- A Maximum Likelihood Approach Vinod Kumar Ramachandran ID: 902 234 6077.

Slides:



Advertisements
Similar presentations
1 ECE 776 Project Information-theoretic Approaches for Sensor Selection and Placement in Sensor Networks for Target Localization and Tracking Renita Machado.
Advertisements

Analysis of variance and statistical inference.
ECG Signal processing (2)
ECE 8443 – Pattern Recognition LECTURE 05: MAXIMUM LIKELIHOOD ESTIMATION Objectives: Discrete Features Maximum Likelihood Resources: D.H.S: Chapter 3 (Part.
Cooperative Multiple Input Multiple Output Communication in Wireless Sensor Network: An Error Correcting Code approach using LDPC Code Goutham Kumar Kandukuri.
Observers and Kalman Filters
Visual Recognition Tutorial
Artificial Learning Approaches for Multi-target Tracking Jesse McCrosky Nikki Hu.
Nov 4, Detection, Classification and Tracking of Targets in Distributed Sensor Networks Presented by: Prabal Dutta Dan Li, Kerry Wong,
Volkan Cevher, Marco F. Duarte, and Richard G. Baraniuk European Signal Processing Conference 2008.
Energy-Efficient Target Coverage in Wireless Sensor Networks Mihaela Cardei, My T. Thai, YingshuLi, WeiliWu Annual Joint Conference of the IEEE Computer.
Location Estimation in Sensor Networks Moshe Mishali.
A Hierarchical Energy-Efficient Framework for Data Aggregation in Wireless Sensor Networks IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, VOL. 55, NO. 3, MAY.
1 On the Performance of Slotted Aloha with Capture Effect in Wireless Networks Arash Behzad and Julan Hsu Professor Mario Gerla CS218 Project UCLA December.
Machine Learning CMPT 726 Simon Fraser University
Lattices for Distributed Source Coding - Reconstruction of a Linear function of Jointly Gaussian Sources -D. Krithivasan and S. Sandeep Pradhan - University.
Arizona State University DMML Kernel Methods – Gaussian Processes Presented by Shankar Bhargav.
Radial Basis Function Networks
Data Selection In Ad-Hoc Wireless Sensor Networks Olawoye Oyeyele 11/24/2003.
EE513 Audio Signals and Systems Statistical Pattern Classification Kevin D. Donohue Electrical and Computer Engineering University of Kentucky.
Binary Variables (1) Coin flipping: heads=1, tails=0 Bernoulli Distribution.
Cooperative spectrum sensing in cognitive radio Aminmohammad Roozgard.
Machine Learning CUNY Graduate Center Lecture 3: Linear Regression.
Isolated-Word Speech Recognition Using Hidden Markov Models
1 Secure Cooperative MIMO Communications Under Active Compromised Nodes Liang Hong, McKenzie McNeal III, Wei Chen College of Engineering, Technology, and.
Template attacks Suresh Chari, Josyula R. Rao, Pankaj Rohatgi IBM Research.
POWER CONTROL IN COGNITIVE RADIO SYSTEMS BASED ON SPECTRUM SENSING SIDE INFORMATION Karama Hamdi, Wei Zhang, and Khaled Ben Letaief The Hong Kong University.
ECE 8443 – Pattern Recognition LECTURE 03: GAUSSIAN CLASSIFIERS Objectives: Normal Distributions Whitening Transformations Linear Discriminants Resources.
Tracking with Unreliable Node Sequences Ziguo Zhong, Ting Zhu, Dan Wang and Tian He Computer Science and Engineering, University of Minnesota Infocom 2009.
Machine Learning Seminar: Support Vector Regression Presented by: Heng Ji 10/08/03.
REVISED CONTEXTUAL LRT FOR VOICE ACTIVITY DETECTION Javier Ram’ırez, Jos’e C. Segura and J.M. G’orriz Dept. of Signal Theory Networking and Communications.
EDGE DETECTION IN COMPUTER VISION SYSTEMS PRESENTATION BY : ATUL CHOPRA JUNE EE-6358 COMPUTER VISION UNIVERSITY OF TEXAS AT ARLINGTON.
Baseband Demodulation/Detection
Fairness-Aware Cooperative Resource Allocation for Self-Healing in SON-based Indoor System Kisong Lee, Student Member, IEEE, Howon Lee, Associate Member,
Energy-Efficient Signal Processing and Communication Algorithms for Scalable Distributed Fusion.
Detection, Classification and Tracking in a Distributed Wireless Sensor Network Presenter: Hui Cao.
A Passive Approach to Sensor Network Localization Rahul Biswas and Sebastian Thrun International Conference on Intelligent Robots and Systems 2004 Presented.
Trade-offs Between Mobility and Density for Coverage in Wireless Sensor Networks Wei Wang, Vikram Srinivasan and Kee-Chaing Chua National University of.
Junfeng Xu, Keqiu Li, and Geyong Min IEEE Globecom 2010 Speak: Huei-Rung, Tsai Layered Multi-path Power Control in Underwater Sensor Networks.
Multiple Antennas Have a Big Multi- User Advantage in Wireless Communications Bertrand Hochwald (Bell Labs)
CHAPTER 5 SIGNAL SPACE ANALYSIS
University of Houston Cullen College of Engineering Electrical & Computer Engineering Capacity Scaling in MIMO Wireless System Under Correlated Fading.
Dr. Sudharman K. Jayaweera and Amila Kariyapperuma ECE Department University of New Mexico Ankur Sharma Department of ECE Indian Institute of Technology,
EE 3220: Digital Communication
Performance Analysis of Complementary Code Keying (CCK) Modulation in a Multi-Path Channel Paul Yang, University of California at Berkeley SURE Program.
The Restricted Matched Filter for Distributed Detection Charles Sestok and Alan Oppenheim MIT DARPA SensIT PI Meeting Jan. 16, 2002.
1 Channel Coding (III) Channel Decoding. ECED of 15 Topics today u Viterbi decoding –trellis diagram –surviving path –ending the decoding u Soft.
ECE 4710: Lecture #31 1 System Performance  Chapter 7: Performance of Communication Systems Corrupted by Noise  Important Practical Considerations: 
Over-fitting and Regularization Chapter 4 textbook Lectures 11 and 12 on amlbook.com.
Elements of Pattern Recognition CNS/EE Lecture 5 M. Weber P. Perona.
Multi-target Detection in Sensor Networks Xiaoling Wang ECE691, Fall 2003.
Spectrum Sensing In Cognitive Radio Networks
Baseband Receiver Receiver Design: Demodulation Matched Filter Correlator Receiver Detection Max. Likelihood Detector Probability of Error.
A Low-Complexity Universal Architecture for Distributed Rate-Constrained Nonparametric Statistical Learning in Sensor Networks Avon Loy Fernandes, Maxim.
Energy-Efficient Signal Processing and Communication Algorithms for Scalable Distributed Fusion.
Distributed Signal Processing Woye Oyeyele March 4, 2003.
Digital Communications I: Modulation and Coding Course Spring Jeffrey N. Denenberg Lecture 3c: Signal Detection in AWGN.
Institute for Experimental Mathematics Ellernstrasse Essen - Germany DATA COMMUNICATION introduction A.J. Han Vinck May 10, 2003.
Part 3: Estimation of Parameters. Estimation of Parameters Most of the time, we have random samples but not the densities given. If the parametric form.
A G3-PLC Network Simulator with Enhanced Link Level Modeling
Deep Feedforward Networks
The Viterbi Decoding Algorithm
LECTURE 09: BAYESIAN ESTIMATION (Cont.)
Computing and Compressive Sensing in Wireless Sensor Networks
LECTURE 03: DECISION SURFACES
Advanced Wireless Networks
Outlier Processing via L1-Principal Subspaces
Where did we stop? The Bayes decision rule guarantees an optimal classification… … But it requires the knowledge of P(ci|x) (or p(x|ci) and P(ci)) We.
EE513 Audio Signals and Systems
Parametric Methods Berlin Chen, 2005 References:
Presentation transcript:

- A Maximum Likelihood Approach Vinod Kumar Ramachandran ID:

Wireless Sensor Networks – Introduction A Network with thousands of tiny sensors deployed in a region of interest to perform a specific task. For example, to detect and classify vehicles moving in a given region Application (1) Battlefield Surveillance (2) Disaster Relief (3) Environmental Monitoring Key Design Issues  Low Battery Power of Sensors Efficient Collaborative Signal Processing Algorithms (CSP) must be developed  Design of proper communication schemes to transmit information to a manager node Philosophy Each Sensor has Limited Sensing and Processing Capabilities But thousands of such sensors can coordinate to achieve a very complex task Main Advantage of Sensor Networks – Ability to accomplish a very complex task with tiny, inexpensive sensors In detection and classification of targets, factors affecting individual decisions  Measurement Noise  Statistical Variability of Target Signals

Multi-Target Classification Objective: To detect and classify the targets present in a region of interest Suppose M distinct targets are possible. Then this becomes a N-ary hypothesis testing problem where N = 2 M For example, when M = 2, four hypotheses are possible H 0 : No target present H 1 : Target 1 alone is present H 2 : Target 2 alone is present H 3 : Both target 1 and target 2 is present Signal Model Signals from all sources are assumed Gaussian Region of interest can be divided into spatial coherence regions (SCRs) Signals obtained from distinct SCRs are independent and signals from sensors with a single SCR are highly correlated Correlated signals within individual SCRs can overcome measurement noise Independent signals across SCRs can overcome statistical variability of target signals

Problem Formulation For M distinct targets, N = 2 M hypotheses possible Probability of m-th target being present = denotes the presence ( = 1) or absence ( = 0 ) of m-th target. Prior probabilities under different hypotheses is given by where is the binary representation of integer j. Signals from different targets are assumed Gaussian with m-th target having a mean of zero and covariance matrix Assume there are G SCRs (independent measurements). The N-ary hypothesis testing problem is where measurement noise is added to the signal vector

Problem Formulation (contd…) Under H j, the probability density function at the k-th SCR is: and the G measurements are i.i.d. Basic Architecture for Multi-target Classification

Classification Strategies Centralized Fusion: Data from all SCRs are directly combined in an optimal fashion. Advantage: Serves as a benchmark as it is optimal. Disadvantage: Heavy communication burden because all data have to be transmitted to manager node. Decision Fusion: Individual SCRs make the decision and the decisions themselves are combined in an optimal manner in the manager node Advantage: Very low communication burden because only decisions are transmitted Disadvantage: May not be as reliable as centralized fusion Optimal Centralized Classifier: Decides the correct hypothesis according to This can also be written as

Performance of Optimal Classifier Note that each SCR has to transmit N likelihoods to the manager node. The probability of error of the optimal centralized classifier can be bounded as [1] Thus the probability of error goes to zero as the number of independent measurements G goes to infinity provided the Kullback-Leibler distances between any pairwise pdfs are strictly positive [1] J.Kotecha, V.Ramachandran, A.Sayeed, “Distributed Multitarget Classification in Wireless Sensor Networks”, IEEE Journal on Selected Areas in Commn., December 2003

Local Classifiers Local decisions are made at the individual SCRs based on the single measurement in that SCR. The local decisions are communicated to the manager node that makes the final optimal decision. These classifiers are also called distributed classifiers. Since only the decisions are transmitted, this comes as a big relief to the network in terms of the communication burden Optimal Local Classifier The optimal local classifier in the k-th SCR makes the decision as The pmfs under different hypothesis are characterized by: The optimal local classifier need to calculate N likelihoods for each decision and this grows exponentially with M targets.

Sub-optimal Local Classifiers To circumvent exponential complexity, the suboptimal local classifiers conduct M tests, one for each target for the presence or absence of the target Partition the set of hypotheses into two sets, and where contains those hypotheses in which the m-th target is present and contains those hypotheses in which it is absent Define Then The feature vector will be distributed as a weighted sum of Gaussians It has been shown in [1] that the suboptimal classifiers give perfect classification in the limit of large G, the number of independent measurements

Sub-optimal Local Classifiers (Contd…) Mixture Gaussian Classifer (MGC) For m = 1,…, M, let ( ) denote the value of the m-th binary hypothesis test between and in the k-th SCR = 1 if or = 0 otherwise For the simple case of M = 2, = 1 if It can be observed that the above test is a weighted sum of two tests Single Gaussian Classifier (SGC) This classifier approximates the pdfs as The value of the m-th test in k-th SCR is one if

Fusion of Local Decisions at the Manager Node Ideal Communication Links  The classifier at the final manager node makes the decision as:  The above expressions apply to all three local classifiers; the only difference is that the different local classifiers induce different pmfs Noisy Communication Links In noisy channels, each SCR sends an amplified version of its local hard decision. The hard decisions are corrupted by additive white Gaussian noise (AWGN). The manager node makes the final decision as:

Simulations Data Source: DARPA SensIT program Simulation Tool: MATLAB Results for Two Targets (M = 2) – Probability of Error versus G (independent Measurements) Measurement SNR = -4 dB Communication SNR = 0 dB, 10 dB

Measurement SNR = 10 dB Communication SNR = 0 dB, 10 dB Chernoff Bounds for M = 2 Targets with Ideal Communication Channel

Results for M = 3 Targets – Probability of Error versus G (independent measurements) Measurement SNR = -4 dB Communication SNR = 0 dB, 10 dB Measurement SNR = 10 dB Communication SNR = 0 dB, 10 dB

Observations In all cases, the error probabilities of the optimal centralized classifier serves as the lower bound and hence this is the best classifier possible. The key observation is that for all the classifiers, the probability of error goes down exponentially with the number of independent measurements, G. (Note that the plots shown are in the log scale). This indicates that we can attain reliable classification by combining a relatively moderate number of much less reliable independent local decisions. The performance improves with increasing measurement SNRs for all classifiers For any distributed classifier, the probability of error is higher with noisy communication channel than with ideal communication links. The performance of the mixture Gaussian classifier (MGC) is close to the optimal distributed classifier in all cases thereby making it an attractive choice in practice. The performance of the single Gaussian classifier (SGC) is worse compared to the MGC and the difference is large at higher measurement and communication SNRs In the simulations performed, the KL distances for all pairwise hypotheses were found to be positive and hence perfect classification is possible in the limit of large G. The Chernoff bounds shown match the error exponent fairly but exhibit an offset. The performance of all the classifiers is worse for M = 3 (eight hypotheses) case than for M = 2 (4 hypotheses) case The difference between the MGC and the optimal distributed classifier seem to increase for the three target case.

Conclusions The performance of the optimal centralized and distributed classifiers with exponential complexity have been compared with the sub-optimal distributed classifiers with linear complexity Several issues warrant further investigation such as: Signal model does not assume path loss in sensing measurements. When path loss is considered, the G measurements will be independent but not identically distributed. The path loss will limit the number of independent measurements. Relationship between the number of targets and the dimensionality of the feature vector. Increasing the feature vector dimension may result in improved performance for higher number of targets The sub-optimal CSP algorithms can be combined with other sub-optimal approaches such as tree-based classifiers to develop a classifier with even lower complexity