FUZZY CONTROL. Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2, IRELAND Nov 15-16th, 2011

Size: px
Start display at page:

Download "FUZZY CONTROL. Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2, IRELAND Nov 15-16th, 2011"

Transcription

1 : Mamdani & akagi-sugeno Controllers Khurshid Ahmad, Professor of Comuter Science, Deartment of Comuter Science rinit College, Dublin-, IRELAND Nov 5-6th, 0 htts:// Control heor? he term control is generall defined as a mechanism used to guide or regulate the oeration of a machine, aaratus or constellations of machines and aaratus. Control heor? An Inut/Outut Relationshi

2 Control heor? An Inut/Outut Relationshi IDENIFIED using Fuzz Logic Control heor? An Inut/Outut Relationshi IDENIFIED using Fuzz Logic 5 Control heor? icall, rules contain membershi functions for both antecedents and consequent. Argument is that the consequent membershi function can be simlified this argument is based on a heuristic that oerators in a control environment divide the variable sace sa, error, change in error and change in control into PARIIONS; Within each artition the outut variable is a simle, often linear function of the inut variables and not membershi functions 6

3 Control heor? icall, rules contain membershi functions for both antecedents and consequent. Mamdani Controller If ek is ositivee and ek is ositive e then uk is ositive u akagi-sugeno Controllers: If ek is ositivee and ek is ositive e then uk αek+ß ek+δ; α, ß and δ are obtained from emirical observations b relating the behaviour of the errors and change in errors over a fied range of changes 7 in control LERS akagi-sugeno Controllers According to Yager and Filev, a known disadvantage of the linguistic modules is that the do not contain in an elicit form the objective knowledge about the sstem if such knowledge cannot be eressed and/or incororated into fuzz set framework' 99:9. icall, such knowledge is available often: for eamle in hsical sstems this kind of knowledge is available in the form of general conditions imosed on the sstem through conservation laws, including energ mass or momentum balance, or through limitations imosed on the values of hsical constants. 8 LERS akagi-sugeno Controllers omohiro akagi and Michio Sugeno recognised two imortant oints:. Comle technological rocesses ma be described in terms of interacting, et simler sub rocesses. his is the mathematical equivalent of fitting a iece-wise linear equation to a comle curve.. he outut variables of a comle hsical sstem, e.g. comle in the sense it can take a number of inut variables to roduce one or more outut variable, can be related to the sstem's inut variable in a linear manner rovided the outut sace can be subdivided into a number of distinct regions. akagi,., & Sugeno, M Fuzz Identification of Sstems and its Alications to Modeling and Control. IEEE ransactions on Sstems, Man and Cbernetics. Volume No. SMC-5 No

4 LERS akagi-sugeno Controllers akagi-sugeno fuzz models have been widel used to identif the structures and arameters of unknown or artiall known lants, and to control nonlinear sstems. 0 LERS akagi-sugeno Controllers Mamdani stle inference: he Good News: his method is regarded widel for caturing eert knowledge and facilitates an intuitivel-lausible descrition of knowledge; he Bad News: his method involves the comutation of a two-dimensional shae b summing, or more accuratel integrating across a continuousl varing function. he comutation can be eensive. LERS akagi-sugeno Controllers Mamdani stle inference: he Bad News: his method involves the comutation of a twodimensional shae b summing, or more accuratel integrating across a continuousl varing function. he comutation can be eensive. For ever rule we have to find the membershi functions for the linguistic variables in the antecedents and the consequents; For ever rule we have to comute, during the inference, comosition and defuzzification rocess the membershi functions for the consequents; Given the non-linear relationshi between the inuts and the outut, it is not eas to identif the membershi functions for the linguistic variables in the consequent

5 LERS akagi-sugeno Controllers Literature on conventional control sstems has suggested that a comle non-linear sstem can be described as a collection of subsstems that were combined based on a logical Boolean switching sstem function. In realistic situations such disjoint cris decomosition is imossible, due to the inherent lack of natural region boundaries in the sstem, and also due to the fragmentar nature of available knowledge about the sstem. LERS akagi-sugeno Controllers akagi and Sugeno 985 have argued that in order to develo a generic and simle mathematical tool for comuting fuzz imlications one needs to look at a fuzz artition of fuzz inut sace. In each fuzz subsace a linear inutoutut relation is formed. he outut of fuzz reasoning is given b the values inferred b some imlications that were alied to an inut. LERS akagi-sugeno Controllers akagi and Sugeno have described a fuzz imlication R as: R: if is A, k is A k then g,, k 5 5

6 A solution for the coefficients of the consequent in SK Sstems Rule : is HEN + COMPOSIION *[ 0 + ] here are two unknowns: 0 and. So we need two simultaneous equations for two values of, sa and, and two values of and ; 6 A solution for the coefficients of the consequent in SK Sstems Consider a two rule sstem: Rule : Rule : is is HEN HEN + COMPOSIION *[ + ] + *[ + *[ 0 + ] + *[ 0 + ] + *[ + ] + *[ + ] ] 0 7 A solution for the coefficients of the consequent in SK Sstems here are unknowns 0,, 0,, so we need equations. And, these can be obtained from observations comrising diffierent values of and *[ + ] + *[ + ] Four values of * * + * + * * + * 0 0 0,,, and for each, will haveavalue + * * + * * 8 + * * 6

7 7 9 A solution for the coefficients of the consequent in SK Sstems here are unknowns 0,, 0,, so we need equations. And, these can be obtained from observations comrising diffierent values of and * * * * * * * * * * * * * *,,,, ] *[ ] *[ haveavalue will each for and of Four values 0 A solution for the coefficients of the consequent in SK Sstems here are unknowns 0,, 0,, so we need equations. [ ] [ ] [ ] [ ] [ ] [ ] Y P P Y 0 0 ] [ * * * * * * * * A solution for the coefficients of the consequent in SK Sstems akagi and Sugeno have a generalised the method to an n-rule, m-arameter sstem; and b claim that this method of identification enables us to obtain just the same arameters as the original sstem, if we have a sufficient number of noiseless outut data for identification akagi and Sugeno, 985:9. [ ] [ ] [ ] [ ] [ ] [ ] Y P P Y 0 0 ] [ * * * * * * * *

8 A solution for the coefficients of the consequent in SK Sstems In order to determine the values of the arameters in the consequents, one solves the LINEAR sstem of algebraic equations and tries to minimize the difference between the ACUAL outut of the sstem Y and the simulation [] [P] : [ Y ] [ ] [ P] ε A solution for the coefficients of the consequent in SK Sstems In order to determine the values of the arameters in the consequents, one solves the LINEAR sstem of algebraic equations and tries to minimize the difference between the ACUAL outut of the sstem Y and the simulation [] [P] : [ Y ] [ ] [ P] ε LERS akagi-sugeno Controllers akagi and Sugeno have described a fuzz imlication R as: R: if is A, k is A k then g,, k, where: A zero order akagi-sugeno Model will be given as R: if is A, k is A k then k 8

9 Knowledge Reresentation & Reasoning: he Air-conditioner Eamle Consider the roblem of controlling an air-conditioner again. he rules that are used to control the airconditioner can be eressed as a cross roduct: CONROL EMP SPEED 5 Knowledge Reresentation & Reasoning: he Air-conditioner Eamle he rules can be eressed as a cross roduct of two term sets: emerature and Seed. CONROL EMP SPEED Where the set of linguistic values of the term sets is given as EMP COLD + COOL + PLEASAN + WARM + HO SPEED MINIMAL + SLOW + MEDIUM + FAS + BLAS 6 Knowledge Reresentation & Reasoning: he Air-conditioner Eamle A Mamdani Controller Recall that the rules governing the airconditioner are as follows: RULE#: IF EMP is COLD HEN SPEED is MINIMAL RULE#: IF EMP is COOL HEN SPEED is SLOW RULE#: IF EMP is PLEASEN HEN SPEED is MEDIUM RULE#: IF EMP is WARM HEN SPEED is FAS RULE#5: IF EMP is HO HEN SPEED is BLAS 7 9

10 Knowledge Reresentation & Reasoning: he Air-conditioner Eamle A Zero-order akagi-sugeno Controller Recall that the rules governing the airconditioner are as follows: RULE#: IF EMP is COLD HEN SPEED k RULE#: IF EMP is COOL HEN SPEED k RULE#: IF EMP is PLEASEN HEN SPEED k RULE#: IF EMP is WARM HEN SPEED k RULE#5: IF EMP is HO HEN SPEED k 5 8 Knowledge Reresentation & Reasoning: he Air-conditioner Eamle A First-order akagi-sugeno Controller Recall that the rules governing the airconditioner are as follows: RULE#: IF EMP is COLD HEN SPEED j +k * RULE#: IF EMP is COOL HEN SPEED j +k * RULE#: IF EMP is PLEASEN HEN SPEED k RULE#: IF EMP is WARM HEN SPEED j + k RULE#5: IF EMP is HO HEN SPEED k 5 9 Knowledge Reresentation & Reasoning: he Air-conditioner Eamle emerature Fuzz Sets r u th V a lu e emerature Degrees C Cold Cool Pleasent Warm Hot 0 0

11 Knowledge Reresentation & Reasoning: he Air-conditioner Eamle he analticall eressed membershi for the reference fuzz subsets for the temerature are: ' COLD ' ; COLD ' COOL ' COOL ; COOL ' PLEASEN ' PLEA ; PLEA ' WARM ' ' WARM WARM ' HO ' HO HO Knowledge Reresentation & Reasoning: he Air-conditioner Eamle Seed Fuzz Sets For FLC of Mamdani te r u t h V a l u e Seed MINIMAL SLOW MEDIUM FAS BLAS Knowledge Reresentation & Reasoning: he Air-conditioner Eamle he zero-order seed control just takes one SINGLEON value at fied values of the velocit; for all other values the membershi function is defined as zero ' MINIMAL' V V 0; ' SLOW ' MEDIUM ' ' FAS ' ' BLAS ' MINIMAL SLOW MED FAS BLAS V V V V V 0 V 50 V 70 V 00

12 Knowledge Reresentation & Reasoning: he Air-conditioner Eamle Let the temerature be 5 degrees centigrade: Fuzzification: 5 degrees means that it can be COOL and COLD; Inference: Rules and will fire: Comosition: he temerature is COLD with a truth value of COLD0.5 the SPEED will be k he temerature is COOL with a truth value of COOL 0.5 the SPEED will be k DEFUZZIFICAION : CONROL seed is COLD *k+ COOL *k/ COLD + COOL 0.5*0+0.5*0/ RPM Knowledge Reresentation & Reasoning: he Air-conditioner Eamle Zero Order akagi Sugeno Controller Membershi Function Seed MINIMAL SLOW MEDIUM FAS BLAS 5 Knowledge Reresentation & Reasoning: he Air-conditioner Eamle FUZZIFICAION: Consider that the temerature is 6 o C and we want our knowledge base to comute the seed. he fuzzification of the the cris temerature gives the following membershi for the emerature fuzz set: COLD COOL PLEASEN WAR M HO em Fire Rule # es/no # no # es # es # no #5 no 6

13 Knowledge Reresentation & Reasoning: he Air-conditioner Eamle INFERENCE: Consider that the temerature is 6 o C and we want our knowledge base to comute the seed. Rule # & are firing and are essentiall the fuzz atches made out of the cross roducts of COOL SLOW PLEASAN MEDIUM 7 Knowledge Reresentation & Reasoning: he Air-conditioner Eamle COMPOSIION: he COOL and PLEASAN sets have an outut of 0. and 0. resectivel. he singleton values for SLOW and MEDIUM have to be given an alha-level cut for these outut values resectivel: Zero-order akagi-sugeno Model 0.5 Membershi Function alha-cut Seed MINIMAL SLOW MEDIUM FAS BLAS 8 Knowledge Reresentation & Reasoning: he Air-conditioner Eamle DEFUZZIFICAION: he roblem of finding a single, cris value is no longer a roblem for a akagi-sugeno controller. All we need is the weighted average of the singleton values of SLOW & MEDIUM. Recall the Centre of Area comutation for the Mamdani controller η Σ outut Σ.... n outut.... n 9

14 Knowledge Reresentation & Reasoning: he Air-conditioner Eamle DEFUZZIFICAION: For akagi-sugeno, the comutation for η is restricted to the singleton values of the SPEED linguistic variable we do not need to sum over all values of the variable : η Σ Σ Σ SLOW *.... n outut.... n outut SLOW _ ' _ ' SLOW. + MEDIUM *. + MEDIUM _ ''. MEDIUM _ ''. 0 Knowledge Reresentation & Reasoning: he Air-conditioner Eamle DEFUZZIFICAION: For akagi-sugeno, the comutation for η is restricted to the singleton values of the SPEED linguistic variable we do not need to sum over all values of the variable : SLOW Σ SLOW * _. + MEDIUM * ' η SLOW MEDIUM _. + _. ' '' 0.* * MEDIUM _ ''. Knowledge Reresentation & Reasoning: he Air-conditioner Eamle DEFUZZIFICAION: Recall the case of the Mamdani equivalent of the fuzz airconditioner where we had fuzz sets for the linguistic variables SLOW and MEDIUM: he Centre of Area COA comutations involved a weighted sum over all values of seed between.5 and 57.5 RPM: in the akagi-sugeno case we onl had to consider values for seeds 0RPM and 50 RPM.

15 Knowledge Reresentation & Reasoning: he Air-conditioner Eamle DEFUZZIFICAION: Recall the case of the Mamdani equivalent of the fuzz air-conditioner where we had fuzz sets for the linguistic variables SLOW and MEDIUM: he Centre of Area COA comutations involved a weighted sum over all values of seed between.5 and 57.5 RPM: in the akagi-sugeno case we onl had to consider values for seeds 0RPM and 50 RPM. SPEED SLOW MEDIUM OUPU OF RULES WEIGHED SPEED he seed is 6.9 RPM SUM Knowledge Reresentation & Reasoning: he Air-conditioner Eamle DEFUZZIFICAION: For Mean of Maima for the Mamdani controller, we had to have an alha-level cut of 0., and the summation ran between RPM, leading to a seed of 50 RPM. We get the same result for akagi-sugeno controllers: η 0.*50/0.50 RPM Knowledge Reresentation & Reasoning: he Air-conditioner Eamle DEFUZZIFICAION: Comaring the results of two model identification eercises Mamdani and akagi-sugeno- we get the following results: Controller akagi- Sugeno RPM Mamdani RPM Centre of Area. 6.9 Mean of Maima

16 Knowledge Reresentation & Reasoning: he Air-conditioner Eamle DEFUZZIFICAION: Comaring the results of two model identification eercises Mamdani and akagi-sugeno- we get the following results: Mamdani Controller and the use of COA is the best result Error Controller akagi-sugeno Mamdani RPM RPM Centre of Area % 0% Mean of Maima 5% 5% 6 LERS akagi-sugeno Controllers A formal derivation Consider a domain where all fuzz sets are associated with linear membershi functions. Let us denote the membershi function of a fuzz set A as A,. All the fuzz sets are associated with linear membershi functions. hus, a membershi function is characterised b two arameters giving the greatest grade and the least grade 0. he truth value of a roosition is m A and is m B is eressed as is A and is B A Λ B 7 LERS- An eamle A worked eamle Consider an FLC of Mamdani te: which eresses rules like: ek N Z P ek N N N Z Z N Z P P Z P P Rule : If ek is negative AND ek is negative then uk is negative ALSO Rule 9: If ek is ositive AND ek is ositive then uk is ositive 8 6

17 LERS- An eamle A worked eamle Consider an FLC of Mamdani te: ek N Z P ek N N N Z Z N Z P P Z P P he nine rules eress the deendence of change in the value of control outut on the error the difference between eected and outut values and the change in error. his deendence will cature some ver comle non-linear, and linear relationshis between e and e and u. 9 LERS- An eamle A zero-order akagi-sugeno Controller ek N Z P ek N α α α Z α α 5 α 6 P α 7 α 8 α 9 which eresses rules like: Rule :If ek is negative AND ek is negative then uk α Rule 9:If ek is ositive AND ek is ositive then uk α9 50 LERS- An eamle A first-order akagi-sugeno Controller ek N Z P ek N α e+ß e +δ α e+ß e+ δ α e+ß e+ δ Z α e+ß e +δ α 5 e+ß 5 e+ δ 5 α 6 e+ß 6 e+ δ 6 P α 7 e+ß 7 e+ δ 7 α 8 e+ß 8 e+ δ 8 α 9 e+ß 9 e+ δ 9 which eresses rules like: Rule :If ek is negative AND ek is negative then uk α e+ß e+δ Rule 9:If ek is ositive AND ek is ositive then uk α 9 e+ß 9 e+δ 9 5 7

18 LERS akagi-sugeno Controllers akagi and Sugeno have described a fuzz imlication R is of the format: R: if is A, k is A k then g,, k, where:,, k m A,.. m A f g Variable of the consequence whose value is inferred Variables of the remise that aear also in the art of the consequence Fuzz sets with linear membershi functions reresenting a fuzz subsace in which the imlication R can be alied for reasoning. Logical function connects the roositions in the remise. Function that imlies the value of when,. 5 k satisfies the remise. LERS akagi-sugeno Controllers In the remise if A i is equal to i for some i where i is the universe of discourse of i, this term is omitted; i is unconditioned; otherwise i is regarded as conditioned. 5 LERS akagi-sugeno Controllers In the remise if A i is equal to i for some i where i is the universe of discourse of i, this term is omitted; i is unconditioned. he following eamle will hel in clarifing the argumentation related to 'conditioned' and 'unconditioned' terms in a given imlication: R: if is small and is big then + +. he above imlication comrises two conditioned remises, and, and one unconditioned remise,. he imlication suggests that if is small and is big, then the value of would deend uon and be equal to the sum of,, and., where is unconditioned in the remise. 5 8

19 LERS akagi-sugeno Controllers icall, for a akagi-sugeno controller, an imlication is written as: R: if is and and k is k then k k. he assumtion here is that onl and connectives are used in the antecedants or remises of the rules. And, that the relationshi between the outut and inuts is strictl a LINEAR weighted average relationshi. he weights here are 0,.. k. 55 LERS akagi-sugeno Controllers Reasoning Algorithm Recall the arguments related to the membershi functions of the union and intersection of fuzz sets. he intersection of sets A and B is given as: A B min A, B We started this discussion b noting that we will elore the roblems of multivariable control MultileInutSingleOutut. Usuall, the rule base in a fuzz control sstem comrises a number of rules; in the case of multivariable control the relevant rules have to be tested for what the iml. 56 LERS akagi-sugeno Controllers Consider a sstem with n imlications rules; the variable of consequence,, will have to be notated for each of these imlications, leading to i variables of consequence. here are three stages of comutations in akagi-sugeno controllers: FUZZIFICAION: Fuzzif the inut. For all inut variables comute the imlication for each of the rules; INFERENCE or CONSEQUENCES: For each imlication comute the consequence for a rule which fires. Comute the outut for the rule b using the linear relationshi between the inuts and the outut k k.. AGGREGAE & DEFUZZIFICAION: he final outut is inferred from n-imlications and given as an average of all individual imlications i with weights i : Σ i * i / Σ i where i stands for the truth value of a given roosition. 57 9

20 LERS akagi-sugeno Controllers Consider the following fuzz imlications or rules R,R, R used in the design of a akagi-sugeno controller: R If is small & is small then + R If is big then R If is big then where i refers to the consequent variable for each rule labelled R i and and refer to the inut variables that aear in remise of the rules. 58 LERS akagi-sugeno Controllers he membershi function for small, small, big and big are given as follows Small Small Big Big LERS akagi-sugeno Controllers he membershi function for small, small, big and big are given as follows akagi-sugeno Eamle 7 Membershi Function Inut Small Small Big Big 60 0

21 LERS akagi-sugeno Controllers An eamle Let us comute the FINAL OUPU for the following values: & 5 using akagi and Sugeno s formula: Σ i * i / Σ i where i stands for the truth value of a given roosition. 6 LERS akagi-sugeno Controllers An eamle FUZZUFICAION: We have the following values of the membershi functions for the two values & 5: Small Small Big Big LERS akagi-sugeno Controllers An eamle INFERENCE & CONSEQUENCE: & 5 Rule Premise Premise Consequenc e R Small 0.5 Small ruth Value Min Premise & Premise Min0.5, R Big 0. R Big

22 LERS akagi-sugeno Controllers An eamle AGGREGAION &DEFUZZIFICAION: & 5 Σ i * i / Σ i Using a Centre of Area comutation for we get: i, i, i * i i 0.5 * * * LERS Ke difference between a Mamdani-te fuzz sstem and the akagi-sugeno-kang Sstem? A zero-order Sugeno fuzz model can be viewed as a secial case of the Mamdani fuzz inference sstem in which each rule is secified b fuzz singleton or a re-defuzzified consequent. In Sugeno s model, each rule has a cris outut, the overall inut is obtained b a weighted average this avoids the timeconsuming rocess of defuzzification required in a Mandani model. he weighted average oerator is relaced b a weighted sum to reduce comutation further. Jang, Sun, Mizutani 997:8. 65 LERS akagi-sugeno Controllers akagi,., & Sugeno, M Fuzz Identification of Sstems and its Alications to Modeling and Control. IEEE ransactions on Sstems, Man and Cbernetics. Volume No. SMC-5 No

23 LERS akagi-sugeno Controllers akagi and Sugeno 985 have argued that in order to develo a generic and simle mathematical tool for comuting fuzz imlications one needs to look at a fuzz artition of fuzz inut sace. In each fuzz subsace a linear inut-outut relation is formed. he outut of fuzz reasoning is given b the values inferred b some imlications that were alied to an inut. 67 Knowledge Reresentation & Reasoning: he Air-conditioner Eamle akagi-sugeno model is an aroimation of a Mamdani controller in that the akagi- Sugeno model ignores the fuzziness of linguistic variables in the consequent, but accounts for the fuzziness of variables in the antecedants; whereas Mamdani controller takes into the fuzziness of variables aearing both in the antecdents and the consequent. 68 Knowledge Reresentation & Reasoning: he Air-conditioner Eamle Model Identification: Given a choice between two models, sa Mamdani and akagi- Sugeno, we have to first identif wh to chose a fuzz logic sstem will a cris descrition not work as it is simler to comute and second whether to use an elaborate model sa Mamdani rather than an aroimation to the model sa, akagi-sugeno. he choice can be based on the relative erformance of the two models 69

Financial Informatics XI: Fuzzy Rule-based Systems

Financial Informatics XI: Fuzzy Rule-based Systems Financial Informatics XI: Fuzzy Rule-based Systems Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2, IRELAND November 19 th, 28. https://www.cs.tcd.ie/khurshid.ahmad/teaching.html

More information

Convex Analysis and Economic Theory Winter 2018

Convex Analysis and Economic Theory Winter 2018 Division of the Humanities and Social Sciences Ec 181 KC Border Conve Analysis and Economic Theory Winter 2018 Toic 16: Fenchel conjugates 16.1 Conjugate functions Recall from Proosition 14.1.1 that is

More information

Planar Transformations and Displacements

Planar Transformations and Displacements Chater Planar Transformations and Dislacements Kinematics is concerned with the roerties of the motion of oints. These oints are on objects in the environment or on a robot maniulator. Two features that

More information

Computer arithmetic. Intensive Computation. Annalisa Massini 2017/2018

Computer arithmetic. Intensive Computation. Annalisa Massini 2017/2018 Comuter arithmetic Intensive Comutation Annalisa Massini 7/8 Intensive Comutation - 7/8 References Comuter Architecture - A Quantitative Aroach Hennessy Patterson Aendix J Intensive Comutation - 7/8 3

More information

Distributed Rule-Based Inference in the Presence of Redundant Information

Distributed Rule-Based Inference in the Presence of Redundant Information istribution Statement : roved for ublic release; distribution is unlimited. istributed Rule-ased Inference in the Presence of Redundant Information June 8, 004 William J. Farrell III Lockheed Martin dvanced

More information

Chapter 7 Sampling and Sampling Distributions. Introduction. Selecting a Sample. Introduction. Sampling from a Finite Population

Chapter 7 Sampling and Sampling Distributions. Introduction. Selecting a Sample. Introduction. Sampling from a Finite Population Chater 7 and s Selecting a Samle Point Estimation Introduction to s of Proerties of Point Estimators Other Methods Introduction An element is the entity on which data are collected. A oulation is a collection

More information

AI*IA 2003 Fusion of Multiple Pattern Classifiers PART III

AI*IA 2003 Fusion of Multiple Pattern Classifiers PART III AI*IA 23 Fusion of Multile Pattern Classifiers PART III AI*IA 23 Tutorial on Fusion of Multile Pattern Classifiers by F. Roli 49 Methods for fusing multile classifiers Methods for fusing multile classifiers

More information

Approximating min-max k-clustering

Approximating min-max k-clustering Aroximating min-max k-clustering Asaf Levin July 24, 2007 Abstract We consider the roblems of set artitioning into k clusters with minimum total cost and minimum of the maximum cost of a cluster. The cost

More information

Fuzzy Controller. Fuzzy Inference System. Basic Components of Fuzzy Inference System. Rule based system: Contains a set of fuzzy rules

Fuzzy Controller. Fuzzy Inference System. Basic Components of Fuzzy Inference System. Rule based system: Contains a set of fuzzy rules Fuzz Controller Fuzz Inference Sstem Basic Components of Fuzz Inference Sstem Rule based sstem: Contains a set of fuzz rules Data base dictionar: Defines the membership functions used in the rules base

More information

Fuzzy Logic and Fuzzy Systems

Fuzzy Logic and Fuzzy Systems Fuzzy Logic and Fuzzy Systems Revision Lecture Khurshid Ahmad, Professor of Computer Science, Department of Computer Science Trinity College, Dublin-2, IRELAND 24 February 2008. https://www.cs.tcd.ie/khurshid.ahmad/teaching.html

More information

Chapter 1: PROBABILITY BASICS

Chapter 1: PROBABILITY BASICS Charles Boncelet, obability, Statistics, and Random Signals," Oxford University ess, 0. ISBN: 978-0-9-0005-0 Chater : PROBABILITY BASICS Sections. What Is obability?. Exeriments, Outcomes, and Events.

More information

1 Entropy 1. 3 Extensivity 4. 5 Convexity 5

1 Entropy 1. 3 Extensivity 4. 5 Convexity 5 Contents CONEX FUNCIONS AND HERMODYNAMIC POENIALS 1 Entroy 1 2 Energy Reresentation 2 3 Etensivity 4 4 Fundamental Equations 4 5 Conveity 5 6 Legendre transforms 6 7 Reservoirs and Legendre transforms

More information

Chapter 10. Classical Fourier Series

Chapter 10. Classical Fourier Series Math 344, Male ab Manual Chater : Classical Fourier Series Real and Comle Chater. Classical Fourier Series Fourier Series in PS K, Classical Fourier Series in PS K, are aroimations obtained using orthogonal

More information

MODEL-BASED MULTIPLE FAULT DETECTION AND ISOLATION FOR NONLINEAR SYSTEMS

MODEL-BASED MULTIPLE FAULT DETECTION AND ISOLATION FOR NONLINEAR SYSTEMS MODEL-BASED MULIPLE FAUL DEECION AND ISOLAION FOR NONLINEAR SYSEMS Ivan Castillo, and homas F. Edgar he University of exas at Austin Austin, X 78712 David Hill Chemstations Houston, X 77009 Abstract A

More information

2010/07/12. Content. Fuzzy? Oxford Dictionary: blurred, indistinct, confused, imprecisely defined

2010/07/12. Content. Fuzzy? Oxford Dictionary: blurred, indistinct, confused, imprecisely defined Content Introduction Graduate School of Science and Technology Basic Concepts Fuzzy Control Eamples H. Bevrani Fuzzy GC Spring Semester, 2 2 The class of tall men, or the class of beautiful women, do not

More information

State Estimation with ARMarkov Models

State Estimation with ARMarkov Models Deartment of Mechanical and Aerosace Engineering Technical Reort No. 3046, October 1998. Princeton University, Princeton, NJ. State Estimation with ARMarkov Models Ryoung K. Lim 1 Columbia University,

More information

ASPECTS OF POLE PLACEMENT TECHNIQUE IN SYMMETRICAL OPTIMUM METHOD FOR PID CONTROLLER DESIGN

ASPECTS OF POLE PLACEMENT TECHNIQUE IN SYMMETRICAL OPTIMUM METHOD FOR PID CONTROLLER DESIGN ASES OF OLE LAEMEN EHNIQUE IN SYMMERIAL OIMUM MEHOD FOR ID ONROLLER DESIGN Viorel Nicolau *, onstantin Miholca *, Dorel Aiordachioaie *, Emil eanga ** * Deartment of Electronics and elecommunications,

More information

Lecture Thermodynamics 9. Entropy form of the 1 st law. Let us start with the differential form of the 1 st law: du = d Q + d W

Lecture Thermodynamics 9. Entropy form of the 1 st law. Let us start with the differential form of the 1 st law: du = d Q + d W Lecture hermodnamics 9 Entro form of the st law Let us start with the differential form of the st law: du = d Q + d W Consider a hdrostatic sstem. o know the required d Q and d W between two nearb states,

More information

Estimating h Boundary Layer Equations

Estimating h Boundary Layer Equations Estimating h Boundar Laer Equations ChE 0B Before, we just assumed a heat transfer coefficient, but can we estimate them from first rinciles? Look at stead laminar flow ast a flat late, again: Clearl,

More information

APPLICATION OF THE TAKAGI-SUGENO FUZZY CONTROLLER FOR SOLVING THE ROBOTS' INVERSE KINEMATICS PROBLEM UDC

APPLICATION OF THE TAKAGI-SUGENO FUZZY CONTROLLER FOR SOLVING THE ROBOTS' INVERSE KINEMATICS PROBLEM UDC FACTA UNIVERSITATIS Series: Mechanics, Automatic Control and Robotics Vol.3, N o 5, 3,. 39-54 APPLICATION OF THE TAKAGI-SUGENO FUZZY CONTROLLER FOR SOLVING THE ROBOTS' INVERSE KINEMATICS PROBLEM UDC 6-5+68.53+68.58

More information

ME 534. Mechanical Engineering University of Gaziantep. Dr. A. Tolga Bozdana Assistant Professor

ME 534. Mechanical Engineering University of Gaziantep. Dr. A. Tolga Bozdana Assistant Professor ME 534 Intelligent Manufacturing Systems Chp 4 Fuzzy Logic Mechanical Engineering University of Gaziantep Dr. A. Tolga Bozdana Assistant Professor Motivation and Definition Fuzzy Logic was initiated by

More information

Use of Transformations and the Repeated Statement in PROC GLM in SAS Ed Stanek

Use of Transformations and the Repeated Statement in PROC GLM in SAS Ed Stanek Use of Transformations and the Reeated Statement in PROC GLM in SAS Ed Stanek Introduction We describe how the Reeated Statement in PROC GLM in SAS transforms the data to rovide tests of hyotheses of interest.

More information

Uncertainty Modeling with Interval Type-2 Fuzzy Logic Systems in Mobile Robotics

Uncertainty Modeling with Interval Type-2 Fuzzy Logic Systems in Mobile Robotics Uncertainty Modeling with Interval Tye-2 Fuzzy Logic Systems in Mobile Robotics Ondrej Linda, Student Member, IEEE, Milos Manic, Senior Member, IEEE bstract Interval Tye-2 Fuzzy Logic Systems (IT2 FLSs)

More information

18.312: Algebraic Combinatorics Lionel Levine. Lecture 12

18.312: Algebraic Combinatorics Lionel Levine. Lecture 12 8.3: Algebraic Combinatorics Lionel Levine Lecture date: March 7, Lecture Notes by: Lou Odette This lecture: A continuation of the last lecture: comutation of µ Πn, the Möbius function over the incidence

More information

Fuzzy Logic Notes. Course: Khurshid Ahmad 2010 Typset: Cathal Ormond

Fuzzy Logic Notes. Course: Khurshid Ahmad 2010 Typset: Cathal Ormond Fuzzy Logic Notes Course: Khurshid Ahmad 2010 Typset: Cathal Ormond April 25, 2011 Contents 1 Introduction 2 1.1 Computers......................................... 2 1.2 Problems..........................................

More information

Chapter 6. Phillip Hall - Room 537, Huxley

Chapter 6. Phillip Hall - Room 537, Huxley Chater 6 6 Partial Derivatives.................................................... 72 6. Higher order artial derivatives...................................... 73 6.2 Matrix of artial derivatives.........................................74

More information

GENERATING FUZZY RULES FOR PROTEIN CLASSIFICATION E. G. MANSOORI, M. J. ZOLGHADRI, S. D. KATEBI, H. MOHABATKAR, R. BOOSTANI AND M. H.

GENERATING FUZZY RULES FOR PROTEIN CLASSIFICATION E. G. MANSOORI, M. J. ZOLGHADRI, S. D. KATEBI, H. MOHABATKAR, R. BOOSTANI AND M. H. Iranian Journal of Fuzzy Systems Vol. 5, No. 2, (2008). 21-33 GENERATING FUZZY RULES FOR PROTEIN CLASSIFICATION E. G. MANSOORI, M. J. ZOLGHADRI, S. D. KATEBI, H. MOHABATKAR, R. BOOSTANI AND M. H. SADREDDINI

More information

Radial Basis Function Networks: Algorithms

Radial Basis Function Networks: Algorithms Radial Basis Function Networks: Algorithms Introduction to Neural Networks : Lecture 13 John A. Bullinaria, 2004 1. The RBF Maing 2. The RBF Network Architecture 3. Comutational Power of RBF Networks 4.

More information

MODELING THE RELIABILITY OF C4ISR SYSTEMS HARDWARE/SOFTWARE COMPONENTS USING AN IMPROVED MARKOV MODEL

MODELING THE RELIABILITY OF C4ISR SYSTEMS HARDWARE/SOFTWARE COMPONENTS USING AN IMPROVED MARKOV MODEL Technical Sciences and Alied Mathematics MODELING THE RELIABILITY OF CISR SYSTEMS HARDWARE/SOFTWARE COMPONENTS USING AN IMPROVED MARKOV MODEL Cezar VASILESCU Regional Deartment of Defense Resources Management

More information

COBB-Douglas, Constant Elasticity of Substitution (CES) and Transcendental Logarithmic Production Functions in Non-linear Type of Special Functions

COBB-Douglas, Constant Elasticity of Substitution (CES) and Transcendental Logarithmic Production Functions in Non-linear Type of Special Functions ISSN: 3-9653; IC Value: 45.98; SJ Imact Factor :6.887 Volume 5 Issue XII December 07- Available at www.ijraset.com COBB-Douglas, Constant Elasticity of Substitution (CES) and Transcendental Logarithmic

More information

Stochastic integration II: the Itô integral

Stochastic integration II: the Itô integral 13 Stochastic integration II: the Itô integral We have seen in Lecture 6 how to integrate functions Φ : (, ) L (H, E) with resect to an H-cylindrical Brownian motion W H. In this lecture we address the

More information

MATH 2710: NOTES FOR ANALYSIS

MATH 2710: NOTES FOR ANALYSIS MATH 270: NOTES FOR ANALYSIS The main ideas we will learn from analysis center around the idea of a limit. Limits occurs in several settings. We will start with finite limits of sequences, then cover infinite

More information

Actual exergy intake to perform the same task

Actual exergy intake to perform the same task CHAPER : PRINCIPLES OF ENERGY CONSERVAION INRODUCION Energy conservation rinciles are based on thermodynamics If we look into the simle and most direct statement of the first law of thermodynamics, we

More information

Research of power plant parameter based on the Principal Component Analysis method

Research of power plant parameter based on the Principal Component Analysis method Research of ower lant arameter based on the Princial Comonent Analysis method Yang Yang *a, Di Zhang b a b School of Engineering, Bohai University, Liaoning Jinzhou, 3; Liaoning Datang international Jinzhou

More information

Micro I. Lesson 5 : Consumer Equilibrium

Micro I. Lesson 5 : Consumer Equilibrium Microecono mics I. Antonio Zabalza. Universit of Valencia 1 Micro I. Lesson 5 : Consumer Equilibrium 5.1 Otimal Choice If references are well behaved (smooth, conve, continuous and negativel sloed), then

More information

Intro. ANN & Fuzzy Systems. Lec 34 Fuzzy Logic Control (II)

Intro. ANN & Fuzzy Systems. Lec 34 Fuzzy Logic Control (II) Lec 34 Fuzz Logic Control (II) Outline Control Rule Base Fuzz Inference Defuzzification FLC Design Procedures (C) 2001 b Yu Hen Hu 2 General form of rule: IF Control Rule Base x 1 is A 1 AND AND x M is

More information

ANALYTICAL MODEL FOR THE BYPASS VALVE IN A LOOP HEAT PIPE

ANALYTICAL MODEL FOR THE BYPASS VALVE IN A LOOP HEAT PIPE ANALYTICAL MODEL FOR THE BYPASS ALE IN A LOOP HEAT PIPE Michel Seetjens & Camilo Rindt Laboratory for Energy Technology Mechanical Engineering Deartment Eindhoven University of Technology The Netherlands

More information

Mean Square Stability Analysis of Sampled-Data Supervisory Control Systems

Mean Square Stability Analysis of Sampled-Data Supervisory Control Systems 17th IEEE International Conference on Control Alications Part of 28 IEEE Multi-conference on Systems and Control San Antonio, Texas, USA, Setember 3-5, 28 WeA21 Mean Square Stability Analysis of Samled-Data

More information

Oil Temperature Control System PID Controller Algorithm Analysis Research on Sliding Gear Reducer

Oil Temperature Control System PID Controller Algorithm Analysis Research on Sliding Gear Reducer Key Engineering Materials Online: 2014-08-11 SSN: 1662-9795, Vol. 621, 357-364 doi:10.4028/www.scientific.net/kem.621.357 2014 rans ech Publications, Switzerland Oil emerature Control System PD Controller

More information

+++ Modeling of Structural-dynamic Systems by UML Statecharts in AnyLogic +++ Modeling of Structural-dynamic Systems by UML Statecharts in AnyLogic

+++ Modeling of Structural-dynamic Systems by UML Statecharts in AnyLogic +++ Modeling of Structural-dynamic Systems by UML Statecharts in AnyLogic Modeling of Structural-dynamic Systems by UML Statecharts in AnyLogic Daniel Leitner, Johannes Krof, Günther Zauner, TU Vienna, Austria, dleitner@osiris.tuwien.ac.at Yuri Karov, Yuri Senichenkov, Yuri

More information

Optimal array pattern synthesis with desired magnitude response

Optimal array pattern synthesis with desired magnitude response Otimal array attern synthesis with desired magnitude resonse A.M. Pasqual a, J.R. Arruda a and P. erzog b a Universidade Estadual de Caminas, Rua Mendeleiev, 00, Cidade Universitária Zeferino Vaz, 13083-970

More information

Solved Problems. (a) (b) (c) Figure P4.1 Simple Classification Problems First we draw a line between each set of dark and light data points.

Solved Problems. (a) (b) (c) Figure P4.1 Simple Classification Problems First we draw a line between each set of dark and light data points. Solved Problems Solved Problems P Solve the three simle classification roblems shown in Figure P by drawing a decision boundary Find weight and bias values that result in single-neuron ercetrons with the

More information

Numerical Computation of the Eigenstructure of Cylindrical Acoustic Waveguides with Heated (or Cooled) Walls

Numerical Computation of the Eigenstructure of Cylindrical Acoustic Waveguides with Heated (or Cooled) Walls Alied Mathematical Sciences, Vol. 3, 29, no. 7, 82-837 Numerical Comutation of the Eigenstructure of Clindrical Acoustic Waveguides with Heated (or Cooled) Walls Brian J. M c Cartin Alied Mathematics,

More information

Recursive Estimation of the Preisach Density function for a Smart Actuator

Recursive Estimation of the Preisach Density function for a Smart Actuator Recursive Estimation of the Preisach Density function for a Smart Actuator Ram V. Iyer Deartment of Mathematics and Statistics, Texas Tech University, Lubbock, TX 7949-142. ABSTRACT The Preisach oerator

More information

MULTIVARIATE STATISTICAL PROCESS OF HOTELLING S T CONTROL CHARTS PROCEDURES WITH INDUSTRIAL APPLICATION

MULTIVARIATE STATISTICAL PROCESS OF HOTELLING S T CONTROL CHARTS PROCEDURES WITH INDUSTRIAL APPLICATION Journal of Statistics: Advances in heory and Alications Volume 8, Number, 07, Pages -44 Available at htt://scientificadvances.co.in DOI: htt://dx.doi.org/0.864/jsata_700868 MULIVARIAE SAISICAL PROCESS

More information

Paper C Exact Volume Balance Versus Exact Mass Balance in Compositional Reservoir Simulation

Paper C Exact Volume Balance Versus Exact Mass Balance in Compositional Reservoir Simulation Paer C Exact Volume Balance Versus Exact Mass Balance in Comositional Reservoir Simulation Submitted to Comutational Geosciences, December 2005. Exact Volume Balance Versus Exact Mass Balance in Comositional

More information

Uniform Sample Generations from Contractive Block Toeplitz Matrices

Uniform Sample Generations from Contractive Block Toeplitz Matrices IEEE TRASACTIOS O AUTOMATIC COTROL, VOL 5, O 9, SEPTEMBER 6 559 Uniform Samle Generations from Contractive Bloc Toelitz Matrices Tong Zhou and Chao Feng Abstract This note deals with generating a series

More information

Observer/Kalman Filter Time Varying System Identification

Observer/Kalman Filter Time Varying System Identification Observer/Kalman Filter Time Varying System Identification Manoranjan Majji Texas A&M University, College Station, Texas, USA Jer-Nan Juang 2 National Cheng Kung University, Tainan, Taiwan and John L. Junins

More information

Topic 7: Using identity types

Topic 7: Using identity types Toic 7: Using identity tyes June 10, 2014 Now we would like to learn how to use identity tyes and how to do some actual mathematics with them. By now we have essentially introduced all inference rules

More information

Feedback-error control

Feedback-error control Chater 4 Feedback-error control 4.1 Introduction This chater exlains the feedback-error (FBE) control scheme originally described by Kawato [, 87, 8]. FBE is a widely used neural network based controller

More information

Intelligent Systems and Control Prof. Laxmidhar Behera Indian Institute of Technology, Kanpur

Intelligent Systems and Control Prof. Laxmidhar Behera Indian Institute of Technology, Kanpur Intelligent Systems and Control Prof. Laxmidhar Behera Indian Institute of Technology, Kanpur Module - 2 Lecture - 4 Introduction to Fuzzy Logic Control In this lecture today, we will be discussing fuzzy

More information

A Bound on the Error of Cross Validation Using the Approximation and Estimation Rates, with Consequences for the Training-Test Split

A Bound on the Error of Cross Validation Using the Approximation and Estimation Rates, with Consequences for the Training-Test Split A Bound on the Error of Cross Validation Using the Aroximation and Estimation Rates, with Consequences for the Training-Test Slit Michael Kearns AT&T Bell Laboratories Murray Hill, NJ 7974 mkearns@research.att.com

More information

Homework Set #3 Rates definitions, Channel Coding, Source-Channel coding

Homework Set #3 Rates definitions, Channel Coding, Source-Channel coding Homework Set # Rates definitions, Channel Coding, Source-Channel coding. Rates (a) Channels coding Rate: Assuming you are sending 4 different messages using usages of a channel. What is the rate (in bits

More information

Participation Factors. However, it does not give the influence of each state on the mode.

Participation Factors. However, it does not give the influence of each state on the mode. Particiation Factors he mode shae, as indicated by the right eigenvector, gives the relative hase of each state in a articular mode. However, it does not give the influence of each state on the mode. We

More information

CMSC 425: Lecture 4 Geometry and Geometric Programming

CMSC 425: Lecture 4 Geometry and Geometric Programming CMSC 425: Lecture 4 Geometry and Geometric Programming Geometry for Game Programming and Grahics: For the next few lectures, we will discuss some of the basic elements of geometry. There are many areas

More information

A MODAL SERIES REPRESENTATION OF GENESIO CHAOTIC SYSTEM

A MODAL SERIES REPRESENTATION OF GENESIO CHAOTIC SYSTEM International Journal of Instrumentation and Control Sstems (IJICS) Vol., o., Jul A MODAL SERIES REPRESETATIO OF GEESIO CHAOTIC SYSTEM H. Ramezanour, B. Razeghi, G. Darmani, S. oei 4, A. Sargolzaei 5 Tübingen

More information

Explosion Protection of Buildings

Explosion Protection of Buildings 1 Exlosion Protection of Buildings Author: Miroslav Mynarz 2 Exlosion Protection of Buildings Exlosion of a Condensed Exlosive and Calculation of Blast Wave Parameters Theory of exlosion of condensed exlosive

More information

Statics and dynamics: some elementary concepts

Statics and dynamics: some elementary concepts 1 Statics and dynamics: some elementary concets Dynamics is the study of the movement through time of variables such as heartbeat, temerature, secies oulation, voltage, roduction, emloyment, rices and

More information

Metrics Performance Evaluation: Application to Face Recognition

Metrics Performance Evaluation: Application to Face Recognition Metrics Performance Evaluation: Alication to Face Recognition Naser Zaeri, Abeer AlSadeq, and Abdallah Cherri Electrical Engineering Det., Kuwait University, P.O. Box 5969, Safat 6, Kuwait {zaery, abeer,

More information

PROFIT MAXIMIZATION. π = p y Σ n i=1 w i x i (2)

PROFIT MAXIMIZATION. π = p y Σ n i=1 w i x i (2) PROFIT MAXIMIZATION DEFINITION OF A NEOCLASSICAL FIRM A neoclassical firm is an organization that controls the transformation of inuts (resources it owns or urchases into oututs or roducts (valued roducts

More information

SLIDING MODE CONTROL OF LINEAR SYNCHRONOUS MOTOR SERVODRIVE

SLIDING MODE CONTROL OF LINEAR SYNCHRONOUS MOTOR SERVODRIVE Journal of Engineering Sciences, Assiut Universit, Vol. 34, No. 4,. 255-264, Jul 2006 SLIDING MODE CONROL OF LINEAR SYNCHRONOUS MOOR SERVODRIVE Electrical Engineering Deartment, Aswan Facult of Engineering,

More information

Applied Fitting Theory VI. Formulas for Kinematic Fitting

Applied Fitting Theory VI. Formulas for Kinematic Fitting Alied Fitting heory VI Paul Avery CBX 98 37 June 9, 1998 Ar. 17, 1999 (rev.) I Introduction Formulas for Kinematic Fitting I intend for this note and the one following it to serve as mathematical references,

More information

Combining Logistic Regression with Kriging for Mapping the Risk of Occurrence of Unexploded Ordnance (UXO)

Combining Logistic Regression with Kriging for Mapping the Risk of Occurrence of Unexploded Ordnance (UXO) Combining Logistic Regression with Kriging for Maing the Risk of Occurrence of Unexloded Ordnance (UXO) H. Saito (), P. Goovaerts (), S. A. McKenna (2) Environmental and Water Resources Engineering, Deartment

More information

Study on the Simulation Method for Wall Burning in Liquid-bath Combustor

Study on the Simulation Method for Wall Burning in Liquid-bath Combustor Study on the Simulation Method for Wall Burning in Liquid-bath Combustor XIAOHAN WANG 1, 2, DAIQING ZHAO 1, LIBO HE 1, YONG CHEN 1 1. Guangzhou Institute of Energy Conversion, the Chinese Academy of Sciences,

More information

Lecture 06. (Fuzzy Inference System)

Lecture 06. (Fuzzy Inference System) Lecture 06 Fuzzy Rule-based System (Fuzzy Inference System) Fuzzy Inference System vfuzzy inference is the process of formulating the mapping from a given input to an output using fuzzy logic. Fuzzy Inference

More information

Uncorrelated Multilinear Principal Component Analysis for Unsupervised Multilinear Subspace Learning

Uncorrelated Multilinear Principal Component Analysis for Unsupervised Multilinear Subspace Learning TNN-2009-P-1186.R2 1 Uncorrelated Multilinear Princial Comonent Analysis for Unsuervised Multilinear Subsace Learning Haiing Lu, K. N. Plataniotis and A. N. Venetsanooulos The Edward S. Rogers Sr. Deartment

More information

Best approximation by linear combinations of characteristic functions of half-spaces

Best approximation by linear combinations of characteristic functions of half-spaces Best aroximation by linear combinations of characteristic functions of half-saces Paul C. Kainen Deartment of Mathematics Georgetown University Washington, D.C. 20057-1233, USA Věra Kůrková Institute of

More information

2-D Analysis for Iterative Learning Controller for Discrete-Time Systems With Variable Initial Conditions Yong FANG 1, and Tommy W. S.

2-D Analysis for Iterative Learning Controller for Discrete-Time Systems With Variable Initial Conditions Yong FANG 1, and Tommy W. S. -D Analysis for Iterative Learning Controller for Discrete-ime Systems With Variable Initial Conditions Yong FANG, and ommy W. S. Chow Abstract In this aer, an iterative learning controller alying to linear

More information

The Logic of Compound Statements. CSE 2353 Discrete Computational Structures Spring 2018

The Logic of Compound Statements. CSE 2353 Discrete Computational Structures Spring 2018 CSE 2353 Discrete Comutational Structures Sring 2018 The Logic of Comound Statements (Chater 2, E) Note: some course slides adoted from ublisher-rovided material Outline 2.1 Logical Form and Logical Equivalence

More information

CSE 311 Lecture 02: Logic, Equivalence, and Circuits. Emina Torlak and Kevin Zatloukal

CSE 311 Lecture 02: Logic, Equivalence, and Circuits. Emina Torlak and Kevin Zatloukal CSE 311 Lecture 02: Logic, Equivalence, and Circuits Emina Torlak and Kevin Zatloukal 1 Toics Proositional logic A brief review of Lecture 01. Classifying comound roositions Converse, contraositive, and

More information

Chapter 7 Rational and Irrational Numbers

Chapter 7 Rational and Irrational Numbers Chater 7 Rational and Irrational Numbers In this chater we first review the real line model for numbers, as discussed in Chater 2 of seventh grade, by recalling how the integers and then the rational numbers

More information

Using a Computational Intelligence Hybrid Approach to Recognize the Faults of Variance Shifts for a Manufacturing Process

Using a Computational Intelligence Hybrid Approach to Recognize the Faults of Variance Shifts for a Manufacturing Process Journal of Industrial and Intelligent Information Vol. 4, No. 2, March 26 Using a Comutational Intelligence Hybrid Aroach to Recognize the Faults of Variance hifts for a Manufacturing Process Yuehjen E.

More information

Graphical Models (Lecture 1 - Introduction)

Graphical Models (Lecture 1 - Introduction) Grahical Models Lecture - Introduction Tibério Caetano tiberiocaetano.com Statistical Machine Learning Grou NICTA Canberra LLSS Canberra 009 Tibério Caetano: Grahical Models Lecture - Introduction / 7

More information

Improved Bounds on Bell Numbers and on Moments of Sums of Random Variables

Improved Bounds on Bell Numbers and on Moments of Sums of Random Variables Imroved Bounds on Bell Numbers and on Moments of Sums of Random Variables Daniel Berend Tamir Tassa Abstract We rovide bounds for moments of sums of sequences of indeendent random variables. Concentrating

More information

Estimation of the large covariance matrix with two-step monotone missing data

Estimation of the large covariance matrix with two-step monotone missing data Estimation of the large covariance matrix with two-ste monotone missing data Masashi Hyodo, Nobumichi Shutoh 2, Takashi Seo, and Tatjana Pavlenko 3 Deartment of Mathematical Information Science, Tokyo

More information

actuators ISSN

actuators ISSN Actuators 2013, 2, 1-18; doi:10.3390/act2010001 Article OPEN ACCESS actuators ISSN 2076-0825 www.mdi.com/journal/actuators State Sace Sstem Identification of 3-Degree-of-Freedom (DOF) Piezo-Actuator-Driven

More information

Design of NARMA L-2 Control of Nonlinear Inverted Pendulum

Design of NARMA L-2 Control of Nonlinear Inverted Pendulum International Research Journal of Alied and Basic Sciences 016 Available online at www.irjabs.com ISSN 51-838X / Vol, 10 (6): 679-684 Science Exlorer Publications Design of NARMA L- Control of Nonlinear

More information

Agricultural Systems

Agricultural Systems Agricultural Systems 101 (2009) 101 109 Contents lists available at ScienceDirect Agricultural Systems journal homeage: www.elsevier.com/locate/agsy A GIS-integrated fuzzy rule-based inference system for

More information

Empirical Bayesian EM-based Motion Segmentation

Empirical Bayesian EM-based Motion Segmentation Emirical Bayesian EM-based Motion Segmentation Nuno Vasconcelos Andrew Liman MIT Media Laboratory 0 Ames St, E5-0M, Cambridge, MA 09 fnuno,lig@media.mit.edu Abstract A recent trend in motion-based segmentation

More information

Monopolist s mark-up and the elasticity of substitution

Monopolist s mark-up and the elasticity of substitution Croatian Oerational Research Review 377 CRORR 8(7), 377 39 Monoolist s mark-u and the elasticity of substitution Ilko Vrankić, Mira Kran, and Tomislav Herceg Deartment of Economic Theory, Faculty of Economics

More information

A Unified 2D Representation of Fuzzy Reasoning, CBR, and Experience Based Reasoning

A Unified 2D Representation of Fuzzy Reasoning, CBR, and Experience Based Reasoning University of Wollongong Research Online Faculty of Commerce - aers (Archive) Faculty of Business 26 A Unified 2D Reresentation of Fuzzy Reasoning, CBR, and Exerience Based Reasoning Zhaohao Sun University

More information

CMSC 425: Lecture 7 Geometric Programming: Sample Solutions

CMSC 425: Lecture 7 Geometric Programming: Sample Solutions CMSC 425: Lecture 7 Geometric Programming: Samle Solutions Samles: In the last few lectures, we have been discussing affine and Euclidean geometr, coordinate frames and affine transformations, and rotations.

More information

The decision-feedback equalizer optimization for Gaussian noise

The decision-feedback equalizer optimization for Gaussian noise Journal of Theoretical and Alied Comuter Science Vol. 8 No. 4 4. 5- ISSN 99-634 (rinted 3-5653 (online htt://www.jtacs.org The decision-feedback eualizer otimization for Gaussian noise Arkadiusz Grzbowski

More information

Towards understanding the Lorenz curve using the Uniform distribution. Chris J. Stephens. Newcastle City Council, Newcastle upon Tyne, UK

Towards understanding the Lorenz curve using the Uniform distribution. Chris J. Stephens. Newcastle City Council, Newcastle upon Tyne, UK Towards understanding the Lorenz curve using the Uniform distribution Chris J. Stehens Newcastle City Council, Newcastle uon Tyne, UK (For the Gini-Lorenz Conference, University of Siena, Italy, May 2005)

More information

Elements of Asymptotic Theory. James L. Powell Department of Economics University of California, Berkeley

Elements of Asymptotic Theory. James L. Powell Department of Economics University of California, Berkeley Elements of Asymtotic Theory James L. Powell Deartment of Economics University of California, Berkeley Objectives of Asymtotic Theory While exact results are available for, say, the distribution of the

More information

DEPARTMENT OF ECONOMICS ISSN DISCUSSION PAPER 20/07 TWO NEW EXPONENTIAL FAMILIES OF LORENZ CURVES

DEPARTMENT OF ECONOMICS ISSN DISCUSSION PAPER 20/07 TWO NEW EXPONENTIAL FAMILIES OF LORENZ CURVES DEPARTMENT OF ECONOMICS ISSN 1441-549 DISCUSSION PAPER /7 TWO NEW EXPONENTIAL FAMILIES OF LORENZ CURVES ZuXiang Wang * & Russell Smyth ABSTRACT We resent two new Lorenz curve families by using the basic

More information

PHYS 301 HOMEWORK #9-- SOLUTIONS

PHYS 301 HOMEWORK #9-- SOLUTIONS PHYS 0 HOMEWORK #9-- SOLUTIONS. We are asked to use Dirichlet' s theorem to determine the value of f (x) as defined below at x = 0, ± /, ± f(x) = 0, - < x

More information

Polar Coordinates; Vectors

Polar Coordinates; Vectors Polar Coordinates; Vectors Earth Scientists Use Fractals to Measure and Predict Natural Disasters Predicting the size, location, and timing of natural hazards is virtuall imossible, but now earth scientists

More information

Basic statistical models

Basic statistical models Basic statistical models Valery Pokrovsky March 27, 2012 Part I Ising model 1 Definition and the basic roerties The Ising model (IM) was invented by Lenz. His student Ising has found the artition function

More information

2x2x2 Heckscher-Ohlin-Samuelson (H-O-S) model with factor substitution

2x2x2 Heckscher-Ohlin-Samuelson (H-O-S) model with factor substitution 2x2x2 Heckscher-Ohlin-amuelson (H-O- model with factor substitution The HAT ALGEBRA of the Heckscher-Ohlin model with factor substitution o far we were dealing with the easiest ossible version of the H-O-

More information

A Note on Guaranteed Sparse Recovery via l 1 -Minimization

A Note on Guaranteed Sparse Recovery via l 1 -Minimization A Note on Guaranteed Sarse Recovery via l -Minimization Simon Foucart, Université Pierre et Marie Curie Abstract It is roved that every s-sarse vector x C N can be recovered from the measurement vector

More information

Improved Capacity Bounds for the Binary Energy Harvesting Channel

Improved Capacity Bounds for the Binary Energy Harvesting Channel Imroved Caacity Bounds for the Binary Energy Harvesting Channel Kaya Tutuncuoglu 1, Omur Ozel 2, Aylin Yener 1, and Sennur Ulukus 2 1 Deartment of Electrical Engineering, The Pennsylvania State University,

More information

RUN-TO-RUN CONTROL AND PERFORMANCE MONITORING OF OVERLAY IN SEMICONDUCTOR MANUFACTURING. 3 Department of Chemical Engineering

RUN-TO-RUN CONTROL AND PERFORMANCE MONITORING OF OVERLAY IN SEMICONDUCTOR MANUFACTURING. 3 Department of Chemical Engineering Coyright 2002 IFAC 15th Triennial World Congress, Barcelona, Sain RUN-TO-RUN CONTROL AND PERFORMANCE MONITORING OF OVERLAY IN SEMICONDUCTOR MANUFACTURING C.A. Bode 1, B.S. Ko 2, and T.F. Edgar 3 1 Advanced

More information

Handling Uncertainty using FUZZY LOGIC

Handling Uncertainty using FUZZY LOGIC Handling Uncertainty using FUZZY LOGIC Fuzzy Set Theory Conventional (Boolean) Set Theory: 38 C 40.1 C 41.4 C 38.7 C 39.3 C 37.2 C 42 C Strong Fever 38 C Fuzzy Set Theory: 38.7 C 40.1 C 41.4 C More-or-Less

More information

An Investigation on the Numerical Ill-conditioning of Hybrid State Estimators

An Investigation on the Numerical Ill-conditioning of Hybrid State Estimators An Investigation on the Numerical Ill-conditioning of Hybrid State Estimators S. K. Mallik, Student Member, IEEE, S. Chakrabarti, Senior Member, IEEE, S. N. Singh, Senior Member, IEEE Deartment of Electrical

More information

Multivariable Generalized Predictive Scheme for Gas Turbine Control in Combined Cycle Power Plant

Multivariable Generalized Predictive Scheme for Gas Turbine Control in Combined Cycle Power Plant Multivariable Generalized Predictive Scheme for Gas urbine Control in Combined Cycle Power Plant L.X.Niu and X.J.Liu Deartment of Automation North China Electric Power University Beiing, China, 006 e-mail

More information

How to Estimate Expected Shortfall When Probabilities Are Known with Interval or Fuzzy Uncertainty

How to Estimate Expected Shortfall When Probabilities Are Known with Interval or Fuzzy Uncertainty How to Estimate Exected Shortfall When Probabilities Are Known with Interval or Fuzzy Uncertainty Christian Servin Information Technology Deartment El Paso Community College El Paso, TX 7995, USA cservin@gmail.com

More information

and INVESTMENT DECISION-MAKING

and INVESTMENT DECISION-MAKING CONSISTENT INTERPOLATIVE FUZZY LOGIC and INVESTMENT DECISION-MAKING Darko Kovačević, č Petar Sekulić and dal Aleksandar Rakićević National bank of Serbia Belgrade, Jun 23th, 20 The structure of the resentation

More information

Chapter 9 Practical cycles

Chapter 9 Practical cycles Prof.. undararajan Chater 9 Practical cycles 9. Introduction In Chaters 7 and 8, it was shown that a reversible engine based on the Carnot cycle (two reversible isothermal heat transfers and two reversible

More information

FE FORMULATIONS FOR PLASTICITY

FE FORMULATIONS FOR PLASTICITY G These slides are designed based on the book: Finite Elements in Plasticity Theory and Practice, D.R.J. Owen and E. Hinton, 1970, Pineridge Press Ltd., Swansea, UK. 1 Course Content: A INTRODUCTION AND

More information