Umesh Shah Mayuresh Patil G P Reddy GUIDES Prof U.B.Desai Prof S.N.Merchant.
MACHINE VISION Machine Vision System Components ENT 273 Ms. HEMA C.R. Lecture 1.
AD-HOC NETWORK SUBMITTED BY:- MIHIR GARG A B.TECH(E&T)/SEC-A.
Baeg, Sanghyeon Reliable & high Speed Computing Lab. Hanyang University.
MAPLD 2005/254C. Papachristou 1 Reconfigurable and Evolvable Hardware Fabric Chris Papachristou, Frank Wolff Robert Ewing Electrical Engineering & Computer.
Milestones, Feedback, Action Items Power Aware Distributed Systems Kickoff August 23, 2000.
NETWORKING COMPONENTS Buddy Steele Assignment 3, Part 1 CECS-5460: Summer 2014.
11 CLUSTERING AND AVAILABILITY Chapter 11. Chapter 11: CLUSTERING AND AVAILABILITY2 OVERVIEW  Describe the clustering capabilities of Microsoft Windows.
Cognitive Radio: Next Generation Communication System
UNIT I. EMBEDDED SYSTEM It is an electrical/electro-mechanical system designed to perform a specific function. It is a combination of hardware and software.
CS 546: Intelligent Embedded Systems Gaurav S. Sukhatme Robotic Embedded Systems Lab Center for Robotics and Embedded Systems Computer Science Department.
Evaluating Wireless Network Performance David P. Daugherty ITEC 650 Radford University March 23, 2006.
An Energy-Efficient and Low-Latency Routing Protocol for Wireless Sensor Networks Antonio G. Ruzzelli, Richard Tynan and G.M.P. O’Hare Adaptive Information.
CONTENTS: 1.Abstract. 2.Objective. 3.Block diagram. 4.Methodology. 5.Advantages and Disadvantages. 6.Applications. 7.Conclusion.
5 June 2002DOM Main Board Engineering Requirements Review 1 DOM Main Board Software Engineering Requirements Review June 5, 2002 LBNL Chuck McParland.
WIRELESS INTEGRATED NETWORK SENSORS
A Blackboard-Based Learning Intrusion Detection System: A New Approach
PADS Power Aware Distributed Systems Architecture Approaches – Deployable Platforms & Reconfigurable Power-aware Comm. USC Information Sciences Institute.
  Computer vision is a field that includes methods for acquiring,prcessing, analyzing, and understanding images and, in general, high-dimensional data.
BORDER SECURITY USING WIRELESS INTEGRATED NETWORK SENSORS (WINS) By B.S.Indrani (07841A0406) Aurora’s Technological and Research Institute.
© 2006 Cisco Systems, Inc. All rights reserved.Cisco PublicITE I Chapter 6 1 Creating the Network Design Designing and Supporting Computer Networks – Chapter.
Software Architecture of Sensors. Hardware - Sensor Nodes Sensing: sensor --a transducer that converts a physical, chemical, or biological parameter into.
Energy Efficiency Energy consumption is the most important factor to determine the life of sensor network. since sensors networks has low power resources,
How to minimize energy consumption of Sensors in WSN Dileep Kumar HMCL 30 th Jan, 2015.
Table of contents INTRODUCTION Background Problem Statement Scope of The Research Objective Method DESIGN SYSTEM TESTING AND EVALUATION CONCLUSION.
Introduction to Machine Learning, its potential usage in network area,
Blue eye technology Prepared by VINIT SHAH 08 CE 099.
Seminar On Blue Eyes Submitted By: Ghaytadak Satish Laxman.
Energy-Efficient Communication Protocol for Wireless Microsensor Networks by Wendi Rabiner Heinzelman, Anantha Chandrakasan, and Hari Balakrishnan Presented.
Presentation transcript:

Sluzek 142/MAPLD Development of a Reconfigurable Sensor Network for Intrusion Detection Andrzej Sluzek & Palaniappan Annamalai Intelligent Systems Centre Nanyang Technological University, Singapore

Sluzek 142/MAPLD RATIONALE Wireless sensor networks are to become an important tool for various security and/or surveillance applications. They may be used fully autonomously, but in a more realistic scenario, sensors network support human decisions by providing data that have been preliminarily analyzed, interpreted and prioritized. AIMS To embed a high level of autonomy and intelligence into FPGA-based nodes of multi-sensor networks. To develop a library of FPGA implementations of various mechanisms for data acquisition, processing and intelligent selection. To develop an experimental platform for testing various applications and scenarios.

Sluzek 142/MAPLD DESIGN METHODOLOGY Two levels of sensor nodes First-level sensor nodes with basic sensing devices (proximity, vibration, acoustic, magnetic, etc.), low computational capabilities, and wireless transmission devices. They monitor conditions in the protected zone and act as preliminary detectors of possible intrusions. Second-level sensor nodes built around a higher-performance FPGA controlling an array of cameras. They perform more advanced data processing to confirm/reject the intrusion detections and to further classify the nature of intrusion (before alerting a human operator).

Sluzek 142/MAPLD 20054

Sluzek 142/MAPLD The first-level nodes: Generally use very simple detection technique (e.g. analog signals with binary signal thresholding) with limited (if any) signal processing capabilities. Are continuously active. Upon capturing a predefined combination of sensor signals from the monitored zone, a message is wirelessly transmitted to the second-level nodes (to those close enough to receive the message). Low energy consumption is a crucial issue since very long operational lifetime is expected. No online reprogrammability/reconfigurability is envisaged. Usually are motionless.

Sluzek 142/MAPLD The second-level nodes: The cameras are generally inactive except for the occasional update of the background image. Are activated (capture several image frames) upon receiving a warning message from the first-level nodes. Perform complex image processing operation to confirm suspected intrusions and to classify their nature. In case of detecting a potentially dangerous intrusion, wirelessly transmit the picture of intruder to the higher level in the decision chain. Incorporate an FPGA module and can be online (e.g. wirelessly) reconfigured for different tasks or applications. Peak energy consumption may be high, but the average power requirements is reduced to the level providing long operational lifetime. Motionless or attached to a mobile platform.

Sluzek 142/MAPLD Implementation details: The first-level node incorporates a wireless communication chip, a low-cost microcontroller (performing sensor data acquisition, generating the warning message and interfacing the wireless chip) and the sensors. Battery power supply is provided. A standard communication protocol for low-power wireless networks is used. The second-level node incorporates: (a) the wireless components of the first-level node; (b) a higher-performance FPGA device with external memory and CPLD module; (c) CCD cameras; (d) camera interfaces; Battery power supply for the second-level node is planned, but currently a power-supply adapter is used.

Sluzek 142/MAPLD Implementation details (cont.): In the first model, selected fragments of commercially available development boards (with many redundant features) have been used – encircled red in the figures. Currently, dedicated platforms are built.

Sluzek 142/MAPLD Exemplary methodologies for FPGA-implemented image processing and intrusion detection and classification: 1.Background update (details depend on the type of application). 2.A complicated operation (utilizing methods of mathematical morphology) of extracting the intruder’s silhouette from the background. Minor disturbances of the background (e.g. swaying trees, grass, vibrations of the device, etc.) are ignored. 3.Further analysis of intruder’s silhouette (e.g. using the method of moments and moment invariants that allow a broad classification of intruders in selected applications). 4.Analysis of intruder’s motion using silhouette variations in a sequence of two (or more) images. The moments of silhouette can be used.

Sluzek 142/MAPLD Exemplary methodologies for FPGA-implemented image processing and intrusion detection and classification (cont.): 5.Detection of interest points in the intruder’s silhouettes (under development). 6.Transmission of the intruder’s image to the higher level in the decision chain. 7.Transmission of interest point to the higher level in the decision chain. Identification of particular intruders based on matching transmitted interest points to the database of known intruders (under development).

Sluzek 142/MAPLD In complex scenarios, the amount of data for a human inspection and/or assessment can be very large. In dynamically changing situations, the required reaction time can be very short (if compared to human capabilities).

Sluzek 142/MAPLD A hypothetical display presenting the only suspicious object detected by one of the cameras.

Sluzek 142/MAPLD RE: Background update (details depend on the type of application).

Sluzek 142/MAPLD RE: Extracting the intruder’s image and silhouette from the background.

Sluzek 142/MAPLD RE: Extracting the intruder’s silhouette from the background.

Sluzek 142/MAPLD RE: Further analysis of intruder’s silhouette (allowing a broad classification of intruders in selected applications). Typical approach: using moment invariants

Sluzek 142/MAPLD RE: Analysis of intruder’s motion using silhouette variations in a sequence of two (or more) images. In this example, the intruder is apparently approaching the camera and turning to the left. The speed of motion can be estimated from the relative size of both silhouettes and their intersection.

Sluzek 142/MAPLD RE: Detection of interest points in the intruder’s silhouettes (under development).

Sluzek 142/MAPLD RE: Transmission of the intruder’s image to the higher level in the decision chain (alternative options available).

Sluzek 142/MAPLD RE: Transmission of interest point to the higher level in the decision chain. Identification of particular intruders based on matching transmitted interest points to the database of known intruders (under development).

Sluzek 142/MAPLD OTHER ISSUES Transmission of the image fragments using Advanced encryption standard (AES128) has been developed and implemented in the FPGA for the communication protocol used in the network. Additionally, experiments have been conducted to directly connect R/T devices to FPGA so that proprietary transmission protocols and methods can be used.