chapter13 - new trends (1)
TRANSCRIPT
-
7/26/2019 Chapter13 - New Trends (1)
1/69
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
New trends and future directions of ICT
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons.
28 May 2014
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 1
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
2/69
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Session Overview
1 New trends and future directions of ICT
Intelligent and Emotional ComputingArtificial IntelligenceKansei Systems
Example in Kansei Engineering
Man-Machine Coexistence
2 Agent-Based SystemsNew Challenges for Computer SystemsCharacteristics of AgentsMulti-Agent SystemsApplications of Agents
3 Genetic AlgorithmBiological ExplorationAlgorithm and Examples in GA
4 Ubiquitous Computing
Application and TechnologySubha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 2
http://find/http://goback/ -
7/26/2019 Chapter13 - New Trends (1)
3/69
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Intelligent and Emotional ComputingEmotional Computing
Emotional Computing, What and Why?
People talking back to a computer/smart-phone is commonenough usually in a moment of frustration.
Getting the computer to respond in kind is a far different taskThe challenge is not of inventing new software or hardware,but to have ethics involved.If computers are to have emotional components, what rolewould they play in everyday life?
Do human beings really want an emotional relationship with amechanical mind?
The field is calledAffective Technology
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 3
http://find/http://goback/ -
7/26/2019 Chapter13 - New Trends (1)
4/69
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Affective TechnologyFace Recognition
Today, machine prototypes exist that measure humanemotional expression through physiological signals such asfacial expressions and voice changes and allow a human-likeresponse.
Face Recognition and Applications
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 4
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
5/69
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Affective TechnologyVoice Recognition
Today, machine prototypes exist that measure humanemotional expression through physiological signals such asfacial expressions and voice changes and allow a human-likeresponse.
Voice Recognition and Applications
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 5
T d d F Di i ICT A B d S G i Al i h Ubi i C i
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
6/69
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Intelligent and Emotional ComputingIntelligent Computing and Artificial Intelligence
Intelligence Computing
What is intelligence? Hard to define unless you list someimportant characteristics, such asReasoning,Learning, andAdaptivity
Machine intelligence is: computer which follows problemsolving processes something like that in humansIntelligent systems display machine-level intelligence,reasoning, often learning, and self-adapting
Artificial Intelligence
Artificial Intelligence (AI) is usually defined as the science ofmaking computers do things that require intelligence whendone by humans.Some important AI Techniques are: Neural Network, GeneticAlgorithm, and Expert Systems
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 6
T d d F t Di i ICT A t B d S t G ti Al ith Ubi it C ti
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
7/69
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Artificial IntelligenceNeural Network
Definition (Neural Network)
Neural Network are computational models inspired by an animalscentral nervous systems (in particular the brain) which is capable
of machine learning as well as pattern recognition.
Artificial neural networks are generally presented as systems of interconnected neurons which cancompute values from inputs.
Applications are in Finger Print Recognition, Face Recognition, Patten Identification,etc.
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 7
Trends and Future Dir in ICT Agent Based Systems Genetic Algorithm Ubiquitous Computing
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
8/69
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Artificial IntelligenceGenetic Algorithm
Definition (Genetic Algorithm)
Genetic Algorithms (GAs) are adaptive heuristic search algorithmpremised on the evolutionary ideas of natural selection and genetic.
The basic concept of GAs is designed to simulate processes in natural system necessary for evolution,specifically those that follow the principles first laid down by Charles Darwin of survival of the fittest.
As such they represent an intelligent exploitation of a random search within a defined search space to solvea problem.
Applications are circuit/car design (http://rednuht.org/genetic_cars_2/ ), traffic controlling, pathfinding, etc.
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 8
Trends and Future Dir in ICT Agent Based Systems Genetic Algorithm Ubiquitous Computing
http://rednuht.org/genetic_cars_2/http://rednuht.org/genetic_cars_2/http://rednuht.org/genetic_cars_2/http://rednuht.org/genetic_cars_2/http://find/ -
7/26/2019 Chapter13 - New Trends (1)
9/69
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Artificial IntelligenceExpert Systems
Definition (Expert Systems)An expert system is computer software that attempts to act like ahuman expert on a particular subject area.
An expert system is made up of three parts:A user interface - This is the system that allows a non-expertuser to query (question) the expert system, and to receiveadvice.A knowledge base - This is a collection of facts and rules. Theknowledge base is created from information provided by humanexpertsAn inference engine - This acts rather like a search engine,examining the knowledge base for information that matchesthe users query
Applications are Medical diagnosis, financial advice, discover locations to drill for water, vacationadvisor(http://www.exsys.com/demomain.html ) etc.
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 9
Trends and Future Dir in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
http://www.exsys.com/demomain.htmlhttp://www.exsys.com/demomain.htmlhttp://find/ -
7/26/2019 Chapter13 - New Trends (1)
10/69
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Artificial Intelligence Software vs. Conventional Software
Application of Expert System
Artificial Intelligence Software vs. Conventional Software
Conventional computer software follow a logical series of stepsto reach a conclusionComputer programmers originally designed software that
accomplished tasks by completing algorithmsAI software uses the techniques of search and pattern matchingProgrammers design AI software to give the computer only theproblem, not the steps necessary to solve it
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 10
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
http://find/http://goback/ -
7/26/2019 Chapter13 - New Trends (1)
11/69
Trends and Future Dir. in ICT Agent Based Systems Genetic Algorithm Ubiquitous Computing
Artificial IntelligenceOur Attempt To Build Models Of Ourselves
Artificial Intelligence (Pros)
Ability to simulate human behavior and cognitive processes(Intuition, Common sense, Judgment, Creativity, Beliefs etc)
Capture and preserve human expertiseFast Response.The ability to comprehend large amounts of data quickly.
Artificial Intelligence (Cons)
No common sense
Cannot readily deal with mixed knowledgeMay have high development costsRaise legal and ethical concerns
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 11
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
12/69
e ds a d utu e . C Age t ased Syste s Ge et c A go t Ub qu tous Co put g
Kansei Systems
Definition (Kansei Engineering)
An consumer oriented technology for new product developmentbased on consumer Kansei (psychological image and feeling)
The attempt is to improve the business by producing product
or delivering services that fit to consumer feelings, emotions,culture, profession, etc.
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 12
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
13/69
g y g q p g
Kansei SystemsAttractive things Work Better
What is attractive? It is three level of processing
Reflective: Cerebral(use brains instead of hearts), emotive(expressing a persons feelings)
Behavioral: Common, and interact with the worldVisceral : relating to deep inward feelings rather than to theintellect
Affective designs impact on usability?
Working with the three levels
Visceral design : AppearanceBehavioral : Pleasure and effectiveness of useReflective: Self esteem and status
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 13
http://find/http://goback/ -
7/26/2019 Chapter13 - New Trends (1)
14/69
Fall 2013 PSYCH / CS 6750 6
Appearance(s)
!
Symmetry = Beauty = Usability ???
ll 013 CS6750
http://find/http://goback/ -
7/26/2019 Chapter13 - New Trends (1)
15/69
Fall 2013 PSYCH / CS 6750 7
Appearance(s)
!
Asymmetry = usable ==> beautiful ???
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
16/69
Fall 2013 PSYCH / CS 6750 8
More!
!
Asymmetry => usability (but, sexy?)
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
17/69
Fall 2013 PSYCH / CS 6750 9
Behavior ?
!
Feel => Function ??
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
18/69
Fall 2013 PSYCH / CS 6750 10
Reflective Design
!
Clever, clean
all 1 0
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
19/69
Fall 2013 PSYCH / CS 6750 11
Reflective
!
Status, image
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
20/69
Fall 2013 PSYCH / CS 6750 15
Taking Off from Maslow
From Anderson, SeductiveInteraction Design
YC S 750
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
21/69
Fall 2013 PSYCH / CS 6750 16
Simple (Positive) Example
16CS 6750 16
Playful!!
Fun!!
Pleasurable!!
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
22/69
Fall 2013 PSYCH / CS 6750 17
Simple (Negative) Example
!
Conveying success in red #
!
More joyful ways to do it? From Anderson, SeductiveInteraction Design
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
23/69
Fall 2013 PSYCH / CS 6750 18
Exclusivity Snobbery
18
Another kind of emotion ..
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
24/69
Man-Machine Coexistence
Definition (What does coexistence mean?)
The word coexistencecan be broken into two parts, co- and -exists.The prefix co- means together and -exist means to be or to live.
Therefore coexistence means being or living togetherCoexistence also has another connotation - peacefulcoexistence.It means more than being in the same place at the same time,getting along with each other.
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 14
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
25/69
Session Overview
1 New trends and future directions of ICTIntelligent and Emotional ComputingArtificial IntelligenceKansei Systems
Example in Kansei Engineering
Man-Machine Coexistence
2 Agent-Based SystemsNew Challenges for Computer SystemsCharacteristics of AgentsMulti-Agent SystemsApplications of Agents
3 Genetic AlgorithmBiological ExplorationAlgorithm and Examples in GA
4 Ubiquitous ComputingApplication and Technology
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 15
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
26/69
New Challenges for Computer Systems
Traditional Design Problem
How can we build a system that produces the correct outputgiven some input?
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 16
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
27/69
New Challenges for Computer Systems
Traditional Design Problem
How can we build a system that produces the correct outputgiven some input?Modern-day Design Problem
Modern-day, many of the systems we need to build in practicehave a reactive flavor, in the sense that they have to maintaina long-term, ongoing interaction with their environment, they
do not simply compute some function of an input and thenterminate.
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 16
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
http://find/http://goback/ -
7/26/2019 Chapter13 - New Trends (1)
28/69
New Challenges for Computer Systems
Traditional Design Problem
How can we build a system that produces the correct outputgiven some input?Modern-day Design Problem
Modern-day, many of the systems we need to build in practicehave a reactive flavor, in the sense that they have to maintaina long-term, ongoing interaction with their environment, they
do not simply compute some function of an input and thenterminate.The main role of reactive systems is to maintain an interactionwith their environment, and therefore must be described interms of their on-going behaviors, such as OS, process control
systems, online banking systems, etc.
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 16
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
http://find/http://goback/ -
7/26/2019 Chapter13 - New Trends (1)
29/69
New Challenges for Computer Systems
Traditional Design Problem
How can we build a system that produces the correct outputgiven some input?Modern-day Design Problem
Modern-day, many of the systems we need to build in practicehave a reactive flavor, in the sense that they have to maintaina long-term, ongoing interaction with their environment, they
do not simply compute some function of an input and thenterminate.The main role of reactive systems is to maintain an interactionwith their environment, and therefore must be described interms of their on-going behaviors, such as OS, process control
systems, online banking systems, etc.A still more complex class of systems is a subset of reactivesystems that we call agent
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 16
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
http://find/http://goback/ -
7/26/2019 Chapter13 - New Trends (1)
30/69
New Challenges for Computer Systems
Traditional Design Problem
How can we build a system that produces the correct outputgiven some input?Modern-day Design Problem
Modern-day, many of the systems we need to build in practicehave a reactive flavor, in the sense that they have to maintaina long-term, ongoing interaction with their environment, they
do not simply compute some function of an input and thenterminate.The main role of reactive systems is to maintain an interactionwith their environment, and therefore must be described interms of their on-going behaviors, such as OS, process control
systems, online banking systems, etc.A still more complex class of systems is a subset of reactivesystems that we call agentAgent is a reactive system that exhibits some degree ofautonomy in the sense that we delegate some task to it, and
the system itself determines how best toachievethistaskSubha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 16
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
S
http://find/http://goback/ -
7/26/2019 Chapter13 - New Trends (1)
31/69
Agent-Based SystemsWhat is an Agent (Wooldridge and Jennings)
Definition (Agent)An agent is a computer system that is situated in someenvironment, and that is capable of autonomous action in thisenvironment in order to meet its design objectives
Characteristics of Agentsbeing situated in an environmentautonomyproactivenessreactivity
social ability
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 17
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
A B d S
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
32/69
Agent-Based SystemsCharacteristics of Agents
Autonomy
Capability of acting independently, exhibiting control over theirinternal stateAt the end of oneend, we have computer programs such asconventional word processors and spreadsheets, which exhibits
little or no autonomy. At the other-end of the autonomyspectrum, you and us. You are completely autonomous. Whereyou can ultimately choose to believe what you want - althoughsociety typically constraints your autonomy in various way.
Proactivness
The ability to exhibitgoal-directedbehavior. If an agent hasbeen delegated a particular goal, then we expect the agent totry to achievethis goal.This is in contrast to Object, where itremains in passive mode until a method invokes on it.
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 18
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
A B d S
http://goforward/http://find/http://goback/ -
7/26/2019 Chapter13 - New Trends (1)
33/69
Agent-Based SystemsCharacteristics of Agents
Reactiveness
Being reactive means being responsive to changes in theenvironment. Implementing a system that achieves an effectivebalance between goal-directed and reactive behavior turns out
to be hardSocial ability
It is not the ability of exchanges bytes, it is the ability ofagents to cooperate and coordinate activities with otheragents, in order to accomplish assigned goals. This
communication happens at the knowledge level. That is, wewant agents to be able to communicate their beliefs, goals andplans to one another.
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 19
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
A t B d S t
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
34/69
Agent-Based SystemsOther Characteristics of Agents
Mobility: the ability of an agent to move around an electronicnetwork
Veracity: an agent will not knowingly communicate false
informationBenevolence: agents do not have conflicting goals, and thatevery agent will therefore always try to do what is asked of it
Rationality: agent will act in order to achieve its goals, andwill not act in such a way as to prevent its goals beingachieved at least in so far as its beliefs permit
Learning/adaption: agents improve performance over time
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 20
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
A t B d S t
http://goforward/http://find/http://goback/ -
7/26/2019 Chapter13 - New Trends (1)
35/69
Agent-Based SystemsEnvironments
Accessible vs. Inaccessible (Observable vs. partiallyobservable)An accessible environment is one in which the agent canobtain complete, accurate, up-to-date information about theenvironments state
Deterministic vs. non-deterministicA deterministic environment is one in which any action has asingle guaranteed effect there is no uncertainty about thestate that will result from performing an action
Episodic vs. non-episodicIn an episodic environment, the performance of an agent is
dependent on a number of discrete episodes, with no linkbetween the performance of an agent in different scenarios
Single Agent vs. Multi-AgentsWhich entities have to be regarded as agents? Are thecompetitive and cooperative actions?
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 21
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Ag t B s s S st s
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
36/69
Agent-Bases SystemsEnvironments
Static vs. dynamic
A static environment is one that can be assumed to remainunchanged except by the performance of actions by the agentA dynamic environment is one that has other processes
operating on it, and which hence changes in ways beyond theagents control
Discrete vs. continuous
An environment is discrete if there are a fixed, finite number ofactions and percepts in it
A chess game as an example of a discrete environment, andtaxi driving as an example of a continuous one.Continuous environments have a certain level of mismatchwith computer systems
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 22
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Agent Based Systems
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
37/69
Agent-Based Systems
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 23
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Structure of Agents
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
38/69
Structure of AgentsRational Agents
Basic StructurePerceive the environment through sensors (Percepts)Act upon the environment through actuators (Actions)Act rational with respect to a performance measure (e.g. goal:money, time, energy, utility)
Rational Behavior depends on
Performance measures (goals)Precept sequencesKnowledge of the environmentPossible actions
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 24
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Agent Based Systems
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
39/69
Agent-Based SystemsExamples of Rational Agents
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 25
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Agent Based Systems
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
40/69
Agent-Based SystemsReflex Agents
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 26
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Agent-Based Systems
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
41/69
Agent-Based SystemsLearning Agents
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 27
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Agent-Based Systems
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
42/69
Agent Based SystemsExample of Learning Agents
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 28
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Multi-Agent Systems
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
43/69
Multi Agent Systems
Definition (Multi-Agent Systems (MAS))
A multi-agent system is a computerized system composed ofmultiple interacting agents within an environment. Multi-agentsystems can be used to solve problems that are difficult orimpossible for an individual agent to solve.
Definition (intelligent agents)
An intelligent agent in a society is a rational agent with followingabilities,
Reactivity
Proactivity
Social Ability: To interact (communicate, cooperate,collaborate) with other agents by using Agent communicationlanguage.
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 29
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Multi-Agent Systems
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
44/69
Multi Agent SystemsAttribute of MAS
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 30
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Multi-Agent Systems
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
45/69
Multi Agent SystemsMAS Coordination
There are two types of agents in MASBenevolent AgentsSelf Interested Agents
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 31
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Multi-Agent Systems
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
46/69
g SyBenevolent Agents- Contract Nets
Benevolent Agents (cooperation)Examples are team of fire-brigades, disaster-rescue team, etc.Agents are assumed to act truthfullyAgents have been designed to help whenever it asks for, whichis called Cooperative distributed problem solving approach
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 32
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Multi-Agent Systems
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
47/69
g ySelf-Interested Agents
Self-Interested Agents (competition)Examples are arrival management system for airport withnumber of different airlines, reverse auction, e-commerce, etc.Agents tries to maximize its expected utilityAgents know what their options are and what the payoff will beStrategic deliberation and decision-making
Agent-based system in buying and selling process:
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 33
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Applications of Agents
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
48/69
pp g
Agents for Work-flow and Business Process ManagementWork-flow systems aim to to automate the process of a business, ensuring that different businesstasks are expedited by the appropriate people at the right time, typically ensuring that a particulardocument flow is maintained and managed within an organization.ADEPT is an example for an agent-based business process management systems, a businessorganization is modeled as a society of negotiating, service providing agents.
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 34
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Applications of Agents
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
49/69
pp g
Agents for Work-flow and Business Process ManagementWork-flow systems aim to to automate the process of a business, ensuring that different businesstasks are expedited by the appropriate people at the right time, typically ensuring that a particulardocument flow is maintained and managed within an organization.ADEPT is an example for an agent-based business process management systems, a businessorganization is modeled as a society of negotiating, service providing agents.
Agents for Distributed SensingThe broad idea is to use multi-agent systems to manage networks of spatially distributed sensors.
The sensors, may, for example, be acoustic sensors on a battlefield, or radars distributed acrosssome airspace.Sensors will typically provide partial and frequently conflicting data: different parts of theenvironment will have different characteristics with respect to the sound and electromagneticsensing spectrum.Agents in the network should cooperate with another, for example, by exchanging informationabout when a vehicle pass from one region to another.
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 34
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Applications of Agents
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
50/69
Agents for Work-flow and Business Process ManagementWork-flow systems aim to to automate the process of a business, ensuring that different businesstasks are expedited by the appropriate people at the right time, typically ensuring that a particulardocument flow is maintained and managed within an organization.ADEPT is an example for an agent-based business process management systems, a businessorganization is modeled as a society of negotiating, service providing agents.
Agents for Distributed SensingThe broad idea is to use multi-agent systems to manage networks of spatially distributed sensors.
The sensors, may, for example, be acoustic sensors on a battlefield, or radars distributed acrosssome airspace.Sensors will typically provide partial and frequently conflicting data: different parts of theenvironment will have different characteristics with respect to the sound and electromagneticsensing spectrum.Agents in the network should cooperate with another, for example, by exchanging informationabout when a vehicle pass from one region to another.
Agents for Electronic commerceAgents for Human-Computer InterfacesComputer programs that employ AI in order to provide assistance to a user dealing with aparticular application, i.e. A personal assistant who is collaborating with the user in the same workenvironment.
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 34
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Applications of Agents
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
51/69
Agents for Information Retrieval and ManagementAn information agent is an agent that has access to at least one and potentially many informationsources.Agent is able to collate and manipulate information obtained from these sources in order to answerqueries posed by users and other information agents.
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 35
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Session Overview
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
52/69
1 New trends and future directions of ICTIntelligent and Emotional Computing
Artificial IntelligenceKansei Systems
Example in Kansei Engineering
Man-Machine Coexistence
2 Agent-Based Systems
New Challenges for Computer SystemsCharacteristics of AgentsMulti-Agent SystemsApplications of Agents
3 Genetic AlgorithmBiological ExplorationAlgorithm and Examples in GA
4 Ubiquitous ComputingApplication and Technology
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 36
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Genetic Algorithm (GA)
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
53/69
Darwins Principle of Natural Selection
Definition (Genetic Algorithm)Genetic Algorithms are search and optimization techniques, basedon Darwins Principle of natural selection
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 37
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Genetic Algorithm (GA)
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
54/69
Darwins Principle of Natural Selection
Definition (Genetic Algorithm)Genetic Algorithms are search and optimization techniques, basedon Darwins Principle of natural selection
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 38
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Genetic Algorithm
http://goforward/http://find/http://goback/ -
7/26/2019 Chapter13 - New Trends (1)
55/69
Biological Exploration
DNA :Is the prime genetic moleculecarrying all the heredityinformation
Chromosome
DNA is associated with proteinsand each DNA and its associatedprotein is called a chromosome.Thus, Chromosome is a compactform of DNA that fits inside the
cellDNA packaged into achromosome can be transmittedefficiently to both daughter cellseach time a cell divides.
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 39
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Genetic Algorithm
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
56/69
Biological Exploration
ChromosomeDifferent kinds of organisms havedifferent numbers of chromosomes.Each parent contributes onechromosome to each pair,
so children get half of theirchromosomes from their mothers andhalf from their fathers.
Gene
A gene is the functional and physical
unit of heredity passed from parent tooffspring.Genes are pieces of DNA, and mostgenes contain the information formaking a specific protein.
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 40
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Vocabulary of GA
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
57/69
Genome
Collection of allchromosomesGenetic information isstored in the chromosomes
Chromosome
Each chromosome is buildof DNACollection of Genes
Locus
The position of a gene on
the chromosome.
Trait
Aspect (features) of achromosome
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 41
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Genetic AlgorithmAl i h
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
58/69
Algorithm
Design of Genotype (Encoding): Determine how solutions ofa given problem are represented as genes.Initialization: Make a given number of individuals (M) withappropriate genes at the first generation.Fitness Evaluation: Calculate the fitness of each individual
with an evaluation function. If there is one that satisfies thetermination condition, it is transformed into Phenotype, thenEND.Selection: Choose the necessary number of individuals forcrossover considering fitness
Crossover: Generate individuals of the next generation byexchanging genes of chosen pairsMutation: Change a pair of genes in the predefined way andwith the predefined mutation probabilitygo toFitness Evaluation
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 42
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
59/69
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
60/69
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
61/69
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
62/69
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
63/69
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
64/69
http://find/http://goback/ -
7/26/2019 Chapter13 - New Trends (1)
65/69
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
66/69
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Session Overview
1 N t d d f t di ti f ICT
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
67/69
1 New trends and future directions of ICTIntelligent and Emotional Computing
Artificial IntelligenceKansei Systems
Example in Kansei Engineering
Man-Machine Coexistence
2 Agent-Based Systems
New Challenges for Computer SystemsCharacteristics of AgentsMulti-Agent SystemsApplications of Agents
3 Genetic AlgorithmBiological ExplorationAlgorithm and Examples in GA
4 Ubiquitous ComputingApplication and Technology
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 43
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Ubiquitous ComputingIntroduction
http://find/http://goback/ -
7/26/2019 Chapter13 - New Trends (1)
68/69
What is Ubiquitous Computing
the method of enhancing computing use by making manydevices (services) available throughout the physicalenvironment, but making them effectively invisible to the usercomputing everywhere:
many embedded, wearable, hand-held devices communicatetransparently to provide different services to the usersdevices mostly have low power and short-range wirelesscommunication capabilities
devices utilize multiple on-board sensors to gather informationabout surrounding environments
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 44
Trends and Future Dir. in ICT Agent-Based Systems Genetic Algorithm Ubiquitous Computing
Ubiquitous ComputingApplication and Technology
http://find/ -
7/26/2019 Chapter13 - New Trends (1)
69/69
Challenges and Requirements
Hardware, Applications, User InterfacesNetworking, Mobility, Scalability, ReliabilityInteroperability, Resource Discovery, Privacy and Security
Subha Fernando, Dr.Eng, M.Eng, B.Sc(Special)Hons. New trends and future directions of ICT,Slide 45
http://find/