Filtyp
In this paper we study two major challenges in few-shot bioacoustic event detection: variable event lengths and false-positives. We use prototypical networks where the embedding function is trained using a multi-label sound event detection model instead of using episodic training as the proxy task on the provided training dataset. This is motivated by polyphonic sound events being present in the b
Background: Intermediate care is often defined as healthcare occurring somewhere between traditional primary (community) and secondary (hospital) care settings. High quality intermediate care is important in dementia, may prevent caregiver burnout and also lead to optimal care for people with dementia. However, very little is known about the point of intermediate care for persons with dementia in
Evaluating the structure of soil prior to building construction is valuable in a large variety of geotechnical and civil engineering applications. To built an effective framework for assessing the strength of the stabilised soil, the presented workflow includes a complex approach of simplex lattice design and X-ray diffraction for the analysis of soil structure. Different from the traditional in s
Mental health problems often appear at a young age. As the labour market places higher demands for education and competence, mental health services are focusing on young adults’ support needs for school and career opportunities. This study is a single case of an integrated supported education and employment unit in Sweden over an 18-month period. Multiple data sources illustrate the process of sup
This work explores the use of reinforcement learning to design a proactive cloud resource auto-scaler that is able to predict usage across a distributed microservice application. The focus is on serving time-sensitive workloads, e.g., industrial automation, connected XR/VR (eXtended Reality/Virtual Reality), etc., where each job has a deadline and there is some cost associated with missing a deadl
In this paper, we extend the control contraction metrics (CCM) approach, which was originally proposed for the universal tracking control of nonlinear systems, to those that evolves on Lie groups. Our idea is to view the manifold as a constrained set that is embedded in Euclidean space, and then propose the sufficient conditions for the existence of a CCM and the associated controller design. Nota
How colour polymorphisms are maintained in natural populations constitutes a key subject of study for evolutionary ecologists. One of the mechanisms that has been put forward to explain this phenomenon is negative frequency-dependent selection, which can be caused by different mechanisms. Among these mechanisms is mate choice, or the selection as a potential mate of the rare or dissimilar colour m
Introduction: Patients with substantial comorbidity burden are underrepresented in clinical trials on endovascular thrombectomy (EVT), despite being common in clinical routine care. Therefore, analysis of observational data is needed to evaluate how increasing comorbidity burden affects procedural success rate, complication rate, and clinical outcome following EVT. Patients and methods: We conduct
External quality assessment (EQA) schemes for pathology are essential, yet large/international programmes do not assess morphology-based biomarkers or address local/regional needs. This study outlines bottom-up initiated, flexible Swedish Digital Pathology EQA rounds for breast pathology, and presents results from the 2021 and 2023 rounds. Six breast carcinoma cases were selected for each EQA roun
Children with cancer experience recurring hospitalizations and isolation during treatment, which affect their school attendance. This study explores experiences of children with cancer, their classmates, and teachers with using the telepresence robot as a learning mediator in the hybrid classroom during treatment periods. 31 children with cancer (aged 7–17 years), 30 teachers, and 118 classmates p
Introduction: Commissioning, calibration, and quality control procedures for nuclear medicine imaging systems are typically performed using hollow containers filled with radionuclide solutions. This leads to multiple sources of uncertainty, many of which can be overcome by using traceable, sealed, long-lived surrogate sources containing a radionuclide of comparable energies and emission probabilit
Chest computed tomography (CT) imaging with the use of an artificial intelligence (AI) analysis program has been helpful for the rapid evaluation of large numbers of patients during the COVID-19 pandemic. We have previously demonstrated that adults with COVID-19 infection with high-risk obstructive sleep apnea (OSA) have poorer clinical outcomes than COVID-19 patients with low-risk OSA. In the cur
The formation of platoons, where groups of vehicles follow each other at close distances, has the potential to increase road capacity. In this paper, a decentralized control approach is presented that extends the well-known constant headway vehicle following approach to the two-dimensional case, i.e., lateral control is included in addition to the longitudinal control. The presented control scheme
Task 3.1 in Work Package (WP) 3 of the CULTIVATE project aims to investigate costs, investments, challenges, drivers, and success factors to establish and maintain urban and peri-urban food sharing initiatives (FSIs). This investigation builds on the conceptual framework, which has been developed from a systematic literature review on the topic of food sharing and enriched with topics from several
This thesis embarks on a journey in the advancement of urban traffic management, centering around the innovative integration of Autonomous Intersection Management (AIM) systems. The research encompasses a comprehensive exploration of various facets of AIM implementation, significantly contributing to the evolution of a more efficient and safer urban transport system.The research investigates the d
This study investigated the applicability and performance of a hydrological model (namely FLEXG) for simulating streamflow in boreal catchment, exemplified by the representative Krycklan catchment. The FLEXG simulated daily streamflow for the whole catchment and its sub-catchments. The Kling-Gupta Efficiency (KGE) and Nash-Sutcliffe Efficiency (NSE) demonstrated favorable model performance during
