Filetype
Objective Image Quality Assessment (IQA) is crucial for evaluating and ensuring the fidelity of images. Traditional human-based evaluations, although reliable, are impractical due to their cost and slow pace, combined with subjective inconsistencies. This thesis aims to address these issues by developing a test and quality bench for Bertin Exensor's dual-head camera, integrating both infrared
The High Luminosity-Large Hadron Collider (HL-LHC) will reach an approximate pile-up of 200 collisions per bunch crossing, ten times more than the current Large Hadron Collider. Beginning operation at the end of the decade, it will accumulate 3000 fb−1, increasing the chances of observing new processes and allowing measurement of rare processes with higher precision. Moreover, the pile-up increase
Arabica coffee production in Africa has declined significantly over the last half century, partly due to Coffee Berry Disease (CBD), caused by the fungus Colletotrichum kahawae. This disease results in substantial economic losses, estimated at USD 350- 500 million annually. Recent advancements in machine learning (ML) and computer vision offer powerful tools for disease detection. However, annotat
Understanding the pH sensitivity of proteins and enzymes across intracellular compartments is crucial for fundamental research. Lizatović et al. [1] aimed to design a peptide incorporating a specific amino acid to form a hexamer structure and lacking it to form a pentamer structure. Unexpectedly, two distinct structures emerged based on pH. At pH 6, a hexamer structure formed, albeit with a surpri
Atrial fibrillation (AF) is an arrhythmia distinguished by irregular heartbeats, which has seen a significant rise in prevalence globally. Due to the risk of strokes, the condition necessitates early detection and intervention to prevent severe complications, highlighting the critical role of early and precise detection techniques. To effectively train and validate machine learning (ML) models, ha
This thesis details the development, implementation, and optimization of a local microservice designed to enhance invoice processing at Hulo, a company that manages au- tomatic payment invoices. This is conducted through Artificial Intelligence (AI) and Machine Learning (ML) techniques, focusing particularly on Computer Vision and Object- detection. Motivated by the need to address the inefficienc
Favouring good soil health is pivotal for ensuring long term agricultural production by minimizing erosion, increasing soil carbon content, increasing the soil water holding capacity and decreasing the soil bulk density. Certain land management practices can disfavour factors for soil health and in-extent lead to soil degradation which can threaten food production and natural habitats. Soil organi
Thanks to the ever-increasing computational power, machine learning has become a staple in computer science. Many computer vision methods have become so reliable that their implementation in the surveillance industry is now the de facto standard for many object detection and classification tasks. The use of machine learning for surveillance is not confined to images and videos, however, it is also
Aims and methods: This study examines the discourse surrounding honour-related violence and oppression, referred to as honour violence. A discourse analysis was conducted on material from the state and organisations working with HRVF, collaborating with midwives. Two in-depth interviews with midwives gathered firsthand experiences from professionals encountering potential victims of honour violenc
Den påtagliga betydelsen av klimatfrågor framträder i allt högre grad. Byggsektorn har en betydande inverkan på klimatet genom sin resursanvändning och avfallsgenerering, vilket tydligt framgår då sektorn står för en tredjedel av Sveriges totala avfallsgenerering. Trä har för närvarande en låg resurseffektivitet och värdet hos materialet utnyttjas inte till sitt fullo. Den omfattande förbrukningenThe tangible significance of climate issues is increasingly evident. The construction sector significantly impacts the climate through resource utilization and waste generation, as is evidenced by the sector's contribution to one-third of Sweden's total waste generation. The current situation shows that wood exhibits low resource efficiency, with its value not fully exploited. The extensiv
This thesis investigates the effectiveness of step size control in the numerical simulation of Stochastic Differential Equations (SDEs). The study is divided into a theoretical exploration and a series of numerical experiments. The theoretical section introduces key definitions and theorems, delves into the properties of Brownian motion, and examines the conditions under which solutions to SDEs ca
Free-electron lasers are capable of producing high-quality radiation in a wide wavelength range and at very high power and brilliance. To reach improved performance especially regarding coherence, bandwidth and wavelength stability, different seeding techniques are often required. However, a successful implementation of seeding typically demands a very high-quality electron beam, in terms of energ
DEBATT. Vi bör undvika att kalla naturfenomen och väderhändelser för sådant som ”100-årsregn”, ”50-årsflöden” och liknande – det lägger grund för missförstånd om hur man bedömer riskerna, skriver forskarna Johanna Sörensen och Rolf Larsson, LTH.
Learning semantic-rich representations from raw unlabeled time series data is critical for downstream tasks such as classification and forecasting. Contrastive learning has recently shown its promising representation learning capability in the absence of expert annotations. However, existing contrastive approaches generally treat each instance independently, which leads to false negative pairs tha
In the realm of cloud computing, the prevalence of intra-phase congestion due to concurrent periodic requests from a multitude of clients frequently results in heightened resource consumption, elongated queuing times, and prolonged response durations. To tackle these challenges, this paper presents a groundbreaking 'Adaptive Out-of-Phase Scheduling' technique, utilizing a server-side PID controlle
Tracing the events surrounding the 1909 general strike (storstrejken), this article explores the role of a network of People’s Parks and People’s Houses, since the early 1890s established by the labour movement to counterweight the difficulties of ensuring stable meeting spaces. As regional and local authorities during the 1909 strike banned striking workers to access many public spaces and condit
