Selaus nimekkeen mukaan kokoelmassa 113 Tietojenkäsittely ja informaatiotieteet
Viitteet 68-87 / 156
-
Effektiv representation av tidsserier för webbapplikationer
(2022)I diplomarbetet diskuteras några metoder för datareduktion av tidsserier i syfte att göra de ofta mycket långa serierna enklare att visualisera i webbläsare. Då en datavisualisering ska vara interaktiv utesluter det ofta ... -
Email classification with limited labeled data
(Åbo Akademi, 2020)In this thesis I evaluate different ways of classifying email messages in the absence of a large number of pre-classified training messages. When using machine learning to classify incoming emails, this lack of pre-labeled ... -
Empowering Interviewer Training : Web application version development report
(2023)This Master's thesis is about the development project of Empowering Interview Training (EIT), specifically its web application version, based on a previous EIT version written in VB.NET. The purpose of EIT is to conduct ... -
Environmental damage assessment based on satellite imagery using machine learning
(Åbo Akademi, 2020)The aim of this thesis is to provide a source of information about damage assessment in forestry using deep learning. A large source of environmental information is provided by satellites imagery. Orbital devices are ... -
Estimating surface areas of mesh objects - A novel approach for signed distance fields
(2022)A tool was developed for surface area estimation of mesh model objects. The tool used signed distance fields together with ray mapping and constructive solid geometry operations to create solids with excluded overlapping ... -
Evaluating fuzzing tools for automated testing of REST APIs using OpenAPI specification
(2023)Web applications and services are widely used today. Security is an important factor since web applications are accessed via the internet. Web services often expose their functionality through web application programming ... -
Evaluating Performance of Generative Models for Time Series Synthesis
(2023)Motivated by successes in the image generation domain, this thesis presents a novel Hybrid VQ-VAE (H-VQ-VAE) approach for generating realistic synthetic time series data with categorical features. The primary motivation ... -
Evaluating the Influence of Character Realism on Avoidance Strategies in VR and a new method to generate virtual crowds using VR and motion capture
(Åbo Akademi, 2020)The MimeTIC team of the IRISA research lab has a long history of studying human behaviours in order to create more natural virtual humans. Multiple studies were done in order to understand how pedestrians avoid each other, ... -
Evaluation of Prediction Models for Smart Oil Filters
(Åbo Akademi, 2019)In this master thesis, different modelling techniques for the remaining useful lifetime (RUL) of oil filter are discussed, implemented and tested. The filter is not only crucial for cleaning the oil, but it also helps ... -
Evaluation of React Native and Flutter for cross-platform mobile application development
(Åbo Akademi, 2020)There is an increasing demand for mobile applications requiring software companies to deliver high-quality products at a fast pace while maintaining reasonable costs. Moreover, an application is often created for multiple ... -
Explainable AI for Multi-agent Control Problem
(2023)This report presents research on the application of policy explanation techniques in the context of coordinated reinforcement learning (CRL) for mobile network optimization. The goal was to improve the interpretability and ... -
Exploratory Studies LAIA@UIB : Al Models for the Detection of Fraudulent Payments
(2023)This thesis investigates the use of AI models for detecting fraudulent payments in electronic payment systems. The main challenges in the development of such models are the lack of labeled data, the need to balance minimizing ... -
Exploratory Studies LAIA@UIB : Pre-trained Natural Language Processing models to respond to domain-specific inputs
(2023)With the rapid development of conversational agents, there is a need to create models that can understand human requests and respond effectively to them. This thesis explores the process of fine-tuning a pre-trained BLOOM ... -
Exploring GitOps for Smaller-Scale Applications
(2024)This thesis explores the application of GitOps principles beyond the Kubernetes ecosystem, specifically focusing on the potential usage in smaller-scale applications. The primary objective is to find out the viability of ... -
FinOps : Monitoring and Controlling GCP costs
(2023)Cloud computing has gained significant popularity in today’s digital landscape, with companies relying on cloud-based solutions to manage their data, applications, and infrastructure. The cloud offers several advantages, ... -
Flexible recurrent neural network for Audio-Visual sequence analysis
(Åbo Akademi, 2020)Embargo until 25.8.2024 -
Football Match Prediction Using Machine Learning
(2023)Football is the most popular sport in the world. It has become so popular since it is easy to play and affordable. Football can be played both inside and outside almost at any place in the world and little equipment is ... -
FRAMEWORKS FOR CENTRALIZED AUTHENTICATION AND AUTHORIZATION
(Åbo Akademi, 2020)A commonly used method of authentication on the Internet is to provide a combination of a username and a password. One way to make this method more secure is to have long passwords. Single sign-on solutions have led to ... -
Fuzzy logic and unmanned surface vehicles : Implementing collision avoidance in Python
(Åbo Akademi, 2018)Autonomous vessels could potentially lower the costs of maritime shipping, by reducing the operating costs and increasing the safety. However, one of the greater challenges in the pursuit of completely autonomous and ...