# Register now to access 7 million high quality study materials (What's Course Hero?) Course Hero is the premier provider of high quality online educational resources. With millions of study documents, online tutors, digital flashcards and free courseware, Course Hero is helping students learn more efficiently and effectively. Whether you're interested in exploring new subjects or mastering key topics for your next exam, Course Hero has the tools you need to achieve your goals.

20 Pages

### s2005_benhong

Course: EE 597, Fall 2009
School: Iowa State
Rating:

Word Count: 1091

#### Document Preview

approach Non-parametric in detection problem Zhang Benhong Outline Introduction Parametric approach: T2 test Non-parametric approach: bootstrap, empirical likelihood test Bai's test (suitable for high dimensional problems) Conclusion Introduction Normally the distribution of the measurement should be known to achieve optimal detection performance In practice the exact distribution may not be available...

Register Now

#### Unformatted Document Excerpt

Coursehero >> Iowa >> Iowa State >> EE 597

Course Hero has millions of student submitted documents similar to the one
below including study guides, practice problems, reference materials, practice exams, textbook help and tutor support.

Course Hero has millions of student submitted documents similar to the one below including study guides, practice problems, reference materials, practice exams, textbook help and tutor support.
approach Non-parametric in detection problem Zhang Benhong Outline Introduction Parametric approach: T2 test Non-parametric approach: bootstrap, empirical likelihood test Bai's test (suitable for high dimensional problems) Conclusion Introduction Normally the distribution of the measurement should be known to achieve optimal detection performance In practice the exact distribution may not be available Non-parametric solutions are introduced and their performances are evaluated asymptotically Problem and Notations Let x = ( x1 , x2 ,..., xN )T be N i.i.d. measurements, each xi is p 1 random vector with mean and variance , denote: N N S = i =1 ( xi - x )( xi - x )T / N - 1 x = i =1 xi / N be the sample mean and be the sample covariance Our goal is to test two hypotheses: H 0 : = 0 H1 : 0 using Neyman-Pearson criterion: Fix PF= and try to achieve largest available PD T2 test The test statistic is set to be: T 2 = N ( x - 0 )T S - 1 ( x - 0 ) and it is well known that when = 0, and the data xi is normally distributed, N-p T 2 ~ Fp , N - p p( N -1) Therefore, the following rule is applied to achieve maximum PD at PF=: T 2 < Fp ,( N - p ), H 0 2 T > Fp ,( N - p ), H1 T2 test (cont.) T2 test is exact ML test under normal data T2 is still asymptotically F distributed when p<<N, without the requirement of data distribution When p is comparable with N, or both p and N are small, the distribution of T2 can not be decided and the performance T2 test will degrade seriously. Especially, when p>N, T2 test can not be used since the sample covariance matrix S is not invertible Bootstrap test Still set the test statistic to be T2 We simulate the distribution of T2 by performing the following steps: 1. Generate resample of size N, by uniformly sampling {x, 0-x} with replacement, denote such resample as x* = {xi*}iN=1 2. Compute T2 based on x*, denote as T*2 {Ti*2 }iB=1 3. Repeat 1,2 B (big) times, the histogram of asymptotically represents the pdf of T2 *2 T(1) T(*2 ... T(*2) {Ti*2 }iB=1 2) B Sort as , bootstrap test is performed as: *2 T 2 < T([ B (1- )]) H 0 2 *2 T > T([ B (1- )]) H1 Bootstrap test (cont.) Bootstrap use Monte Carlo approach to estimate the -quantile of the test statistic, thus is more accurate than original T2 test when T2 is not F distributed When computing T*2 in step 2, S* may not be invertible even if p<N, due to repeated resamples It is still not able to handle p>N case Bootstrap can be considered as a calibration method Empirical likelihood (EL) test In EL test, each xi is assigned multinomial probability pi for i=1,2,...,N. The log likelihood function of mean 0 is: L( 0 ) = max i =1 ln( Npi ) N p subject to the following constraint: N i =1 pi ( xi - 0 ) = 0, N pi 0, i =1 pi = 1 and the log likelihood ratio is defined ^as: l ( 0 ) = -2( L( 0 ) - L( )) EL test (cont.) where L( ) = max L( ) 0 N i=1 pi ( xi - 0 ) = 0 , It is clear that without the constraint L = max i =1 ln Npi = 0 N p ^ at pi=1/N, (i=1,2,...,N), resulting = x ^ To compute L(0), we apply Lagrange multipliers method: f (p) = i =1 ln Npi - N i =1 pi ( xi - 0 ) - (i =1 pi - 1), N N N f (p) / p = 1 / p - N ( x - ) - i i i 0 N g (p) = i =1 pi ( xi - 0 ) = 0 N h(p) = i =1 pi - 1 = 0 EL test (cont.) The group equation has solutions at: = N, xi - 0 1 1 = 0, and pi = i =1 1 + ( x - ) N 1 + ( xi - ) i 0 N The solution of may be found by numerical searching the second equation. Note that the second equation does not have solution when 0 is not located within the convex hull of x, therefore, EL method is not able to give the exact likelihood under such scenario EL test (cont.) In the previous Lagrange multipliers method, the restriction of pi is not considered and therefore the final solution may not be valid. We introduce pseudo-logarithm function to resolve this issue: log( z ), log* ( z ) = log(1 / N ) - 1.5 + 2 Nz - ( Nz ) 2 / 2 if z 1 / N if z < 1 / N Using the pseudo-log function to replace the ordinary log function in the likelihood expression, the value of L(0) does not change at the true solution of pi while 0 pi 1 is guaranteed EL test (cont.) 2 p, It can be proved that l(0) is asymptotically distributed as therefore EL test is performed as the following: 2 l ( 0 ) < p , H 0 2 l ( 0 ) > p , H 1 EL test does not require the measurement distribution 2 p For small N, l(0) may not be well approximated by distribution Bootstrap method can be used here for threshold calibration Bai's test Ordinary T2 test degrades drastically with the increase of dimension p, when p / N = y (0,1) . This is due to the inaccurate estimation of , which is composed of p2 nuance parameters Bai's test totally discards the information of covariance by using the following simple test statistic: M N = ( x - 0 )T ( x - 0 ) - 1 trS N it is proved that MN is asymptotically Gaussian distributed with 0 mean and variance: 2 M = 2 tr ( 2 ) ( N - 1) 2 Bai's test (cont.) where a ratio-consistent estimator of tr(2) is given as: ( N -1) 2 1 B = ( trS 2 - ( trS ) 2 ) ( N +1)( N - 2) N -1 2 The test is formulated as: M N < z H 0 M M N > z H 1 M Bai's test does not require data distribution Bai's test is robust with the inc...

Find millions of documents on Course Hero - Study Guides, Lecture Notes, Reference Materials, Practice Exams and more. Course Hero has millions of course specific materials providing students with the best way to expand their education.

Below is a small sample set of documents:

Iowa State - CE - 326
AIR POLLUTIONCE 326 Principles of Environmental Engineering Prof. Tim Ellis January 16, 2009Announcements No class Monday due to holiday Wednesday lab meet at the ISU PowerPlant see map on course website Air Pollution ProblemsChapter 7: 2
Iowa State - EE - 590
EE 590 Reliability (LOLE) Evaluation for Generation &amp; Transmission AdequacyBrandon Heath October 27th 2008Generation &amp; Transmission (G&amp;T) Adequacy issues throughout history November 9, 1965 The largest blackout to this date in history occurred,
Iowa State - EE - 590
EE590 Transmission Planning Projects and Cost AllocationMing NI Economic Studies, Midwest ISOTransmission Planning Projects Reliability Projects:Identified either in the periodically performed Baseline Reliability Study, or in Facilities Studie
Iowa State - CE - 421
CE421/521 Environmental BiotechnologyNitrogen and Phosphorus Cycles Lecture 91108 Tim EllisBiogeochemcial Cycles (C, N, P, &amp; S) composition of b_ cell (molar formula: C5H7O2N with P 1/5 of the N requirement) limiting nutrients are _ and __
Iowa State - EE - 554
Classical Model 1.0 Assumptions We will cover Sections 2.5, 2.5.1 (but not, yet, 2.5.2, 2.6), and 2.7. Your text, section 2.5, considers a very simplified representation of a synchronous machine, given in Fig. 1.d X'E = E Fig. 1VtIn this m
Iowa State - EE - 554
Equal Area Criterion 1.0 Development of equal area criterion As in previous notes, all powers are in per-unit. I want to show you the equal area criterion a little differently than the book does it. Let's start from Eq. (2.43) in the book.2 H d 2 =
Iowa State - EE - 458
Unit Commitment 3 Illustrations1.0 Introduction Recall our UC problem formulation. However, there was an error in it in that the shutdown variable xij only appeared in the inequality zit zit 1 xit . Therefore, if zit and zit-1 are both zero (whic
Iowa State - EE - 458
Review of Optimization Basics 1.0 IntroductionAt the end of our last discussion (see notes on Cost Curves), we considered generator types that had non-convex cost curves. These included all steam plants that have multiple valve points. It also incl
Iowa State - EE - 590
Real-Time Electricity Markets 1.0 Two-settlement system Material from this section was adapted from [1]. The electricity markets in the US are all two-settlement systems. That is, they are comprised of two interconnected markets, each of which result
Iowa State - EE - 590
Economics of Traditional Planning Methods 1.0 Introduction These notes are partly adaptations of information from four sources in the bibliography [1], [2], [3, ch. 5], with some information obtained from a few other sources also listed in the biblio
Iowa State - EE - 458
Duality #1 1.0 Second iteration for HW problem Recall our LP example problem we have been working on, in equality form, is given below. max F = 3 x1 + 5 x2s.t. x1 2 x2 3 x1 + 2 x2 + x3 + x4 + x5 =4 = 12 = 18x1 0, x2 0, x3 0, x4 0, x5 0 which
Iowa State - EE - 590
Transmission Line Design Information In these notes, I would like to provide you with some background information on AC transmission lines that may be useful to you in your project. AC Transmission Line Impedance Parameters AC transmission is done th
Iowa State - EE - 458
Solving Linear Programs 1.0 Basic form We go back to the form of the basic optimization problem we have considered, which is min f ( x ) s.t. h( x ) = c (1) g ( x)&lt;b We recall that a linear program (LP) requires all functions f, h, and g to be linear
Iowa State - EE - 458
Introduction to Economics: Consumers Surplus 1.0 Introduction Economics is clearly important to electricity markets, because it was economic principles that motivated them in the first place. And so it is appropriate in a course like EE 458 to introd
Iowa State - EE - 458
EE 458 Homework Assignment #1 Due Wednesday, January 23, 2008 Each person has been assigned into a group; you can find your group from the EE 458 home page located at http:/home.eng.iastate.edu/~jdm/ee458/index.htm (see Base Groups link). Each group
Iowa State - EE - 458
Unit Commitment 1 Relation to DAM and Problem Formulation1.0 Introduction We have, at the beginning of the course, discussed the day-ahead market (DAM). In these notes, we will study the main tool used to implement the DAM, which is the security-co
Iowa State - EE - 590
EE 590F Course Project, Due Dec 12, 2008 A. Transmission Planning: The objective of Part A of this project is to design a least-cost transmission 30-year plan for the US capable of moving electric energy from the wind-intense regions to major load ce
Iowa State - EE - 554
Multi- machine Systems 1.0 Introduction and assumptions We have so far studied the one-machine-infinite bus and the two-machine system. Now we extend analysis to a multi- machine system. We will revisit this topic later in the course when we have mor
Iowa State - EE - 458
Introduction to CPLEX 1.0 Overview There are a number of commercial grade LP solvers available. An excellent survey of such surveys can be found at http:/lionhrtpub.com/orms/surveys/LP/LP-survey.html. You can also find a lot of free open source solve
Iowa State - EE - 554
Numerical Methods 1.0 Problem set-up We previously showed that we may write the swing equation for a single machine as a pair of first- order differential equations, according to: =Re2H[ Pm - Pe ( (t )] =(1) (2)Here,Pe(t)isgivenby
Iowa State - EE - 458
Name (1 pt): _EE 458, Economic Systems for Electric Power Planning, Exam 1, Spring 2008, Dr. McCalley Closed book, Closed Notes, No Calculator 1. (24 pts) Consider the generator characteristic given below.a. (6 pts) Compute the maximum efficiency
Iowa State - EE - 458
Three Bus Power Flow Analysis 1.0 IntroductionIn discussions that you will have in the next few weeks, you will make reference to the power system diagram of Fig. 1, where G denotes generators and C denotes consumers.Fig. 1 You will use the notat
Iowa State - EE - 590
HW1, EE 590F, Power System Planning August 27, 2008, Dr. McCalley, Due Monday 5:00 pm, September 8 There is a great deal of talking going on these days about energy. Some samples: Barack Obama (senator and presidential candidate), ABC News, August 4,
Iowa State - EE - 590
Sensitivities1.0 IntroductionOperation of the Eastern Interconnection has become heavily reliant on using the so-called Interchange Distribution Calculator (IDC). This is an internet-accessed system that interfaces with OASIS and allows market par
Iowa State - EE - 573
&lt;html&gt;&lt;center&gt;&lt;head&gt;&lt;TITLE&gt;ISU EE 573 Exam 1 - S98&lt;/TITLE&gt;&lt;/head&gt;&lt;H1&gt;ISU EE 573 SPRING 2000 Exam 1&lt;/H1&gt;&lt;BODY bcolor=&quot;#FFFFFF&quot;&gt;&lt;img src=http:/www.public.iastate.edu/~stat/images/rainbow.gif&gt;&lt;/img&gt;&lt;/center&gt;&lt;p&gt;&lt;PRE&gt;This exam is concerned wi
Iowa State - EE - 573
&lt;html&gt;&lt;center&gt;&lt;head&gt;&lt;TITLE&gt;ISU EE 573 Selected HW / Exam Solutions&lt;/TITLE&gt;&lt;/head&gt;&lt;H1&gt;ISU EE 573 Selected HW / Exam Solutions&lt;/H1&gt;&lt;BODY bcolor=&quot;#FFFFFF&quot;&gt;&lt;img src=http:/www.public.iastate.edu/~stat/images/rainbow.gif&gt;&lt;/img&gt;&lt;/center&gt;&lt;p&gt;&lt;/cent
Iowa State - EE - 573
&lt;html&gt;&lt;center&gt;&lt;head&gt;&lt;TITLE&gt;ISU EE 573 Project S98&lt;/TITLE&gt;&lt;/head&gt;&lt;H1&gt;ISU EE 573 SPRING 1998 Project&lt;/H1&gt;&lt;BODY bcolor=&quot;#FFFFFF&quot;&gt;&lt;img src=http:/www.public.iastate.edu/~stat/images/rainbow.gif&gt;&lt;/img&gt;&lt;/center&gt;&lt;p&gt;&lt;H1&gt;Requirements for Midterm Pro
Iowa State - EE - 573
&lt;html&gt;&lt;center&gt;&lt;head&gt;&lt;TITLE&gt;ISU EE 573 Homework S2001&lt;/TITLE&gt;&lt;/head&gt;&lt;H1&gt;ISU EE 573 SPRING 2001 Homeworks&lt;/H1&gt;&lt;BODY bcolor=&quot;#FFFFFF&quot;&gt;&lt;img src=http:/www.public.iastate.edu/~stat/images/rainbow.gif&gt;&lt;/img&gt;&lt;/center&gt;&lt;p&gt;&lt;UL&gt;&lt;LI&gt;&lt;A HREF=&quot;#MATLABh
Iowa State - EE - 573
The following Matlab code was used to investigate the claim that the random number generator randn generates samples of a ZERO-MEAN random variable. The intent here is to give you an idea of how a specific analysis might proceed, and to familiarize y
Iowa State - EE - 573
Homework 1 Spring09EE/ME/AERE 573 Due 1/21/09 Name_ 1. (20 pts) Consider the system described by the following differential equation: y + 0.2 y + 100 y = 100 x ; y (0) = yo y (0) = vo (a)(5 pts) Give all the system parameters, as they apply to
Iowa State - STAT - 330
Homework 6 STAT 330 S'04Name_1. The purpose of this problem is to investigate just how good an estimator of the true mean the sample mean is. To this end: (a) Compute the mean and variance of a Bernoulli(p) random variable. (b) Use the linearity
Iowa State - STAT - 330
Homework #2 STAT330 1. 2. 3. 4. 5. Book p. 91 #1 Book p.91 #5 Book p.91 #7 Book p.91 #8 Book p.92 #10Spring 2004Due Monday 2 February
Iowa State - STAT - 330
Homework #4 STAT 330 S'04 Name_ 1. p.157 #2 2. p.157 #4 3. p.190 #3 2 4. For X Normal(0,1), find the pdf of Y=X 5. For X Exponential(), Find the conditional pdf of X|X&gt;xo N 2 6. For { X k }k =1 where X k ~ N ( K , k ) and assumed to be mutually ind
Iowa State - STAT - 330
1 Homework 7 STAT 330 S'04 Practice for Exam #2 STAT 330 Exam 2 11/2/01 Name_This exam consists of two conceptual parts, namely equivalent events, and expectations of functions of random variables. Below are some useful related definitions and fact
Iowa State - AERO - 361
DBX BUILT IN ALIAS SETTINGSTYPE alias in dbx to see them a assignb stop atbp stop inbx interceptc contd downdel deletedir directorye filef frameg gotoh historyj st
Iowa State - AERO - 361
Matlab Advanced helpListed below are only few of many matlab commands/ functions. Use the online help facility, or consult the Matlab User's Guide, for more detailed information on the commands and functions. There are many functions beyond these, i
Iowa State - AERO - 361
TMQUICK REFERENCE CARDw Op en Sa ve Pri nt Se nd as att Se ac nd hm as en lin t Re k ge ne ra te Fin dsp in ce ing nte Zo mo r om de in Zo om ou Re t fit Sa ve dv iew La ye s rs Vi ew ma na W ge ire r fra me Hi dd en lin No e hid de Sh nl ad in
Iowa State - AERO - 361
Some basic UNIX commands you will need when developing Web pages Words in bold-italics are commands and should be typed as they are printed. Words in italics should be substituted with the filename or directory you wish to work with. Remember that
Iowa State - AERO - 361
Debugging with GDBThe gnu Source-Level Debugger Ninth Edition, for GDB version 5.3 December 2001Richard Stallman, Roland Pesch, Stan Shebs, et al.(Send bugs and comments on GDB to bug-gdb@gnu.org.) Debugging with GDB TEXinfo 2002-06-04.06Copyr
Iowa State - AERO - 361
GAMSA USER'S GUIDEby: Anthony Brooke David Kendrick Alexander Meeraus Ramesh Raman Tutorial by: Richard E. RosenthalDecember 1998 GAMS Development Corporation, 1998GAMS Development Corporation 1217 Potomac Street, N.W. Washington, DC 20007, USA
Iowa State - AERO - 361
Programming in Maple: The Basics.Michael Monagan Institut fr Wissenschaftliches Rechnen u ETH-Zentrum, CH-8092 Zrich, Switzerland u monagan@inf.ethz.chAbstract This is a tutorial on programming in Maple. The aim is to show how you can write simple
Iowa State - AERO - 361
Fortran Library ReferenceSun ONE Studio 8Sun Microsystems, Inc. 4150 Network Circle Santa Clara, CA 95054 U.S.A. 650-960-1300Part No. 817-0928-10 May 2003 Revision A Send comments about this document to: docfeedback@sun.comCopyright 2003 Sun M
Iowa State - AERO - 361
OpenMP API User's GuideSunTM ONE Studio 8Sun Microsystems, Inc. 4150 Network Circle Santa Clara, CA 95054 U.S.A. 650-960-1300Part No. 817-0933-10 May 2003, Revision A Send comments about this document to: docfeedback@sun.comCopyright 2003 Sun
Iowa State - AERO - 361
Intel Debugger (IDB) ManualLegal NoticesCopyright 2002 Intel Corporation, portions 2001 Compaq Information Technologies Group, L.P. All Rights Reserved Disclaimer: Information in this document is provided in connection with Intel products. No lic
Iowa State - AERO - 361
UMass-Lowell PTC Partnershiphttp:/ptc.servehttp.comTutorial 2: Pro/E Wildfire Modeling and Drawing TutorialDept. of Mechanical Engineering Mechanical Design 22.322 Written By: Chris Morand and Xiang Li Objectives: After completing this tutorial,
Iowa State - AERO - 361
Parametric Technology CorporationPro/ENGINEER WildfireTM New Users OverviewFebruary 2003Copyright 2002 Parametric Technology Corporation. All Rights Reserved.User and training documentation from Parametric Technology Corporation (PTC) is subj
Iowa State - AERO - 361
METBD 410 Surface Model Assembly Release 20001 The goal of this lab is to take the new fuselage; the old wing (unless yours is &quot;fair&quot;), &quot;pull out&quot; a tail, [add a separate cockpit canopy and apply colors to individual surfaces] as well as doing some d
Iowa State - AERO - 361
INTRODUCTION TO Pro/CablingTM Pro/ENGINEER R2000iSubject: Pro/CABLING Lesson #1 Introduction to Cabling Topics Covered:1. 2. 3. 4. 5. 6. Terms you need to know Creating a harness Creating a spool Creating a wire How to designate components How to
Iowa State - AERO - 361
*Frotime Tutorials** Last Date Modified - 09/18/01 * Readme file - SU1_2001 - Intro To Pro/SURFACE #1*INSTRUCTIONSTo properly use this tutorial, please do the following:(1) Create a new directory on your hard drive called SU1_2001.(2)
Iowa State - AERO - 361
Chapter 1Filesystem EssentialsIn this chapter, we will learn how to master les and lesystems. This is a very important aspect of Linux , and is used constantly.1.1The Linux Virtual Filesystem (VFS)All les in Linux are accessible from a singl
Iowa State - AERO - 361
Chapter 1Shell ScriptingThere's nothing more aggravating than having to type out long commands over and over again. Shell scripts are simple text files that list shell commands into a convenient &quot;tool&quot; which you can use more easily than typing in
Iowa State - AERO - 361
Chapter 1The Linux EnvironmentIn Linux and UNIX , you carry many local attributes that control how your immediate shell interface interacts with the system. These attributes are called Shell and Environment Variables, and they are critical to Linu
Iowa State - AERO - 361
Chapter 1Introduction to LinuxLinux is a computer operating system originally developed by Linus Torvalds as a research project. There is some interesting history about the rapid Linux evolution, but suffice it to say, Linux has come a long way in
Iowa State - AERO - 361
Chapter 1Process ControlIn this chapter we will learn how to control your processes both interactively and non-interactively. It is very important to maintain control of your system and manage unruly processes.1.1Creating Foreground and Backgr
Iowa State - AERO - 361
CALLING FORTRAN SUBROUTINES FROM MATLABFRITZ KEINERT DEPARTMENT OF MATHEMATICS IOWA STATE UNIVERSITY AMES, IA 50011 KEINERT@IASTATE.EDUContents 1. Introduction 2. Calling Fortran from Matlab Case Study 1: DGAMMA Case Study 2: CGAMMA Case Study 3:
Iowa State - AERO - 361
MATLAB MANUAL AND INTRODUCTORY TUTORIALSIvan Graham Mathematical Sciences, University of BathJanuary 28, 2003This manual provides an introduction to MATLAB with exercises which are specically oriented to the MATLAB service provided by Bath Unive
Iowa State - AERO - 361
Wing Aerodynamics AnalysisWing DefinitionWe will develop a model for a 3D wing geometry with sweep, taper, and twist. The airfoil section used to construct the wing is arbitrary. Consider the wing shown below:Figure 1z y ctip rootr V cho
Iowa State - AERO - 361
Iowa State - AERO - 361
Once the bow shock off the nacelle cowling strikes the lower wall of the compression chamber it sets off aseries of shock waves that are reflected off the upper and lower wall. The shape of the nose coneand the shape of the nacelle cowling affects
Iowa State - AERO - 361
/Intel Fortran Compiler 9.0 for Linux* Release Notes/ Contents * Overview &lt;#Overview&gt; * Changes &lt;#NewFeatures&gt; * System Requirements &lt;#SystemReq&gt; * Installation &lt;#Install&gt; * Known Issues &lt;#Limitations&gt; * Technical
Iowa State - AERO - 90
/Intel Fortran Compiler 9.0 for Linux* Release Notes/ Contents * Overview &lt;#Overview&gt; * Changes &lt;#NewFeatures&gt; * System Requirements &lt;#SystemReq&gt; * Installation &lt;#Install&gt; * Known Issues &lt;#Limitations&gt; * Technical