Budapest University of Technology and Economics, Faculty of Electrical Engineering and Informatics

    Belépés
    címtáras azonosítással
    vissza a tantárgylistához   nyomtatható verzió    

    Embedded Intelligent Systems Laboratory

    A tantárgy neve magyarul / Name of the subject in Hungarian: Beágyazott intelligens rendszerek laboratórium

    Last updated: 2008. szeptember 1.

    Budapest University of Technology and Economics
    Faculty of Electrical Engineering and Informatics

    Applied Informatics Branch
    Intelligent Systems Specialization

    MSc

     
    Course ID Semester Assessment Credit Tantárgyfélév
    VIMIM306 3 0/0/3/f 4  
    3. Course coordinator and department Dr. Pataki Béla József,
    4. Instructors
    Name:

     

    		Position:

     

    		Department:

     

    Dr. György Strausz

     

    Dániel László Kovács

     

    		associate professor

     

    assistant lecturer

     

    		DMIT

     

    DMIT

     

    5. Required knowledge Artificial Intelligence

     
    6. Pre-requisites
    Ajánlott:
    None
    7. Objectives, learning outcomes and obtained knowledge During the course of the laboratory students are introduced to the practice of embedded intelligent systems. The practices are particularly about ambient intelligent systems. Students practice with sensor fusion; human-agent communication; expert, logical, planning, fuzzy, and decision network based decision systems; and with evolutionary, emergent, and swarm intelligence.

     
    8. Synopsis I. Sensor fusion. Students practice with fusing multi-sensor information from different motes and other stationary sensors.

     

     

    II. Human-agent communication: controlled natural language dialogue. During this practice students extend motes and agents with natural language processing capabilities in order to communicate with humans in a controlled fashion in an intelligent space (e.g. intelligent office).

     

     

    III. Human-agent communication: emotional models. During this practice student extend motes and agents with the emotional models of the humans in the intelligent space (e.g. intelligent office) in order to cooperate with them more effectively.

     

     

    IV. Planning in mote-environment. Students create planning operators abstracting the movement and actions of mobile motes, and then represent concrete mote-tasks in a planning problem description language to generate the solution plans. The correctness of the plans is test by their execution.

     

     

    V. Expert agents. During this practice students control motes and other actuators with agents, which diagnose the actual scenario with expert systems (based on sensory input).

     

     

    VI. Constraint logic programming. During this practice students control motes and other actuators with agents, which make their decisions with a constraint logic solver engine (based on sensory input).

     

     

    VII. Fuzzy production systems. During this practice students control motes and other actuators with agents, which make their decisions with fuzzy production systems (based on sensory input).

     

     

    VIII. Building and applying decision networks. During this practice students represent probability distributions and utility functions. The goal is for them to learn the skill of constructing models in a knowledge engineering approach.

     

     

    IX. Evolutionary methods. Students solve several hard optimization problems with evolutionary/genetic methods, and examine the evolutionary processes in dedicated software environment. They experiment with modifying the genetic coding and genetic operators. The created solutions (parameter vectors, controlling mechanisms) are tested with motes.

     

     

    X. Emergent and swarm intelligence. Students implement and analyze several cooperative social models (bees, ants, etc) in agent societies and appropriately made physical test environments.

     

     

    Theoretical knowledge related to the subject is presented within the Embedded Intelligent Systems.

     
    9. Method of instruction Laboratory. Students participate in 10 laboratory practices in a row.

     
    10. Assessment Finishing every practice and deliver every associated report (the guidelines for making these reports are specified in the practice instructions accordingly).

     

    The final mark is based on the different report marks.

     
    11. Recaps Failed or absent practices can be repeated right after the last practice in the midterm. Maximally 2 practices can be repeated. There is no repetition in the examination period.

     
    12. Consultations As required, upon agreement.

     
    13. References, textbooks and resources Stuart Russell and Peter Norvig: Artificial intelligence. a modern approach, 2nd edition, Prentice Hall, 2003

     
    14. Required learning hours and assignment
    Kontakt óra42
    Félévközi készülés órákra30
    Felkészülés zárthelyire
    Házi feladat elkészítése
    Kijelölt írásos tananyag elsajátítása48
    Vizsgafelkészülés120
    Összesen
    15. Syllabus prepared by
    Name:

     

    		Position:

     

    		Department:

     

    Dr. György Strausz

     

    Dániel László Kovács

     

    		associate professor

     

    assistant lecturer

     

    		DMIT

     

    DMIT