Mid Sweden University
Not a member yet
15329 research outputs found
Sort by
AdVision : An efficient and effective deep learning based advertisement detector for printed media
No full textAutomated advertisement detection in newspapers is a challenging task due to the diversity in print layouts, formats, and design styles. This task has critical applications in media monitoring, content analysis, and advertising analytics. To address these challenges, we introduce AdVision, a deep-learning-based solution that treats advertisements as unique visual objects. We provide a comparative study of various detection architectures, including one-stage, two-stage, and transformer-based detectors, to identify the most effective approach for detecting advertisements. Our results are validated through extensive experiments conducted under different conditions and metrics. Newspapers from four different countries - Denmark, Norway, Sweden, and the UK - were selected to demonstrate the variety of languages and print formats. Additionally, we conduct a cross-analysis to show how training on one language can generalize to another. To enhance the explainability of our results, we employ GradCAM++ (Chattopadhay et al., 2018) heatmaps. Our experiments demonstrate that the YOLOv8 model achieves superior performance, balancing high precision and recall with minimal inference latency, making it particularly suitable for high-throughput advertisement detection
Approaching persistent pain and emotion dysregulation
No full textBackground Persistent pain, one of the most common reasons for suffering and health care seeking, often co-occurs with emotional problems such as depression and anxiety. Within the Center for Health and Medical Psychology at & Ouml;rebro University, Sweden, we have developed a new treatment aimed at addressing co-occurring persistent pain and emotional problems: hybrid emotion-focused exposure treatment. The overarching idea behind the treatment is that patients who struggle with comorbid pain and emotional problems need to develop skills in dealing with emotions as well as pain. With better skills in tolerating and soothing difficult emotions, patients will be more able to approach previously avoided stimuli and situations, such as movements, activities and social interaction.Objectives This review aims to delineate the development of the hybrid emotion-focused exposure treatment. It begins by outlining the theoretical background, then proceeds to describe the techniques, discuss the evidence and conclude with an illustrative case example.ResultsThus far, the treatment has been tested in a single-case study and a randomized controlled trial with promising outcomes. Overall, the hybrid treatment seems to have a good effect on patients' depressive symptoms and pain interference. The treatment is currently being implemented, and the implementation process evaluated, in primary and specialist care across Sweden.ConclusionsThe hybrid emotion-focused exposure treatment seems to be a well-suited treatment for people with a high burden of persistent pain and emotional difficulties. There is good reason to implement the treatment in clinical practice and continue evaluating treatment effects across different contexts.
Unravelling sources of fecal pollution in oligotrophic mountain waters : Integrating Escherichia coli enumeration, microbial source tracking, and eDNA analysis
No full textAquatic ecosystems in mountainous regions are crucial for fulfilling natural and anthropogenic water demands around the world. This study integrates Escherichia coli (E. coli) enumeration, microbial source tracking (MST), and environmental DNA (eDNA) analysis to identify sources of fecal contamination in oligotrophic mountain waters. Conducted in an area with intense tourism and traditional reindeer herding, this research addresses the urgent need to identify fecal pollution sources to safeguard the water quality of these vital ecosystems. Our study reveals that E. coli levels vary significantly across different locations and times, suggesting varied sources of contamination from humans, wildlife, and livestock animals. MST techniques, alongside eDNA analysis, provided insights into the complex patterns of fecal pollution, allowing for the distinction between human and animal contributions to water contamination. Our findings highlight the importance of combining various analytical methods to track fecal pollution sources effectively, and to develop targeted strategies for water quality management
Improved salp swarm algorithm-driven deep CNN for brain tumor analysis
No full textThe efficiency of the swarm-based approach depends on the perfect balance of operators: exploration and exploitation. Due to a lack of balance between these two factors, the Salp Swarm Algorithm (SSA), a recently developed swarm-based metaheuristic approach, suffers from confined minima, stuck and untimely premature convergence. This paper introduces a new, improvised hybrid SSA named Local Search SSA (LS-SSA) to address the pitfalls associated with standard SSA. To prove the competency of the suggested LS-SSA, it is assessed over the twenty-eight functions suite of IEEE-CEC-2017 relating to a diverse set of contemporary methods. Furthermore, a sequence of non-parametric assessments was conducted to establish the statistical significance of the proposed LS-SSA. As a weak exploitation strength for neighbor exploration, SSA may result in less refined parameter tuning of CNN for healthcare-based medical imaging. Hence, LS-SSA is an effective algorithm for hyperparameter tuning of CNNs evaluated on medical imaging datasets, specifically brain MRI. This leads to improved model performance, characterized by higher accuracy, reduced standard deviation, lower minimum RMSE values, and higher average performance. Consequently, optimal candidate solutions with improved and faster convergence toward global optima are achieved.
Role of lithium-ion batteries in microgrid system
No full textMicrogrid systems are a beneficial alternative to decentralized power grids that can provide greener and high quality power with greater efficiency. Use of lithium-ion batteries (LIBs) in the microgrid systems has rapidly gained attention because of their remarkable energy density, durability, and performance characteristics. This paper explores the advantages of using LIBs in microgrid systems including energy storage, load adjustment, and peak shaving, and examines their advantages: high energy efficiency, less carbon footprint, and superior reliability and resilience. Furthermore, the discussion on challenges associated with the use of LIBs in microgrid systems such as cost, safety and need for maintenance and monitoring. The study has also discussed the importance of numerous artificial intelligence (AI) techniques for battery management. In order to create more resilient and sustainable energy systems, this paper emphasizes the significant interest in and promise of LIBs in microgrid systems.
Effect of climate change on hygrothermal performance of timber framed wall with different insulation materials
No full textClimate change, energy consumption, and carbon footprint goals pose challenges for the hygrothermal performance of Nordic building structures. Residential buildings in Finland, designed to last up to 100 years, must perform well under not only the current but also future climate conditions. Realized carbon emissions align with the RCP8.5 scenario predict a temperature rise of over 4 °C by 2100, resulting also in much higher moisture loads for buildings. This study validated numerical models with data from five insulation assemblies to assess their hygrothermal performance and mould growth under future climate conditions. Measurements conducted in a climate cabin over a 70-day period showed strong alignment with simulations. Using Finnish Moisture Design Years (MDYs) for various future climate scenarios, we found the critical point at the exterior side of the interior sheeting gypsum board. Mineral wool insulation inside the vapour barrier performed poorly under increased humidity, while organic insulations showed markedly better performance. Mould growth on tested organic insulations was predicted only in the RCP8.5 2080 scenario. Based on the studied options, optimal structures may combine linen or wood fibre inside and mineral wool outside the vapour barrier, with gypsum board having higher water vapour resistance to mitigate indoor humidity effects.
Large-Scale Compatible Roll-to-Roll Coating of Paper Electrodes and Their Compatibility as Lithium-Ion Battery Anodes
No full textA recyclability perspective is essential in the sustainable development of energy storage devices, such as lithium-ion batteries (LIBs), but the development of LIBs prioritizes battery capacity and energy density over recyclability, and hence, the recycling methods are complex and the recycling rate is low compared to other technologies. To improve this situation, the underlying battery design must be changed and the material choices need to be made with a sustainable mindset. A suitable and effective approach is to utilize bio-materials, such as paper and electrode composites made from graphite and cellulose, and adopt already existing recycling methods connected to the paper industry. To address this, we have developed a concept for fabricating fully disposable and resource-efficient paper-based electrodes with a large-scale roll-to-roll coating operation in which the conductive material is a nanographite and microcrystalline cellulose mixture coated on a paper separator. The overall best result was achieved with coated roll 08 with a coat weight of 12.83(22) g/m2 and after calendering, the highest density of 1.117(97) g/cm3, as well as the highest electrical conductivity with a resistivity of 0.1293(17) m (Formula presented.) m. We also verified the use of this concept as an anode in LIB half-cell coin cells, showing a specific capacity of 147 mAh/g, i.e., 40% of graphite’s theoretical performance, and a good long-term stability of battery capacity over extended cycling. This concept highlights the potential of using paper as a separator and strengthens the outlook of a new design concept wherein paper can both act as a separator and a substrate for coating the anode material.
Svenska visitationszoner i fokus : En kvalitativ studie om ungdomars röster kring trygghet, integritet och tillit
No full text2025-01-13</p
A latent class analysis of technology-facilitated sexual violence : Associations to other victimizations, psychiatric symptoms, and gender
No full textBackground: Poly-victimization research has shown the cumulative detrimental effects of violence exposure on mental health. Latent Class Analysis (LCA) of victimization is a growing research field uncovering specific combinations of violence exposures particularly negative to mental health. Despite a growing concern of technology-facilitated violence (TFSV), it is scarcely included in LCA studies. Objectives: Investigating victimization typologies that includes technology facilitated sexual violence. Participants and setting: Cross-sectional survey data from a representative sample of Swedish young people in the age range of 16–23 (N = 3243, mean age = 18.20, SD = 0.61). Methods: A Latent Class Analysis was conducted using the package PoLCA in R. A model with three classes was deemed to best fit the data. Results: Class 1 (sexual polyvictimization, 10.1 %) had high probabilities of all forms of sexual violence including TFSV and the highest proportion of psychiatric diagnosis (45.2 %). This class consisted of mostly girls. Class 2 (child abuse polyvictimization,14.8 %) was characterized by high probabilities of physical and psychological child abuse and had an even gender distribution. 30.6 % of this class endorsed having a psychiatric diagnosis. Class 3 (75.1 %) was a low victimization/normative subgroup with an even gender distribution and a low (12.8 %) frequency of psychiatric diagnosis. Class 1 exhibited the highest levels of psychiatric symptoms. Conclusions: Prevention efforts targeted against TFSV should consider the whole web of violence that some young people are situated in. Since TFSV seems to be connected to psychiatric symptoms and diagnosis, Child- and Adolescent Psychiatric services should pay more attention to this type of violence among their young patients.
Balancing Tourism and Traditions: Local Stakeholders’ Perspective on the Impacts of Overtourism on the Culture of the Cinque Terre
No full textThis study explores the impacts of overtourism on local traditions and culture in the CinqueTerre area, Italy, analysing the impacts from the perspective of the residents. Through in-depth interviews with local stakeholders employed in the tourism or the local wine cultural sector, such as wine producers, professional sommeliers, tour operators and DMO, the research explores the perceived challenges of managing the high number of tourists’ arrivals while safeguarding the destination’s culture. By utilizing Social Exchange Theory, the study explores what the perceived benefits and costs associated with the current scenario of the Cinque Terreare and revealed that economic gains are not the sole factor contributing to tourism support; the preservation of culture plays a significant role as well. Furthermore, it investigates the strategies perceived to be the most adequate to balance economic benefits from tourism with the need to preserve cultural identity. The results show that these strategies involve implementing regulations of cruise tourism, encouraging tourism dispersal, focusing on the young generation and increase the involvement of the residents in decision-making processes. Using a deductive approach, the study compares the findings with existing literature on overtourism, cultural preservation, and Social Exchange Theory, thereby offering insights into potential future strategiesfor the Cinque Terre and other tourist destinations facing similar challenges.2025-01-17</p