COMPUTER MODELLING OF NEURAL NETWORK OF UNDEVELOPED LIVING CREATURES

Size: px
Start display at page:

Download "COMPUTER MODELLING OF NEURAL NETWORK OF UNDEVELOPED LIVING CREATURES"

Transcription

1 ABSTRACT COMPUTER MODELLING OF NEURAL NETWORK OF UNDEVELOPED LIVING CREATURES Ádám Rák 1, László Dudás 2 1 Student, Fényi Gyula Grammar School 2 PhD, Associate Professor University of Miskolc The article introduces results have been achieved in area of computer simulation of neural network of undeveloped living creatures, namely beetles. For improving the quality of artificial neural network (ANN) of beetles genetic algorithm (GA) had been used. In the simplified two-dimensional artificial world of beetles there are two species of insects: plant-eating group and predacious group. The article discusses the structure of beetles and theirs artificial micro-world and presents the developed capabilities of the newer populations of beetles. Keywords: ANN, GA, multi-agent system, beetle life simulation. INTRODUCTION The simulation of multi-agent system is very widespread today and it is in focus of research of artificial intelligence. Modelling simple biological objects using neural network is in the front of interest of investigations. The results of a four-year long research period initiated by one of the author, dr.lászló Dudás and performed by Ádám Rák fit into these trends. ANN and GA integration for artificial life simulation is introduced in [1]. Different aspects of artificial life are discussed in [2]. THE STRUCTURE OF A BEETLE The applied model of a beetle can be divided into three parts: 1. Sensors 2. ANN 3. Motors. 1. Sensors The applied nightly beetles have two sensors, two feelers that can feel the smell of food. The right and left feelers give input signal to selected neurons of ANN. The strength of the signal is calculated as the reciprocal of the distance between feeler and food. To get stereo effect there is a given distance between left and right feelers that is

2 applied in calculations but this distance is not applied in the modelling of the beetle, every beetle and the food are point-like object. The food for a predacious beetle is a plant-eating beetle. A predacious beetle has sensor for detecting the wall, too. 2. ANN The starter arrangement is shown in Fig.1. The very simplified model of the beetle has three neurons: one for directing the forward motion and two for directing the turning to the left or turning to the right. These two neurons receive the signals of food sensors and determine the direction of turning. As these neurons compete thanks to connections having negative weights only one turning direction is possible at given moment. If the food is exactly in front of the beetle then the two sensors give the same signal and the result is no turning. The beetle will go straight to the food because every turning neuron gives signal to the forward motion neuron. The forward motion neuron gets exiting signal from the turning neurons in every case to induce forward translation parallel to rotation yielding moving to the food. The beetle cannot go backwards. Control of forward motion Control of turning to the left Control of turning to the right Input from left feeler Input from right feeler Fig.1. The starter ANN This simplified ANN is the starter network for the beetle at the beginning of its evolution process. The most important connections wired only, the GA will make other connections later when new beetle instances are born and the mutation produces new random connections. In the more complex view of the ANN can be mentioned the additional capabilities: every beetle can feel the other beetles using different inputs of the ANN. Moreover, there is a communication capacity: if the beetles are close to each other then some of the outputs and inputs of the ANN-s connect to each other. To avoid go away from the food if it is exactly behind the beetle a little random movement is added to the food-directed movement. 3. Motors The motors are the virtual legs realised by software parts that move the drawing of the beetle on the screen depending on the values of the outputs of the forward motion and the turning neurons. Similarly, the virtual mouth is a software component that detects the reaching of the food and eats clears that.

3 THE MICRO-WORLD The micro-world is not limited theoretically but the random generation of a new food accomplished in a rectangle area so this motivates the beetles to stay in or close to this area. If a food is eaten then the world gives a new one in a randomly selected position. The food is point-like too but a bigger cross represents it on the screen. There is a straight wall in the middle of the micro-world. This is because of planteating beetles. They can go across the wall without any problem they cannot detect it so they can escape from predacious beetles. The predacious instances have to go round it. Going across the wall the plant-eating beetles can save their lives and can get a possibility to have a longer life. Six plant-eating and five predacious beetles live in this micro-world in the presented form of the simulation. See Fig. 2. A beetle with feelers The wall The food Fig.2. The visualised part of the micro-world THE LIFE AND EVOLUTION OF BEETLES The life of beetles is managed by the GA. Every beetle has a fitness function. This can be interpreted as vigour. Eating the food results higher value of vigour while the progress of time results continuous decrease of it. A bite of a predacious beetle increases its vigour and decreases the vigour of the attacked plant-eating beetle. The time is divided into intervals; an interval is the life of a predacious population. At the end of intervals the GA destroys the weakest instance and generates a new instance crossing the parameters, neuron weights of the two best members of the predacious group. In the creation of the new instance some mutation is applied too. This mutation may result new connections in the ANN and new input neurons and associated functions can appear. The evolution of the plant-eating beetles happens when a beetle die so the vigour, the fitness value reaches a set low value. In this moment a new instance is created crossing the two best member of the group.

4 STATIONS OF THE EVOLUTION These stations can be interpreted as the results of the research. In the beginning the beetles suffer from different problems: they move too slow, get stuck at wall, lose the smell of food. Later on after growth of speed the low accuracy causes problem. To resolve these insufficiencies different forms of behaviour appear, these new motion forms help the beetle to survive. When suitable speeds are evolved the next problem appear: the beetle cannot turn to the food because it is not capable to control the speed volume. The situation: the beetle circles around the food. See Fig. 3. The other effect of big speed is to miss the food. The next phase of evolution resolves these problems: develops the drop-shaped turn. See Fig. 3. The curve-shaped path is evolved because the beetle can start to the next food in a better orientation if the food was reached in the middle of the turning to the next. Circles around the food Feeling after wall Drop-shaped turn Fig.3. Different evolved forms of behavior The wall is a problem for the predacious beetle in the beginning. However later because of evolution they can go around it. A feeling after wall is evolved as a cyclic moving that looks for the end of the wall. See Fig.3. The competition for the food develops a new capability: the mutation wires new neurons having connection possibility to the close beetle. Using these neurons and the connection to the other member of the group the beetle gives big signal to the other beetle to disturb the motion of that. It is similar to competing of animals that use fearful voice to chase away the other animals from the prey. See Fig.4 in the next page. CONCLUSION

5 The paper presented some of the results of simulating a beetle-population having two species of insects. The multi-agent model applied ANN for modelling the structure of agents and GA for modelling the behaviour and evolution of them. The structure had a flexible simple pre-wired initial creature and evolved to a more complex one that mirrors the requirements of the environment modelled by a microworld and fitness function of agents that can interpret as vigour. Among the results are special evolved behaviours that rational and similar to behaviour of real biological beings. Among the further goals are applying more complex environment, sensors and motors and studying the evolution of adequate ANN and its capabilities. Communication is turned off Communication is turned on Fig.4. Competition for the food REFERENCES [1] Melanie Mitchell, Stephanie Forrest: Genetic Algorithms and Artificial Life (1993) citeseer.nj.nec.com/mitchell93genetic.html [2] Artificial Life Online

What is Evolutionary Computation? Genetic Algorithms. Components of Evolutionary Computing. The Argument. When changes occur...

What is Evolutionary Computation? Genetic Algorithms. Components of Evolutionary Computing. The Argument. When changes occur... What is Evolutionary Computation? Genetic Algorithms Russell & Norvig, Cha. 4.3 An abstraction from the theory of biological evolution that is used to create optimization procedures or methodologies, usually

More information

Deterministic Crowding, Recombination And Self-Similarity

Deterministic Crowding, Recombination And Self-Similarity Deterministic Crowding, Recombination And Self-Similarity Bo Yuan School of Information Technology and Electrical Engineering The University of Queensland Brisbane, Queensland 4072 Australia E-mail: s4002283@student.uq.edu.au

More information

GENETIC ALGORITHMS. Narra Priyanka. K.Naga Sowjanya. Vasavi College of Engineering. Ibrahimbahg,Hyderabad.

GENETIC ALGORITHMS. Narra Priyanka. K.Naga Sowjanya. Vasavi College of Engineering. Ibrahimbahg,Hyderabad. GENETIC ALGORITHMS Narra Priyanka K.Naga Sowjanya Vasavi College of Engineering. Ibrahimbahg,Hyderabad mynameissowji@yahoo.com priyankanarra@yahoo.com Abstract Genetic algorithms are a part of evolutionary

More information

Building Energy Modeling Using Artificial Neural Networks

Building Energy Modeling Using Artificial Neural Networks Energy Research Journal Original Research Paper Building Energy Modeling Using Artificial Neural Networks Maya Arida, Nabil Nassif, Rand Talib and Taher Abu-Lebdeh Department of Civil, Architectural and

More information

Evolving free-form stick ski jumpers and their neural control systems

Evolving free-form stick ski jumpers and their neural control systems Evolving free-form stick ski jumpers and their neural control systems Maciej Komosinski and Jan Polak Institute of Computing Science, Poznan University of Technology, Piotrowo 2, 60-965 Poznan, Poland,

More information

Life on Earth National 5 biology Measuring abiotic factors

Life on Earth National 5 biology Measuring abiotic factors Life on Earth National 5 biology Measuring abiotic factors By the end of these lessons you should be able to: Measure various abiotic factors and state sources of error and how they can be minimised. Analyse

More information

Optimization of Plastic Injection Molding Process by Combination of Artificial Neural Network and Genetic Algorithm

Optimization of Plastic Injection Molding Process by Combination of Artificial Neural Network and Genetic Algorithm Journal of Optimization in Industrial Engineering 13 (2013) 49-54 Optimization of Plastic Injection Molding Process by Combination of Artificial Neural Network and Genetic Algorithm Mohammad Saleh Meiabadi

More information

Informatics solutions for decision support regarding electricity consumption optimizing within smart grids

Informatics solutions for decision support regarding electricity consumption optimizing within smart grids BUCHAREST UNIVERSITY OF ECONOMIC STUDIES Doctoral School of Economic Informatics Informatics solutions for decision support regarding electricity consumption optimizing within smart grids SUMMARY OF DOCTORAL

More information

DYNAMIC MODELLING AND SIMULATION OF A SIX WHEEL AUTOMATIC GUIDED VEHICLE

DYNAMIC MODELLING AND SIMULATION OF A SIX WHEEL AUTOMATIC GUIDED VEHICLE DYNAMIC MODELLING AND SIMULATION OF A SIX WHEEL AUTOMATIC GUIDED VEHICLE Bittencourt G. F., gufbittencourt@poli.ufrj.br Student, Department of Mechanical Engineering, Polytechnic School, Federal University

More information

PRODUCTIVITY AND ACCURACY IN PLASTIC INJECTION MOULD QUOTATION

PRODUCTIVITY AND ACCURACY IN PLASTIC INJECTION MOULD QUOTATION 5th International DAAAM Baltic Conference "INDUSTRIAL ENGINEERING ADDING INNOVATION CAPACITY OF LABOUR FORCE AND ENTREPRENEURS" 20 22 April 2006, Tallinn, Estonia PRODUCTIVITY AND ACCURACY IN PLASTIC INJECTION

More information

Energy management using genetic algorithms

Energy management using genetic algorithms Energy management using genetic algorithms F. Garzia, F. Fiamingo & G. M. Veca Department of Electrical Engineering, University of Rome "La Sapienza", Italy Abstract An energy management technique based

More information

Managing Knowledge in the Digital Firm

Managing Knowledge in the Digital Firm Chapter 12 Managing Knowledge in the Digital Firm 12.1 2006 by Prentice Hall OBJECTIVES Assess the role of knowledge management and knowledge management programs in business Define and describe the types

More information

INTELLIGENT DIGITAL AUTOMATION PLATFORM

INTELLIGENT DIGITAL AUTOMATION PLATFORM A I INTELLIGENT DIGITAL AUTOMATION PLATFORM Gaining competitive advantage through digital transformation of your business processes Sponsored by 1 Introduction Today, every business faces the threat of

More information

IMPLEMENTATION OF AN OPTIMIZATION TECHNIQUE: GENETIC ALGORITHM

IMPLEMENTATION OF AN OPTIMIZATION TECHNIQUE: GENETIC ALGORITHM IMPLEMENTATION OF AN OPTIMIZATION TECHNIQUE: GENETIC ALGORITHM TWINKLE GUPTA* Department of Computer Science, Hindu Kanya MahaVidyalya, Jind, India Abstract We are encountered with various optimization

More information

Bio-inspired Active Vision. Martin Peniak, Ron Babich, John Tran and Davide Marocco

Bio-inspired Active Vision. Martin Peniak, Ron Babich, John Tran and Davide Marocco Bio-inspired Active Vision Martin Peniak, Ron Babich, John Tran and Davide Marocco GPU Computing Lab Traditional Computer Vision 3 Traditional Computer Vision Teaching a computer to classify objects has

More information

Energy is involved in everything that happens. We are aware

Energy is involved in everything that happens. We are aware 57 The Conservation of Energy R EA D I N G Energy is involved in everything that happens. We are aware of energy when it is released or absorbed. Examining the changes of energy in action has led to one

More information

Genetic Algorithm: An Optimization Technique Concept

Genetic Algorithm: An Optimization Technique Concept Genetic Algorithm: An Optimization Technique Concept 1 Uma Anand, 2 Chain Singh 1 Student M.Tech (3 rd sem) Department of Computer Science Engineering Dronacharya College of Engineering, Gurgaon-123506,

More information

PARALLEL LINE AND MACHINE JOB SCHEDULING USING GENETIC ALGORITHM

PARALLEL LINE AND MACHINE JOB SCHEDULING USING GENETIC ALGORITHM PARALLEL LINE AND MACHINE JOB SCHEDULING USING GENETIC ALGORITHM Dr.V.Selvi Assistant Professor, Department of Computer Science Mother Teresa women s University Kodaikanal. Tamilnadu,India. Abstract -

More information

Management System of Distribution Transformer Loading

Management System of Distribution Transformer Loading Management System of Distribution Transformer Loading A. G. Leal, M.Sc J. A. Jardini, Ph.D. L. C. Magrini, Ph.D. S. U. Ahn, Ph.D. D. Battani Abstract - This paper presents an Integrated Management System

More information

The Making of the Fittest: Natural Selection in Humans

The Making of the Fittest: Natural Selection in Humans POPULATION GENETICS, SELECTION, AND EVOLUTION INTRODUCTION A common misconception is that individuals evolve. While individuals may have favorable and heritable traits that are advantageous for survival

More information

CYBERNETICS & CYBORGS

CYBERNETICS & CYBORGS SEMINAR ON CYBERNETICS & CYBORGS PREPARED BY, JAZEEL J COMPUTER ENGINEERING REG.NO:87130025 NO:22 CENTRAL POLYTECHNIC COLLEGE VATTIYOORKAVU,TVPM CONTENTS INTRODUCTION REAL LIFE CYBORGS ROBOTS & CYBORGS

More information

Machine learning in neuroscience

Machine learning in neuroscience Machine learning in neuroscience Bojan Mihaljevic, Luis Rodriguez-Lujan Computational Intelligence Group School of Computer Science, Technical University of Madrid 2015 IEEE Iberian Student Branch Congress

More information

Workshop #2: Evolution

Workshop #2: Evolution The DNA Files: Workshops and Activities The DNA Files workshops are an outreach component of The DNA Files public radio documentary series produced by SoundVision Productions with funding from the National

More information

The Weapon Target Assignment Strategy Research on Genetic Algorithm

The Weapon Target Assignment Strategy Research on Genetic Algorithm 2010 3rd International Conference on Computer and Electrical Engineering (ICCEE 2010) IPCSIT vol. 53 (2012) (2012) IACSIT Press, Singapore DOI: 10.7763/IPCSIT.2012.V53.No.1.75 The Weapon Target Assignment

More information

GOAL STATEMENT: Students will simulate the effects of pesticides on an insect population and observe how the population changes over time.

GOAL STATEMENT: Students will simulate the effects of pesticides on an insect population and observe how the population changes over time. STATE SCIENCE STANDARDS: 6 th, 7 th, 8 th Grade Skills and Processes: 1.0.A.1.h Use mathematics to interpret and communicate data. 1.0.B.1 Review data from a simple experiment, summarize the data, and

More information

Introduction To Genetic Algorithms

Introduction To Genetic Algorithms 1 Introduction To Genetic Algorithms Dr. Rajib Kumar Bhattacharjya Department of Civil Engineering IIT Guwahati Email: rkbc@iitg.ernet.in References 2 D. E. Goldberg, Genetic Algorithm In Search, Optimization

More information

Reproduction Strategy Based on Self-Organizing Map for Real-coded Genetic Algorithms

Reproduction Strategy Based on Self-Organizing Map for Real-coded Genetic Algorithms Neural Information Processing - Letters and Reviews Vol. 5, No. 2, November 2004 LETTER Reproduction Strategy Based on Self-Organizing Map for Real-coded Genetic Algorithms Ryosuke Kubota Graduate School

More information

POPULATION GENETICS AND EVOLUTION

POPULATION GENETICS AND EVOLUTION AP BIOLOGY EVOLUTION ACTIVITY # NAME DATE HOUR POPULATION GENETICS AND EVOLUTION INTRODUCTION In 908 G. H. Hardy and W. Weinberg independently suggest a scheme whereby evolution could be viewed as changes

More information

10. Lecture Stochastic Optimization

10. Lecture Stochastic Optimization Soft Control (AT 3, RMA) 10. Lecture Stochastic Optimization Genetic Algorithms 10. Structure of the lecture 1. Soft control: the definition and limitations, basics of epert" systems 2. Knowledge representation

More information

Computational Intelligence Lecture 20:Intorcution to Genetic Algorithm

Computational Intelligence Lecture 20:Intorcution to Genetic Algorithm Computational Intelligence Lecture 20:Intorcution to Genetic Algorithm Farzaneh Abdollahi Department of Electrical Engineering Amirkabir University of Technology Fall 2012 Farzaneh Abdollahi Computational

More information

WHITE PAPER The Three Stages of Harnessing Inventory in the S&OP Journey. Executive Summary

WHITE PAPER The Three Stages of Harnessing Inventory in the S&OP Journey. Executive Summary WHITE PAPER The Three Stages of Harnessing Inventory in the S&OP Journey Sales and Operations Planning is a cross functional process to align and develop a conscientious plan between sales, marketing and

More information

VISHVESHWARAIAH TECHNOLOGICAL UNIVERSITY S.D.M COLLEGE OF ENGINEERING AND TECHNOLOGY. A seminar report on GENETIC ALGORITHMS.

VISHVESHWARAIAH TECHNOLOGICAL UNIVERSITY S.D.M COLLEGE OF ENGINEERING AND TECHNOLOGY. A seminar report on GENETIC ALGORITHMS. VISHVESHWARAIAH TECHNOLOGICAL UNIVERSITY S.D.M COLLEGE OF ENGINEERING AND TECHNOLOGY A seminar report on GENETIC ALGORITHMS Submitted by Pranesh S S 2SD06CS061 8 th semester DEPARTMENT OF COMPUTER SCIENCE

More information

Chapter 10. The Firm and Industry in the Entrepreneurless Economy

Chapter 10. The Firm and Industry in the Entrepreneurless Economy March 23, 2003 Chapter 10 The Firm and Industry in the Entrepreneurless Economy The model of industry equilibrium in the entrepreneurless economy that we used in Chapter Nine can be used as a basis for

More information

Biol Lecture Notes

Biol Lecture Notes Biol 303 1 Evolutionary Forces: Generation X Simulation To launch the GenX software: 1. Right-click My Computer. 2. Click Map Network Drive 3. Don t worry about what drive letter is assigned in the upper

More information

Analysis of NEAT and application in swarm intelligence

Analysis of NEAT and application in swarm intelligence Bachelor Informatica Informatica Universiteit van Amsterdam Analysis of NEAT and application in swarm intelligence Frank van Beem June 9, 2017 Supervisor(s): Rein van den Boomgaard 2 Abstract In this paper

More information

PROCESS ACCOMPANYING SIMULATION A GENERAL APPROACH FOR THE CONTINUOUS OPTIMIZATION OF MANUFACTURING SCHEDULES IN ELECTRONICS PRODUCTION

PROCESS ACCOMPANYING SIMULATION A GENERAL APPROACH FOR THE CONTINUOUS OPTIMIZATION OF MANUFACTURING SCHEDULES IN ELECTRONICS PRODUCTION Proceedings of the 2002 Winter Simulation Conference E. Yücesan, C.-H. Chen, J. L. Snowdon, and J. M. Charnes, eds. PROCESS ACCOMPANYING SIMULATION A GENERAL APPROACH FOR THE CONTINUOUS OPTIMIZATION OF

More information

Artificial Intelligence in Automotive Production

Artificial Intelligence in Automotive Production Chair Information Management in Mechanical Engineering Artificial Intelligence in Automotive Production 3. Fachkonferenz: Roboter in der Automobilindustrie Stuttgart, Germany, 29 th November 2017 Robotic

More information

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

Journal of Chemical and Pharmaceutical Research, 2014, 6(5): Research Article Available online www.jocpr.com Journal of Chemical and Pharmaceutical Research, 2014, 6(5): 693-697 Research Article ISSN : 0975-7384 CODEN(USA) : JCPRC5 Study on multi-resource constraints vehicle scheduling

More information

Intelligent Techniques Lesson 4 (Examples about Genetic Algorithm)

Intelligent Techniques Lesson 4 (Examples about Genetic Algorithm) Intelligent Techniques Lesson 4 (Examples about Genetic Algorithm) Numerical Example A simple example will help us to understand how a GA works. Let us find the maximum value of the function (15x - x 2

More information

Metaheuristics and Cognitive Models for Autonomous Robot Navigation

Metaheuristics and Cognitive Models for Autonomous Robot Navigation Metaheuristics and Cognitive Models for Autonomous Robot Navigation Raj Korpan Department of Computer Science The Graduate Center, CUNY Second Exam Presentation April 25, 2017 1 / 31 Autonomous robot navigation

More information

PREDICTING EMPLOYEE ATTRITION THROUGH DATA MINING

PREDICTING EMPLOYEE ATTRITION THROUGH DATA MINING PREDICTING EMPLOYEE ATTRITION THROUGH DATA MINING Abbas Heiat, College of Business, Montana State University, Billings, MT 59102, aheiat@msubillings.edu ABSTRACT The purpose of this study is to investigate

More information

An Evolutionary Algorithm Based On The Aphid Life Cycle

An Evolutionary Algorithm Based On The Aphid Life Cycle International Journal of Computer Information Systems and Industrial Management Applications. ISSN 2150-7988 Volume 8 (2016) pp. 155 162 c MIR Labs, www.mirlabs.net/ijcisim/index.html An Evolutionary Algorithm

More information

SIMULATION METHOD FOR DESIGN AND ANALYSIS OF LOGISTICAL PROCESSES

SIMULATION METHOD FOR DESIGN AND ANALYSIS OF LOGISTICAL PROCESSES Advanced Logistic Systems Vol. 10, No. 2 (2016) pp. 65 70. SIMULATION METHOD FOR DESIGN AND ANALYSIS OF LOGISTICAL PROCESSES GYÖRGY KOVÁCS 1 Abstract: There are lot of tools and sophisticated methods for

More information

Neural Networks and Applications in Bioinformatics. Yuzhen Ye School of Informatics and Computing, Indiana University

Neural Networks and Applications in Bioinformatics. Yuzhen Ye School of Informatics and Computing, Indiana University Neural Networks and Applications in Bioinformatics Yuzhen Ye School of Informatics and Computing, Indiana University Contents Biological problem: promoter modeling Basics of neural networks Perceptrons

More information

Anomaly Detection in Vessel Tracking Using Support Vector Machines (SVMs)

Anomaly Detection in Vessel Tracking Using Support Vector Machines (SVMs) 2013 International Conference on Advanced Computer Science Applications and Technologies Anomaly Detection in Vessel Tracking Using Support Vector Machines (SVMs) Dini Oktarina Dwi Handayani 1, Wahju Sediono

More information

Using Neural Network and Genetic Algorithm for Business Negotiation with Maximum Joint Gain in E-Commerce

Using Neural Network and Genetic Algorithm for Business Negotiation with Maximum Joint Gain in E-Commerce EurAsia-ICT 2002, Shiraz-Iran, 29-3 Oct. Using Neural Networ and Genetic Algorithm for Business Negotiation with Maximum Joint Gain in E-Commerce Mohammad Gholypur Pazand Samaneh Information Technology

More information

The Advanced Distribution Management System. The indispensable tool of the Smart Grid era

The Advanced Distribution Management System. The indispensable tool of the Smart Grid era The Advanced Distribution Management System The indispensable tool of the Smart Grid era Telvent utilities group August 2010 The Advanced Distribution Management System The indispensable tool of the Smart

More information

Foundations of Artificial Intelligence

Foundations of Artificial Intelligence Foundations of Artificial Intelligence 21. Combinatorial Optimization: Advanced Techniques Malte Helmert University of Basel April 9, 2018 Combinatorial Optimization: Overview Chapter overview: combinatorial

More information

Designing High Thermal Conductive Materials Using Artificial Evolution MICHAEL DAVIES, BASKAR GANAPATHYSUBRAMANIAN, GANESH BALASUBRAMANIAN

Designing High Thermal Conductive Materials Using Artificial Evolution MICHAEL DAVIES, BASKAR GANAPATHYSUBRAMANIAN, GANESH BALASUBRAMANIAN Designing High Thermal Conductive Materials Using Artificial Evolution MICHAEL DAVIES, BASKAR GANAPATHYSUBRAMANIAN, GANESH BALASUBRAMANIAN The Problem Graphene is one of the most thermally conductive materials

More information

The ABCs of. CA Workload Automation

The ABCs of. CA Workload Automation The ABCs of CA Workload Automation 1 The ABCs of CA Workload Automation Those of you who have been in the IT industry for a while will be familiar with the term job scheduling or workload management. For

More information

Genetic Algorithm: A Search of Complex Spaces

Genetic Algorithm: A Search of Complex Spaces Genetic Algorithm: A Search of Complex Spaces Namita Khurana, Anju Rathi, Akshatha.P.S Lecturer in Department of (CSE/IT) KIIT College of Engg., Maruti Kunj, Sohna Road, Gurgaon, India ABSTRACT Living

More information

A Genetic Algorithm on Inventory Routing Problem

A Genetic Algorithm on Inventory Routing Problem A Genetic Algorithm on Inventory Routing Problem Artvin Çoruh University e-mail: nevin.aydin@gmail.com Volume 3 No 3 (2014) ISSN 2158-8708 (online) DOI 10.5195/emaj.2014.31 http://emaj.pitt.edu Abstract

More information

Machine learning applications in genomics: practical issues & challenges. Yuzhen Ye School of Informatics and Computing, Indiana University

Machine learning applications in genomics: practical issues & challenges. Yuzhen Ye School of Informatics and Computing, Indiana University Machine learning applications in genomics: practical issues & challenges Yuzhen Ye School of Informatics and Computing, Indiana University Reference Machine learning applications in genetics and genomics

More information

Evolutionary Computation

Evolutionary Computation Evolutionary Computation Dean F. Hougen w/ contributions from Pedro Diaz-Gomez & Brent Eskridge Robotics, Evolution, Adaptation, and Learning Laboratory (REAL Lab) School of Computer Science University

More information

Is Machine Learning the future of the Business Intelligence?

Is Machine Learning the future of the Business Intelligence? Is Machine Learning the future of the Business Intelligence Fernando IAFRATE : Sr Manager of the BI domain Fernando.iafrate@disney.com Tel : 33 (0)1 64 74 59 81 Mobile : 33 (0)6 81 97 14 26 What is Business

More information

Understanding Extrusion

Understanding Extrusion Chris Rauwendaal Understanding Extrusion 2nd Edition Sample Chapter 2: Instrumentation and Control ISBNs 978-1-56990-453-4 1-56990-453-7 HANSER Hanser Publishers, Munich Hanser Publications, Cincinnati

More information

IT Reliability through Business Transaction Management

IT Reliability through Business Transaction Management A White Paper IT Reliability through Business Transaction Management Reliability is not just an issue for the IT staffer at the operational level. It s keeping the business decision makers up at night

More information

Rule Minimization in Predicting the Preterm Birth Classification using Competitive Co Evolution

Rule Minimization in Predicting the Preterm Birth Classification using Competitive Co Evolution Indian Journal of Science and Technology, Vol 9(10), DOI: 10.17485/ijst/2016/v9i10/88902, March 2016 ISSN (Print) : 0974-6846 ISSN (Online) : 0974-5645 Rule Minimization in Predicting the Preterm Birth

More information

The Effects of Oil on Marine Life in the Gulf of Mexico

The Effects of Oil on Marine Life in the Gulf of Mexico The Effects of Oil on Marine Life in the Gulf of Mexico New Mexico Supercomputing Challenge Final Report April 6, 2011 Team #13 Aspen Elementary Team Members: Jennifer Esquibel Evan Oro Claire Ticknor

More information

Applying Computational Intelligence in Software Testing

Applying Computational Intelligence in Software Testing www.stmjournals.com Applying Computational Intelligence in Software Testing Saumya Dixit*, Pradeep Tomar School of Information and Communication Technology, Gautam Buddha University, Greater Noida, India

More information

EXTINCTION AND SURVIVAL OF MUCK SWAMP FROGS

EXTINCTION AND SURVIVAL OF MUCK SWAMP FROGS EXTINCTION AND SURVIVAL OF MUCK SWAMP FROGS Somewhere near Xenia, Ohio lives the world's last population of Muck Swamp Frogs (nicknamed "Mucks"). Mucks come in two types, pictured below. Herpetologists

More information

AUTOMATIC TEST CASE GENERATION BASED ON GENETIC ALGORITHM

AUTOMATIC TEST CASE GENERATION BASED ON GENETIC ALGORITHM AUTOMATIC TEST CASE GEERATIO BASED O GEETIC ALGORITHM DA LIU, XUEJU WAG, JIAMI WAG School of Information Science and Technology,Shijiazhuang Tiedao University, Shijiazhuang050043, China E-mail: liudanld@126.com

More information

chief data officer s guide to artificial intelligence

chief data officer s guide to artificial intelligence chief data officer s guide to artificial intelligence An AI roadmap for CSPs Ovum TMT intelligence AI is driving CSP digital transformation Artificial intelligence (AI) is a key component supporting CSPs

More information

ericsson.com/ consumerlab The zero-touch customer experience Uncovering the future of consumer interactions with telecom service providers

ericsson.com/ consumerlab The zero-touch customer experience Uncovering the future of consumer interactions with telecom service providers ericsson.com/ consumerlab The zero-touch customer experience Uncovering the future of consumer interactions with telecom service providers An Ericsson Consumer & IndustryLab Insight Report May 2018 2 Ericsson

More information

WORKLOAD-STUDY OF ISA-DRIVERS A METHOD DESCRIPTION

WORKLOAD-STUDY OF ISA-DRIVERS A METHOD DESCRIPTION WORKLOAD-STUDY OF ISA-DRIVERS A METHOD DESCRIPTION Magnus Hjälmdahl, András Várhelyi Department of Technology and Society, Lund University BOX 118, 221 00 LUND, SWEDEN Phone: +46 46 222 91 29 (Magnus)

More information

EVOLUTION/HERDEDITY UNIT Unit 1 Part 8A Chapter 23 Activity Lab #11 A POPULATION GENETICS AND EVOLUTION

EVOLUTION/HERDEDITY UNIT Unit 1 Part 8A Chapter 23 Activity Lab #11 A POPULATION GENETICS AND EVOLUTION AP BIOLOGY EVOLUTION/HERDEDITY UNIT Unit Part 8A Chapter Activity Lab # A NAME DATE PERIOD POPULATION GENETICS AND EVOLUTION In 908 G. H. Hardy and W. Weinberg independently suggest a scheme whereby evolution

More information

Grade 6 PLV Standards and Objectives Alignment with NeSA Science Standards

Grade 6 PLV Standards and Objectives Alignment with NeSA Science Standards Grade 6 PLV Standards and Objectives Alignment with NeSA Science Standards SC K-12.1 Comprehensive Science Standard Inquiry, the Nature of Science, and Technology Students will combine scientific processes

More information

Evolutionary Algorithms

Evolutionary Algorithms Evolutionary Algorithms Evolutionary Algorithms What is Evolutionary Algorithms (EAs)? Evolutionary algorithms are iterative and stochastic search methods that mimic the natural biological evolution and/or

More information

Jack Weast. Principal Engineer, Chief Systems Engineer. Automated Driving Group, Intel

Jack Weast. Principal Engineer, Chief Systems Engineer. Automated Driving Group, Intel Jack Weast Principal Engineer, Chief Systems Engineer Automated Driving Group, Intel From the Intel Newsroom 2 Levels of Automated Driving Courtesy SAE International Ref: J3061 3 Simplified End-to-End

More information

CHANGE MANAGEMENT. A Presentation by Ian Creery - January 30, The environment we re in How does change work?... 2

CHANGE MANAGEMENT. A Presentation by Ian Creery - January 30, The environment we re in How does change work?... 2 CHANGE MANAGEMENT A Presentation by Ian Creery - January 30, 2012 Table of Contents The environment we re in... 2 How does change work?... 2 Roles in a change process... 3 Change leadership... 3 Change

More information

Validating and Testing Wearable Sensors to Assess Physical Activity and Sedentary Behavior in the Center for Personalized Health Monitoring

Validating and Testing Wearable Sensors to Assess Physical Activity and Sedentary Behavior in the Center for Personalized Health Monitoring University of Massachusetts Medical School escholarship@umms UMass Center for Clinical and Translational Science Research Retreat 2014 UMass Center for Clinical and Translational Science Research Retreat

More information

Briefing to Aerodays 2011 Parallel session 1G Technologies in the European Research Area. Advanced Structures

Briefing to Aerodays 2011 Parallel session 1G Technologies in the European Research Area. Advanced Structures Structural Health Monitoring Systems in Airbus Military Briefing to Aerodays 2011 Parallel session 1G Technologies in the European Research Area. Advanced Structures Javier Gómez-Escalonilla Fatigue &

More information

A PRIMER TO MACHINE LEARNING FOR FRAUD MANAGEMENT

A PRIMER TO MACHINE LEARNING FOR FRAUD MANAGEMENT A PRIMER TO MACHINE LEARNING FOR FRAUD MANAGEMENT TABLE OF CONTENTS Growing Need for Real-Time Fraud Identification... 3 Machine Learning Today... 4 Big Data Makes Algorithms More Accurate... 5 Machine

More information

Application and comparison of several artificial neural networks for forecasting the Hellenic daily electricity demand load

Application and comparison of several artificial neural networks for forecasting the Hellenic daily electricity demand load Application and comparison of several artificial neural networks for forecasting the Hellenic daily electricity demand load L. EKONOMOU 1 D.S. OIKONOMOU 2 1 Hellenic American University, 12 Kaplanon Street,

More information

FacePrints, Maze Solver and Genetic algorithms

FacePrints, Maze Solver and Genetic algorithms Machine Learning CS579 FacePrints, Maze Solver and Genetic algorithms by Jacob Blumberg Presentation Outline Brief reminder genetic algorithms FacePrints a system that evolves faces Improvements and future

More information

Instructor's Manual. to accompany PROJECT MANAGEMENT. A SYSTEMS APPROACH to PLANNING, SCHEDULING, and CONTROLLING ELEVENTH EDITION

Instructor's Manual. to accompany PROJECT MANAGEMENT. A SYSTEMS APPROACH to PLANNING, SCHEDULING, and CONTROLLING ELEVENTH EDITION Instructor's Manual to accompany PROJECT MANAGEMENT A SYSTEMS APPROACH to PLANNING, SCHEDULING, and CONTROLLING ELEVENTH EDITION HAROLD KERZNER, PH.D. John Wiley & Sons, Inc. Table of Contents PART ONE:

More information

PRODUCTION PLANNING SYSTEM CHAPTER 2

PRODUCTION PLANNING SYSTEM CHAPTER 2 9 PRODUCTION PLANNING SYSTEM CHAPTER 2 ANSWERS TO PROBLEMS 2.1 Ending inventory = opening inventory + production demand = 400 + 700 900 = 200 units 2.2 Total working days = 19 + 20 + 21 = 60 Average daily

More information

Bio 6 Natural Selection Lab

Bio 6 Natural Selection Lab Bio 6 Natural Selection Lab Overview In this laboratory you will demonstrate the process of evolution by natural selection by carrying out a predator/prey simulation. Through this exercise you will observe

More information

The Theory of Evolution

The Theory of Evolution The Theory of Evolution Mechanisms of Evolution Notes Pt. 4 Population Genetics & Evolution IMPORTANT TO REMEMBER: Populations, not individuals, evolve. Population = a group of individuals of the same

More information

ProfessionalPLUS Station Software Suite

ProfessionalPLUS Station Software Suite DeltaV Distributed Control System Product Data Sheet September 2017 ProfessionalPLUS Station Software Suite Global database, architected for flexibility and scalability Powerful, graphical engineering

More information

INTRODUCTION TO INFORMATION SYSTEMS & DECISION MAKING

INTRODUCTION TO INFORMATION SYSTEMS & DECISION MAKING INTRODUCTION TO INFORMATION SYSTEMS & DECISION MAKING (August 26, 2015) BUS3500 - Abdou Illia, Fall 2015 1 LEARNING GOALS Explain basic information systems concepts Explain difference b/w data an information

More information

Copywriting 101 Workbook

Copywriting 101 Workbook Copywriting 101 Workbook Complete this workbook for your Module 7 assignment & earn your Copywriting badge 1 Assignment Instructions & Requirements In this assignment, you will use your own business or

More information

Derivative-based Optimization (chapter 6)

Derivative-based Optimization (chapter 6) Soft Computing: Derivative-base Optimization Derivative-based Optimization (chapter 6) Bill Cheetham cheetham@cs.rpi.edu Kai Goebel goebel@cs.rpi.edu used for neural network learning used for multidimensional

More information

What is a mutation? What causes mutations?

What is a mutation? What causes mutations? What is a mutation? What causes mutations? Mutations A mutation is a change in the structure or amount of an organism s genetic material. When a change in genotype produces a change in phenotype, the individual

More information

Biological immune systems

Biological immune systems Immune Systems 1 Introduction 2 Biological immune systems Living organism must protect themselves from the attempt of other organisms to exploit their resources Some would-be exploiter (pathogen) is much

More information

DNA Circuits for Analog Computing

DNA Circuits for Analog Computing DNA Circuits for Analog Computing Tianqi Song Department of Computer Science Duke University 1 Outline Motivation What is DNA computing? Why are we interested in DNA computing? What has been done? Why

More information

FACILITATING AGRICULTURE AUTOMATION USING STANDARDS

FACILITATING AGRICULTURE AUTOMATION USING STANDARDS FACILITATING AGRICULTURE AUTOMATION USING STANDARDS Robert K. Benneweis P. Eng Outline Available standards Developing standards Implemented automation Standard based automation implementation Potential

More information

CEng 713 Evolutionary Computation, Lecture Notes

CEng 713 Evolutionary Computation, Lecture Notes CEng 713 Evolutionary Computation, Lecture Notes Introduction to Evolutionary Computation Evolutionary Computation Elements of Evolution: Reproduction Random variation Competition Selection of contending

More information

Ecology Habitable Planet Lab

Ecology Habitable Planet Lab Ecology Habitable Planet Lab Purpose: To examine the interrelationships between organisms in the environment. Directions: 1. Read ALL Instructions and the introduction section BEFORE doing the lab. 2.

More information

Building Successful Teams Marc Elpel, December 23, 2006

Building Successful Teams Marc Elpel, December 23, 2006 Building Successful Teams Marc Elpel, December 23, 2006 Team building is a broad field and as you have probably already noticed there are many resources available around the web for team exercises, individual

More information

BIOINFORMATICS AND SYSTEM BIOLOGY (INTERNATIONAL PROGRAM)

BIOINFORMATICS AND SYSTEM BIOLOGY (INTERNATIONAL PROGRAM) BIOINFORMATICS AND SYSTEM BIOLOGY (INTERNATIONAL PROGRAM) PROGRAM TITLE DEGREE TITLE Master of Science Program in Bioinformatics and System Biology (International Program) Master of Science (Bioinformatics

More information

2 LEADERSHIP CHALLENGES

2 LEADERSHIP CHALLENGES 2 LEADERSHIP CHALLENGES 16 The Dynamics of Change Leading people in change is a multi-dimensional process that involves opportunities, conflicts and challenges. It is usually not a question of either or,

More information

An Approach to Analyze and Quantify the Functional Requirements in Software System Engineering

An Approach to Analyze and Quantify the Functional Requirements in Software System Engineering An Approach to Analyze and Quantify the Functional Requirements in Software System Engineering M.Karthika, Assistant Professor MCA Department NMSS Vellaichamy Nadar College Tami Nadu, India X.Joshphin

More information

Genetic Algorithm with Upgrading Operator

Genetic Algorithm with Upgrading Operator Genetic Algorithm with Upgrading Operator NIDAPAN SUREERATTANAN Computer Science and Information Management, School of Advanced Technologies, Asian Institute of Technology, P.O. Box 4, Klong Luang, Pathumthani

More information

Getting Down to the Business that Matters ELECTRONIC FIELD TICKETING

Getting Down to the Business that Matters ELECTRONIC FIELD TICKETING Getting Down to the Business that Matters ELECTRONIC FIELD TICKETING Table of Contents INTRODUCTION... 3 SHRINKING THE PAPER MOUNTAIN... 5 THE PERFECT MATCH... 7 BECOMING MORE STRATEGIC... 9 ACCOUNTS RECEIVABLE

More information

CONCEPTUAL DESIGN OF AN AUTOMATED REAL-TIME DATA COLLECTION SYSTEM FOR LABOR-INTENSIVE CONSTRUCTION ACTIVITIES

CONCEPTUAL DESIGN OF AN AUTOMATED REAL-TIME DATA COLLECTION SYSTEM FOR LABOR-INTENSIVE CONSTRUCTION ACTIVITIES CONCEPTUAL DESIGN OF AN AUTOMATED REAL-TIME DATA COLLECTION SYSTEM FOR LABOR-INTENSIVE CONSTRUCTION ACTIVITIES H. Randolph Thomas The Pennsylvania State University Research Building B University Park,

More information

Available Active Power Estimation for the Provision of Control Reserve by Wind Turbines Summary Keywords: 1. Introduction 2.

Available Active Power Estimation for the Provision of Control Reserve by Wind Turbines Summary Keywords: 1. Introduction 2. Available Active Power Estimation for the Provision of Control Reserve by Wind Turbines Dominik Schneider, Kristie Kaminski Küster, Malte Siefert, Markus Speckmann Fraunhofer IWES, Kassel, Germany Koenigstor

More information

WHITE PAPER. Getting to Why in Omnichannel Title Marketing Attribution

WHITE PAPER. Getting to Why in Omnichannel Title Marketing Attribution WHITE PAPER Getting to Why in Omnichannel Title Marketing Attribution ii Contents The state of affairs... 1 The limitations of summarized, siloed channel data...2 Key takeaways... 3 Learn more... 3 1 The

More information

Machine Learning. Genetic Algorithms

Machine Learning. Genetic Algorithms Machine Learning Genetic Algorithms Genetic Algorithms Developed: USA in the 1970 s Early names: J. Holland, K. DeJong, D. Goldberg Typically applied to: discrete parameter optimization Attributed features:

More information

Machine Learning. Genetic Algorithms

Machine Learning. Genetic Algorithms Machine Learning Genetic Algorithms Genetic Algorithms Developed: USA in the 1970 s Early names: J. Holland, K. DeJong, D. Goldberg Typically applied to: discrete parameter optimization Attributed features:

More information