Hide menu

Examensarbeten och uppsatser / Final Theses

Framläggningar på IDA / Presentations at IDA

Se även framläggningar annonserade hos ISY och ITN i Norrköping / See also presentations announced at ISY and ITN in Norrköping (in Swedish)

If nothing is stated about the presentation language then the presentation is in Swedish.

WExUpp - kommande framläggningar
2019-03-26 - AIICS
Lärande av beteendeträd för simulerade stridspiloter i spaningsuppdrag
Pernilla Eilert
Avancerad (30hp)
kl 13:15, Herbert Simon (På svenska)
Fighter pilots often find themselves in situations where they need to make quick decisions. Therefore an intelligent decision support system that suggests how the fighter
pilot should act in a specific situation is vital. The aim of this project is to investigate and evaluate grammatical evolution paired with behaviour trees to develop a decision
support system. This support system should control a simulated fighter pilot during an airborne reconnaissance mission. This thesis evaluates the complexity of the evolved trees and the performance, and robustness of the algorithm. Key factors were identified for a successful system: scenario, fitness function, initialisation technique and control parameters. The used techniques were decided based on increasing performance of the algorithm and decreasing complexity of the tree structures. The initialisation technique, the genetic operators and the selection functions performed well but the fitness function needed more work. Most of the experiments resulted in local maxima. A desired solution could only be found if the initial population contained an individual with a BT succeeding the mission. However, the implementation behaved as expected. More and longer simulations are needed to draw a conclusion of the performance based on robustness, when testing the evolved BT:s on different scenarios. Several methods were studied to decrease the complexity of the trees and the experiments showed a promising variation of complexity through the generations when the best fitness was fixed. A feature was added to the algorithm, to promote lower complexity when equal fitness value. The results were poor and implied that pruning would be a better fit after the simulations. Nevertheless, this thesis suggests that it is suitable to implement a decision support system based on grammatical evolution paired with behaviour trees as framework.
2019-03-26 - HCS
A Detailed Analysis of Semantic Dependency Parsing with Deep Neural Networks
Daniel Roxbo
Avancerad (30hp)
kl 15:15, John Von Neumann (In English)
2019-03-29 - SaS
Ett blockkedjebaserat spårbarhetssytem i en försörjningskedja - En fallstudie hos IKEA
Claes Lööf, Tobias Sund
Avancerad (30hp)
kl 10:15, Donald Knuth (På svenska)
Traceability in global supply chains is a complicated problem. Current solutions for achieving
traceability are expensive or imperfect, and give rise to organizational and trust-related
issues. Blockchain could present itself as a solution to many of these issues. IKEA Supply
Chain is large and complex, and analyzing their information flow resulted in various load
requirements depending on the delay bound, which is defined as a constraint that specifies
the maximum allowed delay for a transaction to be processed and finalized by a system. A
delay bound of five minutes resulted in a load of 5 546 events per second. Through interviews
with personnel at IKEA, 13 requirements were identified and included in the system
design. A system was designed that consists of six components, a client application, a controller,
a smart contract pool, IPFS, Quorum and the smart contracts. In order to reduce the
potential load on the system, certain optimization measures were taken. The system design
resulted in a load requirement of 13 707 for a delay bound of five minutes. The resulting
performance of the developed system revealed itself to be a throughput of 159 tps and a
convergence time of 4.71 seconds, which is not enough to reach the requirement. However,
a solution to divide the network in to many smaller networks that together can produce
the necessary throughput is proposed.

Page responsible: Ola Leifler
Last updated: 2017-04-27