Rev. Téc. Ing. Univ. Zulia. Vol. 39, Nº 1, , 2016

Size: px
Start display at page:

Download "Rev. Téc. Ing. Univ. Zulia. Vol. 39, Nº 1, , 2016"

Transcription

1 Rev. Téc. Ing. Univ. Zulia. Vol. 39, Nº 1, , 216 doi: / Face Deecion and Recogniion Based on an Improved Adaboos Algorihm and Neural Nework Haoian Zhang*, Jiajia Xing, Muian Zhu, Dan Wu, Zheyu Yang Deparmen of Engineering and Compuing Sciences, New York Insiue of Technology, 1855 Broadway, New York, NY , USA School of Overseas Educaion, Nanjing Universiy of Poss and Telecommunicaions, Nanjing, Jiangsu, 21116, China *Corresponding auhor Absrac In recen years, face deecion and face recogniion based on images have been widely used in various fields. This paper focuses on face deecion mehods based on he Adaboos algorihm, opimizes and improves he weigh updaing rules of he Adaboos face deecion algorihm. Resuls indicae ha he opimized Adaboos algorihm has no only been grealy improved in compuing speed and face posiioning effec, bu also been inegraed ino a neural nework model for face idenificaion. I is found ha no only faces of poor image qualiy can be recognized, he compuing speed and ani-inerference abiliy are beer han radiional face deecion and recogniion algorihms. Therein, he comprehensive face recogniion rae in ORL daabase reaches more han 98%. The recogniion rae is high. 1. INTRODUCTION Face deecion is a key echnology in face informaion processing. Reliable face deecion is a premise of efficien face recogniion(turk M and Penland A, 1991; Sirovich L and Kirby M, 1987).Among hem, he use of face informaion mainly includes wo aspecs: face deecion and face recogniion. Face deecion is he firs link in he exracion of face informaion, whose deecion performance will direcly affec he exracion of face informaion and furher affec subsequen face recogniion. In recen years, face deecion and face recogniion echnology based on saic images and dynamic videos has been brough o grea aenion in he field of paern recogniion and compuer vision (Reed T R and Du Buf J M H, 1993; Chen C H and Pan L F, 1993;Brooks R A, 1983; Pope A R, 1994; Chin R T and Dyer C R, 1986). Generally speaking, curren face deecion mehods can be divided ino wo ypes: deecion based on knowledge and deecion based on saisics (Brunelli R and Poggio T,1993). Face deecion based on knowledge mainly regards face as a combinaion of organ feaures according o prior knowledge. I deecs faces based on feaures of eyes, e yebrows, mouh, nose and oher organs, as well as heir relaive geomeric posiions. Face deecion based on saisics, however, regards face as a 2D daa marix and judge wheher a face exiss or no from similariy, by consrucing face paern space. This paper carries ou an in-deph sudy ino face deecion mehods based on Adaboos, pus forward an improved he opimized Adaboos algorihm, exracs all face informaion in an image using his model and inegraes i ino a neural nework model(brosch T and Tam R, 215), o deec and recognize various faceconaining images (Y. Boureau and F. Bach, 21; I. J. Goodfellow and Q. V. Le, 29; G. E. Hinon, S, 26; J. Yang and K. Yu, 29; Marina E. Plissii and HrisophorosNikou, 211; Q. C. Chen and Q. S. Sun, 28). Experimenal resuls show ha boh he face deecion and face recogniion raes of he opimized Adaboos algorihm inegraed ino neural nework model in his paper are high. No only images of poor qualiy can be processed, he compuing speed and ani-inerference abiliy are beer han radiional face deecion and recogniion mehods. 2. OPTIMIZATION OF THE ADABOOST FACE DETECTION ALGORITHM The core idea of radiional Adaboos algorihms is aimed a he same raining daabase. Several differen weak classifiers are produced in he process of raining and some beer classifiers are combined ino ulimae srong classifiers. The raining process only includes: (1)To exrac Haar feaures in an image; (2)To ransform he Haar feaures ino corresponding weak classifiers; (3)To selec he bes weak classifiers from a large number of weak classifiers and combine hem ino opimal srong classifiers. However, he daa size during face deecion and face raining is large. Generally each weak classifier has ens of housands of raining samples. When here are many sample objecs ha are difficul o disinguish in raining samples, ofen as rainings imes increase, he weighs of indisinguishable sample images will be high and model raining will focus on his par of samples. As a resul, he raining will be oo long and over fiing will occur in model resuls. Therefore, his paper improves he weigh updaing algorihm in he Adaboos

2 Rev. Téc. Ing. Univ. Zulia. Vol. 39, Nº 1, , 216 raining process and judges wheher a weigh needs o be updaed by seing a weigh updaing hreshold. The deailed calculaion seps of he opimized model are as follows: Sep 1: To classify and number N raining samples, where m face samples are labeled as y i =1 and N-m non-face samples are labeled as y i =-1. Sep 2: To iniialize he weighs of N raining samples. Sep 3: In he process of he h ieraion raining, selec T weak classifiers, and calculae he ieraion error sum of T weak classifiers see formula (1) and relaive error raio see formula (2). N w h y (1) i i1 ij i i (2) 1 Sep 4: In each ieraion, calculae he hreshold HW. When various image weighs are updaed, if a weigh is greaer han HW or a sample belongs o a correc class, he weigh will no longer be adjused. Oherwise, when a sample is wrongly classified and he curren weigh D i is smaller han he hreshold HW of curren ieraion, he weigh of image should be adjused. The calculaion formulas of weigh adjusmen expression and hreshold HW in each ieraion are as follows: a e hi yi Di a Di 1 e hi yi, Di HW (3) Zi a e hi yi, Di HW Di i (4) HW 1 N Where Z is he normalizaion facor of Di 1( xi ), generally D i 1 ( x 1 ). HW is he weigh updaing hreshold of he h ieraion. Sep 5: Afer a model raining ieraion is compleed, several beer classifiers will be combined linearly o ge srong classifiers. As shown below, hey will be conneced in series o form a sric cascade classifier. T 1 T 1 (log1 ) ( ) log1 1 h x 1 h ( ) 2 f x (5) T 1 T (log1 ) ( ) log1 1 h x FACE DETECTION EXPERIMENT ON THE OPTIMIZED ADABOOST ALGORITHM The above improved Adaboos algorihm is used for face deecion. Images of differen qualiies are esed respecively. Experimenal resuls show ha he opimized Adaboos algorihm has beer face deecion performance. The resuls are shown in Table 1 below, and par of he face deecion resuls are shown in Fig. (1) below: Table 1. Face Deecion Resuls Real Faces Deeced Faces Deecion Rae% Loss Rae% Error Rae% Image Qualiy N

3 Rev. Téc. Ing. Univ. Zulia. Vol. 39, Nº 1, , 216 Figure 1. Par of he Face Deecion Resuls From he above experimenal resuls of he opimized Adaboos face deecion model, we can see ha for images of differen qualiies, face deecion can sill be achieved perfecly. Boh he compuing speed and aniinerference abiliy are beer han radiional Adaboos face deecion algorihms. 4. FACE RECOGNITION EXPERIMENT ON THE OPTIMIZED ADABOOST INTEGRATED INTO NEURAL NETWORK MODEL The purpose of face recogniion is o exrac personalized feaures from face images, so as o idenify he ideniy of a person. A complee face recogniion sysem mainly includes face deecion, face sandardizaion, face characerizaion and face recogniion. From he above face deecion experimen, we can see ha for a given image, he opimized Adaboos algorihm can basically deec all exising faces in an image. In order o fully demonsrae ha he opimized Adaboos model can provide favorable values for subsequen face idenificaion, on his basis, his paper probes ino a face recogniion model based on he opimized Adaboos algorihm inegraed ino neural nework. The face recogniion model flows of he opimized Adaboos algorihm inegraed ino neural nework designed in his paper are as follows: Sep 1: Firs of all, unify pixel sizes of all face raining samples as 2*5. Exrac each line of pixels according o pixel levels and ransform hem ino a column marix line by line as inpu informaion o rain BP neural nework model. The deailed nework convergence and nework srucure parameers in he firs deecion and recogniion are shown in Table 2 below: Sep 2: To use he opimized Adaboos algorihm o deec faces in a given image and exrac all of hem. Sep 3: To process pixels in he exraced face areas in Sep 2, according o Sep 1. Sep 4: To inpu face informaion derived from Sep 3 ino a neural nework model and recognize relevan faces. Par of he face deecion and recogniion resuls of he opimized Adaboos algorihm inegraed ino neural nework model is shown in Fig. (2) below:

4 Rev. Téc. Ing. Univ. Zulia. Vol. 39, Nº 1, , 216 Figure 2. Resuls of BP Nework Model Training Convergence Table 2. Key Parameers in Nework Training Seing and Nework Convergence Nework Training Parameers Nodes a he firs level Nodes a he second level Nework arge error Nework raining funcion *e-8 rainrp Nework Convergence Parameers Nework raining imes Nework raining ime (sec) Nework convergence error Nework goodness of fi *1-8 1 (a) (b) Figure 3. Face Recogniion Resuls of he Opimized Adaboos Algorihm Inegraed ino Neural Nework Model. Fig. (a) The deecion and recogniion of differen expressions of he same face; Fig. (b) The deecion and recogniion of differen faces and expressions

5 Rev. Téc. Ing. Univ. Zulia. Vol. 39, Nº 1, , 216 The above opimized Adaboos model inegraed ino neural nework is used for face recogniion. The face daa base involved is ORL face daa base from Olivee Lab. There are a oal of 4 face images in ORL daabase. This daabase includes 4 persons and 1 face images of each. The resoluion of each image is 92 pixels by 112 pixels. In order o ensure he generaliy of experimen, 4 images of each person are seleced and made ino raining samples during experimen. The remaining face images of each person (6) are made ino es samples. During es, he raining samples and es samples are esed separaely for 5 imes. The derived 5 comprehensive recogniion raes are averaged, as recogniion accuracy rae of he final model. The recogniion resuls are shown in Table 3 below: Tes Times Table 3. Face Recogniion Rae of he Opimized Adaboos Model Inegraed ino Neural Nework Training Samples Tes Samples Recogniion Accuracy of Training Samples Recogniion Accuracy of Tes Samples Comprehensive Recogniion Accuracy CONCLUSION By opimizing and improving he weigh updaing rules of he Adaboos face deecion algorihm, his paper prevens model raining from focusing on difficul samples a he laer sage and oo large weighs of difficul samples, caused by he exisence of difficul raining samples. By seing new weigh updaing rules, overmaching is avoided. Resuls show ha he opimized Adaboos algorihm has no only been grealy improved in compuing speed and face posiioning effec, bu also been inegraed ino a neural nework model for face idenificaion. I is found ha no only faces of poor image qualiy can be recognized, he compuing speed and ani-inerference abiliy are beer han radiional face deecion and recogniion algorihms. Therein, he comprehensive face recogniion rae in ORL daabase reaches more han 99%. The recogniion rae is high. CONFLICT OF INTEREST The auhors confirm ha his aricle conen has no conflics of ineres. Acknowledgmen This work is suppored by he Key Projec of Science and Technology Innovaion Training Program (STITP) No. XZD REFERENCES Turk M, Penland A. (1987) Eigenfaxes for recogniion,.journal of Cogniive Neuroscience,3(1), pp Sirovich L, Kirby M. (1987) -dimensional procedure for he characerizaion of human faces.journal of he Opical Sociey of America A:Opics Image Seience and Vision,4(3), pp Reed T R, Du Buf J M H. (1993) A review of recen exure segmenaion, feaure exracion echniques.cvgip Image Undersanding,1993(57), pp Chen C H, Pan L F, Wang P S P.(1993) Handbook of Paern Recogniion and Compuer Vision. Singapore: world Scienific Publishing, pp Brooks R A. Model-based hree-dimensional inerpreaions of wo-dimensional images.paern Analysis and Machine Inelligence, 1983,5(2), pp Pope A R. (214) Model-Based Objec Recogniion: A Survey of Recen Research. Technical Repor, 1994, 22(11), pp Chin R T, Dyer C R. (1986) Model-Based Recogniion in Robo Vision. Compuing Surveys,18(1), pp Brunelli R, Poggio T. Face recogniion: Feaures versus emplaes. Paern Analysis and Machine Inelligence, 1993,15(1), pp Brosch T, Tam R.(215) Efficien Training of Convoluional Deep Belief Neworks in he Frequency Domain for Applicaion o High-Resoluion 2D and 3D Images. Neural Compuaion, 27(1), pp Y. Boureau, F. Bach, Y. LeCun, and J. Ponce. (21) Learning mid-level feaures for recogniion. In IEEE Conference on Compuer Vision and Paern Recogniion. Pp

6 Rev. Téc. Ing. Univ. Zulia. Vol. 39, Nº 1, , 216 I. J. Goodfellow, Q. V. Le, A. M. Saxe, H. Lee, and A. Y. Ng. Measuring invariances in deep neworks. In NIPS, 29. G. E. Hinon, S. Osindero, and Y. W. Teh. A fas learning algorihm for deep belief nes. Neural Compuaion. 26, 18(7), pp J. Yang, K. Yu, Y. Gong, and T. S. Huang. Linear spaial pyramid maching using sparse coding for image classificaion. In CVPR, 29, Marina E. Plissii, HrisophorosNikou. Anonia Charchani, Combining shape, exure and inensiy feaures for cell nuclei exracion in Pap smear images, Paern Recogniion Leers. 211, 23, pp Q. C. Chen, Q. S. Sun, P. A. Heng and D. S. Xia, "Adouble-hreshold image binarizaion mehod based on edge deecor", Paern Recogniion. 28, (41), pp

A Video Vehicle Detection Algorithm Based on Improved Adaboost Algorithm Weiguang Liu and Qian Zhang*

A Video Vehicle Detection Algorithm Based on Improved Adaboost Algorithm Weiguang Liu and Qian Zhang* A Video Vehicle Deecion Algorihm Based on Improved Adaboos Algorihm Weiguang Liu and Qian Zhang* Zhongyuan Universiy of Technology, Zhengzhou 450000, China lwg66123@163.com, 2817343431@qq.com *The corresponding

More information

Ensamble methods: Bagging and Boosting

Ensamble methods: Bagging and Boosting Lecure 21 Ensamble mehods: Bagging and Boosing Milos Hauskrech milos@cs.pi.edu 5329 Senno Square Ensemble mehods Mixure of expers Muliple base models (classifiers, regressors), each covers a differen par

More information

Ensamble methods: Boosting

Ensamble methods: Boosting Lecure 21 Ensamble mehods: Boosing Milos Hauskrech milos@cs.pi.edu 5329 Senno Square Schedule Final exam: April 18: 1:00-2:15pm, in-class Term projecs April 23 & April 25: a 1:00-2:30pm in CS seminar room

More information

Adaptive Compressive Tracking Based on Perceptual Hash Algorithm Lei ZHANG, Zheng-guang XIE * and Hong-jun LI

Adaptive Compressive Tracking Based on Perceptual Hash Algorithm Lei ZHANG, Zheng-guang XIE * and Hong-jun LI 2017 2nd Inernaional Conference on Informaion Technology and Managemen Engineering (ITME 2017) ISBN: 978-1-60595-415-8 Adapive Compressive Tracking Based on Percepual Hash Algorihm Lei ZHANG, Zheng-guang

More information

Random Walk with Anti-Correlated Steps

Random Walk with Anti-Correlated Steps Random Walk wih Ani-Correlaed Seps John Noga Dirk Wagner 2 Absrac We conjecure he expeced value of random walks wih ani-correlaed seps o be exacly. We suppor his conjecure wih 2 plausibiliy argumens and

More information

Subspace LDA Methods for Solving the Small Sample Size Problem in Face Recognition

Subspace LDA Methods for Solving the Small Sample Size Problem in Face Recognition Proceedings of he Inernaional Conference on Compuer and Informaion Science and Technology Oawa, Onario, Canada, May 11 12, 2015 Paper No. 126 Subspace LDA Mehods for Solving he Small Sample Size Problem

More information

Content-Based Shape Retrieval Using Different Shape Descriptors: A Comparative Study Dengsheng Zhang and Guojun Lu

Content-Based Shape Retrieval Using Different Shape Descriptors: A Comparative Study Dengsheng Zhang and Guojun Lu Conen-Based Shape Rerieval Using Differen Shape Descripors: A Comparaive Sudy Dengsheng Zhang and Guojun Lu Gippsland School of Compuing and Informaion Technology Monash Universiy Churchill, Vicoria 3842

More information

CHAPTER 10 VALIDATION OF TEST WITH ARTIFICAL NEURAL NETWORK

CHAPTER 10 VALIDATION OF TEST WITH ARTIFICAL NEURAL NETWORK 175 CHAPTER 10 VALIDATION OF TEST WITH ARTIFICAL NEURAL NETWORK 10.1 INTRODUCTION Amongs he research work performed, he bes resuls of experimenal work are validaed wih Arificial Neural Nework. From he

More information

Article from. Predictive Analytics and Futurism. July 2016 Issue 13

Article from. Predictive Analytics and Futurism. July 2016 Issue 13 Aricle from Predicive Analyics and Fuurism July 6 Issue An Inroducion o Incremenal Learning By Qiang Wu and Dave Snell Machine learning provides useful ools for predicive analyics The ypical machine learning

More information

Retrieval Models. Boolean and Vector Space Retrieval Models. Common Preprocessing Steps. Boolean Model. Boolean Retrieval Model

Retrieval Models. Boolean and Vector Space Retrieval Models. Common Preprocessing Steps. Boolean Model. Boolean Retrieval Model 1 Boolean and Vecor Space Rerieval Models Many slides in his secion are adaped from Prof. Joydeep Ghosh (UT ECE) who in urn adaped hem from Prof. Dik Lee (Univ. of Science and Tech, Hong Kong) Rerieval

More information

STATE-SPACE MODELLING. A mass balance across the tank gives:

STATE-SPACE MODELLING. A mass balance across the tank gives: B. Lennox and N.F. Thornhill, 9, Sae Space Modelling, IChemE Process Managemen and Conrol Subjec Group Newsleer STE-SPACE MODELLING Inroducion: Over he pas decade or so here has been an ever increasing

More information

Single-Pass-Based Heuristic Algorithms for Group Flexible Flow-shop Scheduling Problems

Single-Pass-Based Heuristic Algorithms for Group Flexible Flow-shop Scheduling Problems Single-Pass-Based Heurisic Algorihms for Group Flexible Flow-shop Scheduling Problems PEI-YING HUANG, TZUNG-PEI HONG 2 and CHENG-YAN KAO, 3 Deparmen of Compuer Science and Informaion Engineering Naional

More information

Deep Learning: Theory, Techniques & Applications - Recurrent Neural Networks -

Deep Learning: Theory, Techniques & Applications - Recurrent Neural Networks - Deep Learning: Theory, Techniques & Applicaions - Recurren Neural Neworks - Prof. Maeo Maeucci maeo.maeucci@polimi.i Deparmen of Elecronics, Informaion and Bioengineering Arificial Inelligence and Roboics

More information

Application of a Stochastic-Fuzzy Approach to Modeling Optimal Discrete Time Dynamical Systems by Using Large Scale Data Processing

Application of a Stochastic-Fuzzy Approach to Modeling Optimal Discrete Time Dynamical Systems by Using Large Scale Data Processing Applicaion of a Sochasic-Fuzzy Approach o Modeling Opimal Discree Time Dynamical Sysems by Using Large Scale Daa Processing AA WALASZE-BABISZEWSA Deparmen of Compuer Engineering Opole Universiy of Technology

More information

Tracking. Announcements

Tracking. Announcements Tracking Tuesday, Nov 24 Krisen Grauman UT Ausin Announcemens Pse 5 ou onigh, due 12/4 Shorer assignmen Auo exension il 12/8 I will no hold office hours omorrow 5 6 pm due o Thanksgiving 1 Las ime: Moion

More information

Hidden Markov Models

Hidden Markov Models Hidden Markov Models Probabilisic reasoning over ime So far, we ve mosly deal wih episodic environmens Excepions: games wih muliple moves, planning In paricular, he Bayesian neworks we ve seen so far describe

More information

Presentation Overview

Presentation Overview Acion Refinemen in Reinforcemen Learning by Probabiliy Smoohing By Thomas G. Dieerich & Didac Busques Speaer: Kai Xu Presenaion Overview Bacground The Probabiliy Smoohing Mehod Experimenal Sudy of Acion

More information

Object Tracking. Computer Vision Jia-Bin Huang, Virginia Tech. Many slides from D. Hoiem

Object Tracking. Computer Vision Jia-Bin Huang, Virginia Tech. Many slides from D. Hoiem Objec Tracking Compuer Vision Jia-Bin Huang Virginia Tech Man slides from D. Hoiem Adminisraive suffs HW 5 (Scene caegorizaion) Due :59pm on Wed November 6 oll on iazza When should we have he final exam?

More information

Mechanical Fatigue and Load-Induced Aging of Loudspeaker Suspension. Wolfgang Klippel,

Mechanical Fatigue and Load-Induced Aging of Loudspeaker Suspension. Wolfgang Klippel, Mechanical Faigue and Load-Induced Aging of Loudspeaker Suspension Wolfgang Klippel, Insiue of Acousics and Speech Communicaion Dresden Universiy of Technology presened a he ALMA Symposium 2012, Las Vegas

More information

Supplement for Stochastic Convex Optimization: Faster Local Growth Implies Faster Global Convergence

Supplement for Stochastic Convex Optimization: Faster Local Growth Implies Faster Global Convergence Supplemen for Sochasic Convex Opimizaion: Faser Local Growh Implies Faser Global Convergence Yi Xu Qihang Lin ianbao Yang Proof of heorem heorem Suppose Assumpion holds and F (w) obeys he LGC (6) Given

More information

Air Traffic Forecast Empirical Research Based on the MCMC Method

Air Traffic Forecast Empirical Research Based on the MCMC Method Compuer and Informaion Science; Vol. 5, No. 5; 0 ISSN 93-8989 E-ISSN 93-8997 Published by Canadian Cener of Science and Educaion Air Traffic Forecas Empirical Research Based on he MCMC Mehod Jian-bo Wang,

More information

Modal identification of structures from roving input data by means of maximum likelihood estimation of the state space model

Modal identification of structures from roving input data by means of maximum likelihood estimation of the state space model Modal idenificaion of srucures from roving inpu daa by means of maximum likelihood esimaion of he sae space model J. Cara, J. Juan, E. Alarcón Absrac The usual way o perform a forced vibraion es is o fix

More information

Air Quality Index Prediction Using Error Back Propagation Algorithm and Improved Particle Swarm Optimization

Air Quality Index Prediction Using Error Back Propagation Algorithm and Improved Particle Swarm Optimization Air Qualiy Index Predicion Using Error Back Propagaion Algorihm and Improved Paricle Swarm Opimizaion Jia Xu ( ) and Lang Pei College of Compuer Science, Wuhan Qinchuan Universiy, Wuhan, China 461406563@qq.com

More information

Particle Swarm Optimization

Particle Swarm Optimization Paricle Swarm Opimizaion Speaker: Jeng-Shyang Pan Deparmen of Elecronic Engineering, Kaohsiung Universiy of Applied Science, Taiwan Email: jspan@cc.kuas.edu.w 7/26/2004 ppso 1 Wha is he Paricle Swarm Opimizaion

More information

Vehicle Arrival Models : Headway

Vehicle Arrival Models : Headway Chaper 12 Vehicle Arrival Models : Headway 12.1 Inroducion Modelling arrival of vehicle a secion of road is an imporan sep in raffic flow modelling. I has imporan applicaion in raffic flow simulaion where

More information

The ROC-Boost Design Algorithm for Asymmetric Classification

The ROC-Boost Design Algorithm for Asymmetric Classification The ROC-Boos Design Algorihm for Asymmeric Classificaion Guido Cesare Deparmen of Mahemaics Universiy of Genova (Ialy guido.cesare@gmail.com Robero Manduchi Deparmen of Compuer Engineering Universiy of

More information

Journal of Chemical and Pharmaceutical Research, 2014, 6(5): Research Article

Journal of Chemical and Pharmaceutical Research, 2014, 6(5): Research Article Available online www.jocpr.com Journal of Chemical and Pharmaceuical Research, 204, 6(5):70-705 Research Aricle ISSN : 0975-7384 CODEN(USA) : JCPRC5 Cells formaion wih a muli-objecive geneic algorihm Jun

More information

5 The fitting methods used in the normalization of DSD

5 The fitting methods used in the normalization of DSD The fiing mehods used in he normalizaion of DSD.1 Inroducion Sempere-Torres e al. 1994 presened a general formulaion for he DSD ha was able o reproduce and inerpre all previous sudies of DSD. The mehodology

More information

HYPERSPECTRAL IMAGE CLASSIFICATIO BASED O A FAST BREGMA SPARSE MULTI OMIAL LOGISTIC REGRESSIO ALGORITHM. Portugal - (jun,

HYPERSPECTRAL IMAGE CLASSIFICATIO BASED O A FAST BREGMA SPARSE MULTI OMIAL LOGISTIC REGRESSIO ALGORITHM. Portugal - (jun, HYPERSPECRAL IMAGE CLASSIFICAIO BASED O A FAS BREGMA SPARSE MULI OMIAL LOGISIC REGRESSIO ALGORIHM J. Li a, *, J. Bioucas-Dias a, Anonio Plaza b a Insiuo de elecomunicações, Insiuo Superior écnico, 049-00,

More information

An introduction to the theory of SDDP algorithm

An introduction to the theory of SDDP algorithm An inroducion o he heory of SDDP algorihm V. Leclère (ENPC) Augus 1, 2014 V. Leclère Inroducion o SDDP Augus 1, 2014 1 / 21 Inroducion Large scale sochasic problem are hard o solve. Two ways of aacking

More information

ODEs II, Lecture 1: Homogeneous Linear Systems - I. Mike Raugh 1. March 8, 2004

ODEs II, Lecture 1: Homogeneous Linear Systems - I. Mike Raugh 1. March 8, 2004 ODEs II, Lecure : Homogeneous Linear Sysems - I Mike Raugh March 8, 4 Inroducion. In he firs lecure we discussed a sysem of linear ODEs for modeling he excreion of lead from he human body, saw how o ransform

More information

Time series Decomposition method

Time series Decomposition method Time series Decomposiion mehod A ime series is described using a mulifacor model such as = f (rend, cyclical, seasonal, error) = f (T, C, S, e) Long- Iner-mediaed Seasonal Irregular erm erm effec, effec,

More information

Ensemble Confidence Estimates Posterior Probability

Ensemble Confidence Estimates Posterior Probability Ensemble Esimaes Poserior Probabiliy Michael Muhlbaier, Aposolos Topalis, and Robi Polikar Rowan Universiy, Elecrical and Compuer Engineering, Mullica Hill Rd., Glassboro, NJ 88, USA {muhlba6, opali5}@sudens.rowan.edu

More information

HW6: MRI Imaging Pulse Sequences (7 Problems for 100 pts)

HW6: MRI Imaging Pulse Sequences (7 Problems for 100 pts) HW6: MRI Imaging Pulse Sequences (7 Problems for 100 ps) GOAL The overall goal of HW6 is o beer undersand pulse sequences for MRI image reconsrucion. OBJECTIVES 1) Design a spin echo pulse sequence o image

More information

Authors. Introduction. Introduction

Authors. Introduction. Introduction Auhors Hidden Applied in Agriculural Crops Classificaion Caholic Universiy of Rio de Janeiro (PUC-Rio Paula B. C. Leie Raul Q. Feiosa Gilson A. O. P. Cosa Hidden Applied in Agriculural Crops Classificaion

More information

Explaining Total Factor Productivity. Ulrich Kohli University of Geneva December 2015

Explaining Total Factor Productivity. Ulrich Kohli University of Geneva December 2015 Explaining Toal Facor Produciviy Ulrich Kohli Universiy of Geneva December 2015 Needed: A Theory of Toal Facor Produciviy Edward C. Presco (1998) 2 1. Inroducion Toal Facor Produciviy (TFP) has become

More information

Hidden Markov Models. Adapted from. Dr Catherine Sweeney-Reed s slides

Hidden Markov Models. Adapted from. Dr Catherine Sweeney-Reed s slides Hidden Markov Models Adaped from Dr Caherine Sweeney-Reed s slides Summary Inroducion Descripion Cenral in HMM modelling Exensions Demonsraion Specificaion of an HMM Descripion N - number of saes Q = {q

More information

SUPPLEMENTARY INFORMATION

SUPPLEMENTARY INFORMATION SUPPLEMENTARY INFORMATION DOI: 0.038/NCLIMATE893 Temporal resoluion and DICE * Supplemenal Informaion Alex L. Maren and Sephen C. Newbold Naional Cener for Environmenal Economics, US Environmenal Proecion

More information

Isolated-word speech recognition using hidden Markov models

Isolated-word speech recognition using hidden Markov models Isolaed-word speech recogniion using hidden Markov models Håkon Sandsmark December 18, 21 1 Inroducion Speech recogniion is a challenging problem on which much work has been done he las decades. Some of

More information

Spring Ammar Abu-Hudrouss Islamic University Gaza

Spring Ammar Abu-Hudrouss Islamic University Gaza Chaper 7 Reed-Solomon Code Spring 9 Ammar Abu-Hudrouss Islamic Universiy Gaza ١ Inroducion A Reed Solomon code is a special case of a BCH code in which he lengh of he code is one less han he size of he

More information

3.1 More on model selection

3.1 More on model selection 3. More on Model selecion 3. Comparing models AIC, BIC, Adjused R squared. 3. Over Fiing problem. 3.3 Sample spliing. 3. More on model selecion crieria Ofen afer model fiing you are lef wih a handful of

More information

GMM - Generalized Method of Moments

GMM - Generalized Method of Moments GMM - Generalized Mehod of Momens Conens GMM esimaion, shor inroducion 2 GMM inuiion: Maching momens 2 3 General overview of GMM esimaion. 3 3. Weighing marix...........................................

More information

Refinement of Document Clustering by Using NMF *

Refinement of Document Clustering by Using NMF * Refinemen of Documen Clusering by Using NMF * Hiroyuki Shinnou and Minoru Sasaki Deparmen of Compuer and Informaion Sciences, Ibaraki Universiy, 4-12-1 Nakanarusawa, Hiachi, Ibaraki JAPAN 316-8511 {shinnou,

More information

Exponential Weighted Moving Average (EWMA) Chart Under The Assumption of Moderateness And Its 3 Control Limits

Exponential Weighted Moving Average (EWMA) Chart Under The Assumption of Moderateness And Its 3 Control Limits DOI: 0.545/mjis.07.5009 Exponenial Weighed Moving Average (EWMA) Char Under The Assumpion of Moderaeness And Is 3 Conrol Limis KALPESH S TAILOR Assisan Professor, Deparmen of Saisics, M. K. Bhavnagar Universiy,

More information

Shiva Akhtarian MSc Student, Department of Computer Engineering and Information Technology, Payame Noor University, Iran

Shiva Akhtarian MSc Student, Department of Computer Engineering and Information Technology, Payame Noor University, Iran Curren Trends in Technology and Science ISSN : 79-055 8hSASTech 04 Symposium on Advances in Science & Technology-Commission-IV Mashhad, Iran A New for Sofware Reliabiliy Evaluaion Based on NHPP wih Imperfec

More information

Lecture 2-1 Kinematics in One Dimension Displacement, Velocity and Acceleration Everything in the world is moving. Nothing stays still.

Lecture 2-1 Kinematics in One Dimension Displacement, Velocity and Acceleration Everything in the world is moving. Nothing stays still. Lecure - Kinemaics in One Dimension Displacemen, Velociy and Acceleraion Everyhing in he world is moving. Nohing says sill. Moion occurs a all scales of he universe, saring from he moion of elecrons in

More information

A unit root test based on smooth transitions and nonlinear adjustment

A unit root test based on smooth transitions and nonlinear adjustment MPRA Munich Personal RePEc Archive A uni roo es based on smooh ransiions and nonlinear adjusmen Aycan Hepsag Isanbul Universiy 5 Ocober 2017 Online a hps://mpra.ub.uni-muenchen.de/81788/ MPRA Paper No.

More information

Speaker Adaptation Techniques For Continuous Speech Using Medium and Small Adaptation Data Sets. Constantinos Boulis

Speaker Adaptation Techniques For Continuous Speech Using Medium and Small Adaptation Data Sets. Constantinos Boulis Speaker Adapaion Techniques For Coninuous Speech Using Medium and Small Adapaion Daa Ses Consaninos Boulis Ouline of he Presenaion Inroducion o he speaker adapaion problem Maximum Likelihood Sochasic Transformaions

More information

CE 395 Special Topics in Machine Learning

CE 395 Special Topics in Machine Learning CE 395 Special Topics in Machine Learning Assoc. Prof. Dr. Yuriy Mishchenko Fall 2017 DIGITAL FILTERS AND FILTERING Why filers? Digial filering is he workhorse of digial signal processing Filering is a

More information

1. VELOCITY AND ACCELERATION

1. VELOCITY AND ACCELERATION 1. VELOCITY AND ACCELERATION 1.1 Kinemaics Equaions s = u + 1 a and s = v 1 a s = 1 (u + v) v = u + as 1. Displacemen-Time Graph Gradien = speed 1.3 Velociy-Time Graph Gradien = acceleraion Area under

More information

Testing for a Single Factor Model in the Multivariate State Space Framework

Testing for a Single Factor Model in the Multivariate State Space Framework esing for a Single Facor Model in he Mulivariae Sae Space Framework Chen C.-Y. M. Chiba and M. Kobayashi Inernaional Graduae School of Social Sciences Yokohama Naional Universiy Japan Faculy of Economics

More information

Using the Kalman filter Extended Kalman filter

Using the Kalman filter Extended Kalman filter Using he Kalman filer Eended Kalman filer Doz. G. Bleser Prof. Sricker Compuer Vision: Objec and People Tracking SA- Ouline Recap: Kalman filer algorihm Using Kalman filers Eended Kalman filer algorihm

More information

Dimitri Solomatine. D.P. Solomatine. Data-driven modelling (part 2). 2

Dimitri Solomatine. D.P. Solomatine. Data-driven modelling (part 2). 2 Daa-driven modelling. Par. Daa-driven Arificial di Neural modelling. Newors Par Dimiri Solomaine Arificial neural newors D.P. Solomaine. Daa-driven modelling par. 1 Arificial neural newors ANN: main pes

More information

Linear Time-invariant systems, Convolution, and Cross-correlation

Linear Time-invariant systems, Convolution, and Cross-correlation Linear Time-invarian sysems, Convoluion, and Cross-correlaion (1) Linear Time-invarian (LTI) sysem A sysem akes in an inpu funcion and reurns an oupu funcion. x() T y() Inpu Sysem Oupu y() = T[x()] An

More information

OBJECTIVES OF TIME SERIES ANALYSIS

OBJECTIVES OF TIME SERIES ANALYSIS OBJECTIVES OF TIME SERIES ANALYSIS Undersanding he dynamic or imedependen srucure of he observaions of a single series (univariae analysis) Forecasing of fuure observaions Asceraining he leading, lagging

More information

The field of mathematics has made tremendous impact on the study of

The field of mathematics has made tremendous impact on the study of A Populaion Firing Rae Model of Reverberaory Aciviy in Neuronal Neworks Zofia Koscielniak Carnegie Mellon Universiy Menor: Dr. G. Bard Ermenrou Universiy of Pisburgh Inroducion: The field of mahemaics

More information

Stability and Bifurcation in a Neural Network Model with Two Delays

Stability and Bifurcation in a Neural Network Model with Two Delays Inernaional Mahemaical Forum, Vol. 6, 11, no. 35, 175-1731 Sabiliy and Bifurcaion in a Neural Nework Model wih Two Delays GuangPing Hu and XiaoLing Li School of Mahemaics and Physics, Nanjing Universiy

More information

Zürich. ETH Master Course: L Autonomous Mobile Robots Localization II

Zürich. ETH Master Course: L Autonomous Mobile Robots Localization II Roland Siegwar Margaria Chli Paul Furgale Marco Huer Marin Rufli Davide Scaramuzza ETH Maser Course: 151-0854-00L Auonomous Mobile Robos Localizaion II ACT and SEE For all do, (predicion updae / ACT),

More information

Adaptive Noise Estimation Based on Non-negative Matrix Factorization

Adaptive Noise Estimation Based on Non-negative Matrix Factorization dvanced cience and Technology Leers Vol.3 (ICC 213), pp.159-163 hp://dx.doi.org/1.14257/asl.213 dapive Noise Esimaion ased on Non-negaive Marix Facorizaion Kwang Myung Jeon and Hong Kook Kim chool of Informaion

More information

0.1 MAXIMUM LIKELIHOOD ESTIMATION EXPLAINED

0.1 MAXIMUM LIKELIHOOD ESTIMATION EXPLAINED 0.1 MAXIMUM LIKELIHOOD ESTIMATIO EXPLAIED Maximum likelihood esimaion is a bes-fi saisical mehod for he esimaion of he values of he parameers of a sysem, based on a se of observaions of a random variable

More information

Particle Swarm Optimization Combining Diversification and Intensification for Nonlinear Integer Programming Problems

Particle Swarm Optimization Combining Diversification and Intensification for Nonlinear Integer Programming Problems Paricle Swarm Opimizaion Combining Diversificaion and Inensificaion for Nonlinear Ineger Programming Problems Takeshi Masui, Masaoshi Sakawa, Kosuke Kao and Koichi Masumoo Hiroshima Universiy 1-4-1, Kagamiyama,

More information

Resource Allocation in Visible Light Communication Networks NOMA vs. OFDMA Transmission Techniques

Resource Allocation in Visible Light Communication Networks NOMA vs. OFDMA Transmission Techniques Resource Allocaion in Visible Ligh Communicaion Neworks NOMA vs. OFDMA Transmission Techniques Eirini Eleni Tsiropoulou, Iakovos Gialagkolidis, Panagiois Vamvakas, and Symeon Papavassiliou Insiue of Communicaions

More information

Waveform Transmission Method, A New Waveform-relaxation Based Algorithm. to Solve Ordinary Differential Equations in Parallel

Waveform Transmission Method, A New Waveform-relaxation Based Algorithm. to Solve Ordinary Differential Equations in Parallel Waveform Transmission Mehod, A New Waveform-relaxaion Based Algorihm o Solve Ordinary Differenial Equaions in Parallel Fei Wei Huazhong Yang Deparmen of Elecronic Engineering, Tsinghua Universiy, Beijing,

More information

Navneet Saini, Mayank Goyal, Vishal Bansal (2013); Term Project AML310; Indian Institute of Technology Delhi

Navneet Saini, Mayank Goyal, Vishal Bansal (2013); Term Project AML310; Indian Institute of Technology Delhi Creep in Viscoelasic Subsances Numerical mehods o calculae he coefficiens of he Prony equaion using creep es daa and Herediary Inegrals Mehod Navnee Saini, Mayank Goyal, Vishal Bansal (23); Term Projec

More information

LAB 5: Computer Simulation of RLC Circuit Response using PSpice

LAB 5: Computer Simulation of RLC Circuit Response using PSpice --3LabManualLab5.doc LAB 5: ompuer imulaion of RL ircui Response using Ppice PURPOE To use a compuer simulaion program (Ppice) o invesigae he response of an RL series circui o: (a) a sinusoidal exciaion.

More information

A High-Speed Machining Algorithm For Continuous Corners

A High-Speed Machining Algorithm For Continuous Corners IOSR Journal of Mechanical and Civil Engineering (IOSR-JMCE) e-issn: 78-1684,p-ISSN: 30-334X, Volume 15, Issue 5 Ver. III (Sep. - Oc. 018), PP 64-69 www.iosrjournals.org A High-Speed Machining Algorihm

More information

Subtractive Clustering Based RBF Neural Network Model for Outlier Detection

Subtractive Clustering Based RBF Neural Network Model for Outlier Detection JOURNAL OF COMPUTERS, VOL. 4, NO. 8, AUGUST 9 755 Subracive Clusering Based RBF Neural Nework Model for Oulier Deecion Peng Yang School of Compuer Science, Chongqing Universiy, Chongqing, China Email:

More information

Written HW 9 Sol. CS 188 Fall Introduction to Artificial Intelligence

Written HW 9 Sol. CS 188 Fall Introduction to Artificial Intelligence CS 188 Fall 2018 Inroducion o Arificial Inelligence Wrien HW 9 Sol. Self-assessmen due: Tuesday 11/13/2018 a 11:59pm (submi via Gradescope) For he self assessmen, fill in he self assessmen boxes in your

More information

A Hop Constrained Min-Sum Arborescence with Outage Costs

A Hop Constrained Min-Sum Arborescence with Outage Costs A Hop Consrained Min-Sum Arborescence wih Ouage Coss Rakesh Kawara Minnesoa Sae Universiy, Mankao, MN 56001 Email: Kawara@mnsu.edu Absrac The hop consrained min-sum arborescence wih ouage coss problem

More information

Comparing Theoretical and Practical Solution of the First Order First Degree Ordinary Differential Equation of Population Model

Comparing Theoretical and Practical Solution of the First Order First Degree Ordinary Differential Equation of Population Model Open Access Journal of Mahemaical and Theoreical Physics Comparing Theoreical and Pracical Soluion of he Firs Order Firs Degree Ordinary Differenial Equaion of Populaion Model Absrac Populaion dynamics

More information

A Framework for Efficient Document Ranking Using Order and Non Order Based Fitness Function

A Framework for Efficient Document Ranking Using Order and Non Order Based Fitness Function A Framework for Efficien Documen Ranking Using Order and Non Order Based Finess Funcion Hazra Imran, Adii Sharan Absrac One cenral problem of informaion rerieval is o deermine he relevance of documens

More information

ONLINE EVALUATION OF TRACKING ALGORITHM PERFORMANCE

ONLINE EVALUATION OF TRACKING ALGORITHM PERFORMANCE ONLINE EVALUATION OF TRACKING ALGORITHM PERFORMANCE Duc Phu CHAU, François BREMOND and Monique THONNAT Pulsar eam, INRIA, 2004 roue des Lucioles, 06560 Valbonne, France {Duc-Phu.Chau, Francois.Bremond,

More information

Self assessment due: Monday 4/29/2019 at 11:59pm (submit via Gradescope)

Self assessment due: Monday 4/29/2019 at 11:59pm (submit via Gradescope) CS 188 Spring 2019 Inroducion o Arificial Inelligence Wrien HW 10 Due: Monday 4/22/2019 a 11:59pm (submi via Gradescope). Leave self assessmen boxes blank for his due dae. Self assessmen due: Monday 4/29/2019

More information

Tracking and Classifying Moving Objects from Video *

Tracking and Classifying Moving Objects from Video * Tracking and Classifying Moving Objecs from Video * Quming Zhou and J.K.Aggarwal Compuer and Vision Research Cener Deparmen of Elecrical and Compuer Engineering The Universiy of Texas a Ausin Ausin, TX

More information

Biol. 356 Lab 8. Mortality, Recruitment, and Migration Rates

Biol. 356 Lab 8. Mortality, Recruitment, and Migration Rates Biol. 356 Lab 8. Moraliy, Recruimen, and Migraion Raes (modified from Cox, 00, General Ecology Lab Manual, McGraw Hill) Las week we esimaed populaion size hrough several mehods. One assumpion of all hese

More information

Time Series Forecasting using CCA and Kohonen Maps - Application to Electricity Consumption

Time Series Forecasting using CCA and Kohonen Maps - Application to Electricity Consumption ESANN'2000 proceedings - European Symposium on Arificial Neural Neworks Bruges (Belgium), 26-28 April 2000, D-Faco public., ISBN 2-930307-00-5, pp. 329-334. Time Series Forecasing using CCA and Kohonen

More information

SOFTWARE RELIABILITY GROWTH MODEL WITH LOGISTIC TESTING-EFFORT FUNCTION CONSIDERING LOG-LOGISTIC TESTING-EFFORT AND IMPERFECT DEBUGGING

SOFTWARE RELIABILITY GROWTH MODEL WITH LOGISTIC TESTING-EFFORT FUNCTION CONSIDERING LOG-LOGISTIC TESTING-EFFORT AND IMPERFECT DEBUGGING Inernaional Journal of Compuer Science and Communicaion Vol. 2, No. 2, July-December 2011, pp. 605-609 SOFTWARE RELIABILITY GROWTH MODEL WITH LOGISTIC TESTING-EFFORT FUNCTION CONSIDERING LOG-LOGISTIC TESTING-EFFORT

More information

Online Convex Optimization Example And Follow-The-Leader

Online Convex Optimization Example And Follow-The-Leader CSE599s, Spring 2014, Online Learning Lecure 2-04/03/2014 Online Convex Opimizaion Example And Follow-The-Leader Lecurer: Brendan McMahan Scribe: Sephen Joe Jonany 1 Review of Online Convex Opimizaion

More information

Comparison for Edge Detection of Colony Images

Comparison for Edge Detection of Colony Images IJCSNS Inernaional Journal of Compuer Science and Nework Securiy, VOL.6 No.9A, Sepemer 2006 211 Comparison for Edge Deecion of Colony Images Wang Luo Universiy of Elecronic Science and Technology of China,

More information

A Forward-Backward Splitting Method with Component-wise Lazy Evaluation for Online Structured Convex Optimization

A Forward-Backward Splitting Method with Component-wise Lazy Evaluation for Online Structured Convex Optimization A Forward-Backward Spliing Mehod wih Componen-wise Lazy Evaluaion for Online Srucured Convex Opimizaion Yukihiro Togari and Nobuo Yamashia March 28, 2016 Absrac: We consider large-scale opimizaion problems

More information

Probabilistic Robotics The Sparse Extended Information Filter

Probabilistic Robotics The Sparse Extended Information Filter Probabilisic Roboics The Sparse Exended Informaion Filer MSc course Arificial Inelligence 2018 hps://saff.fnwi.uva.nl/a.visser/educaion/probabilisicroboics/ Arnoud Visser Inelligen Roboics Lab Informaics

More information

Morning Time: 1 hour 30 minutes Additional materials (enclosed):

Morning Time: 1 hour 30 minutes Additional materials (enclosed): ADVANCED GCE 78/0 MATHEMATICS (MEI) Differenial Equaions THURSDAY JANUARY 008 Morning Time: hour 30 minues Addiional maerials (enclosed): None Addiional maerials (required): Answer Bookle (8 pages) Graph

More information

An Invariance for (2+1)-Extension of Burgers Equation and Formulae to Obtain Solutions of KP Equation

An Invariance for (2+1)-Extension of Burgers Equation and Formulae to Obtain Solutions of KP Equation Commun Theor Phys Beijing, China 43 2005 pp 591 596 c Inernaional Academic Publishers Vol 43, No 4, April 15, 2005 An Invariance for 2+1-Eension of Burgers Equaion Formulae o Obain Soluions of KP Equaion

More information

The Rosenblatt s LMS algorithm for Perceptron (1958) is built around a linear neuron (a neuron with a linear

The Rosenblatt s LMS algorithm for Perceptron (1958) is built around a linear neuron (a neuron with a linear In The name of God Lecure4: Percepron and AALIE r. Majid MjidGhoshunih Inroducion The Rosenbla s LMS algorihm for Percepron 958 is buil around a linear neuron a neuron ih a linear acivaion funcion. Hoever,

More information

EXPLICIT TIME INTEGRATORS FOR NONLINEAR DYNAMICS DERIVED FROM THE MIDPOINT RULE

EXPLICIT TIME INTEGRATORS FOR NONLINEAR DYNAMICS DERIVED FROM THE MIDPOINT RULE Version April 30, 2004.Submied o CTU Repors. EXPLICIT TIME INTEGRATORS FOR NONLINEAR DYNAMICS DERIVED FROM THE MIDPOINT RULE Per Krysl Universiy of California, San Diego La Jolla, California 92093-0085,

More information

Numerical Dispersion

Numerical Dispersion eview of Linear Numerical Sabiliy Numerical Dispersion n he previous lecure, we considered he linear numerical sabiliy of boh advecion and diffusion erms when approimaed wih several spaial and emporal

More information

The electromagnetic interference in case of onboard navy ships computers - a new approach

The electromagnetic interference in case of onboard navy ships computers - a new approach The elecromagneic inerference in case of onboard navy ships compuers - a new approach Prof. dr. ing. Alexandru SOTIR Naval Academy Mircea cel Bărân, Fulgerului Sree, Consanţa, soiralexandru@yahoo.com Absrac.

More information

Diebold, Chapter 7. Francis X. Diebold, Elements of Forecasting, 4th Edition (Mason, Ohio: Cengage Learning, 2006). Chapter 7. Characterizing Cycles

Diebold, Chapter 7. Francis X. Diebold, Elements of Forecasting, 4th Edition (Mason, Ohio: Cengage Learning, 2006). Chapter 7. Characterizing Cycles Diebold, Chaper 7 Francis X. Diebold, Elemens of Forecasing, 4h Ediion (Mason, Ohio: Cengage Learning, 006). Chaper 7. Characerizing Cycles Afer compleing his reading you should be able o: Define covariance

More information

The Potential Effectiveness of the Detection of Pulsed Signals in the Non-Uniform Sampling

The Potential Effectiveness of the Detection of Pulsed Signals in the Non-Uniform Sampling The Poenial Effeciveness of he Deecion of Pulsed Signals in he Non-Uniform Sampling Arhur Smirnov, Sanislav Vorobiev and Ajih Abraham 3, 4 Deparmen of Compuer Science, Universiy of Illinois a Chicago,

More information

Methodology. -ratios are biased and that the appropriate critical values have to be increased by an amount. that depends on the sample size.

Methodology. -ratios are biased and that the appropriate critical values have to be increased by an amount. that depends on the sample size. Mehodology. Uni Roo Tess A ime series is inegraed when i has a mean revering propery and a finie variance. I is only emporarily ou of equilibrium and is called saionary in I(0). However a ime series ha

More information

3.1.3 INTRODUCTION TO DYNAMIC OPTIMIZATION: DISCRETE TIME PROBLEMS. A. The Hamiltonian and First-Order Conditions in a Finite Time Horizon

3.1.3 INTRODUCTION TO DYNAMIC OPTIMIZATION: DISCRETE TIME PROBLEMS. A. The Hamiltonian and First-Order Conditions in a Finite Time Horizon 3..3 INRODUCION O DYNAMIC OPIMIZAION: DISCREE IME PROBLEMS A. he Hamilonian and Firs-Order Condiions in a Finie ime Horizon Define a new funcion, he Hamilonian funcion, H. H he change in he oal value of

More information

Principal Component Analysis)

Principal Component Analysis) 1 shirai@ci.risumei.ac.jp @ jp www.i.ci.risumei.ac.jp/~shirai/ Principal Componen Analysis) n p i i,...,, =1,2 x φ x 3 i T i x z φ = φ 2 φ 3 φ 1 x 2 n s n i i T / 1 2 2 = = x φ x 1 φ φ φ φ φ ) / ( ) /

More information

MEASUREMENTS AND THEORETICAL CALCULATIONS OF DIFFUSED RADIATION AND ATMOSPHERE LUCIDITY

MEASUREMENTS AND THEORETICAL CALCULATIONS OF DIFFUSED RADIATION AND ATMOSPHERE LUCIDITY ENGINEERING FOR RURAL DEVELOPMENT Jelgava, 8.-9.5.9. MEASUREMENTS AND THEORETICAL CALCULATIONS OF DIFFUSED RADIATION AND ATMOSPHERE LUCIDITY Ilze Pelēce, Uldis Iljins, Imans Ziemelis Lavia Universiy of

More information

Simulation-Solving Dynamic Models ABE 5646 Week 2, Spring 2010

Simulation-Solving Dynamic Models ABE 5646 Week 2, Spring 2010 Simulaion-Solving Dynamic Models ABE 5646 Week 2, Spring 2010 Week Descripion Reading Maerial 2 Compuer Simulaion of Dynamic Models Finie Difference, coninuous saes, discree ime Simple Mehods Euler Trapezoid

More information

Dynamic Econometric Models: Y t = + 0 X t + 1 X t X t k X t-k + e t. A. Autoregressive Model:

Dynamic Econometric Models: Y t = + 0 X t + 1 X t X t k X t-k + e t. A. Autoregressive Model: Dynamic Economeric Models: A. Auoregressive Model: Y = + 0 X 1 Y -1 + 2 Y -2 + k Y -k + e (Wih lagged dependen variable(s) on he RHS) B. Disribued-lag Model: Y = + 0 X + 1 X -1 + 2 X -2 + + k X -k + e

More information

A DELAY-DEPENDENT STABILITY CRITERIA FOR T-S FUZZY SYSTEM WITH TIME-DELAYS

A DELAY-DEPENDENT STABILITY CRITERIA FOR T-S FUZZY SYSTEM WITH TIME-DELAYS A DELAY-DEPENDENT STABILITY CRITERIA FOR T-S FUZZY SYSTEM WITH TIME-DELAYS Xinping Guan ;1 Fenglei Li Cailian Chen Insiue of Elecrical Engineering, Yanshan Universiy, Qinhuangdao, 066004, China. Deparmen

More information

An Auto-Regressive Model for Improved Low Delay Distributed Video Coding

An Auto-Regressive Model for Improved Low Delay Distributed Video Coding An Auo-Regressive Model for Improved Low Delay Disribued Video Coding Yongbing Zhang* a, Debin Zhao a, Siwei Ma b, Ronggang Wang c, Wen Gao b a Deparmen of Compuer Science, Harbin Insiue of Technology,

More information

A Hilbert Warping Method for Camera-based Finger-writing Recognition

A Hilbert Warping Method for Camera-based Finger-writing Recognition A Hilber Warping Mehod for Camera-based Finger-wriing Recogniion Hiroyuki Ishida 1,2, Tomokazu Takahashi 3,IchiroIde 1 and Hiroshi Murase 1 1 Nagoya Universiy, Furo-cho, Chikusa-ku, Nagoya, Aichi, 464-861

More information

Compressive Online Robust Principal Component Analysis with Optical Flow for Video Foreground-Background Separation

Compressive Online Robust Principal Component Analysis with Optical Flow for Video Foreground-Background Separation Compressive Online Robus Principal Componen Analysis wih Opical Flow for Video Foreground-Background Separaion Srivasa Praivadibhayankaram, Huynh Van Luong*, Thanh-Ha Le, and André Kaup arxiv:7.96v [cs.cv]

More information

Pedestrian Motion Tracking and Crowd Abnormal Behavior Detection Based on Intelligent Video Surveillance

Pedestrian Motion Tracking and Crowd Abnormal Behavior Detection Based on Intelligent Video Surveillance 2598 JOURNAL OF NETWORKS, VOL. 9, NO. 10, OCTOBER 2014 Pedesrian Moion Tracing and Crowd Abnormal Behavior Deecion Based on Inelligen Video Surveillance Fan Zhao School of Compuer Science and Informaion

More information