PREDICTION OF DESIGN PARAMETERS IN SHIP DESIGNING BASED ON DATA MINING TECHNIQUE BY COMBINING GENETIC PROGRAMMING WITH SELF ORGANIZING MAP

Size: px
Start display at page:

Download "PREDICTION OF DESIGN PARAMETERS IN SHIP DESIGNING BASED ON DATA MINING TECHNIQUE BY COMBINING GENETIC PROGRAMMING WITH SELF ORGANIZING MAP"

Transcription

1 PREDICTION OF DESIGN PARAMETERS IN SHIP DESIGNING BASED ON DATA MINING TECHNIQUE BY COMBINING GENETIC PROGRAMMING WITH SELF ORGANIZING MAP Kyungho Lee Department of Naval Architecture & Ocean Engineering INHA University South Korea Jonghoon Park Donggeun Kim Daesuk Kim Department of Naval Architecture & Ocean Engineering, Graduate School INHA University South Korea ABSTRACT Engineering data contains the eperiences and knowhow of eperts. Data mining technique is useful to etract knowledge or information from the accumulated eisting data. Although Korean shipyards have accumulated a great amount of data, they do not have appropriate tools to utilize the data in practical works. Most of shipyards utilize empirical formulas for the prediction of design parameters in preliminary design stage. But these formulas generated from past eisting ship data are old-fashioned, so it is not adequate to apply the formulas to new ship design for the prediction of parameters. This paper presents a machine learning method based on genetic programming (GP), which can be one of the components for the realization of data mining. Differing from neural network model which is black bo, user cannot perceive the predicted formula, GP can be seen. Users can use the generated formula in real design system. In practical cases, we don t have enough learning samples, but there are many design input parameters. Therefore, reducing the number of input parameters is essential. In order to reducing the number of input parameters, self organizing map (SOM) is adopted. By applying SOM to accumulated data, the influence of input parameters on design outputs can be found. The developed data mining system by combining GP with SOM can be powerful tool for the generation of empirical formulas to predict design parameters in ship design. KEYWORDS Data mining, Genetic Programming, Self Organizing Map (SOM), Ship Design, Machine 1. INTRODUCTION In engineering domain, the utilization of accumulated eisting data is very important problem to secure productivity. Because engineering data itself contains the eperiences and know-how of eperts. In viewpoint of the development of intelligent system, the approaches have been slowly changing from knowledge-based approach, in which knowledge is difficult to etract and represent, to data-driven approach, which is relatively easy to handle. As mentioned before, the reason why this kind of changing is that engineering data contains meaningful information such as the eperiences and know-how of eperts, so the development of data analysis and utilization method is very important. In order to support this concept, data mining or knowledge discovery in database (KDD) technique is one of the useful tools. The utilization of eisting data is very important concept in ship designing process, and most of ship design is performed by modifying the previous similar ship data. Especially, most of design parameters are determined by using empirical formulas, which are generated from eisting ship data, in preliminary ship design stage. But these empirical formulas had been made on the basis of traditional ships, such as bulk carrier, crude oil tanker and so on. So they are too old-fashioned to utilize in 67

2 building new typed high value added ships, such as LNG carrier, drill ship and so on. Generating new typed empirical formulas to adapt to high value added ships is essential issue. Unfortunately, although Korean shipyards have accumulated a great amount of data, they do not have appropriate tools to utilize the data in practical works. Data utilization tool to adapt to ship design has been developed by using genetic programming (GP) since last several years (Lee, K.H. et al., 006a; 006b). That is, polynomial GP and linear model GP were presented. They focus on how to adapt for ship designing, especially on the generation of empirical formulas to predict design parameters in preliminary ship design stage. Usually, artificial neural network (ANN) as a training system for the prediction is utilized in most engineering fields. But if the characteristics of the training data are nonlinear and discontinuous, the performance of the training result deteriorates. And also the trained results cannot be reflected in the artificial neural network; that is, ANN becomes a black-bo system. On the other hand, GP has ecellent ability to approimate with non-linear and discontinued data. Above all, GP can show the trained result as a function tree. Generally, a lot of accumulated data is needed for the training by using ANN or GP. But in a real situation in the ship designing field, we do not have enough data to utilize for the training procedure. Polynomial GP (PGP), Linear model GP (LM-GP) and combining GP (PLM-GP) were presented in previous papers. In this paper, the data mining system by integrating the three types of GP model to support predicting design parameters in ship designing process is presented. Figure 1 shows the typical concept of the developed system in this paper. In practical cases, we don t have enough learning samples, but there can be many design input parameters. Generally speaking, a lot of data is needed for generating empirical formulas to predict the relations of input parameters and output design parameters. Therefore, reducing the number of input parameters is essential issue. In order to reducing the number of input parameters, self organizing map (SOM) is adopted. By applying SOM to accumulated data, the influence of input parameters on design outputs can be found. The developed data mining system by combining GP with SOM can be powerful tool for the generation of empirical formulas to predict design parameters in ship design. Figure 1 Concept of data mining system in this paper In fore part of this paper, the developed GP programs will be introduced briefly. And then integrated data mining system and combining model with SOM are presented.. POLYNOMIAL GENETIC PROGRAMMING (PGP) Polynomials are widely used in many engineering applications such as response surface modeling (Simpson, T.W. et al., 1998; Malik, Z. et al., 1986; Alotto, P. et al., 1997; Ishikawa, T. et al., 1997; Myers, L.H. et al., 1995), since the mathematical form of a polynomial is simple, and very easy to handle. In the mechanical, electrical and electronic engineering field, the response surface method is adopted to reduce the computational cost required for analysis and simulation during the optimization design process. Thus, it is desirable to use the minimal size of samples to construct response surfaces. The classical method for attaining good polynomials is to use all-possible-regressions and stepwise regression methods (Ott, R.L., 199; Myers, L.H. et al., 1995), but there are limitations in obtaining polynomials with a desired accuracy. In the paper (Lee, K.H. et al., 006b), we tried to use Genetic Programming (Koza, J.R., 199) for generating optimal polynomials that approimate very highly nonlinear response surfaces using only minimal or very small size of learning samples. Major issues regarding finding such polynomials using GP are addressed below. First, the GP tree can easily represent the polynomial if a function set contains only +, -, * operators, and a terminal set includes only variables and constants, but it is difficult to epect for GP to generate polynomials enabling to model a nonlinear function using only such a function and terminal set. We tackled this problem by the use of low order Taylor series of various mathematical functions in a function set. That effectively makes GP produce very high order polynomials. But the generated 68

3 polynomial tends to become too comple, and it is necessary to control the size of polynomials. Our idea for easily generating a high order polynomial is to use Taylor series of mathematic functions in the function set. If high order series are taken, the GP tree produces a very comple polynomial. So, we determine to take only two or third order polynomials from whole Taylor series. We use the following function and terminal set. F i = { +,,*, g ( i = 1,...,18)} T = { one, rand, i ( i = 1,..., n)} Where, g i is a low order Taylor series as followings. g 1 : sin( ) =, g! : cos( ) = 1! g : tan( ) = +, g 4 : log(1 + ) = +! g 5 : ep( ) = , 1!!! g 6 : sinh( ) = +, g 7 : cosh( ) = 1+!! Second, the overfitting problem can be very serious, because we only have small learning samples, and there are no other kinds of additional samples. So, we introduced the EDS(Etended Data Set) method (Yeun, Y.S., et al., 1999) with the FNS(Function Node Stabilization) method. The detail description of the methods is shown at some references.. LINEAR MODEL IN GENETIC PROGRAMMING (LM-GP) The regression or function approimation finds the underlying model that can best eplain the given samples with consideration of the generalization capability. Perhaps, one of most important tasks is the selection of an appropriate functional form of a model. For instance, polynomials, sigmoid based neural networks, and radical based function networks can be considered. After the base functions are selected, a proper model form is constructed by combining these bases in a predefined way. Usually the model contains numerical coefficients or weights, which should be estimated in such a way that the learning error or other criterion is minimized by applying the optimization method. On the other hand, GP can offer a very different alternative for regression problems. GP deals with a tree-structured program, called a GP tree, whose structure evolves towards the minimization of its fitness value by using genetic operators. Unlike the traditional approimation methods, where the structure of an approimate model is fied, the structure of the GP tree itself is modified and optimized, and thus GP trees can be more appropriate or accurate approimate models. Much research has been done on GP through regression problems and system identifications (Lee, K.H., et al., 00). If the population includes several hundred trees, several hundred optimization processes are required for each generation. Computational cost is a heavy burden on the use of GP in many engineering applications such as the response surface method in optimization problems (Lee, K.H., et al., 00). Although the fast estimation technique based on linear associative memories has been proposed (Yeun, Y.S., et al., 000), this method also has difficulty in providing accurate values of the weights. Simply, the GP tree, that gives the minimum fitness value based on only the error measure of the learning samples, cannot be the one that generalizes best with the good description of the underlying regularity of samples. To select the best GP trees, statistical inference such as the Rissanen s modern minimum description length (MDL) principle (Barron, A., et al., 1998) may be required. As can be epected, it is nearly intractable to use the MDL criterion in GP because of the requirement of multiple integrations of the nonlinear GP tree. (Lee, K.H., et al., 006a) focuses on Rissanen s modern MDL for computing the fitness of the GP tree. MDL tries to find the model that is encoded with the shortest code length, and at the same time best describes all learning samples. So, the philosophical foundation behind MDL is closely related to Ockham s Razor, which insists that the simplest model with good fitting of samples is the best one. This paper investigates linear model GP (LM-GP) and MDL with a directional derivative based the smoothing (DDBS) method. The detail description can be referred from some references. 4. INTEGRATED DATA MINING SYSTEM The suggested prediction model, such as PGP, LM- GP and PLM-GP, were validated by adapting to mathematical models or real ship design problem in previous papers. 69

4 Figure Polynomial GP and its optional functions in the integrated data mining system Figure 4 Linear model GP and its optional mathematical functions in the integrated data mining system Figure Linear model GP and its optional mathematical functions in the integrated data mining system In this paper, the data mining system for a data analysis and utilization by using enhanced genetic programming with integrated model is developed. That is, the system is contrived to apply to ship design under the case that the accumulated data is not enough to make learning process. The integrated system can make fitting functions with types of GP, such as GP with high order polynomial (PGP), linear model GP with polynomial (PLM-GP) and linear model GP with math functions (LM-GP). Figure and Figure show the developed system for a data mining by using PGP and LM-GP respectively. Users can make the process of function approimation by selecting arbitrary functions that they want to use. According to selected type of GP, all sorts of options to eecute the system, such as the number of population, the number of initial tree, crossover Figure 5 Generated function tree can be convert to C code automatically in this system probability rate (Pc), mutation probability rate (Pm) and optional functions to be used for the generation of approimation function, are displayed. And the generated function tree by GP is very complicate to use in real design works as shown at Figure 4. This figure is an eample of generated GP tree. To reduce the effort of the utilization of this function, and occurrence of errors in the process of converting this function to computer program, the data mining system can convert the generated GP tree to C code in order to integrate with other program. Figure 5 shows an eample of converted C code for the generated GP tree. The system is implemented by using Microsoft Visual Studio.Net C# programming. This system is installed in DSME (Daewoo Shipbuilding & Marine Engineering) 70

5 company, one of world best shipyards in Korea, and utilized for real ship designing. 5. IMPROVED SYSTEM BY COMBINING GP WITH SELF ORGANIZING MAP In the previous chapters, data mining system to predict design parameters by generating empirical formulas with GP is presented. But if training data is not enough to eecute this system, fatal problem such like overfitting can be occurred. So the avoidance of overfitting problem is the most important issue in regression domain. Generally speaking, the number of training data is closely related to the number of input parameters. If the number of input parameters is increased, more and more training data is need. As mentioned before, we don t have enough data in ship designing process. So reducing input parameters prior to training process is required. In order to reduce input parameters, we have to know the influence of the input parameters. Self Organizing Map (SOM) is appropriate tool to find the influence of input parameters for output parameters. SOM is a well-known model of artificial neural network. It is devised by Kohonen, and is a typical method for competitive learning. In our approach, influence analysis for input parameters by SOM is performed firstly. According to the results, input parameters with low influence are removed in training data for GP. By combining GP with SOM, the performance and accuracy of training can be enhanced Eperiment of combining system for the prediction of design parameters for ship In order to validate the combining system, the prediction of block coefficient (Cb) for crude oil tanker, which is one of the most important design parameter to be estimated, is carried out. First of all, just 70 training data (not enough to perform training) are gathered, and 60 of them are used for training process, the remaining 10 data are used for test. Figure 6 is a part of training sample data. As shown at the figure, the learning sample consists of 7 input parameters, such as dead weight (DWT), length (LBP), speed, breadth, draft, depth and frude number (Fn), and output parameter, Cb. In this eperiment, the performance of prediction which can be compared by the value of RMSE (root Figure 6 A part of 70 learning samples to predict block coefficient (Cb) for crude oil tanker (7 input parameters, 1 output parameter) mean square error) is carried out for the following approaches. (1) Prediction by traditional empirical formula (Yamagata Formula) Cb = Fn Fn< 0. 4 = Fn Fn> 0. 4 = Fn> () Prediction by PLM-GP () Prediction by PLM-GP combining with SOM Although we have just 70 training data, but input parameters are 7. That is, input parameters are too many comparing with the number of training data. So we have to reduce input parameters by the evaluation of influence through SOM. The result of SOM is shown at Figure 7. By the evaluation of influence for the input parameters, Frude number (Fn) has the lowest influence value among input parameters. So Fn is removed from input parameters. Figure 8 represents the prediction result by Yamagata empirical formula. Figure 9 shows the prediction result by PLM-GP, and Figure 10 by PLM-GP combining with SOM. The cross dashed line is eact values of Cb (i.e estimated value is equal to real value). 71

6 Comparing Two Cb Values RMSE = Real Cb Values Estimated Cb Values by Yamagata's Formula Figure 7 Visualization of the influence value for each parameters in Self Organizing Map (SOM) 5.. Evaluation of the eperiments As we epect, the prediction result by Yamagata formula (Figure 8) is not good. But they have their own trend. The reason why the bad result is the formula was generated by using old-fashioned ship data. On the other hand, the result by GP trained by 60 learning data is considerably improved (RMSE is ). The developed PLM-GP can predict the design parameters very well with small learning samples. Finally, the result by PLM-GP combining with SOM is better than other results as we epect (RMSE is ). In this case, we use only 5 parameters as input (Fn is removed). 6. CONCLUSIONS In this paper, data mining system for the prediction of design parameters to assist the ship designing process with insufficient learning samples is developed. The integrated system is presented with PGP, LM-GP and PLM-GP. Designer can generate his/her empirical formulas by using this system easily with small learning samples. In order to improve the performance of prediction, SOM is combined with GP program. Through the evaluation of influence for the input parameters by SOM, the performance of prediction was considerably enhanced. The validation test and the adoption of the developed method in the ship designing process are presented. As a result, the system is good for nonlinear function approimation with limited amount of Figure 8 Prediction result by Yamagata empirical formula (RMSE is ) Real Values Real Values the Result of Data Mining before applying SOM RMSE = Estimated Values Figure 9 Prediction result by using PLM-GP (RMSE is ) the Result of Data Mining applying SOM RMSE = Estimated Values Figure 10 Prediction result by combining GP with SOM (RMSE is ) 7

7 learning data, without overfitting. The developed data mining system can be used in real preliminary ship design process to generate new empirical formulas for the net generation high value added ships, such as LNG carrier, FPSO, and so on. ACKNOWLEDGMENTS This work is supported by Advanced Ship Engineering Research Center (R ). REFERENCES Lee, K.H., Yeun, Y.S., Yang, Y.S., Lee, J.H. and Oh, J. (006 a), Data Analysis and Utilization Method based on Genetic Programming in Ship Design, Lecture Notes on Computer Science, 981, Lee, K.H., Oh, J. and Park, J.H. (006 b), Development of Data Miner for the Ship Design based on Polynomial Genetic Programming, Lecture Notes in Artificial Intelligence, 404, Simpson, T.W., Allen, J.K., and Mistree, F. (1998), Spatial Correlation and Metamodels for Global Approimation in Structural Design Optimization, Proc. Of DETC98, ASME. Malik, Z., Su, H. and Nelder, J. (1986), Informative Eperimental Design for Electronic Circuits, Quality and Reliability Engineering, vol.14, Alotto, P., Gaggero, M., Molinari, G. and Nervi, M. (1997), A Design of Eperiment and Statistical Approach to Enhance the Generalized Response Surface Method in the Optimization of Multi- Minimas, IEEE Transactions on Magnetics, Vol., No., Ishikawa, T. and Matsunami, M. (1997), An Optimization Method Based on Radial Basis Function, IEEE Transactions on Magnetics, Vol., No. /II, Ott, R.L. (199), An Introduction to Statistical Methods and Data Analysis, Wadsworth Inc. Myers, R.H. and Montgomery, D.C. (1995), Response Surface Methodology: Process and Product Optimization Using Designed Eperiments, John Wiley & Sons, Inc. Koza, J.R. (199), Genetic Programming: On the Programming of Computers by Means of Natural Selection, The MIT Press. Yeun, Y.S., Lee, K.H. and Yang, Y.S. (1999), Function Approimations by Coupling Neural Networks and Genetic Programming Trees with Oblique Design Trees, AI in Engineering, Vol.1, No. Lee, K.H., Yeun, Y.S., Ruy, W.S. and Yang, Y.S. (00), Polynomial genetic programming for response surface modeling, Proc. on 4th International Workshop on Frontiers in Evolutionary Algorithms(FEA00), In conjunction with Sith Joint Conference on Information Sciences. Yeun, Y.S., Suh, J.C. and Yang, Y.S. (000), Function approimation by superimposing genetic programming trees: with application to engineering problems, Information Sciences, vol.1, issue -4. Barron, A., Rissanen, J. and Yu, B. (1998), The minimum description length principle in coding and modeling, IEEE Trans. Information Theory, vol. 44, no. 6,

A Hybrid Intelligent System for Fault Detection in Power Systems

A Hybrid Intelligent System for Fault Detection in Power Systems A Hybrid Intelligent System for Fault Detection in Power Systems Hiroyuki Mori Hikaru Aoyama Dept. of Electrical and Electronics Eng. Meii University Tama-ku, Kawasaki 14-8571 Japan Toshiyuki Yamanaka

More information

Relation Organization of SOM Initial Map by Improved Node Exchange

Relation Organization of SOM Initial Map by Improved Node Exchange JOURNAL OF COMPUTERS, VOL. 3, NO. 9, SEPTEMBER 2008 77 Relation Organization of SOM Initial Map by Improved Node Echange MIYOSHI Tsutomu Department of Information and Electronics, Tottori University, Tottori,

More information

FEATURE GENERATION USING GENETIC PROGRAMMING BASED ON FISHER CRITERION

FEATURE GENERATION USING GENETIC PROGRAMMING BASED ON FISHER CRITERION FEATURE GENERATION USING GENETIC PROGRAMMING BASED ON FISHER CRITERION Hong Guo, Qing Zhang and Asoke K. Nandi Signal Processing and Communications Group, Department of Electrical Engineering and Electronics,

More information

NAG Library Chapter Introduction. D04 Numerical Differentiation

NAG Library Chapter Introduction. D04 Numerical Differentiation D4 Numerical Differentiation Introduction D4 NAG Library Chapter Introduction D4 Numerical Differentiation Contents 1 Scope of the Chapter... 2 2 Background to the Problems... 2 2.1 Description of the

More information

Investigating the Application of Genetic Programming to Function Approximation

Investigating the Application of Genetic Programming to Function Approximation Investigating the Application of Genetic Programming to Function Approximation Jeremy E. Emch Computer Science Dept. Penn State University University Park, PA 16802 Abstract When analyzing a data set it

More information

Parameter optimization model in electrical discharge machining process *

Parameter optimization model in electrical discharge machining process * 14 Journal of Zhejiang University SCIENCE A ISSN 1673-565X (Print); ISSN 1862-1775 (Online) www.zju.edu.cn/jzus; www.springerlink.com E-mail: jzus@zju.edu.cn Parameter optimization model in electrical

More information

x y

x y 10. LECTURE 10 Objectives I understand the difficulty in finding an appropriate function for a data set in general. In some cases, I can define a function type that may fit a data set well. Last time,

More information

Multi-Objective Memetic Algorithm using Pattern Search Filter Methods

Multi-Objective Memetic Algorithm using Pattern Search Filter Methods Multi-Objective Memetic Algorithm using Pattern Search Filter Methods F. Mendes V. Sousa M.F.P. Costa A. Gaspar-Cunha IPC/I3N - Institute of Polymers and Composites, University of Minho Guimarães, Portugal

More information

Session 3. Rational and Radical Equations. Math 30-1 R 3. (Revisit, Review and Revive)

Session 3. Rational and Radical Equations. Math 30-1 R 3. (Revisit, Review and Revive) Session 3 Rational and Radical Equations Math 30-1 R 3 (Revisit, Review and Revive) Rational Functions Review Specific Outcome 14 Graph and analyze rational functions (limited to numerators and denominators

More information

A Classifier with the Function-based Decision Tree

A Classifier with the Function-based Decision Tree A Classifier with the Function-based Decision Tree Been-Chian Chien and Jung-Yi Lin Institute of Information Engineering I-Shou University, Kaohsiung 84008, Taiwan, R.O.C E-mail: cbc@isu.edu.tw, m893310m@isu.edu.tw

More information

Heavy Facilities Tension Prediction Using Flexible Neural Trees

Heavy Facilities Tension Prediction Using Flexible Neural Trees Heavy Facilities Tension Prediction Using Fleible Neural Trees Tomáš Novosád, Jan Platoš, Václav Snášel, Ajith Abraham Department of Computer Science VŠB-Technical University of Ostrava Ostrava, Czech

More information

CONFIDENCE INTERVALS FROM A SINGLE SIMULATION USING THE DELTA METHOD 1

CONFIDENCE INTERVALS FROM A SINGLE SIMULATION USING THE DELTA METHOD 1 CONFIDENCE INTERVALS FROM A SINGLE SIMULATION USING THE DELTA METHOD Christoph Roser Masaru Nakano Toyota Central Research and Development Laboratories Nagakute, Aichi, 480-9, JAPAN croser@robotics.tytlabs.co.jp

More information

Radical Functions Review

Radical Functions Review Radical Functions Review Specific Outcome 3 Graph and analyze radical functions (limited to functions involving one radical) Acceptable Standard sketch and analyze (domain, range, invariant points, - and

More information

CE4031 and CZ4031 Database System Principles

CE4031 and CZ4031 Database System Principles CE431 and CZ431 Database System Principles Course CE/CZ431 Course Database System Principles CE/CZ21 Algorithms; CZ27 Introduction to Databases CZ433 Advanced Data Management (not offered currently) Lectures

More information

Midterm Wednesday Oct. 27, 7pm, room 142

Midterm Wednesday Oct. 27, 7pm, room 142 Regression Testing Midterm Wednesday Oct. 27, 7pm, room 142 In class, closed book eam Includes all the material covered up (but not including) symbolic eecution Need to understand the concepts, know the

More information

Artificial Neural Networks MLP, RBF & GMDH

Artificial Neural Networks MLP, RBF & GMDH Artificial Neural Networks MLP, RBF & GMDH Jan Drchal drchajan@fel.cvut.cz Computational Intelligence Group Department of Computer Science and Engineering Faculty of Electrical Engineering Czech Technical

More information

4.12 Generalization. In back-propagation learning, as many training examples as possible are typically used.

4.12 Generalization. In back-propagation learning, as many training examples as possible are typically used. 1 4.12 Generalization In back-propagation learning, as many training examples as possible are typically used. It is hoped that the network so designed generalizes well. A network generalizes well when

More information

On-line Estimation of Power System Security Limits

On-line Estimation of Power System Security Limits Bulk Power System Dynamics and Control V, August 26-31, 2001, Onomichi, Japan On-line Estimation of Power System Security Limits K. Tomsovic A. Sittithumwat J. Tong School of Electrical Engineering and

More information

ET-based Test Data Generation for Multiple-path Testing

ET-based Test Data Generation for Multiple-path Testing 2016 3 rd International Conference on Engineering Technology and Application (ICETA 2016) ISBN: 978-1-60595-383-0 ET-based Test Data Generation for Multiple-path Testing Qingjie Wei* College of Computer

More information

Evolving SQL Queries for Data Mining

Evolving SQL Queries for Data Mining Evolving SQL Queries for Data Mining Majid Salim and Xin Yao School of Computer Science, The University of Birmingham Edgbaston, Birmingham B15 2TT, UK {msc30mms,x.yao}@cs.bham.ac.uk Abstract. This paper

More information

Experimental Comparison of Different Techniques to Generate Adaptive Sequences

Experimental Comparison of Different Techniques to Generate Adaptive Sequences Experimental Comparison of Different Techniques to Generate Adaptive Sequences Carlos Molinero 1, Manuel Núñez 1 and Robert M. Hierons 2 1 Departamento de Sistemas Informáticos y Computación, Universidad

More information

Kernel Density Construction Using Orthogonal Forward Regression

Kernel Density Construction Using Orthogonal Forward Regression Kernel ensity Construction Using Orthogonal Forward Regression S. Chen, X. Hong and C.J. Harris School of Electronics and Computer Science University of Southampton, Southampton SO7 BJ, U.K. epartment

More information

Automatic Shadow Removal by Illuminance in HSV Color Space

Automatic Shadow Removal by Illuminance in HSV Color Space Computer Science and Information Technology 3(3): 70-75, 2015 DOI: 10.13189/csit.2015.030303 http://www.hrpub.org Automatic Shadow Removal by Illuminance in HSV Color Space Wenbo Huang 1, KyoungYeon Kim

More information

Design and Realization of Data Mining System based on Web HE Defu1, a

Design and Realization of Data Mining System based on Web HE Defu1, a 4th International Conference on Machinery, Materials and Computing Technology (ICMMCT 2016) Design and Realization of Data Mining System based on Web HE Defu1, a 1 Department of Quartermaster, Wuhan Economics

More information

CE4031 and CZ4031 Database System Principles

CE4031 and CZ4031 Database System Principles CE4031 and CZ4031 Database System Principles Academic AY1819 Semester 1 CE/CZ4031 Database System Principles s CE/CZ2001 Algorithms; CZ2007 Introduction to Databases CZ4033 Advanced Data Management (not

More information

Image Classification and Processing using Modified Parallel-ACTIT

Image Classification and Processing using Modified Parallel-ACTIT Proceedings of the 2009 IEEE International Conference on Systems, Man, and Cybernetics San Antonio, TX, USA - October 2009 Image Classification and Processing using Modified Parallel-ACTIT Jun Ando and

More information

Rounding Theorem the Possibility of Applying the Cryptosystems on the Decimal Numbers

Rounding Theorem the Possibility of Applying the Cryptosystems on the Decimal Numbers Journal of Mathematics and Statistics 4 (): 5-20, 2008 ISSN 549-3644 2008 Science Publications Rounding Theorem the Possibility of Applying the Cryptosystems on the Decimal Numbers Rand Alfaris, Muhamad

More information

Chapter 28. Outline. Definitions of Data Mining. Data Mining Concepts

Chapter 28. Outline. Definitions of Data Mining. Data Mining Concepts Chapter 28 Data Mining Concepts Outline Data Mining Data Warehousing Knowledge Discovery in Databases (KDD) Goals of Data Mining and Knowledge Discovery Association Rules Additional Data Mining Algorithms

More information

LOESS curve fitted to a population sampled from a sine wave with uniform noise added. The LOESS curve approximates the original sine wave.

LOESS curve fitted to a population sampled from a sine wave with uniform noise added. The LOESS curve approximates the original sine wave. LOESS curve fitted to a population sampled from a sine wave with uniform noise added. The LOESS curve approximates the original sine wave. http://en.wikipedia.org/wiki/local_regression Local regression

More information

Using Artificial Neural Networks for Prediction Of Dynamic Human Motion

Using Artificial Neural Networks for Prediction Of Dynamic Human Motion ABSTRACT Using Artificial Neural Networks for Prediction Of Dynamic Human Motion Researchers in robotics and other human-related fields have been studying human motion behaviors to understand and mimic

More information

Aero-engine PID parameters Optimization based on Adaptive Genetic Algorithm. Yinling Wang, Huacong Li

Aero-engine PID parameters Optimization based on Adaptive Genetic Algorithm. Yinling Wang, Huacong Li International Conference on Applied Science and Engineering Innovation (ASEI 215) Aero-engine PID parameters Optimization based on Adaptive Genetic Algorithm Yinling Wang, Huacong Li School of Power and

More information

Research on Applications of Data Mining in Electronic Commerce. Xiuping YANG 1, a

Research on Applications of Data Mining in Electronic Commerce. Xiuping YANG 1, a International Conference on Education Technology, Management and Humanities Science (ETMHS 2015) Research on Applications of Data Mining in Electronic Commerce Xiuping YANG 1, a 1 Computer Science Department,

More information

Imputation for missing data through artificial intelligence 1

Imputation for missing data through artificial intelligence 1 Ninth IFC Conference on Are post-crisis statistical initiatives completed? Basel, 30-31 August 2018 Imputation for missing data through artificial intelligence 1 Byeungchun Kwon, Bank for International

More information

QUALITATIVE MODELING FOR MAGNETIZATION CURVE

QUALITATIVE MODELING FOR MAGNETIZATION CURVE Journal of Marine Science and Technology, Vol. 8, No. 2, pp. 65-70 (2000) 65 QUALITATIVE MODELING FOR MAGNETIZATION CURVE Pei-Hwa Huang and Yu-Shuo Chang Keywords: Magnetization curve, Qualitative modeling,

More information

Genetic Programming Practice and Theory

Genetic Programming Practice and Theory R. Poli - University of Esse 2 Overview Genetic Programming Practice and Theory Riccardo Poli Department of Computing and Electronic Systems University of Esse Basics Eamples and Applications Theory Conclusions

More information

Genetic Programming Part 1

Genetic Programming Part 1 Genetic Programming Part 1 Evolutionary Computation Lecture 11 Thorsten Schnier 06/11/2009 Previous Lecture Multi-objective Optimization Pareto optimality Hyper-volume based indicators Recent lectures

More information

Enhancing Forecasting Performance of Naïve-Bayes Classifiers with Discretization Techniques

Enhancing Forecasting Performance of Naïve-Bayes Classifiers with Discretization Techniques 24 Enhancing Forecasting Performance of Naïve-Bayes Classifiers with Discretization Techniques Enhancing Forecasting Performance of Naïve-Bayes Classifiers with Discretization Techniques Ruxandra PETRE

More information

Santa Fe Trail Problem Solution Using Grammatical Evolution

Santa Fe Trail Problem Solution Using Grammatical Evolution 2012 International Conference on Industrial and Intelligent Information (ICIII 2012) IPCSIT vol.31 (2012) (2012) IACSIT Press, Singapore Santa Fe Trail Problem Solution Using Grammatical Evolution Hideyuki

More information

Response Network Emerging from Simple Perturbation

Response Network Emerging from Simple Perturbation Journal of the Korean Physical Society, Vol 44, No 3, March 2004, pp 628 632 Response Network Emerging from Simple Perturbation S-W Son, D-H Kim, Y-Y Ahn and H Jeong Department of Physics, Korea Advanced

More information

ISSN: [Keswani* et al., 7(1): January, 2018] Impact Factor: 4.116

ISSN: [Keswani* et al., 7(1): January, 2018] Impact Factor: 4.116 IJESRT INTERNATIONAL JOURNAL OF ENGINEERING SCIENCES & RESEARCH TECHNOLOGY AUTOMATIC TEST CASE GENERATION FOR PERFORMANCE ENHANCEMENT OF SOFTWARE THROUGH GENETIC ALGORITHM AND RANDOM TESTING Bright Keswani,

More information

A Genetic Programming Approach for Distributed Queries

A Genetic Programming Approach for Distributed Queries Association for Information Systems AIS Electronic Library (AISeL) AMCIS 1997 Proceedings Americas Conference on Information Systems (AMCIS) 8-15-1997 A Genetic Programming Approach for Distributed Queries

More information

Prediction of traffic flow based on the EMD and wavelet neural network Teng Feng 1,a,Xiaohong Wang 1,b,Yunlai He 1,c

Prediction of traffic flow based on the EMD and wavelet neural network Teng Feng 1,a,Xiaohong Wang 1,b,Yunlai He 1,c 2nd International Conference on Electrical, Computer Engineering and Electronics (ICECEE 215) Prediction of traffic flow based on the EMD and wavelet neural network Teng Feng 1,a,Xiaohong Wang 1,b,Yunlai

More information

Previous Lecture Genetic Programming

Previous Lecture Genetic Programming Genetic Programming Previous Lecture Constraint Handling Penalty Approach Penalize fitness for infeasible solutions, depending on distance from feasible region Balanace between under- and over-penalization

More information

STATE SPACE MODELING OF 2-D RECURSIVE DIGITAL FILTERS

STATE SPACE MODELING OF 2-D RECURSIVE DIGITAL FILTERS STTE SPCE MODELING OF -D RECURSIVE DIGITL FILTERS Stela ngelova Stefanova Technology School Electronic System associated with the Technical University of Sofia, Mladost, 750 Sofia, Bulgaria, +359 8750040,

More information

Fuzzy Partitioning with FID3.1

Fuzzy Partitioning with FID3.1 Fuzzy Partitioning with FID3.1 Cezary Z. Janikow Dept. of Mathematics and Computer Science University of Missouri St. Louis St. Louis, Missouri 63121 janikow@umsl.edu Maciej Fajfer Institute of Computing

More information

A Combined Encryption Compression Scheme Using Chaotic Maps

A Combined Encryption Compression Scheme Using Chaotic Maps BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volume 13, No 2 Sofia 2013 Print ISSN: 1311-9702; Online ISSN: 1314-4081 DOI: 10.2478/cait-2013-0016 A Combined Encryption Compression

More information

Data Imbalance Problem solving for SMOTE Based Oversampling: Study on Fault Detection Prediction Model in Semiconductor Manufacturing Process

Data Imbalance Problem solving for SMOTE Based Oversampling: Study on Fault Detection Prediction Model in Semiconductor Manufacturing Process Vol.133 (Information Technology and Computer Science 2016), pp.79-84 http://dx.doi.org/10.14257/astl.2016. Data Imbalance Problem solving for SMOTE Based Oversampling: Study on Fault Detection Prediction

More information

Extending a Hybrid CBR-ANN Model by Modeling Predictive Attributes using Fuzzy Sets

Extending a Hybrid CBR-ANN Model by Modeling Predictive Attributes using Fuzzy Sets Etending a Hybrid CBR-ANN by ing Predictive Attributes using Fuzzy Sets. Etending a Hybrid CBR-ANN by ing Predictive Attributes using Fuzzy Sets Yanet Rodríguez 1, Maria M. García 1, Bernard De Baets 2,

More information

A Structural Optimization Method of Genetic Network Programming. for Enhancing Generalization Ability

A Structural Optimization Method of Genetic Network Programming. for Enhancing Generalization Ability International Journal of Engineering Innovation and Management Vol.6, No.2, 2016 A Structural Optimization Method of Genetic Network Programming for Enhancing Generalization Ability Shingo Mabu, Yamaguchi

More information

Semantic Forward Propagation for Symbolic Regression

Semantic Forward Propagation for Symbolic Regression Semantic Forward Propagation for Symbolic Regression Marcin Szubert 1, Anuradha Kodali 2,3, Sangram Ganguly 3,4, Kamalika Das 2,3, and Josh C. Bongard 1 1 University of Vermont, Burlington VT 05405, USA

More information

An Application of Genetic Algorithm for Auto-body Panel Die-design Case Library Based on Grid

An Application of Genetic Algorithm for Auto-body Panel Die-design Case Library Based on Grid An Application of Genetic Algorithm for Auto-body Panel Die-design Case Library Based on Grid Demin Wang 2, Hong Zhu 1, and Xin Liu 2 1 College of Computer Science and Technology, Jilin University, Changchun

More information

A Comparative Study of Linear Encoding in Genetic Programming

A Comparative Study of Linear Encoding in Genetic Programming 2011 Ninth International Conference on ICT and Knowledge A Comparative Study of Linear Encoding in Genetic Programming Yuttana Suttasupa, Suppat Rungraungsilp, Suwat Pinyopan, Pravit Wungchusunti, Prabhas

More information

CHAPTER 3 AN OVERVIEW OF DESIGN OF EXPERIMENTS AND RESPONSE SURFACE METHODOLOGY

CHAPTER 3 AN OVERVIEW OF DESIGN OF EXPERIMENTS AND RESPONSE SURFACE METHODOLOGY 23 CHAPTER 3 AN OVERVIEW OF DESIGN OF EXPERIMENTS AND RESPONSE SURFACE METHODOLOGY 3.1 DESIGN OF EXPERIMENTS Design of experiments is a systematic approach for investigation of a system or process. A series

More information

Multi-Criterion Optimal Design of Building Simulation Model using Chaos Particle Swarm Optimization

Multi-Criterion Optimal Design of Building Simulation Model using Chaos Particle Swarm Optimization , pp.21-25 http://dx.doi.org/10.14257/astl.2014.69.06 Multi-Criterion Optimal Design of Building Simulation Model using Chaos Particle Swarm Optimization Young-Jin, Kim 1,*, Hyun-Su Kim 1 1 Division of

More information

Lesson 3: Solving Equations; Floating-point Computation

Lesson 3: Solving Equations; Floating-point Computation Lesson 3: Solving Equations; Floating-point Computation restart; A hard equation Last time we were looking at this equation. eq := * sin() = Pi/2; (1.1) Maple didn't know the solutions. solve(eq,,allsolutions);

More information

Genetic-PSO Fuzzy Data Mining With Divide and Conquer Strategy

Genetic-PSO Fuzzy Data Mining With Divide and Conquer Strategy Genetic-PSO Fuzzy Data Mining With Divide and Conquer Strategy Amin Jourabloo Department of Computer Engineering, Sharif University of Technology, Tehran, Iran E-mail: jourabloo@ce.sharif.edu Abstract

More information

Developing Population Codes By Minimizing Description Length

Developing Population Codes By Minimizing Description Length Developing Population Codes By Minimizing Description Length Richard S. Zemel CNL, The Salk Institute 10010 North Torrey Pines Rd. La J oua, CA 92037 Geoffrey E. Hinton Department of Computer Science University

More information

Additive Regression Applied to a Large-Scale Collaborative Filtering Problem

Additive Regression Applied to a Large-Scale Collaborative Filtering Problem Additive Regression Applied to a Large-Scale Collaborative Filtering Problem Eibe Frank 1 and Mark Hall 2 1 Department of Computer Science, University of Waikato, Hamilton, New Zealand eibe@cs.waikato.ac.nz

More information

Evolution of the Discrete Cosine Transform Using Genetic Programming

Evolution of the Discrete Cosine Transform Using Genetic Programming Res. Lett. Inf. Math. Sci. (22), 3, 117-125 Available online at http://www.massey.ac.nz/~wwiims/research/letters/ Evolution of the Discrete Cosine Transform Using Genetic Programming Xiang Biao Cui and

More information

An Introduction to Maple This lab is adapted from a lab created by Bob Milnikel.

An Introduction to Maple This lab is adapted from a lab created by Bob Milnikel. Some quick tips for getting started with Maple: An Introduction to Maple This lab is adapted from a lab created by Bob Milnikel. [Even before we start, take note of the distinction between Tet mode and

More information

Revision of a Floating-Point Genetic Algorithm GENOCOP V for Nonlinear Programming Problems

Revision of a Floating-Point Genetic Algorithm GENOCOP V for Nonlinear Programming Problems 4 The Open Cybernetics and Systemics Journal, 008,, 4-9 Revision of a Floating-Point Genetic Algorithm GENOCOP V for Nonlinear Programming Problems K. Kato *, M. Sakawa and H. Katagiri Department of Artificial

More information

Optimization Methods for Machine Learning (OMML)

Optimization Methods for Machine Learning (OMML) Optimization Methods for Machine Learning (OMML) 2nd lecture Prof. L. Palagi References: 1. Bishop Pattern Recognition and Machine Learning, Springer, 2006 (Chap 1) 2. V. Cherlassky, F. Mulier - Learning

More information

A New Technique using GA style and LMS for Structure Adaptation

A New Technique using GA style and LMS for Structure Adaptation A New Technique using GA style and LMS for Structure Adaptation Sukesh Kumar Das and Nirmal Kumar Rout School of Electronics Engineering KIIT University, BHUBANESWAR, INDIA skd_sentu@rediffmail.com routnirmal@rediffmail.com

More information

Metamodeling. Modern optimization methods 1

Metamodeling. Modern optimization methods 1 Metamodeling Most modern area of optimization research For computationally demanding objective functions as well as constraint functions Main idea is that real functions are not convex but are in some

More information

Optimal Design of Steel Columns with Axial Load Using Artificial Neural Networks

Optimal Design of Steel Columns with Axial Load Using Artificial Neural Networks 2017 2nd International Conference on Applied Mechanics and Mechatronics Engineering (AMME 2017) ISBN: 978-1-60595-521-6 Optimal Design of Steel Columns with Axial Load Using Artificial Neural Networks

More information

Scheme of Big-Data Supported Interactive Evolutionary Computation

Scheme of Big-Data Supported Interactive Evolutionary Computation 2017 2nd International Conference on Information Technology and Management Engineering (ITME 2017) ISBN: 978-1-60595-415-8 Scheme of Big-Data Supported Interactive Evolutionary Computation Guo-sheng HAO

More information

Computer-Aided Diagnosis in Abdominal and Cardiac Radiology Using Neural Networks

Computer-Aided Diagnosis in Abdominal and Cardiac Radiology Using Neural Networks Computer-Aided Diagnosis in Abdominal and Cardiac Radiology Using Neural Networks Du-Yih Tsai, Masaru Sekiya and Yongbum Lee Department of Radiological Technology, School of Health Sciences, Faculty of

More information

Concept Explanation Examples Distance formula The distance between (x 1, y 1 ) and (x 2, y 2 ) is d = 2(x 2 - x 1 ) 2 + ( y 2 - y 1 ) 2.

Concept Explanation Examples Distance formula The distance between (x 1, y 1 ) and (x 2, y 2 ) is d = 2(x 2 - x 1 ) 2 + ( y 2 - y 1 ) 2. 660_ch0pp00-075.qd 0/6/08 4:8 PM Page 4 4 CHAPTER Introduction to Functions and Graphs continued from previous page Concept Eplanation Eamples Distance formula The distance between (, y ) and (, y ) is

More information

The Study of Genetic Algorithm-based Task Scheduling for Cloud Computing

The Study of Genetic Algorithm-based Task Scheduling for Cloud Computing The Study of Genetic Algorithm-based Task Scheduling for Cloud Computing Sung Ho Jang, Tae Young Kim, Jae Kwon Kim and Jong Sik Lee School of Information Engineering Inha University #253, YongHyun-Dong,

More information

Lesson 2.1 Exercises, pages 90 96

Lesson 2.1 Exercises, pages 90 96 Lesson.1 Eercises, pages 9 96 A. a) Complete the table of values. 1 1 1 1 1. 1 b) For each function in part a, sketch its graph then state its domain and range. For : the domain is ; and the range is.

More information

Review on Methods of Selecting Number of Hidden Nodes in Artificial Neural Network

Review on Methods of Selecting Number of Hidden Nodes in Artificial Neural Network Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 3, Issue. 11, November 2014,

More information

The Bootstrap and Jackknife

The Bootstrap and Jackknife The Bootstrap and Jackknife Summer 2017 Summer Institutes 249 Bootstrap & Jackknife Motivation In scientific research Interest often focuses upon the estimation of some unknown parameter, θ. The parameter

More information

Traffic Signal Control Based On Fuzzy Artificial Neural Networks With Particle Swarm Optimization

Traffic Signal Control Based On Fuzzy Artificial Neural Networks With Particle Swarm Optimization Traffic Signal Control Based On Fuzzy Artificial Neural Networks With Particle Swarm Optimization J.Venkatesh 1, B.Chiranjeevulu 2 1 PG Student, Dept. of ECE, Viswanadha Institute of Technology And Management,

More information

Complexity Challenges to the Discovery of Relationships in Eddy Current Non-destructive Test Data

Complexity Challenges to the Discovery of Relationships in Eddy Current Non-destructive Test Data Complexity Challenges to the Discovery of Relationships in Eddy Current Non-destructive Test Data CPT John R. Brence United States Military Academy Donald E. Brown, PhD University of Virginia Outline Background

More information

Linking Correlations Spanning Adjacent Applicability Domains

Linking Correlations Spanning Adjacent Applicability Domains Ian David Lockhart Bogle and Michael Fairweather (Editors), Proceedings of the 22nd European Symposium on Computer Aided Process Engineering, 17-20 June 2012, London. 2012 Elsevier B.V. All rights reserved.

More information

arxiv: v1 [cs.lg] 3 Oct 2018

arxiv: v1 [cs.lg] 3 Oct 2018 Real-time Clustering Algorithm Based on Predefined Level-of-Similarity Real-time Clustering Algorithm Based on Predefined Level-of-Similarity arxiv:1810.01878v1 [cs.lg] 3 Oct 2018 Rabindra Lamsal Shubham

More information

Hybrid PSO-SA algorithm for training a Neural Network for Classification

Hybrid PSO-SA algorithm for training a Neural Network for Classification Hybrid PSO-SA algorithm for training a Neural Network for Classification Sriram G. Sanjeevi 1, A. Naga Nikhila 2,Thaseem Khan 3 and G. Sumathi 4 1 Associate Professor, Dept. of CSE, National Institute

More information

Reducing the Number of Test Cases for Performance Evaluation of Components

Reducing the Number of Test Cases for Performance Evaluation of Components Reducing the Number of Test Cases for Performance Evaluation of Components João W. Cangussu Kendra Cooper Eric Wong Department of Computer Science University of Texas at Dallas Richardson-TX 75-, USA cangussu,kcooper,ewong

More information

Analytical model A structure and process for analyzing a dataset. For example, a decision tree is a model for the classification of a dataset.

Analytical model A structure and process for analyzing a dataset. For example, a decision tree is a model for the classification of a dataset. Glossary of data mining terms: Accuracy Accuracy is an important factor in assessing the success of data mining. When applied to data, accuracy refers to the rate of correct values in the data. When applied

More information

Function Approximation and Feature Selection Tool

Function Approximation and Feature Selection Tool Function Approximation and Feature Selection Tool Version: 1.0 The current version provides facility for adaptive feature selection and prediction using flexible neural tree. Developers: Varun Kumar Ojha

More information

Learning Graph Grammars

Learning Graph Grammars Learning Graph Grammars 1 Aly El Gamal ECE Department and Coordinated Science Laboratory University of Illinois at Urbana-Champaign Abstract Discovery of patterns in a given graph - in the form of repeated

More information

Introduction to Artificial Intelligence

Introduction to Artificial Intelligence Introduction to Artificial Intelligence COMP307 Evolutionary Computing 3: Genetic Programming for Regression and Classification Yi Mei yi.mei@ecs.vuw.ac.nz 1 Outline Statistical parameter regression Symbolic

More information

9.1A Exploring Rational Functions Using Transformations

9.1A Exploring Rational Functions Using Transformations PC 30 9.A Eploring Rational Functions Using Transformations To Identify and Sketch the graph of a Rational Function with Denominator Degree One Using Transformations. RATIONAL FUNCTION: A RATIONAL FUNCTION

More information

IMAGE FUSION PARAMETER ESTIMATION AND COMPARISON BETWEEN SVD AND DWT TECHNIQUE

IMAGE FUSION PARAMETER ESTIMATION AND COMPARISON BETWEEN SVD AND DWT TECHNIQUE IMAGE FUSION PARAMETER ESTIMATION AND COMPARISON BETWEEN SVD AND DWT TECHNIQUE Gagandeep Kour, Sharad P. Singh M. Tech Student, Department of EEE, Arni University, Kathgarh, Himachal Pardesh, India-7640

More information

SIMULATION APPROACH OF CUTTING TOOL MOVEMENT USING ARTIFICIAL INTELLIGENCE METHOD

SIMULATION APPROACH OF CUTTING TOOL MOVEMENT USING ARTIFICIAL INTELLIGENCE METHOD Journal of Engineering Science and Technology Special Issue on 4th International Technical Conference 2014, June (2015) 35-44 School of Engineering, Taylor s University SIMULATION APPROACH OF CUTTING TOOL

More information

Robot Path Planning Method Based on Improved Genetic Algorithm

Robot Path Planning Method Based on Improved Genetic Algorithm Sensors & Transducers 2014 by IFSA Publishing, S. L. http://www.sensorsportal.com Robot Path Planning Method Based on Improved Genetic Algorithm 1 Mingyang Jiang, 2 Xiaojing Fan, 1 Zhili Pei, 1 Jingqing

More information

Automatic Programming with Ant Colony Optimization

Automatic Programming with Ant Colony Optimization Automatic Programming with Ant Colony Optimization Jennifer Green University of Kent jg9@kent.ac.uk Jacqueline L. Whalley University of Kent J.L.Whalley@kent.ac.uk Colin G. Johnson University of Kent C.G.Johnson@kent.ac.uk

More information

Section 2.5: Continuity

Section 2.5: Continuity Section 2.5: Continuity 1. The Definition of Continuity We start with a naive definition of continuity. Definition 1.1. We say a function f() is continuous if we can draw its graph without lifting out

More information

Recent advances in Metamodel of Optimal Prognosis. Lectures. Thomas Most & Johannes Will

Recent advances in Metamodel of Optimal Prognosis. Lectures. Thomas Most & Johannes Will Lectures Recent advances in Metamodel of Optimal Prognosis Thomas Most & Johannes Will presented at the Weimar Optimization and Stochastic Days 2010 Source: www.dynardo.de/en/library Recent advances in

More information

Review: Final Exam CPSC Artificial Intelligence Michael M. Richter

Review: Final Exam CPSC Artificial Intelligence Michael M. Richter Review: Final Exam Model for a Learning Step Learner initially Environm ent Teacher Compare s pe c ia l Information Control Correct Learning criteria Feedback changed Learner after Learning Learning by

More information

Genetic programming. Lecture Genetic Programming. LISP as a GP language. LISP structure. S-expressions

Genetic programming. Lecture Genetic Programming. LISP as a GP language. LISP structure. S-expressions Genetic programming Lecture Genetic Programming CIS 412 Artificial Intelligence Umass, Dartmouth One of the central problems in computer science is how to make computers solve problems without being explicitly

More information

Building Classifiers using Bayesian Networks

Building Classifiers using Bayesian Networks Building Classifiers using Bayesian Networks Nir Friedman and Moises Goldszmidt 1997 Presented by Brian Collins and Lukas Seitlinger Paper Summary The Naive Bayes classifier has reasonable performance

More information

School of Mathematics, Statistics and Computer Science. Computer Science. Object Detection using Neural Networks and Genetic Programming

School of Mathematics, Statistics and Computer Science. Computer Science. Object Detection using Neural Networks and Genetic Programming T E W H A R E W Ā N A N G A O T E Ū P O K O O T E I K A A M Ā U I ÎÍÏ V I C T O R I A UNIVERSITY OF WELLINGTON School of Mathematics, Statistics and Computer Science Computer Science Object Detection using

More information

Adaptive Filtering using Steepest Descent and LMS Algorithm

Adaptive Filtering using Steepest Descent and LMS Algorithm IJSTE - International Journal of Science Technology & Engineering Volume 2 Issue 4 October 2015 ISSN (online): 2349-784X Adaptive Filtering using Steepest Descent and LMS Algorithm Akash Sawant Mukesh

More information

Extracting Propositions from Trained Neural Networks

Extracting Propositions from Trained Neural Networks Extracting Propositions from Trained Neural Networks Hiroshi Tsukimoto Research & Development Center, Toshiba Corporation 7, Yanagi-cho, Saiwai-ku, Kawasaki, 2 Japan Abstract This paper presents an algorithm

More information

AN APPROACH OF SEMIAUTOMATED ROAD EXTRACTION FROM AERIAL IMAGE BASED ON TEMPLATE MATCHING AND NEURAL NETWORK

AN APPROACH OF SEMIAUTOMATED ROAD EXTRACTION FROM AERIAL IMAGE BASED ON TEMPLATE MATCHING AND NEURAL NETWORK AN APPROACH OF SEMIAUTOMATED ROAD EXTRACTION FROM AERIAL IMAGE BASED ON TEMPLATE MATCHING AND NEURAL NETWORK Xiangyun HU, Zuxun ZHANG, Jianqing ZHANG Wuhan Technique University of Surveying and Mapping,

More information

CT79 SOFT COMPUTING ALCCS-FEB 2014

CT79 SOFT COMPUTING ALCCS-FEB 2014 Q.1 a. Define Union, Intersection and complement operations of Fuzzy sets. For fuzzy sets A and B Figure Fuzzy sets A & B The union of two fuzzy sets A and B is a fuzzy set C, written as C=AUB or C=A OR

More information

Encoding Words into String Vectors for Word Categorization

Encoding Words into String Vectors for Word Categorization Int'l Conf. Artificial Intelligence ICAI'16 271 Encoding Words into String Vectors for Word Categorization Taeho Jo Department of Computer and Information Communication Engineering, Hongik University,

More information

Research on time optimal trajectory planning of 7-DOF manipulator based on genetic algorithm

Research on time optimal trajectory planning of 7-DOF manipulator based on genetic algorithm Acta Technica 61, No. 4A/2016, 189 200 c 2017 Institute of Thermomechanics CAS, v.v.i. Research on time optimal trajectory planning of 7-DOF manipulator based on genetic algorithm Jianrong Bu 1, Junyan

More information

Using a Modified Genetic Algorithm to Find Feasible Regions of a Desirability Function

Using a Modified Genetic Algorithm to Find Feasible Regions of a Desirability Function Using a Modified Genetic Algorithm to Find Feasible Regions of a Desirability Function WEN WAN 1 and JEFFREY B. BIRCH 2 1 Virginia Commonwealth University, Richmond, VA 23298-0032 2 Virginia Polytechnic

More information