Search results for "590"
showing 10 items of 644 documents
Non-contractual churn prediction using Hierarchical Temporal Memory
2018
Master's thesis Information- and communication technology IKT590 - University of Agder 2018 As markets become more saturated and industry leaders compete over the existing customer base, competitors look for ways to improve customer retention with their customers. It is considered much more expensive to gain a new customer than retaining one, so the industry leaders look for ways in which churn in a customer can be predicted and potentially be avoided by incentivizing the customer to stay. Several of the previously proposed approaches struggle with combining the linearity with the non-linearity that exist within churn analysis and prediction. This emphasizes the need for research into state…
Neuroevolution of Actively Controlled Virtual Characters
2017
Master's thesis Information- and communication technology IKT590 - University of Agder 2017 Physics-based character animation offer an attractive alternative to traditional animation techniques, however, physics-based approaches often struggle to incorporate active user control of these characters. This thesis suggests a different approach to the problem of actively controlled virtual characters. The proposed solution takes a neuroevolutionary approach, using HyperNEAT to evolve neural controllers for a simulated eight-legged character, a previously untested character morphology for this algorithm. Using these controllers this thesis aims to evaluate the robustness and responsiveness of a c…
Imitation Accelerated Q-learning on a Simulated Formula Student Driverless Racecar
2020
Master's thesis in Information- and communication technology (IKT590) In the international Formula Student competition, only a handful compete in the driverless category. Most of them using expensive hardware such as LIDAR’s. By leveraging reinforcement learning, a cheaper camera based system can be created .In order to train this system a simulator based on a fork of Microsoft’s AirSim by Formula Technion was used. A virtual replica of a Formula Student car designed for 2020 by Align Racing UiA, functioned as the test vehicle. In order to decrease the required training time, a pre-trained imitation learning network was used. This was implemented into a Deep Q-Learning network in four diffe…
User centered design of an emergency support solution for horseback riders
2021
Master's thesis in Information- and communication technology (IKT590) As horseback riding has become increasingly popular, and is such a dangerous sport, there is a need for an emergency support solution for horseback riders that can help themget the assistance they require in time. In order to design such a solution, firstly, the design aspects that should be considered for implementation were identified through a user research performed on expert horseback riders. The user research proved that there is a need for such a solution and highlighted the importance of involving potential users in the design process of an emergency support solution. From the feedback that was obtained, it was de…
A DEEP LEARNING SEGMENTATION APPROACH FOR AUTOMATIC INVOICE IDENTIFICATION
2019
Master's thesis Information- and communication technology IKT590 - University of Agder 2019 The research on object detection has come a long way and has in recent years become so efficient andreliable that we see many practical applications in simple detection of objects in pictures to advancesegmentation in video recordings. Despite its popularity, there are no de facto approach availableand several methods are competing to be superior.This thesis focuses on object detection in photos where the desired object is letters and numbers, andthe photo is a PDF-file of an invoice without any use of OCR and any knowledge of the layout. Theresearch compares Tensorflow’s Object Detection API with SS…
A Supervised Attention-Based Multiclass Classifier for Tile Discarding in Japanese Mahjong
2021
Master's thesis in Information- and communication technology (IKT590) Japanese Mahjong, an imperfect-information, multiplayer, multi-round game, has become an area of interest for the AI community due to its immense imperfect-information space and complex playing and scoring rules. In 2020 Microsoft unveiled the Mahjong AI Suphx that managed to outdo most of the top human players in Tenhou.net, the most popular platform for Japanese Mahjong. With supervised learning, Suphx’s discard model reached a prediction accuracy of 76.7% when tested on game logs from Tenhou.net. Two recurring problems with state-of-the-art Mahjong AIs, including Suphx, are their heightened architecture complexity and …
A Machine Learning based Prediction Model for Bursty Traffic in 5G mMTC Networks
2019
Master's thesis Information- and communication technology IKT590 - University of Agder 2019 The rapid growth in popularity for the Internet of Things (IoT) has paved the way for a newtype of communication, called Machine-type Communication (MTC), causing substantially in-creased traffic volume. The existing network infrastructure is facing challenges when handlingthe increased traffic load, especially under bursty conditions. Consequently, the network willmore often experience congestion during bursty conditions, which will in turn reduce through-put, and lead to a decline in quality of service.Several improvements have been studied to help support the increasing mMTC traffic load.However, …
A comparison of database systems for rapid search results in large amounts of leaked data
2019
Master's thesis Information- and communication technology IKT590 - University of Agder 2019 A large portion of the information on the Internet is stored in databases, since databases arethe natural place among online services for storage of user information. Hackers occasionallybreach web sites and publish database records online, resulting in personal user informationleaked in the public domain and available for abuse by malicious actors.Several web services offer the opportunity to search in numerous data breaches with as muchas six billion records or more and response times less than one second for each single query.This thesis investigates performance optimization methods that can be ap…
Road Detection as a part of the Reward System for Reinforcement Learning-based Autonomous Cars
2019
Master's thesis Information- and communication technology IKT590 - University of Agder 2019 Human drivers are subject to numerous flaws. It is common that the driversget tired and lose control of the vehicle, and some even get drunk or high, whichresults in dangerous situations for themselves and others.Autonomous driving is a field of study which has gained notoriety lately, as itattempts to get more reliable than humans at driving; Though there is still muchresearch to be done in the field. We are far away from replacing human driverswith safe AI-equivalents.In this thesis, we aim to validate a road detection algorithm as a part of thereward system of the autonomous vehicle1. We introduce…
User-Centered Design and Evaluation of an Augmented Reality-based Decision Support Prototype for Ambulance Workers
2021
Master's thesis in Information- and communication technology (IKT590) Background: The demand for healthcare services is increasing globally, and there is a need for improved, sustainable health services. The Norwegian Ministry of Health and Care Services highlights the need for improved coordination between the various health-care providers to ensure a cohesive patient journey. Ambulance services play an important role in the early phases of the patient journey. There is an increasing demand for per-forming clinical tasks in ambulance services while having limited support. Objective: The main objective of this study is to investigate how technological solutions can increase information avai…