21st Mediterranean Conference on Control and Automation

Slides:



Advertisements
Similar presentations
INTRODUCTION TO MODELING
Advertisements

Soft Systems Methodology
Lecture 11: Recursive Parameter Estimation
Building Knowledge-Driven DSS and Mining Data
1 Enviromatics Decision support systems Decision support systems Вонр. проф. д-р Александар Маркоски Технички факултет – Битола 2008 год.
1 User Interface Design CIS 375 Bruce R. Maxim UM-Dearborn.
1 Prediction of Software Reliability Using Neural Network and Fuzzy Logic Professor David Rine Seminar Notes.
Optimization of thermal processes2007/2008 Optimization of thermal processes Maciej Marek Czestochowa University of Technology Institute of Thermal Machinery.
What is Business Analysis Planning & Monitoring?
The 2nd International Conference of e-Learning and Distance Education, 21 to 23 February 2011, Riyadh, Saudi Arabia Prof. Dr. Torky Sultan Faculty of Computers.
Genetic Algorithm.
Business Analysis and Essential Competencies
Department of Electrical Engineering, Southern Taiwan University Robotic Interaction Learning Lab 1 The optimization of the application of fuzzy ant colony.
Introduction Complex and large SW. SW crises Expensive HW. Custom SW. Batch execution Structured programming Product SW.
INVESTIGATORS R. King S. Fang J. Joines H. Nuttle STUDENTS N. Arefi Y. Dai S. Lertworasirikul Industrial Engineering Textiles Engineering, Chem. and Science.
INVENTORY CONTROL AS IDENTIFICATION PROBLEM BASED ON FUZZY LOGIC ALEXANDER ROTSHTEIN Dept. of Industrial Engineering and Management, Jerusalem College.
Mining Weather Data for Decision Support Roy George Army High Performance Computing Research Center Clark Atlanta University Atlanta, GA
Generic Tasks by Ihab M. Amer Graduate Student Computer Science Dept. AUC, Cairo, Egypt.
MODELING AND ANALYSIS Pertemuan-4
1 Motion Fuzzy Controller Structure(1/7) In this part, we start design the fuzzy logic controller aimed at producing the velocities of the robot right.
SSQSA present and future Gordana Rakić, Zoran Budimac Department of Mathematics and Informatics Faculty of Sciences University of Novi Sad
Does GridGIS require more intelligence than GIS? Claire Jarvis Department of Geography GEOGRAPHY.
Scenario: Coconut Yield Management
FCM WIZARD IN ACTION SCENARIO: AUTISM PREDICTION IN CHILDREN Main developers: Gonzalo NÁPOLES and Isel GRAU Supervisors: Elpiniki PAPAGEORGIOU and Koen.
ANALYSIS PHASE OF BUSINESS SYSTEM DEVELOPMENT METHODOLOGY.
FCM WIZARD IN ACTION SCENARIO: RISK MANAGEMENT OF IT PROJECTS Main developers: Gonzalo NÁPOLES and Isel GRAU Supervisors: Elpiniki PAPAGEORGIOU and Koen.
Application of the GA-PSO with the Fuzzy controller to the robot soccer Department of Electrical Engineering, Southern Taiwan University, Tainan, R.O.C.
Robodog Frontal Facial Recognition AUTHORS GROUP 5: Jing Hu EE ’05 Jessica Pannequin EE ‘05 Chanatip Kitwiwattanachai EE’ 05 DEMO TIMES: Thursday, April.
Department of Electrical Engineering, Southern Taiwan University 1 Robotic Interaction Learning Lab The ant colony algorithm In short, domain is defined.
Business Analytics Several odds and ends Copyright © 2016 Curt Hill.
A Presentation on Adaptive Neuro-Fuzzy Inference System using Particle Swarm Optimization and it’s Application By Sumanta Kundu (En.R.No.
Peter P. Groumpos Professor, Electrical and Computer Engineering Department University of Patras Eleni S. Vergini PhD Canditate, Electrical and Computer.
Fuzzy Systems Simulation Session 5
New Advanced Technology Methods on Energy Efficiency of Buildings
15th International Conference on Bioinformatics & Bioengineering (BIBE) Nov-02-04, 2015, Belgrade, Serbia A Two-Level Competitive Fuzzy Cognitive Map for.
Algorithms and Problem Solving
Classification of models
Chapter 7. Classification and Prediction
Management & Planning Tools
Artificial Neural Networks
CHAPTER 1 Introduction BIC 3337 EXPERT SYSTEM.
Introduction to Quantitative Analysis
Oleh: Beni Setiawan, Wahyu Budi Sabtiawan
Object-Oriented Software Engineering Using UML, Patterns, and Java,
ΜΠΣ ΠΡΑΣΙΝΗ ΕΝΕΡΓΕΙΑ ΤΜΗΜΑ ΗΜ&ΤΥ
A New Meniscus Injury Diagnostic Model Using Fuzzy Cognitive Maps
DSS & Warehousing Systems
Real Neurons Cell structures Cell body Dendrites Axon
Iterative design and prototyping
Artificial Intelligence
Neural Networks A neural network is a network of simulated neurons that can be used to recognize instances of patterns. NNs learn by searching through.
with Daniel L. Silver, Ph.D. Christian Frey, BBA April 11-12, 2017
Case-Based Reasoning.
Module C: Presentation The Engineering / Design Process
Professor S K Dubey,VSM Amity School of Business
Unit# 9: Computer Program Development
Foundations of Technology Mr. Brooks
of the Artificial Neural Networks.
Introduction To software engineering
Module C: Presentation The Engineering / Design Process
Algorithms and Problem Solving
Market-based Dynamic Task Allocation in Mobile Surveillance Systems
Theory of Computability
Decision Support Systems
Facilities Planning and Design Course code:
Theory of Computability
Chapter 2: Development process and organizations
ECE 576 POWER SYSTEM DYNAMICS AND STABILITY
Introduction to Decision Sciences
Multidisciplinary Optimization
Presentation transcript:

21st Mediterranean Conference on Control and Automation Non Linear Hebbian Learning Techniques and Fuzzy Cognitive Maps in Modeling the Parkinson’s Disease PhD Student Antigoni P. Anninou Professor Peter P. Groumpos Laboratory for Automation and Robotics Department of Electrical and Computer Engineering 27/6/2013

Outline Problem Formulation Fuzzy Cognitive Maps Non-Linear Hebbian Learning Decision Support System in Parkinson’s Disease Simulation Results Conclusions 27/6/2013

Aim Construction and training of a Fuzzy Cognitive Map (FCM) in modeling a Decision Support System, to help in diagnosis concerning the disease of Parkinson 27/6/2013

Fuzzy Cognitive Maps (FCM) (1/5) Modeling method for describing particular domains Fyzzy-graph structures for representing causal reasoning 27/6/2013

Fuzzy Cognitive Maps (2/5) Nodes: Represent the system’s concepts or variables Arrows: Interconnection between nodes. Show the cause-effect relationship between them. W: Interrelationship between two nodes: W>0 positive causality W<0 negative causality W=0 no relationship 27/6/2013

Fuzzy Cognitive Maps (3/5) The value of each concept at every simulation step is calculated, computing the influence of the interconnected concepts to the specific concept, by applying the following calculation rule: 27/6/2013

Fuzzy Cognitive Maps (4/5) Ai(k+1) : the value of the concept Ci at the iteration step k+1 Ai(k): the value of the concept Cj at the iteration step k Wij : the weight of interconnection from concept Ci to concept Cj k1: the influence of the interconnected concepts in the configuration of the new value of the concept Ai k2: the proportion of the contribution of the previous value of the concept in the computation of the new value f : the sigmoid function 27/6/2013

Fuzzy Cognitive Maps (5/5) Weaknesses Direct dependence of the initial knowledge of experts Convergence to undesirable situations Solution Training the FCM 27/6/2013

Non-Linear Hebbian Learning (NHL) (1/2) Increase the effectiveness of FCMs and their implementation in real problems Update weights associated only with edges that are initially suggested by experts All concepts in FCM model are triggered at each iteration step and change their values Output concepts → Desired Output Concepts (DOCs) 27/6/2013

Non-Linear Hebbian Learning (2/2) Algorithm that modifies the weights: h:learning parameter g: weight reduction parameter Nodes are triggered simultaneously and interact in the same iteration step, and their values updated through this process of interaction 27/6/2013

Criteria 1st : Minimization of the objective function F DOCi: the value of the output concept i as indicated in each iteration Ti: the mean target value of the concept DOCi m: the number of the desired output nodes 2nd : Minimization of the variation of two subsequent values of DOCs F2 = | DOCi (k+1)- DOCi (k) | 27/6/2013

NHL Algorithm Read input state A0 and initial weight matrix W0 Repeat for each iteration step k - Calculate Ai according to (1) - Update Wij(k) according to (3) - Calculate the two criterion functions Repeat until the termination conditions are met Return the final weights Wfinal and concept values in convergence region 27/6/2013

Schematic Representation of NHL algorithm 27/6/2013

NHL Parameters The parameters arise from trials and experiments 0.9<g<1 27/6/2013

Decision Support System Definition: Interactive computer – based support system for making decisions in any complex system, when individuals or a team of people are trying to solve unstructured problems on an uncertain environment Aim: Reach acceptable and realistic decisions Methodology: Exploitation of experts’ experience 27/6/2013

Why to model Decision Support Systems with FCMs High amount of data and information from interdisciplinary sources Information may be vague or missing Procedure is complex Many factors may be complementary, contradictory or competitive 27/6/2013

Decision Making Support System in Parkinson’s Disease (1/2) Concepts: C1: Body Bradykinesia C2: Rigidity C3: Postural Instability C4: Movement of upper limbs C5: Gait C6: Tremor C7: Stage of Parkinson’s disease –five stages (output) 27/6/2013

Decision Making Support System 27/6/2013

The Fuzzy Cognitive Map Model 27/6/2013

Simulation Results 1st Scenario: Suppose that the physician decided as initial values of the inputs the following: C1 Strong C2 C3 Medium C4 C5 C6 Very Strong After COA defuzzyfication method the initial values for the concepts would be: A(0)=[0.75 0.75 0.5 0.5 0.75 1 1] 27/6/2013

Subsequent values of concepts till convergence 27/6/2013

Output Without the learning algorithm NHL Algorithm Patient Stage 2 27/6/2013

2nd Scenario: C1 Weak C2 C3 Medium C4 C5 Strong C6 Zero After COA defuzzyfication method the initial values for the concepts would be: A(0)=[0.75 0.75 0.5 0.5 0.75 1 1] 27/6/2013

Subsequent values of concepts till convergence 27/6/2013

Output Without the learning algorithm NHL Algorithm Patient Stage 2 27/6/2013

Results Weight matrices influence the result Easy to use the proposed software tool Without the learning algorithm: Few recursive steps (until 9 steps) Fast diagnosis Convergence to undesired equilibrium points Demands training NHL Algorithm: Much more recursive steps Difficulty and many trials in order to find the right parameters h and g Equilibrium points closer to the reality 27/6/2013

Conclusions (1/2) Modeling with this tool closely represents the way experts perceive it NHL algorithm offers more reasonable results according to physicians NHL algorithm needs more iteration steps in order to reach an equilibrium point By using FCM without a learning algorithm to train it, we have a fast model that after a few iteration steps reaches an equilibrium point The suggested model is easily altered to incorporate other diseases 27/6/2013

Conclusions (2/2) In most cases, FCMs are constructed manually, and, thus, they cannot be applied when dealing with large number of variables. In such cases, their development could be significantly affected by the limited knowledge and skills of the expert. Thus, it is essential to use learning algorithms to accomplish this task Despite the early obtained encouraging results, we still need the opinion of the physicians as to how useful can this FCM modeling approach be to Parkinson’s disease. Future collaboration and consultation with physicians can help this effort 27/6/2013

Thank you for your attention PhD Student Antigoni P. Anninou Email: anninou@ece.upatras.gr Professor Peter P. Groumpos Email: groumpos@ece.upatras.gr 27/6/2013