Göm meny

Framläggning av examensarbeten / Thesis presentations


WExUpp - kommande framläggningar
2017-05-30 - Datorseende
Navigability Assessment for Autonomous Systems Using Deep Neural Networks
Ebba Wimby Schmidt
Avancerad (30hp)
kl 14:15, Transformen (På svenska)
2017-05-31 - Elektroniska kretsar och system
Mot en ljusare framtid - Ett examensarbete rörande närvaromätningar i skollokaler och energieffektivisering genom belysningsstyrning och utbyte av belysningssystem
Erik Muncker
Grundnivå (16hp)
kl 12:30, Nollstället (På svenska)
2017-06-01 - Informationskodning
Augmented Reality and an Inside-Object-View Concept
David Lindqvist
Avancerad (30hp)
kl 10:00, Algoritmen (In English)
2017-06-01 - Reglerteknik
Model-Based Design of a Fork Control System in Very Narrow Aisle Forklifts
Erik Bodin, Henric Davidsson
Avancerad (30hp)
kl 15:15, Algoritmen (På svenska)
2017-06-02 - Reglerteknik
Wheel Brake Noise Analysis
Teodor Hamnholm Löfgren
Avancerad (30hp)
kl 10:00, (In English)
2017-06-02 - Reglerteknik
Lateral Tire-Road Friction Estimation during Dynamic Driving
Jesper Otterholm
Avancerad (30hp)
kl 11:00, Transformen (In English)
2017-06-05 - Kommunikationssystem
Network-Based Positioning Using Last Visited Cells Report
Tor Olofsson
Avancerad (30hp)
kl 11:15, Systemet (In English)
2017-06-05 - Datorseende
Automatic Segmentation of Knee Cartilage Using Quantitative MRI Data
Marcus Lind
Avancerad (30hp)
kl 13:15, Algoritmen (På svenska)
2017-06-07 - Datorseende
Automatic Detection and Classification of Permanent and Non-Permanent Skin Marks
Armand Moulis
Avancerad (30hp)
kl 13:30, Algoritmen (På svenska)
[Abstract]
When forensic examiners try to identify the perpetrator of a felony, they use individual
facial marks when comparing the suspect with the perpetrator. Facial
marks are often used for identification and they are nowadays found manually.
To speed up this process, it is desired to detect interesting facial marks automatically.
This master thesis describes a method to automatically detect and separate
permanent and non-permanent marks. It uses a fast radial symmetry algorithm
as a core element in the mark detector. After candidate skin mark extraction,
the false detections are removed depending on their size, shape and number of
hair pixels. The classification of the skin marks is done with a support vector
machine and the different features are examined. The results show that the facial
mark detector has a good recall value while the precision is poor. The elimination
methods of false detection were analysed as well as the different features for the
classifier. One can conclude that the color of facial marks is more relevant than
the structure when classifying them into permanent and non-permanent marks.
2017-06-07 - Datorseende
Visual Tracking with Deformable Continuous Convolution Operators
Joakim Johnander
Avancerad (30hp)
kl 14:30, Transformen (In English)
[Abstract]
Visual Object Tracking is the computer vision problem of estimating a target trajectory
in a video given only its initial state. A visual tracker often acts as a component in the
intelligent vision systems seen in for instance surveillance, autonomous vehicles or robots,
and unmanned aerial vehicles. Applications may require robust tracking performance
on difficult sequences depicting targets undergoing large changes in appearance, while
enforcing a real-time constraint.
Discriminative correlation filters have shown promising tracking performance in re-
cent years, and continuously improved state-of-the-art. With the advent of deep learning,
new robust features have improved tracking performance considerably. However, meth-
ods based on discriminative correlation filters learn a rigid template describing the target
appearance. This implies an assumption of target rigidity which is not fulfilled in practice.
This thesis introduces an approach which integrates deformability into a state-of-the-art
tracker. The approach is thoroughly tested on three challenging visual tracking bench-
mark, achieving state-of-the-art performance.
2017-06-07 - Datorseende
Data-Efficient Transfer Learning with Pre-Trained Networks
Dennis Lundström
Avancerad (30hp)
kl 15:15, Algoritmen (In English)
[Abstract]
Deep learning has dominated the computer vision field since 2012, but a common
criticism of deep learning methods is their dependence on large amounts
of data. To combat this criticism research into data-efficient deep learning is
growing. The foremost success in data-efficient deep learning is transfer learning
with networks pre-trained on the ImageNet dataset. Pre-trained networks
have achieved state-of-the-art performance on many tasks. We consider the pretrained
network method for a new task where we have to collect the data. We
hypothesize that the data efficiency of pre-trained networks can be improved
through informed data collection. After exhaustive experiments on CaffeNet and
VGG16, we conclude that the data efficiency indeed can be improved. Furthermore,
we investigate an alternative approach to data-efficient learning, namely
adding domain knowledge in the form a spatial transformer to the pre-trained
networks. We find that spatial transformers are difficult to train and seem to not
improve data efficiency.
2017-06-07 - Kommunikationssystem
A Study on Segmentation for Ultra-Reliable Low-Latency Communications
Linnea Faxén
Avancerad (30hp)
kl 16:00, Systemet (In English)
[Abstract]
To enable wireless control of factories, such that sensor measurements can be sent wirelessly to an actuator, the probability to receive data correctly must be very high and the time it takes to the deliver the data from the sensor to the actuator must be very low. Earlier, these requirements have only been met by cables, but in the fifth generation mobile network this is one of the imagined use cases and work is undergoing to create a system capable of wireless control of factories. One of the problems in this scenario is when all data in a packet cannot be sent in one transmission and ensure the very high probability of reception. This thesis studies this problem in detail by proposing methods to cope with the problem and evaluating these methods in a simulator.

The thesis shows that splitting the data into multiple segments and transmit- ting each at an even higher probability of reception is a good candidate, especially when there is time for a retransmission. When there is only one transmission available, a better candidate is to send the same packet twice. Even if the first packet cannot achieve the very high probability of reception, the combination of the first and second packet might be able to.
2017-06-09 - Kommunikationssystem
Hiding in a Social Network
Olle Abrahamsson
Avancerad (30hp)
kl 09:00, Algoritmen (På svenska)
2017-06-09 - Kommunikationssystem
Performance Assessment of Massive MIMO Systems for Positioning and Tracking in Open Highways
Markus Petersson
Avancerad (30hp)
kl 10:15, Algoritmen (In English)
2017-06-09 - Kommunikationssystem
On Social Choice in Social Networks
Ema Becirovic
Avancerad (30hp)
kl 13:15, Systemet (In English)
2017-06-09 - Reglerteknik
Modelling and Control of a Forklift’s Hydraulic Lowering Function
Daniel Fahlén, Ludvig Fri
Avancerad (30hp)
kl 13:15, Transformen (In English)
2017-06-09 - Informationskodning
Performance and Comparison of Post-Quantum Cryptographic Algorithms
Vladimir Valyukh
Avancerad (30hp)
kl 15:00, Systemet (In English)
[Abstract]
Secure and reliable communication have always been critical part of todays infrastructure. Various asymmetric encryption schemes, such as RSA, have been used to achieve this goal. However, with advancements in quantum computing, current encryption schemes are becoming more vulnerable since they are weak to certain quantum attacks, such as Shor’s Algorithm. Therefore demand for post-quantum cryptography (PQC), which is not vulnerable to quantum attacks, is apparent. This work’s goal is to evaluate and compare PQC algorithms.

Studerandeexpedition

ISYs studerandeexpedition hittar ni i B-huset, bredvid Café Java, dvs. D-korridoren, ingång 27.

Öppettider:
Terminstid Måndag, onsdag och torsdag 12:30-13:15
Telefon: 013-281321, vardagar
Frågor som rör examensarbeten -> exjobb@isy.liu.se

Studiehandboken

Mer information om grundutbildningen kan fås i studiehandboken.

Framläggning av examensarbeten, ISY.

Säkerhetsinformation

Viktig information om säkerheten vid LiU.
Åtgärder vid brand.


Informationsansvarig: Exjobbsansvarig
Senast uppdaterad: 2016-02-02