Seasonal Time Series Data Forecasting by Using Neural Networks Multiscale Autoregressive Model

Size: px
Start display at page:

Download "Seasonal Time Series Data Forecasting by Using Neural Networks Multiscale Autoregressive Model"

Transcription

1 American ourna of Appied Sciences 7 (): , 2 ISSN Science Pubications Seasona Time Series Data Forecasting by Using Neura Networks Mutiscae Autoregressive Mode Suhartono, B.S.S. Uama and A.. Endharta Department of Statistics, Facuty of Mathematics and Natura Sciences, Institute Technoogy Sepuuh Nopember, Surabaya 6, Indonesia Abstract: Probem statement: The aim of this research was to study further some atest progress of waveet transform for time series forecasting, particuary about Neura Networks Mutiscae Autoregressive (NN-MAR). Approach: There were three main issues that be considered further in this research. The first was some properties of scae and waveet coefficients from Maxima Overap Discrete Waveet Transform (MODWT) decomposition, particuary at seasona time series data. The second focused on the deveopment of mode buiding procedures of NN-MAR based on the properties of scae and waveet coefficients. Then, the third was empirica study about the impementation of the proposed procedure and comparison study about the forecast accuracy of NN-MAR to other forecasting modes. Resuts: The resuts showed that MODWT at seasona time series data aso has seasona pattern for scae coefficient, whereas the waveet coefficients are stationer. The resut of mode buiding procedure deveopment yieded a new proposed procedure of NN-MAR mode for seasona time series forecasting. In genera, this procedure accommodated input ags of scae and waveet coefficients and other additiona seasona ags. In addition, the resut showed that the proposed procedure works we for determining the best NN-MAR mode for seasona time series forecasting. Concusion: The comparison study of forecast accuracy showed that the NN-MAR mode yieds better forecast than MAR and ARIMA modes. Key words: Neura networks, mutiscae, MODWT, NN-MAR, seasona, time series INTRODUCTION Recenty, neura network has been proposed in many researches about different kinds of statistica anaysis. There are many types of neura network appied to sove many probems. For exampes, Feedforward Neura Network (FFNN) is appied in eectricity demand forecasting Tayor et a. (26), Genera Regression Neura Network (GRNN) is used in exchange rates forecasting and Recurrent Neura Network (RNN) has been appied in detecting changes in autocoreated process for quaity monitoring. Different from those previous researches, here, the predictors or the inputs are not the ags of the variabes or the data variabes, but they are the coefficients from waveet transformation. A new deveopment reated with waveet transformation appication for time series anaysis is proposed. As an overview this can be seen in Nason and von Sachs (999). At the beginning, most waveet research for time series anaysis is focused on periodogram or scaogram anaysis of periodicities and cyces evauation (Priestey, 996; Morettin, 997; Gao, 997; Perciva and Waden, 2). Bjorn (995); Sotani et a. (2) and Renaud et a. (23) are some first researcher groups discussing waveet for time series prediction based on autoregressive mode. In this case, waveet transformation gives good decomposition from a signa or time series, so that the structure can be evauated by parametric or nonparametric modes. WNN is a neura network with waveet function used in processing in transfer function. In time series forecasting cases, input used in WNN is waveet coefficients in certain time and resoution. Recenty, there are some artices about WNN for time series forecasting and fitering, such as Bashir and E-Hawary (2); Renaud et a. (23); Murtagh et a. (24) and Chen et a. (26). Waveet transformation that is mosty used for time series forecasting is Maxima Overap Discrete Waveet Transform (MODWT). The use of MODWT is to sove the imitation of Discrete Waveet Transform (DWT), that requires N = 2 where is positive integer. In practice, time series data rarey Corresponding Author: Suhartono, Department of Statistics, Facuty of Mathematics and Natura Sciences, Institute Technoogy Sepuuh Nopember, Surabaya 6, Indonesia 372

2 fufi those numbers, which are two powered with a positive integer. Some present researches reated with WNN for time series forecasting usuay focus on how to determine the best WNN mode which is appropriate for time series forecasting. The aim of this research is to deveop an accurate procedure for WNN modeing of seasona time series data and to compare the forecast accuracy with Mutiscae Autoregressive (MAR) and ARIMA modes. MATERIALS AND METHODS Data: The number of tourist arrivas to Bai through Ngurah Rai airport, from anuary 986 unti Apri 28, is used as a case study. The in-sampes are first 26 observations and the ast 6 observations are used as the out-sampe dataset. The anaysis starts by appying MODWT decomposition to the data. Based on the scae and waveet coefficients pattern, then the proposed of WNN mode buiding procedure for time series data forecasting wi be deveoped. This procedure is the improvement of genera FFNN mode buiding procedure for time series data forecasting. In this new procedure, the determination of the inputs in WNN mode is done by using waveet coefficient ags and the boundary effects. Whereas, the seection of the best WNN mode is done by empoying a combination between the inferentia statistics for the addition contribution in forward scheme for seecting the optimum number of neurons in the hidden ayer and Wad test in backward scheme for determining the optimum input unit. Waveets and prediction: Waveet means sma wave, whereas by contrast, sinus and cosines are big waves (Perciva and Waden, 2). A function ψ (.) is defined as waveet if it satisfies: ψ (u)du = () ψ 2 (u)du = (2) Am.. Appied Sci., 7 (): , 2 Meyer waveet, Daubechies waveet, Mexican hat waveet, Coifet waveet and ast assymetric waveet (Daubechies, 992). Scae and waveet equations: Scae equation or diate equation shows scae function φ experiencing contraction and transation (Debnath, 2), which is written as: Commony, waveets are functions that have characteristic as in Eq.. If it is integrated on (, ) the resut is zero and the integration of the quadrate of function ψ (.) equas to as written in Eq. 2. There are two functions in waveet transform, i.e., scae function (father waveet) and mother waveet. These two functions give a function famiy that can be used for reconstructing a signa. Some waveet famiies are Haar waveet (the odest and simpest waveet), Transform (MODWT) term. 373 L (3) = φ (t) = 2 g φ(2t ) where, φ(2t ) is scae function φ(t) experiencing contraction or transation in time axis with steps with scae fiter coefficient g. Waveet function ψ is defined as: L (t) 2 ( ) g (2t L 2 ) = ψ = φ + + (4) Coefficient g must satisfy conditions: L L m g = 2 dan ( ) g = = = for m =,, L,(L / 2) and: (5) L gg+ 2m =, m for m =, L,(L / 2) (6) = and: L 2 = g = (7) The reationship between coefficients h and g is + h = ( ) g, or it can be written as g ( ) h. Maxima Overap Discrete Waveet Transform (MODWT): One of modifications from Discrete Waveet Transform (DWT) is Maxima Overap Discrete Waveet Transform (MODWT). MODWT has been discussed in waveet iteratures with some names, such as undecimated-discrete Waveet Transform (DWT), Shift invariant DWT, waveet frames, transation DWT, non decimated DWT. Perciva and Waden (2) stated that essentiay those names are the same with MODWT which have connotation as mod DWT or modified DWT. This is the reason of this research using Maxima Overap Discrete Waveet

3 DWT suppose the data satisfy 2 j. In rea word most time series data has the ength that is not foowing this mutipication. MODWT has the advantage, which can eiminate the presence of data reduction to the haf (down samping). So that in MODWT there are N waveet and scae coefficients in each eves of MODWT (Perciva and Waden, 2). If there is time series data x, with N-ength, the MODWT transformation wi give coumn vectors w,w 2,...,w and v, each with N-ength. Vector w contains scae coefficients. As in DWT, in MODWT the efficient cacuation is done by pyramid agorithm. The smoothing coefficient of signa X is obtained iterativey by mutipying X with scae fiter or ow pass (g) and waveet fiter or high pass (h). In order to abridge the reationship of DWT and MODWT, waveet fiter and scae fiter definitions given by: Definition : (Perciva and Waden, 2): MODWT waveet fiter {h % } through h % h / 2 and MODWT scae fiter {g% } through {g% }g% g / 2. So that MODWT waveet fiter must satisfy this equation: h % =, h % = and h % h % = (8) L L 2 + 2m = = 2 = and the scae fiter must accompish the foowing equation: g% =, g% = and g% g% = (9) L L 2 + 2m = = 2 = Time series prediction by using waveet: Generay, time series forecasting given by using waveet is a forecasting method that use data preprocessing through waveet transform, especiay through MODWT. By the presence of mutiscae decomposition ike waveet, the advantage is automaticay separating the data components, such as trend component and irreguar component in the data. Thereby, this method coud be used for forecasting of stationary data (contain ony irreguar components) or non-stationary data (contain trend and irreguar components). For exampe, suppose that stationary signa X = (X,X 2,,X t ) and assume that vaue X t+ wi be forecasted. The basic idea is to use coefficients that are constructed from the decomposition, i.e., (Renaud et a., 23): Am.. Appied Sci., 7 (): , and: w for k,2,,a, j,2, K, = K j,t 2 (k ) j = v for k =,2, K,A,t 2 (k ) The first step that shoud be known is how many and which waveet coefficients that shoud be used in each scae. Renaud et a. (23) introduced a process to cacuate the forecast at time (t+) th by using waveet mode as iustrated in Fig.. Figure represents the common form of waveet modeing with eve = 4, order A j = 2 and N = 6. Fig. iustrates that if the 8th data wi be forecasted, the input variabes are waveet coefficients in eve at t = 7 and t = 5, eve 2 at t = 7 and t = 3, eve 3 at t = 7 and t = 9, eve 4 at t = 7 and t = and smooth coefficient in eve 4 at t = 7 and t =. Hence, we can concude that the second input at each eve is t-2 j. The basic idea of mutiscae decomposition is trend pattern infuences Low frequency (L) components that tend to be deterministic; whereas High frequency (H) component is sti stochastic. The second point in waveet modeing for forecasting is about the function used to process the inputs, i.e., waveet coefficients to forecast at (t+) th period. Generay, there are two kinds of function that can be used in this input-output processing, such as inear and noninear functions. Renaud et a. (23) deveoped a inear waveet mode known as Mutiscae Autoregressive (MAR) mode. Moreover, Renaud et a. (23) aso introduced the possibiity of the noninear mode use in inputoutput processing of waveet mode, especiay Feed- Forward Neura Network (FFNN). Furthermore the second mode is known as Waveet Neura Network (WNN) mode. These two approaches use the ags of waveet coefficients as the inputs, i.e. scae and smooth coefficients as in Fig.. Fig. : Waveet modeing iustration for = 4 and A j = 2 j

4 Am.. Appied Sci., 7 (): , 2 Mutiscae Autoregressive (MAR): An autoregressive process with order p which is known as AR(p) can be written as: Procedures: There are four proposed procedures for buiding WNN mode for forecasting non-stationary (in mean) time series, i.e.: ˆX p = φˆ X t + k t (k ) k = By using decomposition of waveet coefficients, Renaud et a. (23) expained that AR prediction in this way coud be expanded become Mutiscae Autoregressive (MAR) mode, i.e.: Aj t + j,k j,k j,t 2 (k ) +,t 2 (k ) j= k= k= A j () Xˆ = aˆ w + aˆ v Where: j = The numbers of eve (j =,2,,) A j = Order of MAR mode (k =,2,,A j ) w j,i = Waveet coefficient vaue v j,t = Scae coefficient vaue a j,k = MAR coefficient vaue Waveet neura network: Suppose that a stationary signa X = (X,X 2,,X t ) and assume that X t+ wi be predicted. The basic idea of waveet neura network mode is the coefficients that are cacuated by the decomposition as in Fig. are used as inputs at certain neura network architecture for obtaining the prediction of X t+. Renaud et a. (23) introduced Mutiayer Perceptron (MLP) neura network architecture or known as Feed-Forward Neura Network (FFNN) to process the waveet coefficients. The architecture of this FFNN consists of one hidden ayer with P neurons that is written as: ˆX N+ = P p= bˆ pg A+ A j j= k = k= â â w j,k,p j j,n 2 (k ) v +,k,p j j,n 2 (k ) + () where, g is an activation function in hidden ayer, which is usuay sigmoid ogistic. In this FFNN, the activation function in output ayer is inear. Furthermore, mode in Eq. is known as Waveet Neura Network (WNN) or Mutiresoution Neura Network (MNN). 375 The inputs are the ags of scae and waveet coefficients simiar to Renaud et a. (23) The inputs are the combination between the ags of scae and waveet coefficients proposed by Renaud et a. (23) and some additiona ags that are identified by using stepwise The inputs are the ags of scae and waveet coefficients proposed by Renaud et a. (23) from differencing data The inputs are the combination between the ags of scae and waveet coefficients proposed by Renaud et a. (23) and some additiona ags identified by using stepwise from differencing data In this research, the additiona ags are the seasona ags because of the data pattern. The first and second procedures are used for the stationary data, whereas the third and fourth procedures are used for data that contain a trend. This study ony iustrates the fourth procedure. Stepwise method is used to simpify the process in finding the significant inputs. After buiding WNN mode, the resuts at out-sampe dataset are compared to MAR and ARIMA modes to find the best mode for forecasting the number of tourist arrivas to Bai. At the proposed first new procedure, the seection of the best WNN mode is done firsty by determining an appropriate number of neurons in the hidden ayer. The starting step before appying the proposed procedure is the determination of the eves or in MODWT. In this case, a scae and waveet coefficient ags from MAR() and additiona seasona ags which are significant based on stepwise method are used as inputs. Different from inear waveet mode (MAR) that the modeing process was divided into two additive parts, namey modeing the trend by using waveet coefficients and MAR modeing for the residua by using the waveet and scae coefficient ags. In this proposed procedure, the modeing of WNN is done simutaneousy by using scae and waveet coefficient ags. This is based on the fact that WNN is noninear mode expected to be abe to catch data characteristics simutaneousy by using scae and waveet coefficients from MODWT. The first proposed procedure for WNN mode buiding for forecasting seasona time series data can be seen at Fig. 2.

5 Am.. Appied Sci., 7 (): , 2 Fig. 2: The procedure for WNN mode buiding for forecasting seasona time series data using inference combination of R 2 incrementa and Wad test 376

6 Am.. Appied Sci., 7 (): , 2 RESULTS AND DISCUSSION The time series pot of the number of tourist arrivas to Bai through Ngurah Rai airport is shown in Fig. 3. The pot shows that the data has seasona and trend patterns. These data have been anayzed by using MAR and ARIMA modes and the resuts showed that MAR( = 4;[2,36],[2,36],[36],[],[])-Haar yieded better forecast than ARIMA mode. As the starting step, the modeing focuses to determine an appropriate number of neurons in the hidden ayer. In this study, scae and waveet coefficient ag inputs are assumed as ag inputs in noninearity test in the first step. Every proposed procedure is begun by using noninearity test, i.e., White test and Terasvirta test. By using scae and waveet coefficient ags as the inputs as proposed by Renaud et a. (23), the resuts show that there is a noninear reationship between inputs and the output. Hence, it is correct to use a noninear mode as WNN for forecasting the data. The next step of the fourth procedure is to determine an appropriate number of neurons in the hidden ayer. This step is started from one neuron unti the additiona neuron show does not have significanty contribution. The resuts of the seection process of the number of neurons which is appropriate with WNN mode using ag inputs proposed by Renaud et a. (23) can be seen in Tabe for the Daubechies(4) waveet famiy or D(4) and Tabe 2 for Haar waveet famiy. Moreover, the resuts of forecast accuracy comparison between WNN and MAR coud be seen in Tabe 3. Based on the resuts in Tabe and 2, the first proposed procedure shows that the best WNN mode for forecasting the number of tourist arrivas to Bai consists one neuron in the hidden ayer for both D(4) and Haar waveet. In this architecture, the inputs are the ags of scae and waveet coefficients of MAR() and mutipicative seasona ags which are statisticay significant from stepwise methods. Fig. 3: Pot of the number of tourist arrivas to Bai Tabe : The resut of the first proposed procedure for determining an appropriate number of neurons, using D(4) waveet No. of neurons RMSE of in-sampe RMSE of out-sampe R 2 R 2 increment F p-vaue Tabe 2: The resut of first proposed procedure for determining an appropriate number of neurons, using Haar waveet No. of neurons RMSE of in-sampe RMSE of out-sampe R 2 R 2 increment F p-vaue

7 Am.. Appied Sci., 7 (): , 2 Tabe 3: The resut of forecast accuracy comparison for testing data Method Procedure RMSE of in-sampe RMSE of out-sampe Expanation about the best mode WNN 4 - Haar waveet MAR()-Haar, neuron 4 - Daubechies waveet MAR()-D(4), neuron MAR MAR.85,4 MAR( = 4;[2,36],[2,36],[36],,)-Haar If the seection of WNN mode is done based on cross-vaidation principe, then the best mode is the mode that yieds the minimum vaue of RMSE at testing dataset, i.e., the WNN mode that consists of one neuron in the hidden ayer both for D(4) and Haar waveets with RMSE.973 and.978 respectivey. Hence, WNN mode with one neuron in the hidden ayer that uses D(4) waveet is the best mode. In addition, the resut of forecast accuracy comparison between WNN and MAR modes at Tabe 3 shows that WNN mode with one hidden neuron that uses D(4) waveet famiy yieds the most accurate forecast than other modes. CONCLUSION Based on the resuts at the previous sections, it can be concuded that there is a difference pattern between scae and waveet coefficients of MODWT circuar decomposition. For non-stationary seasona time series data, the scae coefficients have non-stationary and seasona pattern, whereas the waveet coefficients in each decomposition eve tend to have a stationary pattern and the vaues are around zero. Then, new procedures for buiding NN-MAR based on these properties of scae and waveet coefficients are proposed. The empirica resuts by using data of the number of tourist arrivas to Bai show that the proposed procedure for buiding a WNN mode works we for determining appropriate mode architecture. Moreover, the forecast accuracy comparison shows that the proposed procedure using stepwise in the beginning step for determining the ag inputs yieds more parsimony mode and more accurate forecast than other procedures. REFERENCES Bashir, Z. and M.E. E-Hawary, 2. Short term oad forecasting by using waveet neura networks. Proceeding of the Canadian Conference on Eectrica and Computer Engineering, Mar. 7-, IEEE Xpore Press, Haifax, NS., Canada, pp: DOI:.9/CCECE Bjorn, V., 995. Mutiresoution methods for financia time series prediction. Proceeding of the IEEE/IAFE 995 Conference Computationa Inteigence for Financia Engineering, Apr. 9-, IEEE Xpore Press, New York, USA., pp: DOI:.9/CIFER Chen, Y., B. Yang and. Dong, 26. Time-series prediction using a oca waveet neura network. Neurocomputing, 69: DOI:.6/j.neucom Daubechies, I., 992. Ten Lectures on Waveets. st Edn., SIAM: Society for Industria and Appied Mathematics, USA., ISBN: , pp: 377. Debnath, L., 2. Waveet Transform and their Appication. st Edn., Birkhhauser Boston, Boston, ISBN: , pp: 565. Gao, H.Y., 997. Choice of threshods for waveet shrinkage estimate of the spectrum.. Time Ser. Ana., 8: DOI:./ Morettin, P.A., 997. Waveets in statistics. Resenhas, 3: Murtagh, F.,.L. Starckand and O. Renaud, 24. On neuro-waveet modeing. Dec. Support Syst., 37: DOI:.6/S (3)92-7 Nason, G.P. and R. von Sachs, 999. Waveets in time series anaysis. Phi. Trans. R. Soc. Lond. A., 357: DOI:.98/rsta Perciva, D.B. and A.T. Waden, 2. Waveets Methods for Time Series Anaysis. st Edn., Cambridge University Press, Cambridge, ISBN: , pp: 62. Priestey, M.B., 996. Waveets and time-dependent spectra anaysis.. Time Ser. Ana., 7: DOI:./j tb266.x Renaud, O.,.L. Stark and F. Murtagh, 23. Prediction based on a mutiscae decomposition. Int.. Waveets Mutiresout. Inform. Process., : Sotani, S., D. Boichu, P. Simard and S. Canu, 2. The ong-term memory prediction by mutiscae decomposition. Sign. Process., 8: DOI:.6/S65-684()77-3 Tayor,.W., L.M. Menezes and P.E. McSharry, 26. A comparison of univariate methods for forecasting eectricity demand up to a day ahead. Int.. Forecast., 22: -6. DOI:.6/j.ijforecast

Wavelet Neural Networks for Nonlinear Time Series Analysis

Wavelet Neural Networks for Nonlinear Time Series Analysis Applied Mathematical Sciences, Vol. 4, 2010, no. 50, 2485-2495 Wavelet Neural Networks for Nonlinear Time Series Analysis K. K. Minu, M. C. Lineesh and C. Jessy John Department of Mathematics National

More information

A Brief Introduction to Markov Chains and Hidden Markov Models

A Brief Introduction to Markov Chains and Hidden Markov Models A Brief Introduction to Markov Chains and Hidden Markov Modes Aen B MacKenzie Notes for December 1, 3, &8, 2015 Discrete-Time Markov Chains You may reca that when we first introduced random processes,

More information

Study on Fusion Algorithm of Multi-source Image Based on Sensor and Computer Image Processing Technology

Study on Fusion Algorithm of Multi-source Image Based on Sensor and Computer Image Processing Technology Sensors & Transducers 3 by IFSA http://www.sensorsporta.com Study on Fusion Agorithm of Muti-source Image Based on Sensor and Computer Image Processing Technoogy Yao NAN, Wang KAISHENG, 3 Yu JIN The Information

More information

WAVELET FREQUENCY DOMAIN APPROACH FOR TIME-SERIES MODELING

WAVELET FREQUENCY DOMAIN APPROACH FOR TIME-SERIES MODELING 1. Introduction WAVELET FREQUENCY DOMAIN APPROACH FOR TIME-SERIES MODELING Ranit Kumar Pau Indian Agricutura Statistics Research Institute Library Avenue, New Dehi 11001 ranitstat@iasri.res.in Autoregressive

More information

An Algorithm for Pruning Redundant Modules in Min-Max Modular Network

An Algorithm for Pruning Redundant Modules in Min-Max Modular Network An Agorithm for Pruning Redundant Modues in Min-Max Moduar Network Hui-Cheng Lian and Bao-Liang Lu Department of Computer Science and Engineering, Shanghai Jiao Tong University 1954 Hua Shan Rd., Shanghai

More information

Multilayer Kerceptron

Multilayer Kerceptron Mutiayer Kerceptron Zotán Szabó, András Lőrincz Department of Information Systems, Facuty of Informatics Eötvös Loránd University Pázmány Péter sétány 1/C H-1117, Budapest, Hungary e-mai: szzoi@csetehu,

More information

A Solution to the 4-bit Parity Problem with a Single Quaternary Neuron

A Solution to the 4-bit Parity Problem with a Single Quaternary Neuron Neura Information Processing - Letters and Reviews Vo. 5, No. 2, November 2004 LETTER A Soution to the 4-bit Parity Probem with a Singe Quaternary Neuron Tohru Nitta Nationa Institute of Advanced Industria

More information

FRST Multivariate Statistics. Multivariate Discriminant Analysis (MDA)

FRST Multivariate Statistics. Multivariate Discriminant Analysis (MDA) 1 FRST 531 -- Mutivariate Statistics Mutivariate Discriminant Anaysis (MDA) Purpose: 1. To predict which group (Y) an observation beongs to based on the characteristics of p predictor (X) variabes, using

More information

SVM: Terminology 1(6) SVM: Terminology 2(6)

SVM: Terminology 1(6) SVM: Terminology 2(6) Andrew Kusiak Inteigent Systems Laboratory 39 Seamans Center he University of Iowa Iowa City, IA 54-57 SVM he maxima margin cassifier is simiar to the perceptron: It aso assumes that the data points are

More information

FORECASTING TELECOMMUNICATIONS DATA WITH AUTOREGRESSIVE INTEGRATED MOVING AVERAGE MODELS

FORECASTING TELECOMMUNICATIONS DATA WITH AUTOREGRESSIVE INTEGRATED MOVING AVERAGE MODELS FORECASTING TEECOMMUNICATIONS DATA WITH AUTOREGRESSIVE INTEGRATED MOVING AVERAGE MODES Niesh Subhash naawade a, Mrs. Meenakshi Pawar b a SVERI's Coege of Engineering, Pandharpur. nieshsubhash15@gmai.com

More information

Safety Evaluation Model of Chemical Logistics Park Operation Based on Back Propagation Neural Network

Safety Evaluation Model of Chemical Logistics Park Operation Based on Back Propagation Neural Network 1513 A pubication of CHEMICAL ENGINEERING TRANSACTIONS VOL. 6, 017 Guest Editors: Fei Song, Haibo Wang, Fang He Copyright 017, AIDIC Servizi S.r.. ISBN 978-88-95608-60-0; ISSN 83-916 The Itaian Association

More information

A Novel Learning Method for Elman Neural Network Using Local Search

A Novel Learning Method for Elman Neural Network Using Local Search Neura Information Processing Letters and Reviews Vo. 11, No. 8, August 2007 LETTER A Nove Learning Method for Eman Neura Networ Using Loca Search Facuty of Engineering, Toyama University, Gofuu 3190 Toyama

More information

Research of Data Fusion Method of Multi-Sensor Based on Correlation Coefficient of Confidence Distance

Research of Data Fusion Method of Multi-Sensor Based on Correlation Coefficient of Confidence Distance Send Orders for Reprints to reprints@benthamscience.ae 340 The Open Cybernetics & Systemics Journa, 015, 9, 340-344 Open Access Research of Data Fusion Method of Muti-Sensor Based on Correation Coefficient

More information

TWO DENOISING SURE-LET METHODS FOR COMPLEX OVERSAMPLED SUBBAND DECOMPOSITIONS

TWO DENOISING SURE-LET METHODS FOR COMPLEX OVERSAMPLED SUBBAND DECOMPOSITIONS TWO DENOISING SUE-ET METHODS FO COMPEX OVESAMPED SUBBAND DECOMPOSITIONS Jérôme Gauthier 1, aurent Duva 2, and Jean-Christophe Pesquet 1 1 Université Paris-Est Institut Gaspard Monge and UM CNS 8049, 77454

More information

Haar Decomposition and Reconstruction Algorithms

Haar Decomposition and Reconstruction Algorithms Jim Lambers MAT 773 Fa Semester 018-19 Lecture 15 and 16 Notes These notes correspond to Sections 4.3 and 4.4 in the text. Haar Decomposition and Reconstruction Agorithms Decomposition Suppose we approximate

More information

MARKOV CHAINS AND MARKOV DECISION THEORY. Contents

MARKOV CHAINS AND MARKOV DECISION THEORY. Contents MARKOV CHAINS AND MARKOV DECISION THEORY ARINDRIMA DATTA Abstract. In this paper, we begin with a forma introduction to probabiity and expain the concept of random variabes and stochastic processes. After

More information

BP neural network-based sports performance prediction model applied research

BP neural network-based sports performance prediction model applied research Avaiabe onine www.jocpr.com Journa of Chemica and Pharmaceutica Research, 204, 6(7:93-936 Research Artice ISSN : 0975-7384 CODEN(USA : JCPRC5 BP neura networ-based sports performance prediction mode appied

More information

Copyright information to be inserted by the Publishers. Unsplitting BGK-type Schemes for the Shallow. Water Equations KUN XU

Copyright information to be inserted by the Publishers. Unsplitting BGK-type Schemes for the Shallow. Water Equations KUN XU Copyright information to be inserted by the Pubishers Unspitting BGK-type Schemes for the Shaow Water Equations KUN XU Mathematics Department, Hong Kong University of Science and Technoogy, Cear Water

More information

TELECOMMUNICATION DATA FORECASTING BASED ON ARIMA MODEL

TELECOMMUNICATION DATA FORECASTING BASED ON ARIMA MODEL TEECOMMUNICATION DATA FORECASTING BASED ON ARIMA MODE Anjuman Akbar Muani 1, Prof. Sachin Muraraka 2, Prof. K. Sujatha 3 1Student ME E&TC,Shree Ramchandra Coege of Engineering, onikand,pune,maharashtra

More information

How the backpropagation algorithm works Srikumar Ramalingam School of Computing University of Utah

How the backpropagation algorithm works Srikumar Ramalingam School of Computing University of Utah How the backpropagation agorithm works Srikumar Ramaingam Schoo of Computing University of Utah Reference Most of the sides are taken from the second chapter of the onine book by Michae Nieson: neuranetworksanddeepearning.com

More information

Numerical solution of one dimensional contaminant transport equation with variable coefficient (temporal) by using Haar wavelet

Numerical solution of one dimensional contaminant transport equation with variable coefficient (temporal) by using Haar wavelet Goba Journa of Pure and Appied Mathematics. ISSN 973-1768 Voume 1, Number (16), pp. 183-19 Research India Pubications http://www.ripubication.com Numerica soution of one dimensiona contaminant transport

More information

Appendix A: MATLAB commands for neural networks

Appendix A: MATLAB commands for neural networks Appendix A: MATLAB commands for neura networks 132 Appendix A: MATLAB commands for neura networks p=importdata('pn.xs'); t=importdata('tn.xs'); [pn,meanp,stdp,tn,meant,stdt]=prestd(p,t); for m=1:10 net=newff(minmax(pn),[m,1],{'tansig','purein'},'trainm');

More information

Experimental Investigation and Numerical Analysis of New Multi-Ribbed Slab Structure

Experimental Investigation and Numerical Analysis of New Multi-Ribbed Slab Structure Experimenta Investigation and Numerica Anaysis of New Muti-Ribbed Sab Structure Jie TIAN Xi an University of Technoogy, China Wei HUANG Xi an University of Architecture & Technoogy, China Junong LU Xi

More information

A Simple and Efficient Algorithm of 3-D Single-Source Localization with Uniform Cross Array Bing Xue 1 2 a) * Guangyou Fang 1 2 b and Yicai Ji 1 2 c)

A Simple and Efficient Algorithm of 3-D Single-Source Localization with Uniform Cross Array Bing Xue 1 2 a) * Guangyou Fang 1 2 b and Yicai Ji 1 2 c) A Simpe Efficient Agorithm of 3-D Singe-Source Locaization with Uniform Cross Array Bing Xue a * Guangyou Fang b Yicai Ji c Key Laboratory of Eectromagnetic Radiation Sensing Technoogy, Institute of Eectronics,

More information

Nonlinear Analysis of Spatial Trusses

Nonlinear Analysis of Spatial Trusses Noninear Anaysis of Spatia Trusses João Barrigó October 14 Abstract The present work addresses the noninear behavior of space trusses A formuation for geometrica noninear anaysis is presented, which incudes

More information

Reconstructions that Combine Cell Average Interpolation with Least Squares Fitting

Reconstructions that Combine Cell Average Interpolation with Least Squares Fitting App Math Inf Sci, No, 7-84 6) 7 Appied Mathematics & Information Sciences An Internationa Journa http://dxdoiorg/8576/amis/6 Reconstructions that Combine Ce Average Interpoation with Least Squares Fitting

More information

DIGITAL FILTER DESIGN OF IIR FILTERS USING REAL VALUED GENETIC ALGORITHM

DIGITAL FILTER DESIGN OF IIR FILTERS USING REAL VALUED GENETIC ALGORITHM DIGITAL FILTER DESIGN OF IIR FILTERS USING REAL VALUED GENETIC ALGORITHM MIKAEL NILSSON, MATTIAS DAHL AND INGVAR CLAESSON Bekinge Institute of Technoogy Department of Teecommunications and Signa Processing

More information

Converting Z-number to Fuzzy Number using. Fuzzy Expected Value

Converting Z-number to Fuzzy Number using. Fuzzy Expected Value ISSN 1746-7659, Engand, UK Journa of Information and Computing Science Vo. 1, No. 4, 017, pp.91-303 Converting Z-number to Fuzzy Number using Fuzzy Expected Vaue Mahdieh Akhbari * Department of Industria

More information

Terahertz Spectroscopic Material Identification Using Approximate Entropy and Deep Neural Network

Terahertz Spectroscopic Material Identification Using Approximate Entropy and Deep Neural Network Terahertz Spectroscopic Materia Identification Using Approximate Entropy and Deep Neura Network Yichao Li 1, Xiaoping A. Shen 2, Robert L. Ewing 3, and Jia Li 4 1 Schoo of Eectrica Engineering and Computer

More information

Determining The Degree of Generalization Using An Incremental Learning Algorithm

Determining The Degree of Generalization Using An Incremental Learning Algorithm Determining The Degree of Generaization Using An Incrementa Learning Agorithm Pabo Zegers Facutad de Ingeniería, Universidad de os Andes San Caros de Apoquindo 22, Las Condes, Santiago, Chie pzegers@uandes.c

More information

Related Topics Maxwell s equations, electrical eddy field, magnetic field of coils, coil, magnetic flux, induced voltage

Related Topics Maxwell s equations, electrical eddy field, magnetic field of coils, coil, magnetic flux, induced voltage Magnetic induction TEP Reated Topics Maxwe s equations, eectrica eddy fied, magnetic fied of cois, coi, magnetic fux, induced votage Principe A magnetic fied of variabe frequency and varying strength is

More information

A Comparison Study of the Test for Right Censored and Grouped Data

A Comparison Study of the Test for Right Censored and Grouped Data Communications for Statistica Appications and Methods 2015, Vo. 22, No. 4, 313 320 DOI: http://dx.doi.org/10.5351/csam.2015.22.4.313 Print ISSN 2287-7843 / Onine ISSN 2383-4757 A Comparison Study of the

More information

Approach to Identifying Raindrop Vibration Signal Detected by Optical Fiber

Approach to Identifying Raindrop Vibration Signal Detected by Optical Fiber Sensors & Transducers, o. 6, Issue, December 3, pp. 85-9 Sensors & Transducers 3 by IFSA http://www.sensorsporta.com Approach to Identifying Raindrop ibration Signa Detected by Optica Fiber ongquan QU,

More information

Statistical Learning Theory: A Primer

Statistical Learning Theory: A Primer Internationa Journa of Computer Vision 38(), 9 3, 2000 c 2000 uwer Academic Pubishers. Manufactured in The Netherands. Statistica Learning Theory: A Primer THEODOROS EVGENIOU, MASSIMILIANO PONTIL AND TOMASO

More information

Optimality of Inference in Hierarchical Coding for Distributed Object-Based Representations

Optimality of Inference in Hierarchical Coding for Distributed Object-Based Representations Optimaity of Inference in Hierarchica Coding for Distributed Object-Based Representations Simon Brodeur, Jean Rouat NECOTIS, Département génie éectrique et génie informatique, Université de Sherbrooke,

More information

Stochastic Variational Inference with Gradient Linearization

Stochastic Variational Inference with Gradient Linearization Stochastic Variationa Inference with Gradient Linearization Suppementa Materia Tobias Pötz * Anne S Wannenwetsch Stefan Roth Department of Computer Science, TU Darmstadt Preface In this suppementa materia,

More information

The influence of temperature of photovoltaic modules on performance of solar power plant

The influence of temperature of photovoltaic modules on performance of solar power plant IOSR Journa of Engineering (IOSRJEN) ISSN (e): 2250-3021, ISSN (p): 2278-8719 Vo. 05, Issue 04 (Apri. 2015), V1 PP 09-15 www.iosrjen.org The infuence of temperature of photovotaic modues on performance

More information

Wavelet Galerkin Solution for Boundary Value Problems

Wavelet Galerkin Solution for Boundary Value Problems Internationa Journa of Engineering Research and Deveopment e-issn: 2278-67X, p-issn: 2278-8X, www.ijerd.com Voume, Issue 5 (May 24), PP.2-3 Waveet Gaerkin Soution for Boundary Vaue Probems D. Pate, M.K.

More information

Steepest Descent Adaptation of Min-Max Fuzzy If-Then Rules 1

Steepest Descent Adaptation of Min-Max Fuzzy If-Then Rules 1 Steepest Descent Adaptation of Min-Max Fuzzy If-Then Rues 1 R.J. Marks II, S. Oh, P. Arabshahi Λ, T.P. Caude, J.J. Choi, B.G. Song Λ Λ Dept. of Eectrica Engineering Boeing Computer Services University

More information

Training Algorithm for Extra Reduced Size Lattice Ladder Multilayer Perceptrons

Training Algorithm for Extra Reduced Size Lattice Ladder Multilayer Perceptrons Training Agorithm for Extra Reduced Size Lattice Ladder Mutiayer Perceptrons Daius Navakauskas Division of Automatic Contro Department of Eectrica Engineering Linköpings universitet, SE-581 83 Linköping,

More information

MONTE CARLO SIMULATIONS

MONTE CARLO SIMULATIONS MONTE CARLO SIMULATIONS Current physics research 1) Theoretica 2) Experimenta 3) Computationa Monte Caro (MC) Method (1953) used to study 1) Discrete spin systems 2) Fuids 3) Poymers, membranes, soft matter

More information

Adjustment of automatic control systems of production facilities at coal processing plants using multivariant physico- mathematical models

Adjustment of automatic control systems of production facilities at coal processing plants using multivariant physico- mathematical models IO Conference Series: Earth and Environmenta Science AER OEN ACCESS Adjustment of automatic contro systems of production faciities at coa processing pants using mutivariant physico- mathematica modes To

More information

ORTHOGONAL MULTI-WAVELETS FROM MATRIX FACTORIZATION

ORTHOGONAL MULTI-WAVELETS FROM MATRIX FACTORIZATION J. Korean Math. Soc. 46 2009, No. 2, pp. 281 294 ORHOGONAL MLI-WAVELES FROM MARIX FACORIZAION Hongying Xiao Abstract. Accuracy of the scaing function is very crucia in waveet theory, or correspondingy,

More information

First-Order Corrections to Gutzwiller s Trace Formula for Systems with Discrete Symmetries

First-Order Corrections to Gutzwiller s Trace Formula for Systems with Discrete Symmetries c 26 Noninear Phenomena in Compex Systems First-Order Corrections to Gutzwier s Trace Formua for Systems with Discrete Symmetries Hoger Cartarius, Jörg Main, and Günter Wunner Institut für Theoretische

More information

Structural health monitoring of concrete dams using least squares support vector machines

Structural health monitoring of concrete dams using least squares support vector machines Structura heath monitoring of concrete dams using east squares support vector machines *Fei Kang ), Junjie Li ), Shouju Li 3) and Jia Liu ) ), ), ) Schoo of Hydrauic Engineering, Daian University of echnoogy,

More information

Wavelet shrinkage estimators of Hilbert transform

Wavelet shrinkage estimators of Hilbert transform Journa of Approximation Theory 163 (2011) 652 662 www.esevier.com/ocate/jat Fu ength artice Waveet shrinkage estimators of Hibert transform Di-Rong Chen, Yao Zhao Department of Mathematics, LMIB, Beijing

More information

Process Capability Proposal. with Polynomial Profile

Process Capability Proposal. with Polynomial Profile Contemporary Engineering Sciences, Vo. 11, 2018, no. 85, 4227-4236 HIKARI Ltd, www.m-hikari.com https://doi.org/10.12988/ces.2018.88467 Process Capabiity Proposa with Poynomia Profie Roberto José Herrera

More information

(This is a sample cover image for this issue. The actual cover is not yet available at this time.)

(This is a sample cover image for this issue. The actual cover is not yet available at this time.) (This is a sampe cover image for this issue The actua cover is not yet avaiabe at this time) This artice appeared in a journa pubished by Esevier The attached copy is furnished to the author for interna

More information

Bayesian Unscented Kalman Filter for State Estimation of Nonlinear and Non-Gaussian Systems

Bayesian Unscented Kalman Filter for State Estimation of Nonlinear and Non-Gaussian Systems Bayesian Unscented Kaman Fiter for State Estimation of Noninear and Non-aussian Systems Zhong Liu, Shing-Chow Chan, Ho-Chun Wu and iafei Wu Department of Eectrica and Eectronic Engineering, he University

More information

Chapter 4. Moving Observer Method. 4.1 Overview. 4.2 Theory

Chapter 4. Moving Observer Method. 4.1 Overview. 4.2 Theory Chapter 4 Moving Observer Method 4.1 Overview For a compete description of traffic stream modeing, one woud reuire fow, speed, and density. Obtaining these parameters simutaneousy is a difficut task if

More information

II. PROBLEM. A. Description. For the space of audio signals

II. PROBLEM. A. Description. For the space of audio signals CS229 - Fina Report Speech Recording based Language Recognition (Natura Language) Leopod Cambier - cambier; Matan Leibovich - matane; Cindy Orozco Bohorquez - orozcocc ABSTRACT We construct a rea time

More information

DYNAMIC RESPONSE OF CIRCULAR FOOTINGS ON SATURATED POROELASTIC HALFSPACE

DYNAMIC RESPONSE OF CIRCULAR FOOTINGS ON SATURATED POROELASTIC HALFSPACE 3 th Word Conference on Earthquake Engineering Vancouver, B.C., Canada August -6, 4 Paper No. 38 DYNAMIC RESPONSE OF CIRCULAR FOOTINGS ON SATURATED POROELASTIC HALFSPACE Bo JIN SUMMARY The dynamic responses

More information

Evolutionary Product-Unit Neural Networks for Classification 1

Evolutionary Product-Unit Neural Networks for Classification 1 Evoutionary Product-Unit Neura Networs for Cassification F.. Martínez-Estudio, C. Hervás-Martínez, P. A. Gutiérrez Peña A. C. Martínez-Estudio and S. Ventura-Soto Department of Management and Quantitative

More information

Two Kinds of Parabolic Equation algorithms in the Computational Electromagnetics

Two Kinds of Parabolic Equation algorithms in the Computational Electromagnetics Avaiabe onine at www.sciencedirect.com Procedia Engineering 9 (0) 45 49 0 Internationa Workshop on Information and Eectronics Engineering (IWIEE) Two Kinds of Paraboic Equation agorithms in the Computationa

More information

Combining reaction kinetics to the multi-phase Gibbs energy calculation

Combining reaction kinetics to the multi-phase Gibbs energy calculation 7 th European Symposium on Computer Aided Process Engineering ESCAPE7 V. Pesu and P.S. Agachi (Editors) 2007 Esevier B.V. A rights reserved. Combining reaction inetics to the muti-phase Gibbs energy cacuation

More information

Wavelet Methods for Time Series Analysis. Wavelet-Based Signal Estimation: I. Part VIII: Wavelet-Based Signal Extraction and Denoising

Wavelet Methods for Time Series Analysis. Wavelet-Based Signal Estimation: I. Part VIII: Wavelet-Based Signal Extraction and Denoising Waveet Methods for Time Series Anaysis Part VIII: Waveet-Based Signa Extraction and Denoising overview of key ideas behind waveet-based approach description of four basic modes for signa estimation discussion

More information

Traffic data collection

Traffic data collection Chapter 32 Traffic data coection 32.1 Overview Unike many other discipines of the engineering, the situations that are interesting to a traffic engineer cannot be reproduced in a aboratory. Even if road

More information

Statistical Learning Theory: a Primer

Statistical Learning Theory: a Primer ??,??, 1 6 (??) c?? Kuwer Academic Pubishers, Boston. Manufactured in The Netherands. Statistica Learning Theory: a Primer THEODOROS EVGENIOU AND MASSIMILIANO PONTIL Center for Bioogica and Computationa

More information

FOURIER SERIES ON ANY INTERVAL

FOURIER SERIES ON ANY INTERVAL FOURIER SERIES ON ANY INTERVAL Overview We have spent considerabe time earning how to compute Fourier series for functions that have a period of 2p on the interva (-p,p). We have aso seen how Fourier series

More information

Melodic contour estimation with B-spline models using a MDL criterion

Melodic contour estimation with B-spline models using a MDL criterion Meodic contour estimation with B-spine modes using a MDL criterion Damien Loive, Ney Barbot, Oivier Boeffard IRISA / University of Rennes 1 - ENSSAT 6 rue de Kerampont, B.P. 80518, F-305 Lannion Cedex

More information

STA 216 Project: Spline Approach to Discrete Survival Analysis

STA 216 Project: Spline Approach to Discrete Survival Analysis : Spine Approach to Discrete Surviva Anaysis November 4, 005 1 Introduction Athough continuous surviva anaysis differs much from the discrete surviva anaysis, there is certain ink between the two modeing

More information

A Robust Voice Activity Detection based on Noise Eigenspace Projection

A Robust Voice Activity Detection based on Noise Eigenspace Projection A Robust Voice Activity Detection based on Noise Eigenspace Projection Dongwen Ying 1, Yu Shi 2, Frank Soong 2, Jianwu Dang 1, and Xugang Lu 1 1 Japan Advanced Institute of Science and Technoogy, Nomi

More information

A Ridgelet Kernel Regression Model using Genetic Algorithm

A Ridgelet Kernel Regression Model using Genetic Algorithm A Ridgeet Kerne Regression Mode using Genetic Agorithm Shuyuan Yang, Min Wang, Licheng Jiao * Institute of Inteigence Information Processing, Department of Eectrica Engineering Xidian University Xi an,

More information

Inductive Bias: How to generalize on novel data. CS Inductive Bias 1

Inductive Bias: How to generalize on novel data. CS Inductive Bias 1 Inductive Bias: How to generaize on nove data CS 478 - Inductive Bias 1 Overfitting Noise vs. Exceptions CS 478 - Inductive Bias 2 Non-Linear Tasks Linear Regression wi not generaize we to the task beow

More information

Paragraph Topic Classification

Paragraph Topic Classification Paragraph Topic Cassification Eugene Nho Graduate Schoo of Business Stanford University Stanford, CA 94305 enho@stanford.edu Edward Ng Department of Eectrica Engineering Stanford University Stanford, CA

More information

Alberto Maydeu Olivares Instituto de Empresa Marketing Dept. C/Maria de Molina Madrid Spain

Alberto Maydeu Olivares Instituto de Empresa Marketing Dept. C/Maria de Molina Madrid Spain CORRECTIONS TO CLASSICAL PROCEDURES FOR ESTIMATING THURSTONE S CASE V MODEL FOR RANKING DATA Aberto Maydeu Oivares Instituto de Empresa Marketing Dept. C/Maria de Moina -5 28006 Madrid Spain Aberto.Maydeu@ie.edu

More information

Soft Clustering on Graphs

Soft Clustering on Graphs Soft Custering on Graphs Kai Yu 1, Shipeng Yu 2, Voker Tresp 1 1 Siemens AG, Corporate Technoogy 2 Institute for Computer Science, University of Munich kai.yu@siemens.com, voker.tresp@siemens.com spyu@dbs.informatik.uni-muenchen.de

More information

Appendix of the Paper The Role of No-Arbitrage on Forecasting: Lessons from a Parametric Term Structure Model

Appendix of the Paper The Role of No-Arbitrage on Forecasting: Lessons from a Parametric Term Structure Model Appendix of the Paper The Roe of No-Arbitrage on Forecasting: Lessons from a Parametric Term Structure Mode Caio Ameida cameida@fgv.br José Vicente jose.vaentim@bcb.gov.br June 008 1 Introduction In this

More information

SHEARLET-BASED INVERSE HALFTONING

SHEARLET-BASED INVERSE HALFTONING Journa of Theoretica and Appied Information Technoog 3 st March 3. Vo. 49 No.3 5-3 JATIT & LLS. A rights reserved. ISSN: 99-8645 www.atit.org E-ISSN: 87-395 SHEARLET-BASED INVERSE HALFTONING CHENGZHI DENG,

More information

Componentwise Determination of the Interval Hull Solution for Linear Interval Parameter Systems

Componentwise Determination of the Interval Hull Solution for Linear Interval Parameter Systems Componentwise Determination of the Interva Hu Soution for Linear Interva Parameter Systems L. V. Koev Dept. of Theoretica Eectrotechnics, Facuty of Automatics, Technica University of Sofia, 1000 Sofia,

More information

Reliability Improvement with Optimal Placement of Distributed Generation in Distribution System

Reliability Improvement with Optimal Placement of Distributed Generation in Distribution System Reiabiity Improvement with Optima Pacement of Distributed Generation in Distribution System N. Rugthaicharoencheep, T. Langtharthong Abstract This paper presents the optima pacement and sizing of distributed

More information

C. Fourier Sine Series Overview

C. Fourier Sine Series Overview 12 PHILIP D. LOEWEN C. Fourier Sine Series Overview Let some constant > be given. The symboic form of the FSS Eigenvaue probem combines an ordinary differentia equation (ODE) on the interva (, ) with a

More information

Nonlinear Gaussian Filtering via Radial Basis Function Approximation

Nonlinear Gaussian Filtering via Radial Basis Function Approximation 51st IEEE Conference on Decision and Contro December 10-13 01 Maui Hawaii USA Noninear Gaussian Fitering via Radia Basis Function Approximation Huazhen Fang Jia Wang and Raymond A de Caafon Abstract This

More information

A proposed nonparametric mixture density estimation using B-spline functions

A proposed nonparametric mixture density estimation using B-spline functions A proposed nonparametric mixture density estimation using B-spine functions Atizez Hadrich a,b, Mourad Zribi a, Afif Masmoudi b a Laboratoire d Informatique Signa et Image de a Côte d Opae (LISIC-EA 4491),

More information

NEW DEVELOPMENT OF OPTIMAL COMPUTING BUDGET ALLOCATION FOR DISCRETE EVENT SIMULATION

NEW DEVELOPMENT OF OPTIMAL COMPUTING BUDGET ALLOCATION FOR DISCRETE EVENT SIMULATION NEW DEVELOPMENT OF OPTIMAL COMPUTING BUDGET ALLOCATION FOR DISCRETE EVENT SIMULATION Hsiao-Chang Chen Dept. of Systems Engineering University of Pennsyvania Phiadephia, PA 904-635, U.S.A. Chun-Hung Chen

More information

ASummaryofGaussianProcesses Coryn A.L. Bailer-Jones

ASummaryofGaussianProcesses Coryn A.L. Bailer-Jones ASummaryofGaussianProcesses Coryn A.L. Baier-Jones Cavendish Laboratory University of Cambridge caj@mrao.cam.ac.uk Introduction A genera prediction probem can be posed as foows. We consider that the variabe

More information

Research Article Active Power Oscillation Property Classification of Electric Power Systems Based on SVM

Research Article Active Power Oscillation Property Classification of Electric Power Systems Based on SVM Journa of Appied Mathematics, Artice ID 218647, 9 pages http://dx.doi.org/10.1155/2014/218647 Research Artice Active Power Osciation Property Cassification of Eectric Power Systems Based on SVM Ju Liu,

More information

Florida State University Libraries

Florida State University Libraries Forida State University Libraries Eectronic Theses, Treatises and Dissertations The Graduate Schoo Construction of Efficient Fractiona Factoria Mixed-Leve Designs Yong Guo Foow this and additiona works

More information

Gauss Law. 2. Gauss s Law: connects charge and field 3. Applications of Gauss s Law

Gauss Law. 2. Gauss s Law: connects charge and field 3. Applications of Gauss s Law Gauss Law 1. Review on 1) Couomb s Law (charge and force) 2) Eectric Fied (fied and force) 2. Gauss s Law: connects charge and fied 3. Appications of Gauss s Law Couomb s Law and Eectric Fied Couomb s

More information

WAVELET LINEAR ESTIMATION FOR DERIVATIVES OF A DENSITY FROM OBSERVATIONS OF MIXTURES WITH VARYING MIXING PROPORTIONS. B. L. S.

WAVELET LINEAR ESTIMATION FOR DERIVATIVES OF A DENSITY FROM OBSERVATIONS OF MIXTURES WITH VARYING MIXING PROPORTIONS. B. L. S. Indian J. Pure App. Math., 41(1): 275-291, February 2010 c Indian Nationa Science Academy WAVELET LINEAR ESTIMATION FOR DERIVATIVES OF A DENSITY FROM OBSERVATIONS OF MIXTURES WITH VARYING MIXING PROPORTIONS

More information

MATH 172: MOTIVATION FOR FOURIER SERIES: SEPARATION OF VARIABLES

MATH 172: MOTIVATION FOR FOURIER SERIES: SEPARATION OF VARIABLES MATH 172: MOTIVATION FOR FOURIER SERIES: SEPARATION OF VARIABLES Separation of variabes is a method to sove certain PDEs which have a warped product structure. First, on R n, a inear PDE of order m is

More information

Algorithms to solve massively under-defined systems of multivariate quadratic equations

Algorithms to solve massively under-defined systems of multivariate quadratic equations Agorithms to sove massivey under-defined systems of mutivariate quadratic equations Yasufumi Hashimoto Abstract It is we known that the probem to sove a set of randomy chosen mutivariate quadratic equations

More information

Interconnect effects on performance of Field Programmable Analog Array

Interconnect effects on performance of Field Programmable Analog Array nterconnect effects on performance of Fied Programmabe Anaog Array D. Anderson,. Bir, O. A. Pausinsi 3, M. Spitz, K. Reiss Motoroa, SPS, Phoenix, Arizona, USA, University of Karsruhe, Karsruhe, Germany,

More information

Discrete Techniques. Chapter Introduction

Discrete Techniques. Chapter Introduction Chapter 3 Discrete Techniques 3. Introduction In the previous two chapters we introduced Fourier transforms of continuous functions of the periodic and non-periodic (finite energy) type, we as various

More information

D. Prémel, J.M. Decitre and G. Pichenot. CEA, LIST, F Gif-sur-Yvette, France

D. Prémel, J.M. Decitre and G. Pichenot. CEA, LIST, F Gif-sur-Yvette, France SIMULATION OF EDDY CURRENT INSPECTION INCLUDING MAGNETIC FIELD SENSOR SUCH AS A GIANT MAGNETO-RESISTANCE OVER PLANAR STRATIFIED MEDIA COMPONENTS WITH EMBEDDED FLAWS D. Préme, J.M. Decitre and G. Pichenot

More information

Fitting Algorithms for MMPP ATM Traffic Models

Fitting Algorithms for MMPP ATM Traffic Models Fitting Agorithms for PP AT Traffic odes A. Nogueira, P. Savador, R. Vaadas University of Aveiro / Institute of Teecommunications, 38-93 Aveiro, Portuga; e-mai: (nogueira, savador, rv)@av.it.pt ABSTRACT

More information

Bending Analysis of Continuous Castellated Beams

Bending Analysis of Continuous Castellated Beams Bending Anaysis of Continuous Casteated Beams * Sahar Eaiwi 1), Boksun Kim ) and Long-yuan Li 3) 1), ), 3) Schoo of Engineering, Pymouth University, Drake Circus, Pymouth, UK PL4 8AA 1) sahar.eaiwi@pymouth.ac.uk

More information

How the backpropagation algorithm works Srikumar Ramalingam School of Computing University of Utah

How the backpropagation algorithm works Srikumar Ramalingam School of Computing University of Utah How the backpropagation agorithm works Srikumar Ramaingam Schoo of Computing University of Utah Reference Most of the sides are taken from the second chapter of the onine book by Michae Nieson: neuranetworksanddeepearning.com

More information

Discrete Techniques. Chapter Introduction

Discrete Techniques. Chapter Introduction Chapter 3 Discrete Techniques 3. Introduction In the previous two chapters we introduced Fourier transforms of continuous functions of the periodic and non-periodic (finite energy) type, as we as various

More information

Lecture 6: Moderately Large Deflection Theory of Beams

Lecture 6: Moderately Large Deflection Theory of Beams Structura Mechanics 2.8 Lecture 6 Semester Yr Lecture 6: Moderatey Large Defection Theory of Beams 6.1 Genera Formuation Compare to the cassica theory of beams with infinitesima deformation, the moderatey

More information

In-plane shear stiffness of bare steel deck through shell finite element models. G. Bian, B.W. Schafer. June 2017

In-plane shear stiffness of bare steel deck through shell finite element models. G. Bian, B.W. Schafer. June 2017 In-pane shear stiffness of bare stee deck through she finite eement modes G. Bian, B.W. Schafer June 7 COLD-FORMED STEEL RESEARCH CONSORTIUM REPORT SERIES CFSRC R-7- SDII Stee Diaphragm Innovation Initiative

More information

Research Article Research on Fault Diagnosis System of a Diesel Engine Based on Wavelet Analysis and LabVIEW Software

Research Article Research on Fault Diagnosis System of a Diesel Engine Based on Wavelet Analysis and LabVIEW Software Research Journa of Appied Sciences, Engineering and Technoogy 7(18): 3821-3836, 214 DOI:1.1926/rjaset.7.739 ISSN: 24-7459; e-issn: 24-7467 214 Maxwe Scientific Pubication Corp. Submitted: November 4, 213

More information

Two-sample inference for normal mean vectors based on monotone missing data

Two-sample inference for normal mean vectors based on monotone missing data Journa of Mutivariate Anaysis 97 (006 6 76 wwweseviercom/ocate/jmva Two-sampe inference for norma mean vectors based on monotone missing data Jianqi Yu a, K Krishnamoorthy a,, Maruthy K Pannaa b a Department

More information

Multi-Scale Analysis of Long Range Dependent Traffic for Anomaly Detection in Wireless Sensor Networks

Multi-Scale Analysis of Long Range Dependent Traffic for Anomaly Detection in Wireless Sensor Networks 20 50th IEEE Conference on Decision and Contro and European Contro Conference (CDC-ECC) Orando FL USA December 2-5 20 Muti-Scae Anaysis of Long Range Dependent Traffic for Anomay Detection in Wireess Sensor

More information

Characterization of Low-Temperature SU-8 Photoresist Processing for MEMS Applications

Characterization of Low-Temperature SU-8 Photoresist Processing for MEMS Applications Characterization of Low-Temperature SU-8 Photoresist Processing for MEMS Appications Sang Jeen Hong 1, Seungkeun Choi 2, Yoonsu Choi 3, Mark Aen 4*, and Gary S. May 5 Schoo of Eectrica and Computer Engineering

More information

Probabilistic Assessment of Total Transfer Capability Using SQP and Weather Effects

Probabilistic Assessment of Total Transfer Capability Using SQP and Weather Effects J Eectr Eng Techno Vo. 9, No. 5: 52-526, 24 http://dx.doi.org/.537/jeet.24.9.5.52 ISSN(Print) 975-2 ISSN(Onine) 293-7423 Probabiistic Assessment of Tota Transfer Capabiity Using SQP and Weather Effects

More information

An explicit Jordan Decomposition of Companion matrices

An explicit Jordan Decomposition of Companion matrices An expicit Jordan Decomposition of Companion matrices Fermín S V Bazán Departamento de Matemática CFM UFSC 88040-900 Forianópois SC E-mai: fermin@mtmufscbr S Gratton CERFACS 42 Av Gaspard Coriois 31057

More information

Metal Oxide Semiconductor Field Effect Transistors (MOSFETs) Prof. Ali M. Niknejad Prof. Rikky Muller

Metal Oxide Semiconductor Field Effect Transistors (MOSFETs) Prof. Ali M. Niknejad Prof. Rikky Muller EECS 105 Spring 2017, Modue 3 Meta Oxide Semiconductor Fied Effect Transistors (MOSFETs) Prof. Ai M. Niknejad Prof. Rikky Muer Department of EECS University of Caifornia, Berkeey Announcements Prof. Rikky

More information

A Statistical Framework for Real-time Event Detection in Power Systems

A Statistical Framework for Real-time Event Detection in Power Systems 1 A Statistica Framework for Rea-time Event Detection in Power Systems Noan Uhrich, Tim Christman, Phiip Swisher, and Xichen Jiang Abstract A quickest change detection (QCD) agorithm is appied to the probem

More information

https://doi.org/ /epjconf/

https://doi.org/ /epjconf/ HOW TO APPLY THE OPTIMAL ESTIMATION METHOD TO YOUR LIDAR MEASUREMENTS FOR IMPROVED RETRIEVALS OF TEMPERATURE AND COMPOSITION R. J. Sica 1,2,*, A. Haefee 2,1, A. Jaai 1, S. Gamage 1 and G. Farhani 1 1 Department

More information