Filtyp
This thesis explores advancements in Automatic Speaker Verification (ASV) by examining the impact of multiple speaker enrollments and introducing Adaptive Neural Probabilistic Linear Discriminant Analysis (Adaptive NPLDA). Modern ASV combines front-end feature extraction, using state-of-the-art methods based on Deep Neural Networks (DNNs), such as the ReDimNet architectures, with back-end modeling
This thesis presents a pipeline for automated object identification and dot based annotation in User Generated Content (UGC) images. The need for this type of model is motivated by IKEA’s digital product ”Content Recommendations” which aims to enhance customer engagement through shoppable UGC images and addresses the challenge of detecting specific products in various, real-world visual contexts.
With the rapid advancement of urban renewal and the shift toward sustainable development, the integration of Transit-Oriented Development (TOD) and industrial heritage preservation has become a key strategy in revitalizing post-industrial cities. Rather than viewing industrial heritage sites as obsolete, new approaches now emphasize their adaptive reuse within the framework of transit-accessible,
Title: Design and Development of a Digital RAM Tool for AUVs Authors: Oscar Cedell and Jacob Persson Supervisors: Johan Marklund (LTH), Gustav Rehnborg (Saab Naval), and Niklas Blomgren (Saab Naval) Problem description: Autonomous underwater vehicles (AUVs) are longlife, mission-critical systems for which life cycle cost is strongly affected by Reliability, Availability, and Maintainability (RA
Cleanrooms in the pharmaceutical industry are energy-intensive environments where HVAC systems account for roughly 50-75% of energy use due to high air changes per hour and strict conditioning requirements for indoor humidity and temperature. This thesis presents a techno-economic analysis comparing two of the most common HVAC system types. These systems are centralized, using one large AHU to pro
The assessment of sunlight access in buildings is constrained by methods that rely on simplified point-based evaluation. EN 17037 sunlight exposure evaluates sunlight at a single point on the aperture under restricted temporal conditions. This limits the representation of how sunlight interacts with the aperture over time. These characteristics reduce its applicability at early design stages. The
This project investigates the barriers and opportunities of institutionalizing wellbeing metrics by examining how actors across different scales understand and use wellbeing data generated through the Nova Scotia Quality of Life (NSQoL) Survey. The NSQoL Survey is administered by a non-profit organization, Engage Nova Scotia, and includes 200+ questions measuring a broad range of wellbeing dimensi
Financial markets exhibit time-varying volatility and cross-asset correlation. To construct and optimize a risk-adjusted portfolio and account for underlying collinearity between se- curities, a good understanding of these two dynamics is important. In this study global equity indices are modeled with the purpose of improving the forecasting accuracy of time-varying correlations, as well as distin
From Concepts to Action: Building on the foundational work of our 2025 workshop, this second edition shifts from exploring what sustainability means in HRI to producing actionable outcomes for the community. Last year, we identified strong but often unacknowledged engagement with social and environmental sustainability, alongside gaps in shared language and practical frameworks. This year, we focu
Externally bonded reinforcement (EBR) was used to increase load bearing capacity of light weight aggregate concrete (LWA) masonry walls subjected to eccentric axial compression. Ladder type masonry reinforcement, high strength steel wire strips and glass fiber mesh were used for strengthening of eleven, 2.4 m high, 0.5 m long and 0.1 m thick walls. The reinforcement was applied on the dry wall sur
The ability to generate and control movement is essential for human interactions and overall well-being. Neuromuscular impairment caused by neurological injuries and diseases, such as stroke or limb amputation, severely limits the ability of affected individuals to interact with the surrounding environment, necessitating advanced strategies for rehabilitation and restoration of motor function. Vol
Although political governance guides education and research, there are options for researchers, educators and curators to act in the spirit of academic freedom. The deontological ethical guidelines stabilize the archaeological establishment no matter what kind of work. The utilitarian dimensions within archaeological research and higher education open up for critical thinking.Twisting and turning,
We introduce a novel method for extracting a fragmentation model directly from experimental data without requiring an explicit parametric form, called Histories and Observables for Monte-Carlo Event Reweighting (HOMER), consisting of three steps: the training of a classifier between simulation and data, the inference of single fragmentation weights, and the calculation of the weight for the full h
Indoor sensing is challenging because of the multi-bounce effect, spherical wavefront, and spatial nonstationarity (SNS) of the near-field effect. This paper addresses radio-based environment sensing considering these issues. Specifically, graph theory (GT) is used to model the multi-bounce propagation of the near field. In this manner, indoor reflectors/scatterers are modeled as vertices in a pro
Losses and damages from climate change are not just a future risk but already a present reality, and “Loss and Damage” (L&D) as a policy domain has been formalised under the United Nations Framework Convention on Climate Change (UNFCCC), alongside mitigation and adaptation. While climate services currently provide strong support for adaptation and disaster recovery, here we propose that an exp
The revised Payment Services Directive (PSD2) is reshaping traditional banking by requiring banks to grant licensed third-party providers (TPPs) access to customer data. This paper explores PSD2’s impact on Fintech market entry, assessing both opportunities and ongoing structural barriers. Through a qualitative investigation, it identifies key barriers such as API standardization gaps, data access
