Engineering Agent Systems for Decision Support

Slides:



Advertisements
Similar presentations
Modelling with expert systems. Expert systems Modelling with expert systems Coaching modelling with expert systems Advantages and limitations of modelling.
Advertisements

Date: 1 October2013 Meeting: Concertation meeting VRA Speaker and organisation: Maarten Oonk, TNO [ Roadmap Automation in Road Transport.
1 Christophe S. Jelger, Michael Kleis, Burak Simsek, Rolf Stadler, Ralf König, Danny Raz Theories/formal methods in support of autonomic management Dagstuhl.
Some questions o What are the appropriate control philosophies for Complex Manufacturing systems? Why????Holonic Manufacturing system o Is Object -Oriented.
4-1 Management Information Systems for the Information Age Copyright 2002 The McGraw-Hill Companies, Inc. All rights reserved Chapter 4 Decision Support.
Chapter 4 DECISION SUPPORT AND ARTIFICIAL INTELLIGENCE
University of Minho School of Engineering Centre Algoritmi Uma Escola a Reinventar o Futuro – Semana da Escola de Engenharia - 24 a 27 de Outubro de 2011.
The Decision-Making Process IT Brainpower
Agent Mediated Grid Services in e-Learning Chun Yan, Miao School of Computer Engineering Nanyang Technological University (NTU) Singapore April,
A Multi-Agent System for Visualization Simulated User Behaviour B. de Vries, J. Dijkstra.
__________________ Engineering Education Systems for Environmental Project Management - Example of the Amise Simulation Program François Baillon School.
1 Decision Support Systems Real World Applications.
1 Chapter 4 Decision Support and Artificial Intelligence Brainpower for Your Business.
Building Knowledge-Driven DSS and Mining Data
Agents to Simulate Social Human Behaviour in a Work Team Agents to Simulate Social Human Behaviour in a Work Team Barcelona, February Arantza Aldea.
Chapter 4 Brainpower for Your Business Chapter 4 DECISION SUPPORT AND ARTIFICIAL INTELLIGENCE Brainpower for Your Business.
Towards A Multi-Agent System for Network Decision Analysis Jan Dijkstra.
McGraw-Hill/Irwin ©2005 The McGraw-Hill Companies, All rights reserved ©2005 The McGraw-Hill Companies, All rights reserved McGraw-Hill/Irwin.
Measure 26 Strategic Traffic Management Katerina Oktabcova Usti nad Labem Municipality.
Capstone Design Project (CDP) Civil Engineering Department First Semester 1431/1432 H 10/14/20091 King Saud University, Civil Engineering Department.
Semantic Web Technologies Lecture # 2 Faculty of Computer Science, IBA.
Multi-Agent Model to Multi-Process Transformation A Housing Market Case Study Gerhard Zimmermann Informatik University of Kaiserslautern.
Enabling Organization-Decision Making
11 C H A P T E R Artificial Intelligence and Expert Systems.
EIDA Project ( Proposal ) Research and Technical Background Emergency Intelligent Decision Assistant: Emergency Intelligent Decision Assistant: Toolkit.
1 MultiCom, a platform for the design and the evaluation of interactive systems. MultiCom, a platform for the design and the evaluation of interactive.
R. Z. Wenkstern, T. Steel, G. Leask MAVs Lab, University of Texas at Dallas 1.
Introduction Complex and large SW. SW crises Expensive HW. Custom SW. Batch execution Structured programming Product SW.
Prediction of Traffic Density for Congestion Analysis under Indian Traffic Conditions Proceedings of the 12th International IEEE Conference on Intelligent.
The roots of innovation Future and Emerging Technologies (FET) Future and Emerging Technologies (FET) The roots of innovation Proactive initiative on:
Artificial Intelligence and Expert Systems. ARTIFICIAL INTELLIGENCE (AI) is the science of R L Being able to Ability to solve a problem.
Bi-directional incremental evolution Dr Tatiana Kalganova Electronic and Computer Engineering Dept. Bio-Inspired Intelligent Systems Group Brunel University.
Multi-agent Systems in Medicine Štěpán Urban. Content  Introduction to Multi-agent Systems (MAS) What is an Agent? Architecture of Agent MAS Platforms.
Decision-Support-System for the Rehabilitation of Buildings: The MEMSCON Project RISA Sicherheitsanalysen GmbH Berlin 1st MEMSCON Event - 07 October 2010,
Riga Technical University Department of System Theory and Design Usage of Multi-Agent Paradigm in Multi-Robot Systems Integration Assistant professor Egons.
Generic Tasks by Ihab M. Amer Graduate Student Computer Science Dept. AUC, Cairo, Egypt.
Chapter 4 Decision Support System & Artificial Intelligence.
1 Analysing system-user cooperation in KADS H. P. de Greef and J. A. Breuker, Department of Social Science Informatics, University of Amsterdam Knowledge.
Distributed Models for Decision Support Jose Cuena & Sascha Ossowski Pesented by: Gal Moshitch & Rica Gonen.
Model Integrated Computing and Autonomous Negotiating Teams for Autonomic Logistics G.Karsai (ISIS) J. Doyle (MIT) G. Bloor (Boeing)
Unclassified//For Official Use Only 1 RAPID: Representation and Analysis of Probabilistic Intelligence Data Carnegie Mellon University PI : Prof. Jaime.
ΑΝΝΕΧ 10 by EK. Rail Operators‘ Group (1) 1.Background F-Man Cargo operators: FS, CP, SZ. Their responsibilities: - to define their needs for a F-Man.
Done by Fazlun Satya Saradhi. INTRODUCTION The main concept is to use different types of agent models which would help create a better dynamic and adaptive.
Urban Mobility Management and Emissions Measurement System Boile Maria 1,2 Afroditi Anagnostopoulou 1 Evangelia Papargyri 1 1 Centre for Research and Technology.
EasyWay - conclusion.
DATEX Activity 6 Enhanced Usability
Foundations of Technology The Engineering Design Process
Algorithms and Problem Solving
Chapter 11: Artificial Intelligence
7 Big Ideas of Computing:
DSS: Decision Support Systems and AI: Artificial Intelligence
Object oriented system development life cycle
Sana Tariq Sr. Architect Service Orchestration March 26th, 2018
Introduction to the EEA and the EIONET
© James D. Skrentny from notes by C. Dyer, et. al.
Chapter 2 The Process of Design.
Transit Signal Priority: Evolution
Data Warehousing and Data Mining
Foundations of Technology The Engineering Design Process
Market-based Dynamic Task Allocation in Mobile Surveillance Systems
Foundations of Technology The Engineering Design Process
Decision Support Systems
Advanced Design Applications The Engineering Design Process
Meeting of the Directors of Social Statistics
Test-Driven Ontology Development in Protégé
Generic Tasks In the 80’s, KB engineering used approaches like this:
DSS Concepts, Methodologies and Technologies
Kostas Kolomvatsos, Christos Anagnostopoulos
WHO WILL WIN THE RACE TO AUTONOMY ? RONI DULBERG, CEO
Architecture Issue in the New Disciple System
Presentation transcript:

Engineering Agent Systems for Decision Support Alberto Fernández School of Experimental Sciences and Technology University Rey Juan Carlos Madrid - Spain

Introduction Decision Support Systems Relevant in complex domains Intelligent DEcision-making Assistant (IDEA) Reactive: What is happening? Why is it happening? What can be done? What may happen if? Proactively: warnings Application of agent technology to design IDEAs

Analysis UER (User-Environment-Responsibility) technique User-centred Analysis use cases Environment-Centred Analysis reaction cases Responsibility-Centred Analysis goal cases

Task Design Tasks Questions A priori distribution Problem identification, Diagnosis, Action planning, Prediction Questions What is happening?: problem identification + diagnosis What to do?: action planning + prediction What may happen if?: prediction + p. identif.+ diagnosis What to do if?: predict. + identif. + diagnosis + planning A priori distribution physical, organisational, availability of knowledge, ... => multiagent system Interdependencies => co-ordination task

Method Design Tasks => Problem-Solving Methods Problem Identification classification method with two options: a) reference situation + difference classification b) direct classification Diagnosis: several methods a) classification method with additional information b) cover & differentiate method

Method Design Action Planning Prediction Co-ordination classification reasoning on predefined plans collection of plans to perform subtasks plan refinement strategy Prediction a) specific simulation methods b) a simplified model: envisionment graph simple systems, level of precision is not very high Co-ordination 1) dependency detection 2) option generation 3) management decision

An example: Road Traffic Management The domain: urban motorways Traffic Control Centre (TCC) is to assure a smooth flow of vehicles The task: assist TCC engineers in their decision-making respecting coherent signal plans Infrastructure (Barcelona): 52 VMS 3 groups of traffic lights 7 ramp access controls >300 sensors (loop detectors)

Traffic Management: Analysis

Traffic Management: Design Problem Identification and Diagnosis raw data pre-processing + fuzzy abstraction knowledge base of frames (problem scenarios)

Example scenario

Traffic Management: Design Problem Identification and Diagnosis raw data pre-processing + fuzzy abstraction knowledge base of frames (problem scenarios) Action Planning and Prediction calculation of contribution of each path to the problem coherent alternative signal plans are generated knowledge base of frames (traffic distribution scenarios)

Example scenario

Traffic Management: Design Co-ordination Centralised (TRYS) co-ordinator agent knowledge base of rules for managing dependencies Decentralised (TRYSA2) 11 autonomous traffic agents for managing problem areas knowledge base distributed among agents

Conclusions Agent-based approach can be applied to the construction of advanced DSS Agent-oriented knowledge and software engineering techniques can be applied Illustrated in the road traffic domain Improving integration of the different phases Currently, evaluation in traffic control (Basque Country) and bus fleet management (Southern Spain)

Engineering Agent Systems for Decision Support Alberto Fernández School of Experimental Sciences and Technology University Rey Juan Carlos Madrid - Spain