INTELLIGENT SEISMIC STRUCTURAL HEALTH MONITORING SYSTEM FOR THE SECOND PENANG BRIDGE OF MALAYSIA

Size: px
Start display at page:

Download "INTELLIGENT SEISMIC STRUCTURAL HEALTH MONITORING SYSTEM FOR THE SECOND PENANG BRIDGE OF MALAYSIA"

Transcription

1 INTELLIGENT SEISMIC STRUCTURAL HEALTH MONITORING SYSTEM FOR THE SECOND PENANG BRIDGE OF MALAYSIA Reni Suryanita Faculty of Engineering Civil Engineering Department University of Riau, Pekanbaru Azlan Adnan Engineering Seismology & Earthquake Engineering Research (E-Seer), Universiti Teknologi Malaysia Johor Bahru Malaysia Abstract The study aims to analyze and monitor the behavior of the Second Penang Bridge during the earthquake. The monitoring system is developed using the Neural Network (NN) method. The NN inputs are the acceleration, displacement and time history of the bridge structural response while the output is the damage level of the bridge. Damage levels are conducted through nonlinear time history analyses of the nine earthquakes from the PEER ground motion database. The damage level criterion is based on FEMA 356. The Neural Network methods consist of the Feed Forward and the Back-Propagation algorithms. The best prediction was achieved when used three hidden layers with time domain input at R=0.903 in the training and R=0.905 in the testing process.. The implementation of the Neural Network method for the bridge seismic monitoring system can help the bridge authorities to predict the health condition of the bridge at any given time. Key Words: intelligent system, earthquake, Neural Network, acceleration, displacement, damage level. I. INTRODUCTION The Second Penang Bridge is a 24km length and 16.9km above seawater, connecting Peninsular Malaysia and Penang Island. The bridge was completed in 2013, become the longest bridge in Southeast Asia. The second Penang Bridge has more superiority rather than the first Penang Bridge which 8.4km length above seawater as shown in Figure. 1.1 The 2 lanes dual carriageway with 3m motorcycle lane has been designed on the Second Penang Bridge. The seismic designs for the bridge are the 475-year time period with PGA g and the 2500-year time period with PGA g (Taib, 2011). The six levels of ground motion hazard which are 75, 109, 475, 950, 1642 and 2500-year return periods of earthquakes were evaluated for the Second Penang bridge site plant by Adnan, et al (2009). The accelerations from real time histories data were adjusted within the range of 0.5 to 2.0 Hz to produce the targeted spectral acceleration. Other researchers, Meng, et al (2011) has conducted design earthquake with a return period of 475 years and maximum credible earthquake with a return period of 2500 years. Performance of the Second Penang Bridge can be affected by the proximity of the bridge to the fault and site conditions nearest earthquakes from Sumatera-Indonesia. Both factors affect the intensity of ground shaking and ground deformations, as well as variation effects along the length of the bridge. 1

2 Case Study Figure 1.1. The Second Penang Bridge map (Taib, 2011) The study aims to produce an intelligent system for monitoring and detecting the condition of the Second Penang Bridge due to earthquakes load. The neural network inputs in the system consist of bridge structure responses included time responses. II. SEISMIC MONITORING SYSTEM FOR THE SECOND PENANG BRIDGE Bridge seismic design practices have changed over the years, largely reflecting lessons from performance in past earthquakes. The construction era of a bridge is a good indicator of likely performance, with higher damage levels expected in older construction than in newer construction (Chen dan Duan, 2003). In general, seismic monitoring is separate with the seismic analysis system. Especially in Malaysia, there is no seismic monitoring and analysis for bridges, which were made integrality in one the monitoring system. Sometimes the analysis is performed after the evaluation results obtained. So, the analysis is based on the expertise of engineers in the process of evaluation results. In this study, analysis system is integrated with the intelligent system so it can be used to predict damage index of bridges in the seismic zone include high and low earthquake region. The sensors of acceleration are installed at the top of piers and deck along the length of the spans as shown in Figure 2.1. Data acquisition converts the accelerations data and transfers the information into the local server. The Neural Network method is applied to the server and used to interpret and predict input data into a graph and alert warning system. 2

3 Sensors location Data Acquisition Local and remote server Operator Earthquake load Mobile devices Internet connection Bridge authorities/users Figure 2.1. Intelligent monitoring proposed for the Second Penang Bridge (Suryanita, 2014) The intelligent seismic monitoring has been proposed for the Second Penang Bridge that includes two versions namely local and distance monitoring. The remote client system can monitor the acceleration data using far away observation. The function is similar to the local server, including intelligent engine, alert system and monitoring. The Hyper Text Markup Language (HTML) format is necessary for sending the information through remote connection (Suryanita dan Adnan, 2014). The bridge model has been analyzed using Non Linear Time History (NLTH) of nine earthquakes data from Pacific Earthquake Engineering Research Center (PEER, 2012). Data of earthquakes load are shown in Table 2.1. Table 2.1 Data of the earthquakes load 3

4 III. APPLICATION OF NEURAL NETWORKS IN THE SYSTEM Neural Networks are numerical modeling techniques that are inspired by the functioning of the human brain and nerve system. An Artificial Neural Network imitates the basic concept of the brain. Some cells tell the brain that they are experiencing towards any number of sensations. These specialized communication cells are called neurons. The information obtained will be passed between the neurons, based on the structure and synapse weights. The neurons are connected to other neurons. They receive inputs from other neurons and send output to the other neurons and cells. The Neural Network is divided into single and several layers. A single layer is a connectionist model that consists of a single processing unit while multiple layers permit more complex, non-linear relationship of input data to the output result. The architecture of two hidden layers in the Neural Networks system is shown in Figure 3.1. Figure 3.1. Multilayer perceptron The cell of the input layer is represented by u i identifier. Identifying connections within the network are w(j,i), w(k,j) until w(l.k) are known as the weighted connection between the hidden cells and input cells. Through input cells (u 1, u 2, and u 3 ) provide an input value to the hidden and output cells represent a the Sigmoid function f(x), defined as Equation (3.1). (3.1) The equation above sums the product of the weights (w i ), and inputs (u i ) and a bias input (w 0 ). The output (γ) is an activation function. In this study, the Neural Network algorithms refer to Jones (2005) begins with the assignment of randomly generated weights in the feed forward, multilayer networks. The steps are repeated until the mean-squared error (MSE) of the output is sufficiently small. The parameter of learning rate ρ, is 0.5 that can be tuned to determine how quickly the back-propagation algorithm converges toward a solution. The error function of the output neurons is defined as Equation (3.2) 4

5 (3.2) where d k and O k are the desired and predicted value of the outputs, respectively. The error function should be minimized so that the Neural Network achieves the best performance. In training process, the network memorizes the relationships between input and output of the system through the connection weights. Before starting the training process, all the weights associated with the connections between the neurons must be initialized to small random numbers. In this study, normalization input data is the linear normalization as follows: (3.3) where is the normalized input or output values, z i the original data, z max and z min, respectively, the maximum and minimum values, and a and b are the positive constants allowing to fix the limits of the interval for the scaled values. IV. RESULTS AND DISCUSSION The Second Penang Bridge model in Figure 4.1 has analyzed using SAP2000 Non Linear Time History analysis subject to the earthquakes load as shown in Table 2.1. The damage of the piers due to San Francisco earthquake is shown in Figure 4.2. Criterion of bridge damage is based on standard of Federal Emergency Management Agency (FEMA356, 2000). Initial of B is described as operation level, IO is Immediate Occupancy, LS is life safety, and CP is collapse prevention. The level before damage is described with S (safe level). Figure 4.1. The Second Penang bridge model with layout of sensors. Figure 4.2. Damage level of the piers due to San Francisco earthquake In this study, the architecture of Neural Network method as shown in Figure 3.1. The inputs are accelerations, displacements and time domain compared with the input without the time domain in training and testing neural network. The output layer is a damage level of the bridge. The hidden layer used the multiple layers from one to five hidden layers. The inputs are the response of the bridge model through the finite-element analysis at the 5

6 critical point of the damage. The input and output of 1809 data for training neural network as shown in Table 4.1. Table 4.1. Input and output data for neural network method The indicators of the acceptable result in the Neural Network are the Mean Square Error (MSE) approached 0 (zero), and the regression value (R) approached 1 (one). The results show the regression value, R of training and testing process with three hidden layers is more accurate rather than else as shown in Figure 4.3 and Figure 4.4. Figure 4.3. Regression of training process. Figure 4.4. Regression of testing process. Figure 4.5. MSE value of model. Figure 4.6. The Snapshot of the software. 6

7 V. CONCLUSION 2 nd ACE National Conference 2015 The Neural Network methods on the Feed Forward and the Back-Propagation algorithms will be used in the computer program, namely Seer-Monalisa software. This software displays the alert warning system of the Second Penang Bridge based on result prediction of Neural Network analysis. Based on the results, the Neural Network method is recommended use three hidden layers and included the time domain as the input because the MSE value is smaller than others layers and can predict the damage more accurately. Therefore, the implementation of the intelligent Neural Network method for the bridge seismic monitoring system can help the bridge authorities to predict the stability and health condition of the bridge damage at any given time. REFERENCES Adnan, A., Hendriyawan & Suhatril, M. (2009). Seismic Hazard Assessment for Second Penang Bridge. Johor Bahru: SEER & GTIM Universiti Teknologi Malaysia. Chen, W.-F. & Duan, L. (eds.) (2003). Bridge Engineering Seismic Design, Florida: CRC Press. FEMA356 (2000). Prestandard and Commentary for The Seismic Rehabilitation of Buildings. Federal Emergency Management Agency. Jones, M. T. (2005). AI Application Programming. In: PALLAI, D. (ed.). Boston, Massachusetts: Charles River Media. Meng, F. C., Sham, R. & Zhenru, F. (Year). The Design of Second Penang Bridge. In: The Frist International Seminar on the Design and Construction of Second Penang Bridge 2011 Kuala Lumpur. PEER (2012). Pacific Earthquake Engineering Research Ground Motion Database. Suryanita, R. (2014). Integrated Bridge Health Monitoring, Evaluation and Alert System using Neuro-Genetic Hybrids Doctor of Philosophy Program, Universiti Teknologi Malaysia. Suryanita, R. & Adnan, A. (2014). Early-Warning System in Bridge Monitoring Based on Acceleration and Displacement Data Domain. In: Yang, G.-C., AO, S.-I., Huang, X. & Castillo, O. (eds.) Transactions on Engineering Technologies. Springer Netherlands. Taib, I. b. M. (2011). The Second Penang Bridge: Sustainable Design and Construction. Building and Infrastructure Technology Conference. Universiti Sain Malaysia, Kuala Lumpur: Universiti Sain Malaysia. 7

Liquefaction Analysis in 3D based on Neural Network Algorithm

Liquefaction Analysis in 3D based on Neural Network Algorithm Liquefaction Analysis in 3D based on Neural Network Algorithm M. Tolon Istanbul Technical University, Turkey D. Ural Istanbul Technical University, Turkey SUMMARY: Simplified techniques based on in situ

More information

Supervised Learning in Neural Networks (Part 2)

Supervised Learning in Neural Networks (Part 2) Supervised Learning in Neural Networks (Part 2) Multilayer neural networks (back-propagation training algorithm) The input signals are propagated in a forward direction on a layer-bylayer basis. Learning

More information

Dynamic Analysis of Structures Using Neural Networks

Dynamic Analysis of Structures Using Neural Networks Dynamic Analysis of Structures Using Neural Networks Alireza Lavaei Academic member, Islamic Azad University, Boroujerd Branch, Iran Alireza Lohrasbi Academic member, Islamic Azad University, Boroujerd

More information

CS 4510/9010 Applied Machine Learning. Neural Nets. Paula Matuszek Fall copyright Paula Matuszek 2016

CS 4510/9010 Applied Machine Learning. Neural Nets. Paula Matuszek Fall copyright Paula Matuszek 2016 CS 4510/9010 Applied Machine Learning 1 Neural Nets Paula Matuszek Fall 2016 Neural Nets, the very short version 2 A neural net consists of layers of nodes, or neurons, each of which has an activation

More information

CS6220: DATA MINING TECHNIQUES

CS6220: DATA MINING TECHNIQUES CS6220: DATA MINING TECHNIQUES Image Data: Classification via Neural Networks Instructor: Yizhou Sun yzsun@ccs.neu.edu November 19, 2015 Methods to Learn Classification Clustering Frequent Pattern Mining

More information

Fast Learning for Big Data Using Dynamic Function

Fast Learning for Big Data Using Dynamic Function IOP Conference Series: Materials Science and Engineering PAPER OPEN ACCESS Fast Learning for Big Data Using Dynamic Function To cite this article: T Alwajeeh et al 2017 IOP Conf. Ser.: Mater. Sci. Eng.

More information

Neuro-Fuzzy Inverse Forward Models

Neuro-Fuzzy Inverse Forward Models CS9 Autumn Neuro-Fuzzy Inverse Forward Models Brian Highfill Stanford University Department of Computer Science Abstract- Internal cognitive models are useful methods for the implementation of motor control

More information

Seismic Fragility Assessment of Highway Bridge

Seismic Fragility Assessment of Highway Bridge Seismic Fragility Assessment of Highway Bridge S. Mahmoudi & L. Chouinard Dept. of Civil Engineering, McGill University, QC, Canada SUMMARY: This paper addresses issues in the fragility analysis of bridges

More information

LECTURE NOTES Professor Anita Wasilewska NEURAL NETWORKS

LECTURE NOTES Professor Anita Wasilewska NEURAL NETWORKS LECTURE NOTES Professor Anita Wasilewska NEURAL NETWORKS Neural Networks Classifier Introduction INPUT: classification data, i.e. it contains an classification (class) attribute. WE also say that the class

More information

Finding Dominant Parameters For Fault Diagnosis Of a Single Bearing System Using Back Propagation Neural Network

Finding Dominant Parameters For Fault Diagnosis Of a Single Bearing System Using Back Propagation Neural Network International Journal of Mechanical & Mechatronics Engineering IJMME-IJENS Vol:13 No:01 40 Finding Dominant Parameters For Fault Diagnosis Of a Single Bearing System Using Back Propagation Neural Network

More information

Software Based Transmission Line Fault Analysis

Software Based Transmission Line Fault Analysis International journal of scientific and technical research in engineering (IJSTRE) www.ijstre.com Volume 1 Issue 3 ǁ June 2016. Software Based Transmission Line Fault Analysis E. O. Ogunti 1 1 (Department

More information

Neural Networks. CE-725: Statistical Pattern Recognition Sharif University of Technology Spring Soleymani

Neural Networks. CE-725: Statistical Pattern Recognition Sharif University of Technology Spring Soleymani Neural Networks CE-725: Statistical Pattern Recognition Sharif University of Technology Spring 2013 Soleymani Outline Biological and artificial neural networks Feed-forward neural networks Single layer

More information

Perceptrons and Backpropagation. Fabio Zachert Cognitive Modelling WiSe 2014/15

Perceptrons and Backpropagation. Fabio Zachert Cognitive Modelling WiSe 2014/15 Perceptrons and Backpropagation Fabio Zachert Cognitive Modelling WiSe 2014/15 Content History Mathematical View of Perceptrons Network Structures Gradient Descent Backpropagation (Single-Layer-, Multilayer-Networks)

More information

COMPUTATIONAL INTELLIGENCE

COMPUTATIONAL INTELLIGENCE COMPUTATIONAL INTELLIGENCE Fundamentals Adrian Horzyk Preface Before we can proceed to discuss specific complex methods we have to introduce basic concepts, principles, and models of computational intelligence

More information

International Research Journal of Computer Science (IRJCS) ISSN: Issue 09, Volume 4 (September 2017)

International Research Journal of Computer Science (IRJCS) ISSN: Issue 09, Volume 4 (September 2017) APPLICATION OF LRN AND BPNN USING TEMPORAL BACKPROPAGATION LEARNING FOR PREDICTION OF DISPLACEMENT Talvinder Singh, Munish Kumar C-DAC, Noida, India talvinder.grewaal@gmail.com,munishkumar@cdac.in Manuscript

More information

Opening the Black Box Data Driven Visualizaion of Neural N

Opening the Black Box Data Driven Visualizaion of Neural N Opening the Black Box Data Driven Visualizaion of Neural Networks September 20, 2006 Aritificial Neural Networks Limitations of ANNs Use of Visualization (ANNs) mimic the processes found in biological

More information

USING NEURAL NETWORK FOR PREDICTION OF THE DYNAMIC PERIOD AND AMPLIFICATION FACTOR OF SOIL FOR MICROZONATION IN URBAN AREA

USING NEURAL NETWORK FOR PREDICTION OF THE DYNAMIC PERIOD AND AMPLIFICATION FACTOR OF SOIL FOR MICROZONATION IN URBAN AREA USING NEURAL NETWORK FOR PREDICTION OF THE DYNAMIC PERIOD AND AMPLIFICATION FACTOR OF SOIL FOR MICROZONATION IN URBAN AREA Tahamoli Roodsari, Mehrzad 1 and Habibi, Mohammad Reza 2 1 M.S. in Earthquake

More information

Earthquake Engineering Problems in Parallel Neuro Environment

Earthquake Engineering Problems in Parallel Neuro Environment Earthquake Engineering Problems in Parallel Neuro Environment Sanjay Singh IBM Global Services India Pvt. Ltd., Bangalore and Sudhirkumar V Barai Department of Civil Engineering, IIT Kharagpur Email: skbarai@civil.iitkgp.ernet.in

More information

17. SEISMIC ANALYSIS MODELING TO SATISFY BUILDING CODES

17. SEISMIC ANALYSIS MODELING TO SATISFY BUILDING CODES 17. SEISMIC ANALYSIS MODELING TO SATISFY BUILDING CODES The Current Building Codes Use the Terminology: Principal Direction without a Unique Definition 17.1 INTRODUCTION { XE "Building Codes" }Currently

More information

Artificial Neural Network-Based Prediction of Human Posture

Artificial Neural Network-Based Prediction of Human Posture Artificial Neural Network-Based Prediction of Human Posture Abstract The use of an artificial neural network (ANN) in many practical complicated problems encourages its implementation in the digital human

More information

11/14/2010 Intelligent Systems and Soft Computing 1

11/14/2010 Intelligent Systems and Soft Computing 1 Lecture 7 Artificial neural networks: Supervised learning Introduction, or how the brain works The neuron as a simple computing element The perceptron Multilayer neural networks Accelerated learning in

More information

SEISMIC TESTING OF LARGE SCALE STRUCTURES WITH DISSIPATOR DEVICES

SEISMIC TESTING OF LARGE SCALE STRUCTURES WITH DISSIPATOR DEVICES 11 th International Conference on Vibration Problems Z. Dimitrovová et al. (eds.) Lisbon, Portugal, 9-12 September 2013 SEISMIC TESTING OF LARGE SCALE STRUCTURES WITH DISSIPATOR DEVICES Beatriz Zapico*

More information

CS 4510/9010 Applied Machine Learning

CS 4510/9010 Applied Machine Learning CS 4510/9010 Applied Machine Learning Neural Nets Paula Matuszek Spring, 2015 1 Neural Nets, the very short version A neural net consists of layers of nodes, or neurons, each of which has an activation

More information

PROGRAM LIST. 1* Backpropagation Neuro-Control*1 #include <stdio.h> #include <math.h> #include <string.h> #include <stdlib.h>

PROGRAM LIST. 1* Backpropagation Neuro-Control*1 #include <stdio.h> #include <math.h> #include <string.h> #include <stdlib.h> PROGRAM LIST 1* This program can be used to train a neural network model with *1 1* one hidden layer to learn the inverse dynamics of the plant *1 1* Once trained the neural network model can *1 1* be

More information

International Journal of Electrical and Computer Engineering 4: Application of Neural Network in User Authentication for Smart Home System

International Journal of Electrical and Computer Engineering 4: Application of Neural Network in User Authentication for Smart Home System Application of Neural Network in User Authentication for Smart Home System A. Joseph, D.B.L. Bong, and D.A.A. Mat Abstract Security has been an important issue and concern in the smart home systems. Smart

More information

Face Detection Using Radial Basis Function Neural Networks with Fixed Spread Value

Face Detection Using Radial Basis Function Neural Networks with Fixed Spread Value IJCSES International Journal of Computer Sciences and Engineering Systems, Vol., No. 3, July 2011 CSES International 2011 ISSN 0973-06 Face Detection Using Radial Basis Function Neural Networks with Fixed

More information

Evaluation of Neural Networks in the Subject of Prognostics As Compared To Linear Regression Model

Evaluation of Neural Networks in the Subject of Prognostics As Compared To Linear Regression Model International Journal of Engineering & Technology IJET-IJENS Vol:10 No:06 50 Evaluation of Neural Networks in the Subject of Prognostics As Compared To Linear Regression Model A. M. Riad, Hamdy K. Elminir,

More information

Global Journal of Engineering and Technology Review

Global Journal of Engineering and Technology Review Global Journal of Engineering and Technology Review Journal homepage: www.gjetr.org Global J. Eng. Tec. Review 3 (2) 30 38 (2018) Hardware and Software Implementation of Artificial Neural Network in Hybrid

More information

OMBP: Optic Modified BackPropagation training algorithm for fast convergence of Feedforward Neural Network

OMBP: Optic Modified BackPropagation training algorithm for fast convergence of Feedforward Neural Network 2011 International Conference on Telecommunication Technology and Applications Proc.of CSIT vol.5 (2011) (2011) IACSIT Press, Singapore OMBP: Optic Modified BackPropagation training algorithm for fast

More information

Example Applications of A Stochastic Ground Motion Simulation Methodology in Structural Engineering

Example Applications of A Stochastic Ground Motion Simulation Methodology in Structural Engineering Example Applications of A Stochastic Ground Motion Simulation Methodology in Structural Engineering S. Rezaeian & N. Luco U.S. Geological Survey, Golden, CO, USA ABSTRACT: Example engineering applications

More information

Recitation Supplement: Creating a Neural Network for Classification SAS EM December 2, 2002

Recitation Supplement: Creating a Neural Network for Classification SAS EM December 2, 2002 Recitation Supplement: Creating a Neural Network for Classification SAS EM December 2, 2002 Introduction Neural networks are flexible nonlinear models that can be used for regression and classification

More information

Simulation of Back Propagation Neural Network for Iris Flower Classification

Simulation of Back Propagation Neural Network for Iris Flower Classification American Journal of Engineering Research (AJER) e-issn: 2320-0847 p-issn : 2320-0936 Volume-6, Issue-1, pp-200-205 www.ajer.org Research Paper Open Access Simulation of Back Propagation Neural Network

More information

Implementing Machine Learning in Earthquake Engineering

Implementing Machine Learning in Earthquake Engineering CS9 MACHINE LEARNING, DECEMBER 6 Implementing Machine Learning in Earthquake Engineering Cristian Acevedo Civil and Environmental Engineering Stanford University, Stanford, CA 9435, USA Abstract The use

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

Artificial Neuron Modelling Based on Wave Shape

Artificial Neuron Modelling Based on Wave Shape Artificial Neuron Modelling Based on Wave Shape Kieran Greer, Distributed Computing Systems, Belfast, UK. http://distributedcomputingsystems.co.uk Version 1.2 Abstract This paper describes a new model

More information

Lecture #11: The Perceptron

Lecture #11: The Perceptron Lecture #11: The Perceptron Mat Kallada STAT2450 - Introduction to Data Mining Outline for Today Welcome back! Assignment 3 The Perceptron Learning Method Perceptron Learning Rule Assignment 3 Will be

More information

Nuclear Research Reactors Accidents Diagnosis Using Genetic Algorithm/Artificial Neural Networks

Nuclear Research Reactors Accidents Diagnosis Using Genetic Algorithm/Artificial Neural Networks Nuclear Research Reactors Accidents Diagnosis Using Genetic Algorithm/Artificial Neural Networks Abdelfattah A. Ahmed**, Nwal A. Alfishawy*, Mohamed A. Albrdini* and Imbaby I. Mahmoud** * Dept of Comp.

More information

Implementation of Neural Network Methods in Measurement of the Orientation Variables of Spherical Joints

Implementation of Neural Network Methods in Measurement of the Orientation Variables of Spherical Joints International Journal of Science and Engineering Investigations vol. 7, issue 74, March 2018 ISSN: 2251-8843 Implementation of Neural Network Methods in Measurement of the Orientation Variables of Spherical

More information

Neural Networks. Robot Image Credit: Viktoriya Sukhanova 123RF.com

Neural Networks. Robot Image Credit: Viktoriya Sukhanova 123RF.com Neural Networks These slides were assembled by Eric Eaton, with grateful acknowledgement of the many others who made their course materials freely available online. Feel free to reuse or adapt these slides

More information

USING IMAGES PATTERN RECOGNITION AND NEURAL NETWORKS FOR COATING QUALITY ASSESSMENT Image processing for quality assessment

USING IMAGES PATTERN RECOGNITION AND NEURAL NETWORKS FOR COATING QUALITY ASSESSMENT Image processing for quality assessment USING IMAGES PATTERN RECOGNITION AND NEURAL NETWORKS FOR COATING QUALITY ASSESSMENT Image processing for quality assessment L.-M. CHANG and Y.A. ABDELRAZIG School of Civil Engineering, Purdue University,

More information

28th Seismic Research Review: Ground-Based Nuclear Explosion Monitoring Technologies

28th Seismic Research Review: Ground-Based Nuclear Explosion Monitoring Technologies APPLICATION OF ARTIFICIAL NEURAL NETWORK MODELING TO THE ANALYSIS OF THE AUTOMATED RADIOXENON SAMPLER-ANALYZER STATE OF HEALTH SENSORS James C. Hayes, Pamela G. Doctor, Tom R. Heimbigner, Charles W. Hubbard,

More information

Motivation. Problem: With our linear methods, we can train the weights but not the basis functions: Activator Trainable weight. Fixed basis function

Motivation. Problem: With our linear methods, we can train the weights but not the basis functions: Activator Trainable weight. Fixed basis function Neural Networks Motivation Problem: With our linear methods, we can train the weights but not the basis functions: Activator Trainable weight Fixed basis function Flashback: Linear regression Flashback:

More information

Artificial Neural Network Model of Traffic Operations at Signalized Junction in Johor Bahru, Malaysia

Artificial Neural Network Model of Traffic Operations at Signalized Junction in Johor Bahru, Malaysia Artificial Neural Network Model of Traffic Operations at Signalized Junction in Johor Bahru, Malaysia ARASH MORADKHANI ROSHANDEH 1, OTHMAN CHE PUAN 1 and MAJID JOSHANI 2 1 Department of Geotechnics and

More information

Data Mining. Neural Networks

Data Mining. Neural Networks Data Mining Neural Networks Goals for this Unit Basic understanding of Neural Networks and how they work Ability to use Neural Networks to solve real problems Understand when neural networks may be most

More information

9. Lecture Neural Networks

9. Lecture Neural Networks Soft Control (AT 3, RMA) 9. Lecture Neural Networks Application in Automation Engineering Outline of the lecture 1. Introduction to Soft Control: definition and limitations, basics of "smart" systems 2.

More information

Machine Learning 13. week

Machine Learning 13. week Machine Learning 13. week Deep Learning Convolutional Neural Network Recurrent Neural Network 1 Why Deep Learning is so Popular? 1. Increase in the amount of data Thanks to the Internet, huge amount of

More information

GeoDAS Software of GeoSIG

GeoDAS Software of GeoSIG GeoDAS Software of GeoSIG 1 GeoDAS, 25.03.2009 www.geosig.com Introduction Major Features General Tasks of GeoDAS Data Analysis Strong Motion Data Processing Messenger of GeoDAS Network Links of GeoDAS

More information

Natural Language Processing CS 6320 Lecture 6 Neural Language Models. Instructor: Sanda Harabagiu

Natural Language Processing CS 6320 Lecture 6 Neural Language Models. Instructor: Sanda Harabagiu Natural Language Processing CS 6320 Lecture 6 Neural Language Models Instructor: Sanda Harabagiu In this lecture We shall cover: Deep Neural Models for Natural Language Processing Introduce Feed Forward

More information

Pattern Classification Algorithms for Face Recognition

Pattern Classification Algorithms for Face Recognition Chapter 7 Pattern Classification Algorithms for Face Recognition 7.1 Introduction The best pattern recognizers in most instances are human beings. Yet we do not completely understand how the brain recognize

More information

A *69>H>N6 #DJGC6A DG C<>C::G>C<,8>:C8:H /DA 'D 2:6G, ()-"&"3 -"(' ( +-" " " % '.+ % ' -0(+$,

A *69>H>N6 #DJGC6A DG C<>C::G>C<,8>:C8:H /DA 'D 2:6G, ()-&3 -(' ( +-   % '.+ % ' -0(+$, The structure is a very important aspect in neural network design, it is not only impossible to determine an optimal structure for a given problem, it is even impossible to prove that a given structure

More information

Fitting Fragility Functions to Structural Analysis Data Using Maximum Likelihood Estimation

Fitting Fragility Functions to Structural Analysis Data Using Maximum Likelihood Estimation Fitting Fragility Functions to Structural Analysis Data Using Maximum Likelihood Estimation 1. Introduction This appendix describes a statistical procedure for fitting fragility functions to structural

More information

Image Compression: An Artificial Neural Network Approach

Image Compression: An Artificial Neural Network Approach Image Compression: An Artificial Neural Network Approach Anjana B 1, Mrs Shreeja R 2 1 Department of Computer Science and Engineering, Calicut University, Kuttippuram 2 Department of Computer Science and

More information

Neural Networks (Overview) Prof. Richard Zanibbi

Neural Networks (Overview) Prof. Richard Zanibbi Neural Networks (Overview) Prof. Richard Zanibbi Inspired by Biology Introduction But as used in pattern recognition research, have little relation with real neural systems (studied in neurology and neuroscience)

More information

Identification of Multisensor Conversion Characteristic Using Neural Networks

Identification of Multisensor Conversion Characteristic Using Neural Networks Sensors & Transducers 3 by IFSA http://www.sensorsportal.com Identification of Multisensor Conversion Characteristic Using Neural Networks Iryna TURCHENKO and Volodymyr KOCHAN Research Institute of Intelligent

More information

Ship Energy Systems Modelling: a Gray-Box approach

Ship Energy Systems Modelling: a Gray-Box approach MOSES Workshop: Modelling and Optimization of Ship Energy Systems Ship Energy Systems Modelling: a Gray-Box approach 25 October 2017 Dr Andrea Coraddu andrea.coraddu@strath.ac.uk 30/10/2017 Modelling &

More information

Selection of ground motion time series and limits on scaling

Selection of ground motion time series and limits on scaling Soil Dynamics and Earthquake Engineering 26 (2006) 477 482 www.elsevier.com/locate/soildyn Selection of ground motion time series and limits on scaling Jennie Watson-Lamprey a, *, Norman Abrahamson b a

More information

CS 354R: Computer Game Technology

CS 354R: Computer Game Technology CS 354R: Computer Game Technology AI Fuzzy Logic and Neural Nets Fall 2018 Fuzzy Logic Philosophical approach Decisions based on degree of truth Is not a method for reasoning under uncertainty that s probability

More information

Seismic Soil-Structure Interaction Analysis of the Kealakaha Stream Bridge on Parallel Computers

Seismic Soil-Structure Interaction Analysis of the Kealakaha Stream Bridge on Parallel Computers Seismic Soil-Structure Interaction Analysis of the Kealakaha Stream Bridge on Parallel Computers Seung Ha Lee and Si-Hwan Park Department of Civil and Environmental Engineering University of Hawaii at

More information

Transactions, SMiRT-22 San Francisco, California, August 18-23, 2013 Division 5

Transactions, SMiRT-22 San Francisco, California, August 18-23, 2013 Division 5 Transactions, SMiRT-22 San Francisco, California, August 18-23, 2013 LACK OF CORRELATION (INCOHERENCE) MODELING AND EFFECTS FROM REALISTIC 3D, INCLINED, BODY AND SURFACE SEISMIC MOTIONS N. Tafazzoli 1,

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

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

Research Article Forecasting SPEI and SPI Drought Indices Using the Integrated Artificial Neural Networks

Research Article Forecasting SPEI and SPI Drought Indices Using the Integrated Artificial Neural Networks Computational Intelligence and Neuroscience Volume 2016, Article ID 3868519, 17 pages http://dx.doi.org/10.1155/2016/3868519 Research Article Forecasting SPEI and SPI Drought Indices Using the Integrated

More information

NEURO-PREDICTIVE CONTROL DESIGN BASED ON GENETIC ALGORITHMS

NEURO-PREDICTIVE CONTROL DESIGN BASED ON GENETIC ALGORITHMS NEURO-PREDICTIVE CONTROL DESIGN BASED ON GENETIC ALGORITHMS I.Sekaj, S.Kajan, L.Körösi, Z.Dideková, L.Mrafko Institute of Control and Industrial Informatics Faculty of Electrical Engineering and Information

More information

Use of Artificial Neural Networks to Investigate the Surface Roughness in CNC Milling Machine

Use of Artificial Neural Networks to Investigate the Surface Roughness in CNC Milling Machine Use of Artificial Neural Networks to Investigate the Surface Roughness in CNC Milling Machine M. Vijay Kumar Reddy 1 1 Department of Mechanical Engineering, Annamacharya Institute of Technology and Sciences,

More information

Framework for Performance-Based Earthquake Engineering. Helmut Krawinkler, Stanford U.

Framework for Performance-Based Earthquake Engineering. Helmut Krawinkler, Stanford U. Framework for Performance-Based Earthquake Engineering Helmut Krawinkler, Stanford U. PEER Summative Meeting June 13, 2007 Where were we 10 years ago? SEAOC Vision 2000, FEMA 273, ATC-40 Descriptive performance

More information

DIFFERENT TECHNIQUES FOR THE MODELING OF POST-TENSIONED CONCRETE BOX-GIRDER BRIDGES

DIFFERENT TECHNIQUES FOR THE MODELING OF POST-TENSIONED CONCRETE BOX-GIRDER BRIDGES DIFFERENT TECHNIQUES FOR THE MODELING OF POST-TENSIONED CONCRETE BOX-GIRDER BRIDGES Deepak Rayamajhi Naveed Anwar Jimmy Chandra Graduate Student Associate Director Graduate Student Structural Engineering

More information

Damage assessment in structure from changes in static parameter using neural networks

Damage assessment in structure from changes in static parameter using neural networks Sādhanā Vol. 29, Part 3, June 2004, pp. 315 327. Printed in India Damage assessment in structure from changes in static parameter using neural networks DAMODAR MAITY and ASISH SAHA Civil Engineering Department,

More information

Seismic regionalization based on an artificial neural network

Seismic regionalization based on an artificial neural network Seismic regionalization based on an artificial neural network *Jaime García-Pérez 1) and René Riaño 2) 1), 2) Instituto de Ingeniería, UNAM, CU, Coyoacán, México D.F., 014510, Mexico 1) jgap@pumas.ii.unam.mx

More information

SEMI-ACTIVE CONTROL OF BUILDING STRUCTURES USING A NEURO-FUZZY CONTROLLER WITH ACCELERATION FEEDBACK

SEMI-ACTIVE CONTROL OF BUILDING STRUCTURES USING A NEURO-FUZZY CONTROLLER WITH ACCELERATION FEEDBACK Proceedings of the 6th International Conference on Mechanics and Materials in Design, Editors: J.F. Silva Gomes & S.A. Meguid, P.Delgada/Azores, 26-30 July 2015 PAPER REF: 5778 SEMI-ACTIVE CONTROL OF BUILDING

More information

Linear Separability. Linear Separability. Capabilities of Threshold Neurons. Capabilities of Threshold Neurons. Capabilities of Threshold Neurons

Linear Separability. Linear Separability. Capabilities of Threshold Neurons. Capabilities of Threshold Neurons. Capabilities of Threshold Neurons Linear Separability Input space in the two-dimensional case (n = ): - - - - - - w =, w =, = - - - - - - w = -, w =, = - - - - - - w = -, w =, = Linear Separability So by varying the weights and the threshold,

More information

COMP 551 Applied Machine Learning Lecture 14: Neural Networks

COMP 551 Applied Machine Learning Lecture 14: Neural Networks COMP 551 Applied Machine Learning Lecture 14: Neural Networks Instructor: (jpineau@cs.mcgill.ca) Class web page: www.cs.mcgill.ca/~jpineau/comp551 Unless otherwise noted, all material posted for this course

More information

CSC 578 Neural Networks and Deep Learning

CSC 578 Neural Networks and Deep Learning CSC 578 Neural Networks and Deep Learning Fall 2018/19 7. Recurrent Neural Networks (Some figures adapted from NNDL book) 1 Recurrent Neural Networks 1. Recurrent Neural Networks (RNNs) 2. RNN Training

More information

Machine Learning Applications for Data Center Optimization

Machine Learning Applications for Data Center Optimization Machine Learning Applications for Data Center Optimization Jim Gao, Google Ratnesh Jamidar Indian Institute of Technology, Kanpur October 27, 2014 Outline Introduction Methodology General Background Model

More information

Climate Precipitation Prediction by Neural Network

Climate Precipitation Prediction by Neural Network Journal of Mathematics and System Science 5 (205) 207-23 doi: 0.7265/259-529/205.05.005 D DAVID PUBLISHING Juliana Aparecida Anochi, Haroldo Fraga de Campos Velho 2. Applied Computing Graduate Program,

More information

Optimization of Cutting Parameters for Milling Operation using Genetic Algorithm technique through MATLAB

Optimization of Cutting Parameters for Milling Operation using Genetic Algorithm technique through MATLAB International Journal for Ignited Minds (IJIMIINDS) Optimization of Cutting Parameters for Milling Operation using Genetic Algorithm technique through MATLAB A M Harsha a & Ramesh C G c a PG Scholar, Department

More information

Open Access Research on the Prediction Model of Material Cost Based on Data Mining

Open Access Research on the Prediction Model of Material Cost Based on Data Mining Send Orders for Reprints to reprints@benthamscience.ae 1062 The Open Mechanical Engineering Journal, 2015, 9, 1062-1066 Open Access Research on the Prediction Model of Material Cost Based on Data Mining

More information

Week 3: Perceptron and Multi-layer Perceptron

Week 3: Perceptron and Multi-layer Perceptron Week 3: Perceptron and Multi-layer Perceptron Phong Le, Willem Zuidema November 12, 2013 Last week we studied two famous biological neuron models, Fitzhugh-Nagumo model and Izhikevich model. This week,

More information

APPLICATIONS OF INTELLIGENT HYBRID SYSTEMS IN MATLAB

APPLICATIONS OF INTELLIGENT HYBRID SYSTEMS IN MATLAB APPLICATIONS OF INTELLIGENT HYBRID SYSTEMS IN MATLAB Z. Dideková, S. Kajan Institute of Control and Industrial Informatics, Faculty of Electrical Engineering and Information Technology, Slovak University

More information

CHAPTER 7 MASS LOSS PREDICTION USING ARTIFICIAL NEURAL NETWORK (ANN)

CHAPTER 7 MASS LOSS PREDICTION USING ARTIFICIAL NEURAL NETWORK (ANN) 128 CHAPTER 7 MASS LOSS PREDICTION USING ARTIFICIAL NEURAL NETWORK (ANN) Various mathematical techniques like regression analysis and software tools have helped to develop a model using equation, which

More information

The Application Research of Neural Network in Embedded Intelligent Detection

The Application Research of Neural Network in Embedded Intelligent Detection The Application Research of Neural Network in Embedded Intelligent Detection Xiaodong Liu 1, Dongzhou Ning 1, Hubin Deng 2, and Jinhua Wang 1 1 Compute Center of Nanchang University, 330039, Nanchang,

More information

Proceedings of the 2016 International Conference on Industrial Engineering and Operations Management Detroit, Michigan, USA, September 23-25, 2016

Proceedings of the 2016 International Conference on Industrial Engineering and Operations Management Detroit, Michigan, USA, September 23-25, 2016 Neural Network Viscosity Models for Multi-Component Liquid Mixtures Adel Elneihoum, Hesham Alhumade, Ibrahim Alhajri, Walid El Garwi, Ali Elkamel Department of Chemical Engineering, University of Waterloo

More information

Neural Networks Laboratory EE 329 A

Neural Networks Laboratory EE 329 A Neural Networks Laboratory EE 329 A Introduction: Artificial Neural Networks (ANN) are widely used to approximate complex systems that are difficult to model using conventional modeling techniques such

More information

A PREDICTIVE COMPUTER PROGRAM FOR PROACTIVE DEMOLITION PLANNING

A PREDICTIVE COMPUTER PROGRAM FOR PROACTIVE DEMOLITION PLANNING A PREDICTIVE COMPUTER PROGRAM FOR PROACTIVE DEMOLITION PLANNING Quarterly Progress Report For the period ending November 30, 2017 Submitted by: PI - Seung Jae Lee, Ph.D. Affiliation: Department of Civil

More information

Dr. Qadri Hamarsheh Supervised Learning in Neural Networks (Part 1) learning algorithm Δwkj wkj Theoretically practically

Dr. Qadri Hamarsheh Supervised Learning in Neural Networks (Part 1) learning algorithm Δwkj wkj Theoretically practically Supervised Learning in Neural Networks (Part 1) A prescribed set of well-defined rules for the solution of a learning problem is called a learning algorithm. Variety of learning algorithms are existing,

More information

Artificial Neural Network and Multi-Response Optimization in Reliability Measurement Approximation and Redundancy Allocation Problem

Artificial Neural Network and Multi-Response Optimization in Reliability Measurement Approximation and Redundancy Allocation Problem International Journal of Mathematics and Statistics Invention (IJMSI) E-ISSN: 2321 4767 P-ISSN: 2321-4759 Volume 4 Issue 10 December. 2016 PP-29-34 Artificial Neural Network and Multi-Response Optimization

More information

Gauss-Sigmoid Neural Network

Gauss-Sigmoid Neural Network Gauss-Sigmoid Neural Network Katsunari SHIBATA and Koji ITO Tokyo Institute of Technology, Yokohama, JAPAN shibata@ito.dis.titech.ac.jp Abstract- Recently RBF(Radial Basis Function)-based networks have

More information

Deep (1) Matthieu Cord LIP6 / UPMC Paris 6

Deep (1) Matthieu Cord LIP6 / UPMC Paris 6 Deep (1) Matthieu Cord LIP6 / UPMC Paris 6 Syllabus 1. Whole traditional (old) visual recognition pipeline 2. Introduction to Neural Nets 3. Deep Nets for image classification To do : Voir la leçon inaugurale

More information

Lecture 20: Neural Networks for NLP. Zubin Pahuja

Lecture 20: Neural Networks for NLP. Zubin Pahuja Lecture 20: Neural Networks for NLP Zubin Pahuja zpahuja2@illinois.edu courses.engr.illinois.edu/cs447 CS447: Natural Language Processing 1 Today s Lecture Feed-forward neural networks as classifiers simple

More information

Introduction to ANSYS DesignXplorer

Introduction to ANSYS DesignXplorer Lecture 4 14. 5 Release Introduction to ANSYS DesignXplorer 1 2013 ANSYS, Inc. September 27, 2013 s are functions of different nature where the output parameters are described in terms of the input parameters

More information

Improving Classification Accuracy for Single-loop Reliability-based Design Optimization

Improving Classification Accuracy for Single-loop Reliability-based Design Optimization , March 15-17, 2017, Hong Kong Improving Classification Accuracy for Single-loop Reliability-based Design Optimization I-Tung Yang, and Willy Husada Abstract Reliability-based design optimization (RBDO)

More information

IMPLEMENTATION OF FPGA-BASED ARTIFICIAL NEURAL NETWORK (ANN) FOR FULL ADDER. Research Scholar, IIT Kharagpur.

IMPLEMENTATION OF FPGA-BASED ARTIFICIAL NEURAL NETWORK (ANN) FOR FULL ADDER. Research Scholar, IIT Kharagpur. Journal of Analysis and Computation (JAC) (An International Peer Reviewed Journal), www.ijaconline.com, ISSN 0973-2861 Volume XI, Issue I, Jan- December 2018 IMPLEMENTATION OF FPGA-BASED ARTIFICIAL NEURAL

More information

Machine Learning in Biology

Machine Learning in Biology Università degli studi di Padova Machine Learning in Biology Luca Silvestrin (Dottorando, XXIII ciclo) Supervised learning Contents Class-conditional probability density Linear and quadratic discriminant

More information

Keywords: ANN; network topology; bathymetric model; representability.

Keywords: ANN; network topology; bathymetric model; representability. Proceedings of ninth International Conference on Hydro-Science and Engineering (ICHE 2010), IIT Proceedings Madras, Chennai, of ICHE2010, India. IIT Madras, Aug 2-5,2010 DETERMINATION OF 2 NETWORK - 5

More information

Classification Lecture Notes cse352. Neural Networks. Professor Anita Wasilewska

Classification Lecture Notes cse352. Neural Networks. Professor Anita Wasilewska Classification Lecture Notes cse352 Neural Networks Professor Anita Wasilewska Neural Networks Classification Introduction INPUT: classification data, i.e. it contains an classification (class) attribute

More information

SNIWD: Simultaneous Weight Noise Injection With Weight Decay for MLP Training

SNIWD: Simultaneous Weight Noise Injection With Weight Decay for MLP Training SNIWD: Simultaneous Weight Noise Injection With Weight Decay for MLP Training John Sum and Kevin Ho Institute of Technology Management, National Chung Hsing University Taichung 4, Taiwan. pfsum@nchu.edu.tw

More information

NNIGnets, Neural Networks Software

NNIGnets, Neural Networks Software NNIGnets, Neural Networks Software Tânia Fontes 1, Vânia Lopes 1, Luís M. Silva 1, Jorge M. Santos 1,2, and Joaquim Marques de Sá 1 1 INEB - Instituto de Engenharia Biomédica, Campus FEUP (Faculdade de

More information

Network traffic anomaly prediction using Artificial Neural Network

Network traffic anomaly prediction using Artificial Neural Network Network traffic anomaly prediction using Artificial Neural Network Hening Titi Ciptaningtyas, Chastine Fatichah, and Altea Sabila Citation: AIP Conference Proceedings 1818, 020010 (2017); View online:

More information

Central Manufacturing Technology Institute, Bangalore , India,

Central Manufacturing Technology Institute, Bangalore , India, 5 th International & 26 th All India Manufacturing Technology, Design and Research Conference (AIMTDR 2014) December 12 th 14 th, 2014, IIT Guwahati, Assam, India Investigation on the influence of cutting

More information

An Algorithm For Training Multilayer Perceptron (MLP) For Image Reconstruction Using Neural Network Without Overfitting.

An Algorithm For Training Multilayer Perceptron (MLP) For Image Reconstruction Using Neural Network Without Overfitting. An Algorithm For Training Multilayer Perceptron (MLP) For Image Reconstruction Using Neural Network Without Overfitting. Mohammad Mahmudul Alam Mia, Shovasis Kumar Biswas, Monalisa Chowdhury Urmi, Abubakar

More information

Impact of Complex System Behavior on Seismic Assessment of RC Bridges

Impact of Complex System Behavior on Seismic Assessment of RC Bridges Impact of Complex System Behavior on Seismic Assessment of RC Bridges Amr S. Elnashai Department of Civil and Environmental Engineering Based on the PhD Work of Thomas Frankie, Advised by Kuchma, Spencer

More information