0
 
<ul><li>Presentation Outline </li></ul><ul><li>Smart systems of the future - Applications </li></ul><ul><li>The need for s...
<ul><li>With the Internet as driving factor, socio-technical and industrial e-Networked ecosystems are about to change our...
<ul><li>In current medicine (the discipline) professional care is encouraged. Through access to information, this model ma...
<ul><li>Teachers - leave the students alone! </li></ul><ul><li>E-Learning is fueling one of the most radical revolutions i...
<ul><li>The roaring successes of e-Bay, Amazon, and Google and others who broke the traditional models for commerce. </li>...
<ul><li>Paradigm shift from silo-oriented to service-oriented architectures </li></ul><ul><li>From directly accessing loca...
<ul><li>Devices and machines will be able to discover each others with no previous knowledge on each other's type and coll...
<ul><li>Social networks have taken the lead to push the world from a traditional closed competitive environment to an open...
<ul><li>Ubiquitous Technology allowing internet connection anytime, anywhere  -- A new world where anyone can freely conne...
<ul><li>ICT systems in all domains of society has opened the door to entirely new forms of social organization characteriz...
<ul><li>From the rise of global identity theft; to nation sponsored cyber attacks and the realities of combined warfare, t...
Web Services  and Quality of Service <ul><li>Application QoS </li></ul><ul><ul><li>User perception, response time, Securit...
Service Level Agreements Negotiation Client Provider Can you do X for me for Y in return? No SLA SLA Can you do Z for me f...
SLA Variations  Client Providers SLA SLA Multi-provider SLA Single SLA is divided across multiple providers SLA dependenci...
Future Information Systems System has to be autonomous and able to continuously adapt, providing the required quality of s...
Problem Complexity
Parking a Car Generally, a car can be parked rather easily. If it were specified to within, say, a fraction of a millimete...
Traditional Approaches <ul><li>Mathematical models, Black boxes, number crunching. </li></ul><ul><li>Rule-based systems (c...
In nature it works… Why not for our digital ecosystem?
Artificial Neural Network Artificial neuron Mammalian neuron
<ul><li>Fuzzy Logic </li></ul>A = Set of Old People Multi-Valued Logic --  Jan Łukasiewicz
Rough Set –  Zdzisław Pawlak The rough set concept overlaps—to some extent—with many other mathematical tools developed to...
Computational Theory of Perceptions  (Zadeh) <ul><li>Humans have remarkable capability to perform a wide variety of physic...
<ul><li>How to Model Perceptions </li></ul><ul><li>Perceptions are both fuzzy and granular </li></ul><ul><li>Boundaries of...
Evolutionary Algorithms Evolutionary Algorithms can be described by x [ t  + 1] =  s ( v ( x [ t ])) <ul><ul><li>x [ t ] :...
Hybrid Approaches
Ant Colony Optimization
ACO in Real Life TSP  Scheduling Clustering
Particle Swarm Optimization x p g p i v P best G best
Some Pitfalls of PSO <ul><li>Particles tend to cluster, i.e., converge too fast and get stuck at local optimum </li></ul><...
Turbulent PSO (TPSO)
FATPSO – Griewank Function - 100 D
FATPSO – Levy Function - 100 D
FATPSO – Schwefel Function - 100 D
Smart System Application Example Improving the delivery of health care in geriatric residences
The Problem.. Over the past 30 years, the number of Europeans over 60 years of age has risen by about 50 percent, and now ...
The Solution <ul><li>Ambient Intelligence is the vision of an environment </li></ul><ul><li>filled with smart and communic...
The Environment Alzheimer Santísima Trinidad Residence of Salamanca, Spain The Residence is for  Alzheimer’s patients  ove...
Technologies Used Multi-agent system, which is a dynamic system for the management of different aspects of the geriatric c...
Technologies Used System  uses microchips mounted on bracelets worn on the patient ’ s wrist or ankle, and sensors install...
Software Architecture Patient :  monitoring, location, daily tasks, and anomalies  Doctor:  treats patients Nurse:  schedu...
Software Architecture
Patient Agent The beliefs that were seen to define a general patient state: weight, temperature, blood pressure, feeding (...
Patient Agent Manager and Patient agents run in a central computer, but GerAg agents run on mobile devices, so a robust wi...
Agent System Manager and Patient agents run in a central computer, but other agents run on mobile devices Every agent save...
System Interfaces Manager Nurse
How Effective?
Automatic Design of Fuzzy Systems   As a way to overcome the curse-of-dimensionality, it was suggested to arrange several ...
Automatic Design of Hierarchical Takagi-Sugeno Type Fuzzy Systems   <ul><li>The problems in designing a hierarchical fuzzy...
Automatic Design of Hierarchical Takagi-Sugeno Type Fuzzy Systems  
  <ul><li>A tree-structural based encoding method.  </li></ul><ul><li>The reasons for choosing this representation:  </li>...
Encoding   Assume that the used instruction set is I={+2, +3, x1, x2, x3, x4, where +2 and +3 denote non-leaf nodes' instr...
Comparison of the incremental type multilevel FRS (IFRS), aggregated type mutilevel FRS (AFRS), and the hierarchical TS-FS...
The structure of the evolved hierarchical TS-FS model for predicting of Mackey-Glass time-series The importance degree of ...
 
The developed optimal H-TS-FS architectures (Irisdata)
 
The developed optimal H-TS-FS architectures (Wine data)
Flexible Neural Trees
Flexible Neural Trees
Flexible Neural Trees
Flexible Neural Trees
Flexible Neural Trees
Intrusion Detection
Flexible Neural Trees - IDS
FNT– Colon Cancer / Leukemia
FNT– Colon Cancer / Leukemia
MIMO - FNT
Flexible Radial Basis Function Trees
Flexible Radial Basis Function Trees Breast Cancer Detection
What is Risk? <ul><li>Risk is the potential that a chosen action or activity (or inaction) will lead to a loss (or an unde...
Enterprise Risk <ul><li>Internal: </li></ul><ul><li>Activities range from storage of data to providing information to empl...
Why risk modelling is complex? <ul><li>It affects us at the personal, corporate and government levels.  </li></ul><ul><li>...
Establish the Context Identify Analyze Evaluate Treatment Monitoring and Review Communication and Consultation Risk Manage...
Risk Components Threat Vulnerability Asset Value
What is Threat? Threat  is anything that is capable of acting against an asset in a manner that can result in harm.  A tor...
What is Vulnerability? Weakness that may be exploited! A condition in which threat capability (force) is greater than the ...
What is Asset? Asset  can be any data, device, or other component of the environment that supports information-related act...
Risk Assessment – A Soft Approach There is no such thing as an “exact” value of risk.  The advantage of the  fuzzy  approa...
Risk Assessment <ul><li>Fuzzy  modeling of risk assessment  </li></ul><ul><li>Threat level </li></ul><ul><li>Vulnerability...
Fuzzy modeling of Risk
Takagi-Sugeno Neuro-Fuzzy  System
Hierarchical Takagi-Sugeno Type Fuzzy Systems  
  <ul><li>A tree-structural based encoding method.  </li></ul><ul><li>the tree has a natural and typical hierarchical laye...
Developed Fuzzy Risk Assessment Model
Genetic Programming <ul><ul><li>Generation of different programs  that solve the problem more or less accurately </li></ul...
Program obtained by the best individual is as follows: (cos(exp(1 / (log10( x[5] )) +  x[0] ))) * (tan(1 / (exp(cos((tan( ...
How Can We Teach Things to Computers? In order for a program to be capable of learning something, it must first be capable...
 
Building Smart Systems: Some Challenges <ul><li>Most of the existing frameworks rely on user specified  parameters. </li><...
Conclusions <ul><li>Managing Complexity:  Can autonomy be planned or decentralization be controlled? Can evolution be desi...
Q A & Thank You [email_address]
 
Upcoming SlideShare
Loading in...5
×

Evolving Future Information Systems: Challenges, Perspectives and Applications

403

Published on

Evolving Future Information Systems: Challenges, Perspectives and Applications
Ajith Abraham
Machine Intelligence Research Labs (MIR Labs), USA

Published in: Technology, Education
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total Views
403
On Slideshare
0
From Embeds
0
Number of Embeds
1
Actions
Shares
0
Downloads
30
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide
  • 06/28/11
  • 06/28/11
  • 06/28/11
  • 06/28/11
  • 06/28/11
  • 06/28/11
  • 06/28/11
  • 06/28/11
  • 06/28/11
  • 06/28/11
  • 06/28/11
  • 06/28/11
  • 06/28/11
  • 06/28/11
  • We want to talk in depth about how the algorithm works here
  • With a change in the environment, swarm intelligent systems will adapt to this change and find the new optimal solution. This is achieved because ants choose to follow a path withcertain probability, therefore ants are always re-testing paths that were previously found to ineffiecient.
  • 06/28/11
  • 06/28/11
  • 06/28/11
  • 06/28/11
  • 06/28/11
  • 06/28/11
  • 06/28/11
  • 06/28/11
  • 06/28/11
  • 06/28/11
  • 06/28/11
  • 06/28/11
  • 06/28/11
  • 06/28/11 9
  • 06/28/11 9
  • 06/28/11 9
  • 06/28/11 9
  • 06/28/11 9
  • 06/28/11
  • This figure shows the architecture of the proposed DIPS. As mentioned on earlier slides the IDS system is a basis for the DIPS. They will send alarms to the HMM module that try to determine the state of the network. Information about very serious attacks will also be sent to the local controller, so immediate actions can be taken. The HMM module will have one HMM model for each IDS agent, used to estimate the system state based on alarms from that particular IDS Agent. Information from the HMM module is used to predict Intrusion and together with information about assets in the network used to do online risk assessment. If the intrusion prediction module believe there is an ongoing attack, it will be reported to the local controller and necessary action will be taken to stop the intrusion. The local controller will also take actions based on input from the traffic rate monitor, and give an overview of current network status through the Administrative Console. More than one DIPS may exchange information through a central controller.
  • This figure shows the architecture of the proposed DIPS. As mentioned on earlier slides the IDS system is a basis for the DIPS. They will send alarms to the HMM module that try to determine the state of the network. Information about very serious attacks will also be sent to the local controller, so immediate actions can be taken. The HMM module will have one HMM model for each IDS agent, used to estimate the system state based on alarms from that particular IDS Agent. Information from the HMM module is used to predict Intrusion and together with information about assets in the network used to do online risk assessment. If the intrusion prediction module believe there is an ongoing attack, it will be reported to the local controller and necessary action will be taken to stop the intrusion. The local controller will also take actions based on input from the traffic rate monitor, and give an overview of current network status through the Administrative Console. More than one DIPS may exchange information through a central controller.
  • This figure shows the architecture of the proposed DIPS. As mentioned on earlier slides the IDS system is a basis for the DIPS. They will send alarms to the HMM module that try to determine the state of the network. Information about very serious attacks will also be sent to the local controller, so immediate actions can be taken. The HMM module will have one HMM model for each IDS agent, used to estimate the system state based on alarms from that particular IDS Agent. Information from the HMM module is used to predict Intrusion and together with information about assets in the network used to do online risk assessment. If the intrusion prediction module believe there is an ongoing attack, it will be reported to the local controller and necessary action will be taken to stop the intrusion. The local controller will also take actions based on input from the traffic rate monitor, and give an overview of current network status through the Administrative Console. More than one DIPS may exchange information through a central controller.
  • This figure shows the architecture of the proposed DIPS. As mentioned on earlier slides the IDS system is a basis for the DIPS. They will send alarms to the HMM module that try to determine the state of the network. Information about very serious attacks will also be sent to the local controller, so immediate actions can be taken. The HMM module will have one HMM model for each IDS agent, used to estimate the system state based on alarms from that particular IDS Agent. Information from the HMM module is used to predict Intrusion and together with information about assets in the network used to do online risk assessment. If the intrusion prediction module believe there is an ongoing attack, it will be reported to the local controller and necessary action will be taken to stop the intrusion. The local controller will also take actions based on input from the traffic rate monitor, and give an overview of current network status through the Administrative Console. More than one DIPS may exchange information through a central controller.
  • There is no such thing as an “exact” value of risk. Results of traditional quantitative risk assessments are usually qualified with a statement of uncertainties. Fuzzy logic is used to characterise the robustness of the SMS as the variable, which determines the likelihood of incidents. The advantage of the fuzzy approach is that it enables processing of vaguely defined variables, and variables whose relationships cannot be defined by mathematical relationships. Fuzzy logic can incorporate expert human judgement to define those variable and their relationships. The model can be closer to reality and network specific than that by some of the other methods.
  • We propose to use hierarchical fuzzy modeling in the risk assessment. In the DIPS framework, we model the risk analysis using threat levels, vulnerability and asset Threat level: is modeled as frequency of attacks or intrusions obtained from HMM predications described on earlier slides, probability of an attack being successful in overcoming protective controls and gaining access to the organization or assets, and the severity of the attacks. Vulnerability: My be described as the probability that an asset may be unable to resist the actions of an intruder. We have modeled the vulnerability as threat resistance and threat capability Asset value: To determine the asset loss may be one of the hardest parts in the task of analyzing the risk. We model the asset value as cost, criticality, sensitivity and recovery.
  • This slide shows the fuzzy rules used by the Risk assessment Master FLC, it illustrates the if then rules.
  • 06/28/11 9
  • 06/28/11 9
  • Quoted by Push Singh in Open Mind paper
  • 06/28/11
  • 06/28/11
  • Transcript of "Evolving Future Information Systems: Challenges, Perspectives and Applications"

    1. 2. <ul><li>Presentation Outline </li></ul><ul><li>Smart systems of the future - Applications </li></ul><ul><li>The need for soft approaches </li></ul><ul><li>Application examples </li></ul><ul><li>Conclusions </li></ul>
    2. 3. <ul><li>With the Internet as driving factor, socio-technical and industrial e-Networked ecosystems are about to change our lives again! </li></ul><ul><li>Rocketing speed of technological ICT advances. </li></ul><ul><li>As technology is getting ahead of society - the new ways disrupt the way we used to do things and even the way we used to think about the world. </li></ul><ul><li>Digital Convergence </li></ul><ul><li>Change the way we work, and we learn, and we live </li></ul>
    3. 4. <ul><li>In current medicine (the discipline) professional care is encouraged. Through access to information, this model may be changed. </li></ul><ul><li>Body Sensor Networks ! </li></ul><ul><li>ICT will play an increasingly important for curative and preventative medicine. </li></ul>
    4. 5. <ul><li>Teachers - leave the students alone! </li></ul><ul><li>E-Learning is fueling one of the most radical revolutions in education, by focused student-driven environment leveraging web-based individualized content. </li></ul><ul><li>Is learning to be regarded as a universal right and accessible irrespective of geography with open educational resources accessible to everyone from everywhere? </li></ul>
    5. 6. <ul><li>The roaring successes of e-Bay, Amazon, and Google and others who broke the traditional models for commerce. </li></ul><ul><li>Web 2.0, P2P, Social Networks, Blogs have fuelled the developments. </li></ul><ul><li>The future only gets interesting as we dare to solve problems that were unsolvable at the scale we are seeing before in terms of infrastructure, platforms, data, and applications, with participatory resources like people and computing. </li></ul><ul><li>Nature of e-Commerce of the future? </li></ul>
    6. 7. <ul><li>Paradigm shift from silo-oriented to service-oriented architectures </li></ul><ul><li>From directly accessing local computers to accessing remote computing and application services. </li></ul><ul><li>Grid and Cloud infrastructures available could enhance the Internet by seamlessly integrating computers, storage, sensor networks, digital experiments and instruments. </li></ul><ul><li>Users could access these resources and services through a simple Web browser, remotely, securely, transparently! </li></ul><ul><li>Just as another utility, from the wall socket. </li></ul>
    7. 8. <ul><li>Devices and machines will be able to discover each others with no previous knowledge on each other's type and collaborate towards the resolution of a common goal. </li></ul><ul><li>They will use dynamic architectures allowing autonomous re/configuration of hardware and software structures, deploying software agents that can intelligently use web services in order to build adaptive systems. </li></ul><ul><li>Semantic web services, embedded systems, wireless networks, sensor networks etc. </li></ul>
    8. 9. <ul><li>Social networks have taken the lead to push the world from a traditional closed competitive environment to an open, loosely coupled, collaborative environment. </li></ul><ul><li>Value by making connections through the pervasive use of the modern infrastructure and collaborative IT frameworks. </li></ul>
    9. 10. <ul><li>Ubiquitous Technology allowing internet connection anytime, anywhere -- A new world where anyone can freely connect to computer networks regardless of time and place. </li></ul><ul><li>Multifunctional Administrative City, Innovation City, Enterprise City </li></ul>
    10. 11. <ul><li>ICT systems in all domains of society has opened the door to entirely new forms of social organization characterized by a high degree of decentralization. </li></ul><ul><li>Myriads of artifacts and humans, connected via networks and computing elements, exhibit self-organization and unpredictability that fundamentally challenge traditional systems engineering--based upon requirements and top-down management. </li></ul><ul><li>This spontaneous trend has preceded our ability as designers to comprehend and control it, while also opening new opportunities for exploiting the formidable potential of ICT advances. </li></ul>
    11. 12. <ul><li>From the rise of global identity theft; to nation sponsored cyber attacks and the realities of combined warfare, the safety and security of a nation, its people and its place in the global market is becoming more difficult. </li></ul><ul><li>Can governments successfully fulfill their obligation to protect? </li></ul><ul><li>Requires complex and integrated solutions and novel approaches. </li></ul>
    12. 13. Web Services and Quality of Service <ul><li>Application QoS </li></ul><ul><ul><li>User perception, response time, Security, etc. </li></ul></ul><ul><li>Middleware QoS </li></ul><ul><ul><li>Computation, Memory and Storage </li></ul></ul><ul><li>Network QoS </li></ul><ul><ul><li>Band width, Packet loss, Delay, Jitter etc. </li></ul></ul>
    13. 14. Service Level Agreements Negotiation Client Provider Can you do X for me for Y in return? No SLA SLA Can you do Z for me for Y in return? Negotiation Phase (Single or Multi-Round) SLA-Offer SLA-CounterOffer SLA-Offer
    14. 15. SLA Variations Client Providers SLA SLA Multi-provider SLA Single SLA is divided across multiple providers SLA dependencies For an SLA to be valid, Another SLA has to be agreed Client Providers SLA
    15. 16. Future Information Systems System has to be autonomous and able to continuously adapt, providing the required quality of service levels according to different service level agreements, without requiring the need of much human intervention. The challenge is to design intelligent machines and networks that could communicate and adapt according to critic or error information, self organize and resilient in case of a system, service or component failure due to natural cause or a malicious attack.
    16. 17. Problem Complexity
    17. 18. Parking a Car Generally, a car can be parked rather easily. If it were specified to within, say, a fraction of a millimeter, it would take hours of maneuvering and precise measurements of distance and angular position to solve the problem.  High precision carries a high cost  The challenge is to exploit the tolerance for imprecision by devising methods of computation which lead to an acceptable solution at low cost. This, in essence, is the guiding principle of modern intelligent computing.
    18. 19. Traditional Approaches <ul><li>Mathematical models, Black boxes, number crunching. </li></ul><ul><li>Rule-based systems (crisp and bivalent): Large rule bases </li></ul>
    19. 20. In nature it works… Why not for our digital ecosystem?
    20. 21. Artificial Neural Network Artificial neuron Mammalian neuron
    21. 22. <ul><li>Fuzzy Logic </li></ul>A = Set of Old People Multi-Valued Logic -- Jan Łukasiewicz
    22. 23. Rough Set – Zdzisław Pawlak The rough set concept overlaps—to some extent—with many other mathematical tools developed to deal with vagueness and uncertainty, in particular with the Dempster-Shafer theory of evidence. Rough set does not compete with fuzzy set theory, with which it is frequently contrasted, but rather complements it. One of the main advantages of rough set theory is that it does not need any preliminary or additional information about data, such as probability distribution in statistics, basic probability assignment in the Dempster-Shafer theory, or grade of membership or the value of possibility in fuzzy set theory.
    23. 24. Computational Theory of Perceptions (Zadeh) <ul><li>Humans have remarkable capability to perform a wide variety of physical and mental tasks without any measurement and computations. </li></ul><ul><li>Reflecting the finite ability of the sensory organs and (finally the brain) to resolve details, Perceptions are inherently imprecise. </li></ul>Provides capability to compute and reason with perception based information
    24. 25. <ul><li>How to Model Perceptions </li></ul><ul><li>Perceptions are both fuzzy and granular </li></ul><ul><li>Boundaries of perceived classes are un-sharp </li></ul><ul><li>Values of attributes are granulated </li></ul><ul><li>Example: </li></ul><ul><li>Granules in age: very young, young, not so old,… </li></ul>Perceptions are described by propositions drawn from a natural language
    25. 26. Evolutionary Algorithms Evolutionary Algorithms can be described by x [ t + 1] = s ( v ( x [ t ])) <ul><ul><li>x [ t ] : the population at time t under representation x </li></ul></ul><ul><ul><li>v : is the reproduction operator (s) </li></ul></ul><ul><ul><li>s : is the selection operator </li></ul></ul>Evolution strategies Evolutionary Algorithms Genetic Programming Evolutionary Programming Genetic Algorithm
    26. 27. Hybrid Approaches
    27. 28. Ant Colony Optimization
    28. 29. ACO in Real Life TSP Scheduling Clustering
    29. 30. Particle Swarm Optimization x p g p i v P best G best
    30. 31. Some Pitfalls of PSO <ul><li>Particles tend to cluster, i.e., converge too fast and get stuck at local optimum </li></ul><ul><li>Movement of particle carried it into infeasible region </li></ul><ul><li>Inappropriate mapping of particle space into solution space </li></ul>
    31. 32. Turbulent PSO (TPSO)
    32. 33. FATPSO – Griewank Function - 100 D
    33. 34. FATPSO – Levy Function - 100 D
    34. 35. FATPSO – Schwefel Function - 100 D
    35. 36. Smart System Application Example Improving the delivery of health care in geriatric residences
    36. 37. The Problem.. Over the past 30 years, the number of Europeans over 60 years of age has risen by about 50 percent, and now represents more than 25 percent of the population. Within 20 years, experts estimate that this percentage will rise to one-third of the population. Creating secure, unobtrusive, and adaptable environments for monitoring and optimizing healthcare will become vital in the near future. Dynamic: New patients arrive and others pass away! While the staff rotation is also relatively high and they normally work in shifts of eight hours.
    37. 38. The Solution <ul><li>Ambient Intelligence is the vision of an environment </li></ul><ul><li>filled with smart and communicating devices </li></ul><ul><li>which are naturally embedded in the environment and in common objects </li></ul><ul><li>while their presence is kept as seamless as possible </li></ul><ul><li>When coupled with RFID, Wi-Fi technologies, and handheld devices, such systems offer many new possibilities. </li></ul><ul><li>Our system aims to support elderly and Alzheimer patients in all aspects of daily life, predicting potential hazardous situations and delivering physical and cognitive support. </li></ul>
    38. 39. The Environment Alzheimer Santísima Trinidad Residence of Salamanca, Spain The Residence is for Alzheimer’s patients over 65 years old. Its services and facilities include medical service, including occupational therapy and technical assistance Comprises of : a terrace and a garden; laundry and tailoring services; a hairdressing salon; a chapel and religious services; a cafeteria and various rooms, including a geriatric bathroom, a multipurpose room, and separate rooms for reading, socializing, visiting with guests, and watching TV.
    39. 40. Technologies Used Multi-agent system, which is a dynamic system for the management of different aspects of the geriatric center. Radio Frequency Identification (RFID) technology for ascertaining patients’ location. Mobile devices and Wi-Fi technology to provide the personnel of the residence with updated information about the center and the patients, to provide the working plan, information about alarms or potential problems and to keep track of their movements and actions within the center. From the user’s point of view the complexity of the solution has been reduced with the help of friendly user interfaces and a robust and easy to use multi-agent system.
    40. 41. Technologies Used System uses microchips mounted on bracelets worn on the patient ’ s wrist or ankle, and sensors installed over protected zones, with an adjustable capture range up to 2 meters. The microchips or transponders use a 125 kHz signal to locate the patients, which can be identified by consulting the software agents installed in PDA’s.
    41. 42. Software Architecture Patient : monitoring, location, daily tasks, and anomalies Doctor: treats patients Nurse: schedules the nurse ’ s working day obtaining dynamic plans depending on the tasks needed for each assigned patient Security: controls the patients ’ location and manages locks and alarms Manager: manages the medical record database and the doctor-patient and nurse-patient assignment
    42. 43. Software Architecture
    43. 44. Patient Agent The beliefs that were seen to define a general patient state: weight, temperature, blood pressure, feeding (diet characteristics and next time to eat), medication, posture change, toileting, personal hygiene, and exercise. The beliefs and goals for every patient depend on the plan or plans corresponding to the treatments or medicine that the doctors prescribe. The patient agent must have periodic communication with the doctor and nurse agent. Must ensure that all the actions indicated in the treatment are fullfiled.
    44. 45. Patient Agent Manager and Patient agents run in a central computer, but GerAg agents run on mobile devices, so a robust wireless network has been installed as an extension to the existing wired LAN. With respect to the question of failure recovery, a continuous monitoring of the system is carried out. Every agent saves its memory (personal data) onto a data base. The most sensitive agents are patient agents, so these agents save their state every hour. When an agent fails, another instance can be easily created from the latest backup
    45. 46. Agent System Manager and Patient agents run in a central computer, but other agents run on mobile devices Every agent saves its memory (personal data) onto a data base. The most sensitive agents are patient agents, so these agents save their state every hour. When an agent fails, another instance can be easily created from the latest backup
    46. 47. System Interfaces Manager Nurse
    47. 48. How Effective?
    48. 49. Automatic Design of Fuzzy Systems   As a way to overcome the curse-of-dimensionality, it was suggested to arrange several low-dimensional rule base in a hierarchical structure, i.e., a tree, causing the number of possible rules to grow in a linear way according to the number of inputs. Building a hierarchical fuzzy system is a difficult task. This is because we need to define the architecture of the system (the modules, the input variables of each module, and the interactions between modules), as well as the rules of each modules.
    49. 50. Automatic Design of Hierarchical Takagi-Sugeno Type Fuzzy Systems   <ul><li>The problems in designing a hierarchical fuzzy logic system includes the following: </li></ul><ul><li>Selecting an appropriate hierarchical structure; </li></ul><ul><li>Selecting the inputs for each fuzzy TS sub-model </li></ul><ul><li>Determining the rule base for each fuzzy TS sub-model </li></ul><ul><li>Optimizing the parameters in the antecedent parts and the linear weights in the consequent parts. </li></ul>
    50. 51. Automatic Design of Hierarchical Takagi-Sugeno Type Fuzzy Systems  
    51. 52.   <ul><li>A tree-structural based encoding method. </li></ul><ul><li>The reasons for choosing this representation: </li></ul><ul><li>the tree has a natural and typical hierarchical layer; </li></ul><ul><li>with pre-defined instruction sets, the tree can be created and evolved using the existing tree-structure-based approaches, i.e., Genetic Programming (GP) and PIPE algorithms. </li></ul>Encoding
    52. 53. Encoding   Assume that the used instruction set is I={+2, +3, x1, x2, x3, x4, where +2 and +3 denote non-leaf nodes' instructions taking 2 and 3 arguments, respectively. x1, x2, x3, x4 are leaf nodes' instructions taking zero arguments each.
    53. 54. Comparison of the incremental type multilevel FRS (IFRS), aggregated type mutilevel FRS (AFRS), and the hierarchical TS-FS for Mackey-Glass time-series prediction Model layer No. of rules No. of para. RMSE(train) RMSE(Test) IFRS 4 25 58 0.0240 0.0253 AFRS 5 36 78 0.0267 0.0256 HTS-FS 3 24 33 0.0179 0.0167
    54. 55. The structure of the evolved hierarchical TS-FS model for predicting of Mackey-Glass time-series The importance degree of each input variables for Mackey-Glass time-series xi x 0 x 1 x 2 x 3 x 4 x 5 Impo ( xi ) 0.247 0.332 0.072 0.113 0.056 0.180
    55. 57. The developed optimal H-TS-FS architectures (Irisdata)
    56. 59. The developed optimal H-TS-FS architectures (Wine data)
    57. 60. Flexible Neural Trees
    58. 61. Flexible Neural Trees
    59. 62. Flexible Neural Trees
    60. 63. Flexible Neural Trees
    61. 64. Flexible Neural Trees
    62. 65. Intrusion Detection
    63. 66. Flexible Neural Trees - IDS
    64. 67. FNT– Colon Cancer / Leukemia
    65. 68. FNT– Colon Cancer / Leukemia
    66. 69. MIMO - FNT
    67. 70. Flexible Radial Basis Function Trees
    68. 71. Flexible Radial Basis Function Trees Breast Cancer Detection
    69. 72. What is Risk? <ul><li>Risk is the potential that a chosen action or activity (or inaction) will lead to a loss (or an undesirable outcome). </li></ul><ul><li>Risk – The probable frequency and probable magnitude of future loss </li></ul><ul><li>Risk analysis is fundamentally all about establishing probabilities! </li></ul><ul><li>Uncertainty is the central issue of IT risk! </li></ul>
    70. 73. Enterprise Risk <ul><li>Internal: </li></ul><ul><li>Activities range from storage of data to providing information to employees </li></ul><ul><li>External: </li></ul><ul><li>Networks and the Internet for many activities related to customers/clients, vendors, competitors, etc. </li></ul><ul><li>Traditional models of risk management: </li></ul><ul><li>Financial planning and insurance - Do they work in IT? </li></ul><ul><li>IT risks are more challenging to quantify than traditional risks because “the data on the likelihood and costs associated with information security risk factors are often more limited and because risk factors are constantly changing. </li></ul>
    71. 74. Why risk modelling is complex? <ul><li>It affects us at the personal, corporate and government levels. </li></ul><ul><li>It is cross-disciplinary. The subject has been further complicated by the development of diverse approaches of varying reliability. </li></ul><ul><li>Is grounded on the need to make trade-offs among all relevant and important cost, benefits, and risks in a multi-object framework, without assignment weights with which to commensurate risks costs and benefits. </li></ul>
    72. 75. Establish the Context Identify Analyze Evaluate Treatment Monitoring and Review Communication and Consultation Risk Management in Practice
    73. 76. Risk Components Threat Vulnerability Asset Value
    74. 77. What is Threat? Threat is anything that is capable of acting against an asset in a manner that can result in harm. A tornado is a threat, as is a hacker. The key consideration is that threats apply the force (eg: exploit code) against an asset that can cause a loss event to occur. Threat level depends on many factors: (1) frequency of attacks (2) probability that attack being successful (3) Type and severity of attack.
    75. 78. What is Vulnerability? Weakness that may be exploited! A condition in which threat capability (force) is greater than the ability to resist that force. Vulnerability is always dependent upon the type and level of force being applied Vulnerability depends upon: (1) threat capability and (2) system threat resistance
    76. 79. What is Asset? Asset can be any data, device, or other component of the environment that supports information-related activities, which can be illicitly accessed, used, disclosed, altered, destroyed, and/or stolen, resulting in loss. Even ‘’reputation’ is an asset Asset value/loss depends upon: (1) cost (2) criticality (3) sensitivity and (4) recovery.
    77. 80. Risk Assessment – A Soft Approach There is no such thing as an “exact” value of risk. The advantage of the fuzzy approach is that it enables processing of vaguely defined variables, and variables whose relationships cannot be defined by mathematical relationships. Fuzzy logic can incorporate expert human judgement to define those variable and their relationships. The model can be closer to reality and network specific than that by some of the other methods.
    78. 81. Risk Assessment <ul><li>Fuzzy modeling of risk assessment </li></ul><ul><li>Threat level </li></ul><ul><li>Vulnerability </li></ul><ul><li>Asset value </li></ul>
    79. 82. Fuzzy modeling of Risk
    80. 83. Takagi-Sugeno Neuro-Fuzzy System
    81. 84. Hierarchical Takagi-Sugeno Type Fuzzy Systems  
    82. 85.   <ul><li>A tree-structural based encoding method. </li></ul><ul><li>the tree has a natural and typical hierarchical layer; </li></ul><ul><li>with pre-defined instruction sets, the tree can be created and evolved using the existing tree-structure-based approaches, i.e., Genetic Programming (GP) and PIPE algorithms. </li></ul>Encoding
    83. 86. Developed Fuzzy Risk Assessment Model
    84. 87. Genetic Programming <ul><ul><li>Generation of different programs that solve the problem more or less accurately </li></ul></ul><ul><ul><li>Improvement of better solutions </li></ul></ul>? Input Output
    85. 88. Program obtained by the best individual is as follows: (cos(exp(1 / (log10( x[5] )) + x[0] ))) * (tan(1 / (exp(cos((tan( x[5] )) * x[0] ))))) It is to be noted that, not all variables are required for building the risk assessment models. For example, the best individual used only 3 input variables, while the worst individual required just 2 input variables. What Genetic Programming Can Do?
    86. 89. How Can We Teach Things to Computers? In order for a program to be capable of learning something, it must first be capable of being told it. John McCarthy Easy: If dogs are mammals and mammals are animals, are dogs mammals? Difficult: If most Canadians have brown eyes, and most brown eyed people have good eyesight, then do most Canadians have good eyesight? We Divide Things Into Concepts
    87. 91. Building Smart Systems: Some Challenges <ul><li>Most of the existing frameworks rely on user specified parameters. </li></ul><ul><li>Adaptation process could learn from success and mistakes and apply that knowledge to new problems. </li></ul><ul><li>No free Lunch Theorem </li></ul><ul><li>Managing computational complexity: Parallel algorithms? </li></ul>
    88. 92. Conclusions <ul><li>Managing Complexity: Can autonomy be planned or decentralization be controlled? Can evolution be designed? </li></ul><ul><li>Safety and Security: T he safety and security of a nation, its people and its place in the global market is becoming more difficult. </li></ul><ul><li>. Culture, media, ethics: Movies, television, cell phones, computer games, and the internet have all, in one way or another, collapsed the local into more international, creating a blur of perceptions, dreams and social mores. </li></ul>
    89. 93. Q A & Thank You [email_address]
    1. A particular slide catching your eye?

      Clipping is a handy way to collect important slides you want to go back to later.

    ×