Prilagodljivost bežične mreže osjetila temeljena na umjetnom imunološkom sustavu

doctoral thesis

• Title (english): Wireless Sensor Network Adaptability Based On Artificial Immune System
• Author: Igor Čavrak
• Mentor: Mario Žagar (mentor)
• Committee member: Leo Budin (član povjerenstva)
• Committee member: Mario Žagar (član povjerenstva)
• Committee member: Davor Antonić (član povjerenstva)
• Committee member: Mario Kovač (član povjerenstva)
• Committee member: Zdenko Kovačić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; (Department of Control and Computer Engineering); Zagreb
• Defense date and country: 2006-04-07, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing; Process Computing
• Universal decimal classification (UDC): 004 - Computer science and technology. Computing. Data processing

Abstract

Doktorska disertacija istražuje mogućnosti ostvarenja adaptivnosti bežične mreže osjetila temeljene na metaforama i mehanizmima imunološkog sustava. U disertaciji su istražena svojstva bežičnih mreža osjetila s naglaskom na ograničenost resursa i problematiku bežične komunikacije čvorova mreže, kao i metode njihova programiranja. Analizirane su osnovne komponente i mehanizmi imunološkog sustava čovjeka te proučene postojeće implementacije i uporabe umjetnih imunoloških sustava. Definiran je model bežične mreže osjetila temeljen na strukturi i funkciji, te homeostazi kao načinu njihova održavanja. Na osnovu predloženog modela definiran je mehanizam samo organizacije i samo prilagodbe bežične mreže osjetila zasnovan na apstrakcijama i mehanizmima imunološke mreže. Analizirana su svojstva predloženog mehanizma s obzirom na svojstva organizacije, prilagodljivosti, robusnosti i skalabilnosti. Izvedena je implementacija sustava za platformu TinyOS i ispitan njen rad u simulatoru.

Abstract (english)

This thesis investigates the prospect of realising wireless sensor network adaptability based on metaphors and mechanisms of immune system. The thesis investigates various wireless sensor network properties primarily focusing on resource constraints and issues related to inter-node wireless communication, as well as existing methods of their programming. Analysis of basic components and mechanisms of human immune system was conducted, accompanied with the survey of existing implementations and applications of artificial immune systems. Wireless sensor network model was defined with structure and function as its building blocks, along with homeostasis as a mean of structure and function preservation. With respect to the proposed model an immune system based mechanism has been defined in order to provide properties of self-organisation and self-adaptation to the wireless sensor network. Analysis of the proposed mechanism has been conducted with respect to desired properties of self-organization, adaptability, robustness and scalability. A TinyOS based version of the system was implemented and tested in a simulator.

• Keywords: Bežične mreže osjetila; umjetni imunološki sustav; samo organizacija; adaptivni sustavi; izviruće ponašanje; homeostaza; simulacija
• Keywords (english): Wireless sensor networks; artificial immune system; self-organisation; adaptive systems; emergent behaviour; homeostasis; simulation
• Language: croatian
• URN:NBN: urn:nbn:hr:168:796402
• Study programme: Title: Computer Science; Study programme type: university; Study level: postgraduate; Academic / professional title: Doktor znanosti (Doktor znanosti)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-07-17 11:03:23