Mid Sweden University
Not a member yet
15329 research outputs found
Sort by
Early detection of mental health disorders using machine learning models using behavioral and voice data analysis
No full textPeople of all demographics are impacted by mental illness, which has become a widespread and international health problem. Effective treatment and support for mental illnesses depend on early discovery and precise diagnosis. Notably, delayed diagnosis may lead to suicidal thoughts, destructive behaviour, and death. Manual diagnosis is time-consuming and laborious. With the advent of AI, this research aims to develop a novel mental health disorder detection network with the objective of maximum accuracy and early discovery. For this reason, this study presents a novel framework for the early detection of mental illness disorders using a multi-modal approach combining speech and behavioral data. This framework preprocesses and analyzes two distinct datasets to handle missing values, normalize data, and eliminate outliers. The proposed NeuroVibeNet combines Improved Random Forest (IRF) and Light Gradient-Boosting Machine (LightGBM) for behavioral data and Hybrid Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) for voice data. Finally, a weighted voting mechanism is applied to consolidate predictions. The proposed model achieves robust performance and a competitive accuracy of 99.06% in distinguishing normal and pathological conditions. This framework validates the feasibility of multi-modal data integration for reliable and early mental illness detection.
Pilot-testing the tools for the introduction of AI in education
No full textDuring the last years there have been a rapid development of a plethora of artificial intelligence (AI) tools, including generative AI (GenAI) models that challenges the existing teaching and learning design in higher education. The current AI hype might be followed by a new AI winter, but the impact on teaching and learning in higher education will be permanent (Pons, 2023; Whitham et al., 2023). Several studies have pointed out the importance of teacher professional development in the field of AI in education (AIED) (Escalona-Márquez et al., 2024; Mouta et al., 2024). A professional development should involve practical, theoretical as well as ethical aspects of AIED. This study was conducted as a part of the initial phase of the project FAITH (Frontline Application of AI and Technology-enhanced Learning for Transforming Higher Education). This is a pedagogical development project that aims to develop institutional teaching development in higher education programs. With the use of GenAI and technology-enhanced learning, teachers in higher education should revise and develop their educational programmes to involve GenAI tools in teaching and learning activities. The project will be implemented during 2024-2026 (Jaldemark et al., 2024). The aim of the study is to introduce, analyse and discuss some GenAI tools for teaching. Data was collected by a web survey at a webinar workshop with 39 participants (36 student participants + 3 course teachers) that was a part of a course on AI for education and work-life. Before answering the questions participants tested AI tools. Questionnaire answers (n=19) were analysed and categorised in a directed content analysis. The theoretical lens for the study was the Self-determination theory (SDT) as outlined by Ryan and Deci (2024). STD postulates that there are three basic psychological needs that must be satisfied for people to experience wellness, ongoing growth and integrity. Among 11the survey participants, common age group were 45-54 (n=9), followed by 25-34 (n=4) and 35-44 (n=3). Their occupations covered work in, for example: government agencies, schools and universities, industry, project management, marketing, and HR. Results of the preliminary analysis highlights that AI can support language development and analysis, idea generation, more efficient work, and be an assistant in schools. However, answers to the survey also highlight that AI have several limitations, such as lack of emotional understanding and critical and creative thinking. Participants highlight that AI can strengthen and develop human competences, but also, that it is necessary to develop competences within AI for future society. On the negative side it is noted that too much emphasis on AI can make us downgrade human thinking in the human-AI-collaboration, potential loss of human jobs, and that all may not receive adequate competence development in schools and industry
Toward intelligence or ignorance? Performativity and uncertainty in government tech narratives
No full textEmerging technologies are often accompanied by optimistic “tech narratives” that emphasize their potential benefits to society. These narratives appear in various sources, including public policy documents, media coverage, and academic literature. However, identifying their origins and underlying rationale can be challenging. This paper addresses the research question (RQ): How can government tech narratives be traced and unveiled? To answer this question, we draw on the theoretical frameworks of “performativity” and “uncertainty assessment” to develop a two-step approach for investigating tech narratives. We apply this methodology to trace a narrative promoting the benefits of artificial intelligence (AI) in the Swedish public sector back to its source, an emerging government AI policy program. Our analysis reveals a hybridization of economic and political interests, as well as a recognized ignorance reflected in the lack of scrutiny of highly uncertain calculations. By presenting this two-step methodology for tracing and critically examining tech narratives, this paper makes a methodological contribution. In applying this approach, we also provide empirical insights into how tech narratives facilitate the materialization of technological infrastructures
Tonåringar med psykisk ohälsa : Skolsköterskors perspektiv
No full textBakgrund: Psykisk ohälsa bland tonåringar är ett växande folkhälsoproblem som kan påverka skolgång och välbefinnande. Skolsköterskan har ett viktigt ansvar i att tidigt identifiera och stödja tonåringar med psykisk ohälsa, men det finns begränsad forskning om deras erfarenheter. Syfte: Att belysa skolsköterskors erfarenheter av att möta tonåringar med psykisk ohälsa. Metod: Kvalitativ deskriptiv studie med induktiv ansats. Nio skolsköterskor intervjuades och materialet analyserades med kvalitativ innehållsanalys. Resultat: Psykisk ohälsa yttrade sig ofta genom subtila symtom som skolfrånvaro, isolering och självskadebeteende. Skolsköterskorna betonade vikten av relationer, tillgänglighet och samverkan. Riskfaktorer som lyftes fram var sociala medier, skolstress och bristande stöd. Metoddiskussion: Den kvalitativa ansatsen gav fördjupad förståelse. Variation i urvalet stärkte bredden, men det geografiska området kan begränsa överförbarheten. Resultatdiskussion: Tidiga insatser, tillit och samverkan var centralt. Enligt Orems teori behövs stöd för att stärka ungas egenvårdsförmåga vid psykisk ohälsa. Slutsats: Skolsköterskan har ett viktigt ansvar att stödja tonåringar med psykisk ohälsa. Förbättrade förutsättningar och ökad samverkan krävs för att stärka det hälsofrämjande arbetet
Äldre med undernäring och distriktssköterskans hälsofrämjande arbete : - inom hemsjukvården
No full textBakgrund: Undernäring bland äldre i ordinärt boende är ett komplext och växande problem som kräver individanpassade omvårdnadsinsatser och tvärprofessionell samverkan. Distriktssköterskan har en central roll i att identifi era, behandla och följa upp näringsrelaterade behov. Studiens teoretiska referensram utgår ifrån Orlandos interaktionsteori. Syfte: Att beskriva distriktssköterskans upplevelse av att förebygga och hantera undernäring av äldre i hemsjukvården i Sverige. Metod: Designen var en kvalitativ induktiv ansats. Intervjuer med distriktssköterskor verksamma inom hemsjukvård genomfördes. Manifest innehållsanalys användes. Resultat: Två huvudkategorier identifi erades: Individanpassad omvårdnad och Samverkan. Distriktssköterskorna använde klinisk erfarenhet, strukturerade bedömningsinstrument samt samtal med patienter och anhöriga för att skapa en helhetsbild av näringsstatus och behov. Åtgärder anpassades utifrån patientens behov, preferenser och livssituation, där kostberikning och måltidsstöd var centrala. Uppföljning skedde genom viktkontroller, observationer och kontinuerlig kommunikation med omvårdnadspersonal. Begränsningar i resurser, dokumentation, samt bristande samverkan med läkare och dietister framkom som hinder. Samverkan med hemtjänst och närstående lyftes som avgörande faktorer för en hållbar och eff ektiv nutritionsvård. Slutsats: Distriktssköterskans arbete med undernäring kräver ett individcentrerat förhållningssätt, strukturerad uppföljning och ett välfungerande samarbete med vårdteamet och patientens nätverk. Etiska utmaningar i komplexa vårdsituationer väcker refl ektioner
Styrning av natrium/svavelbalanser med multivariata dataanalysmetoder : En analys av kemikalieflöden och variationer i sulfiditet i lutssystemet vid Östrands massafabrik
No full textIn the Paper Pulp Industry, precise control of chemical flows is essential to achieve a high product quality and a sustainableproduction process. The aim of this study was based on the Six sigma improvement methodology and multivariate data analysis methods such as PCA and PLS to identify the in- and outflows who have the greatest impact on the mills sulfidityand the mill’s sodium/sulfur balance at SCA Östrand. Ash purges were identified as an outlier in the PCA model. The PLS model identified in- and outflows who have the greatest impact on the mill’s sulfidity, however the interpretation of the results should be complemented with process knowledgeor experimental methods. The result of the study shows that it is possible to develop a predictive model that can describe the variations in sulfidity accurately and can be used as support for improved process control in the mill. Future research should include more variables and in particular smaller side streams to improve the model and increase the reliability of the results. Inom pappersmassaindustrin är en noggrann styrning av kemikalieflöden avgörande för att uppnå en hög produktkvalitet och en hållbar produktion. Syftet med studien var att utifrån förbättringsmetodiken Six sigma och multivariata dataanalysmetoder som PCA och PLS identifiera de in- och utflöden som har störst påverkan på sulfiditetenoch natrium/svavelbalansen på SCA Östrand. Utifrån PCAmodellen kunde avvikande observationer i form av dumpad aska datamaterialet identifieras. PLS-modellen visade vilka in- och utflöden som hade störst påverkan på sulfiditeten, men tolkningen av resultatet bör kompletteras med kunskap om processen eller experimentella metoder. Studiens resultat visar att det är möjligt att ta fram en prediktiv modell som kan beskriva variationerna i sulfiditet väl och kan användas som stöd för en förbättrad processtyrning i fabriken. För attförbättra modellen och få mer tillförlitliga resultat kan fler variabler med mindre sidoströmmar inkluderas i framtida forskning
Nyckeln som saknas? Fritidens potential i samverkan : En kvalitativ studie om fritidens roll i SSPF:s brottspreventiva arbete
No full text2025-06-03</p
InfraVis - The Swedish Research Infrastructure for Visualization Support
No full textEssentially all academic research of today relies on analysis of data from a wide range of sources. Several underpinning, and rapidly developing, technologies are supporting the analysis of this data. Visualization serves as an interface to this ecosystem of tools and methods and integrates them into environments supporting scientific workflows, effectively sharing cognitive load between computers and humans. There is, however, a gap between the state-of-the-art in visual data analysis and current wide-spread academic practice. Support for the introduction of new, improved and tailored, visual data analysis environments thus has the potential to address challenges involving large and complex data, creating competitive advantages for researchers. To fill the gap and capitalize on this opportunity, the InfraVis initiative has been created in Sweden with the mission to operate an infrastructure consisting of visualization experts, software solutions, and access to high-end visualization laboratories. Users of InfraVis are offered assistance through a national helpdesk with rapid response times as well as more in-depth projects addressing specific data and software challenges. InfraVis provides software solutions based on development within connected research groups, curation of international software and best practice, and user training in the form of courses, seminars and on-line documentation. To build an infrastructure with national coverage, we have pooled together nine visualization environments in Sweden interconnected in a nodal structure. The nodes are hosted in proximity to research environments in visualization, which enables direct access to the research front as well as to state-of-art facilities. The governance structure of InfraVis is based on the leading researchers in visualization in Sweden as well as an international advisory board
Hälsoapp : Applikation hos Skatteverket
No full textThe purpose of this project has been to develop an application that promotes physical activity and health, particularly for individuals with sedentary jobs. By making exercise measurable and rewarding through a point system, the goal is to create motivation for increased movement in everyday life. To achieve this, a web application has been developed where users can register activities, earn points based on duration and type of exercise, and track their own and others' performance via a leaderboard. The application features a user friendly, responsive interface built with Angular, a backend developed in Java/ Spring Boot, and data storage in MySQL. Communication is handled via a REST API, and security is ensured through JWT authentication. The result is a functioning application where users can create profiles, log in, register activities, and receive weekly summaries. User testing was conducted to identify areas for improvement in both interface and functionality. The conclusion is that it is possible, with relatively simple technical implementation, to create a digital tool that encourages physical activity while handling data in a structured and secure manner. There is potential for further development of the application, for example by adding social features. Syftet med detta projekt har varit att utveckla en applikation som främjar fysisk aktivitet och hälsa, särskilt för personer med stilla sittande arbete. Genom att göra träning mätbar och belönande med poängsystem är målet att skapa motivation till ökad rörelse i vardagen. För att uppnå detta har en webbapplikation utvecklats där användaren kan registrera aktiviteter, få poäng baserat på tidsåtgång och typ av träning, samt följa sina och andras prestationer via en poängtavla. Applikationen består av ett an vändarvänligt, responsivt gränssnitt byggt i Angular, med en backend i Java/ Spring Boot och datalagring i MySQL. Kommunikation sker via ett REST-API och säkerhet hanteras genom JWT-autentisering. Resultatet blev en fungerade applikation där användare kan skapa profil, logga in, registrera aktiviteter och få veckovisa sammanställningar. Användartester genomfördes för att identifiera förbättringsområden i gränssnitt och funktionalitet. Slutsatsen är att det är möjligt att genom relativt enkelt teknisk implementation skapa ett digitalt verktyg som uppmuntrar till rörelse, samtidigt som data hanteras strukturerat och säkert. Det finns potential att vidareutveckla applikationen med exempelvis sociala funktioner.
GUIDING THROUGH UNCERTAINTY : CLIMATE CHANGE THROUGH THE LENS OF SWEDISH NATURE–BASED TOURISM GUIDES
No full textThis thesis explores how Swedish nature–based tourism guides perceive and adapt to climate change, using a qualitative, hermeneutic phenomenological approach that combines semi–structured interviews with photo–elicitation. Fifteen guides, plus two additional correspondents, representing both winter and summer tourism, participated. They discussed their firsthand experiences with climate impacts and submitted photos illustrating environmental changes. The data was analysed inductively, following Moustakas’s framework. Findings showed that guides experience climate change as an immediate reality. Many described the recent winter's erratic weather–low snow cover, rain, and storms–which disrupted tours and conflicted with visitors' expectations. Photographs supported these accounts. Guides reported ongoing short–term adaptations, such as adjusting routes or offering summer alternatives, while expressing fatigue and concern for the future. A generational divide emerged: newer guides leaned toward climate–resilient offerings, while seasoned guides showed signs of resignation or considered leaving the field. Guides also took on pedagogical roles, explaining climate processes to visitors, often feeling guilty about tourism’s carbon footprint, and aiming to raise environmental awareness. Many cited other immediate ecological threats, like deforestation and overhunting, as equally pressing. The study highlights the value of guides' place–based knowledge and suggests that integrating their insights into adaptation planning would strengthen tourism resilience. Given guides' preference for local, community–driven solutions, support should focus on collaborative networks rather than top–down policies. Policymakers and industry leaders should recognize guides as key climate knowledge holders. Future research should track how guides’ strategies evolve in response to ongoing climate change.2025-06-06</p