Opin vísindi
Opin vísindi er varðveislusafn vísindaefnis og doktorsritgerða í opnum aðgangi á vegum íslenskra háskóla og Landsbókasafns Íslands - Háskólabókasafns.
Opinn aðgangur að rannsóknaniðurstöðum er í samræmi við 10. gr. laga nr. 3/2003 um opinberan stuðning við vísindarannsóknir sem og kröfur innlendra og erlendra rannsóknasjóða. Markmiðið með opnum aðgangi er að niðurstöður rannsókna séu aðgengilegar sem flestum óhindrað og án endurgjalds á rafrænu formi. Vistun í varðveislusafninu er varanleg og ætlað að tryggja aðgang að vísindaefni íslenskra háskóla í opnum aðgangi um ókomna tíð. Varðveislusafnið Opin vísindi er tengt við rannsóknagáttina IRIS og rannsóknaniðurstöður í opnum aðgangi sem eru skráðar í IRIS eru um leið vistaðar og gerðar aðgengilegar til framtíðar í varðveislusafninu. Með því að safna þessu efni saman í eitt safn verður aðgangur að því einfaldur og þægilegur fyrir alla sem vilja kynna sér það og geta þannig notið þess öfluga vísindastarfs sem fram fer í háskólum landsins.
Varðveislusafnið er OpenAIRE / OpenAIREplus samhæft og samrýmist kröfum sem gerðar eru um birtingu rannsóknaniðurstaðna úr verkefnum sem styrkt eru úr evrópsku rannsóknaáætlununum FP7 og H2020.
Varðveislusafnið notar opna hugbúnaðinn DSpace.
Opinn aðgangur að rannsóknaniðurstöðum er í samræmi við 10. gr. laga nr. 3/2003 um opinberan stuðning við vísindarannsóknir sem og kröfur innlendra og erlendra rannsóknasjóða. Markmiðið með opnum aðgangi er að niðurstöður rannsókna séu aðgengilegar sem flestum óhindrað og án endurgjalds á rafrænu formi. Vistun í varðveislusafninu er varanleg og ætlað að tryggja aðgang að vísindaefni íslenskra háskóla í opnum aðgangi um ókomna tíð. Varðveislusafnið Opin vísindi er tengt við rannsóknagáttina IRIS og rannsóknaniðurstöður í opnum aðgangi sem eru skráðar í IRIS eru um leið vistaðar og gerðar aðgengilegar til framtíðar í varðveislusafninu. Með því að safna þessu efni saman í eitt safn verður aðgangur að því einfaldur og þægilegur fyrir alla sem vilja kynna sér það og geta þannig notið þess öfluga vísindastarfs sem fram fer í háskólum landsins.
Varðveislusafnið er OpenAIRE / OpenAIREplus samhæft og samrýmist kröfum sem gerðar eru um birtingu rannsóknaniðurstaðna úr verkefnum sem styrkt eru úr evrópsku rannsóknaáætlununum FP7 og H2020.
Varðveislusafnið notar opna hugbúnaðinn DSpace.
Nýlega bætt við
Collaborative GenAI : Humanized Interaction Fields for Knowledge Creation
(Academic Conferences and Publishing International Limited, 2025) Böhm, Karsten; Durst, Susanne; Kianto, Aino; Toth, Ilona; Department of Business and Economics
Generative AI (GenAI) is increasingly becoming part of our habits, both in our professional and private lives. The use of this is a way to shape, change and influence knowledge creation and utilisation, and thus a very interesting phenomenon for the field of Knowledge Management (KM). In a previous work, the authors of this paper focused on the bidirectional effects of KM processes due to the interaction between humans and machines using natural language as a medium. The result of this work was the generative and responsive artificial intelligence (GRAI) model, which not only generates content on demand, but also adapts and modifies knowledge-related interactions. This research focusses on the concept of interaction fields and investigates the collaborative nature of those interaction fields to develop the conceptual model even further. This is achieved by relating to the characteristics of collaborative robotics (COBOTs) as an established form of human-machine interaction and the main differences of human-machine interactions to derive the concept of Humanized Interaction Fields (HIF) that describe relevant aspects of interaction in the field of Human-centered AI (HCAI). The research contributes to the understanding for the co-creation of knowledge between human and machine.
AI Evaluations of Sarcoma From Magnetic Resonance Imaging
(2025-11-18) Gunnarsson, Arnar Evgení; Gargiulo, Paolo; Department of Engineering
Background: Sarcomas are a rare and heterogeneous group of malignant tu- mors, making early detection and diagnosis a high priority. Diagnosis tradition- ally relies on expert interpretation of radiological imaging and histopathological biopsies, processes that are time-consuming, subjective, prone to inter-observer variability and are invasive. Methods: This research investigates the potential of artificial intelligence (AI), specifically radiomics and machine learning (ML), to support sarcoma diagnosis, characterization and grading based on MRI scans. Quantitative features were ex- tracted from multiple image transforms, including original, wavelet, Laplacian of Gaussian, square, square root, logarithm, exponential, gradient, and local binary pattern transforms. From these images, first-order statistics and texture descrip- tors (GLCM, GLSZM, GLRLM, NGTDM) were computed. A diverse set of ML models were evaluated, including Random Forest, Logistic Regression, SGDClas- sifier, Ridge Classifier, LightGBM, XGBoost, and CatBoost. Models were trained on three primary tasks: (1) binary classification of healthy vs. sarcoma tissue, (2) sarcoma grading based on the FNCLCC system, and (3) differentiation between bone and soft tissue sarcomas. In addition, a habitat generation framework was introduced, clustering radiomic segments into biologically meaningful subregions to enhance grade and sub-group classification. Model performance was assessed using AUC-ROC, accuracy, and macro- and micro-averaged F1-score, precision, and recall. Results: For binary classification of healthy vs. sarcoma tissue, models per- formed strongly, achieving AUC-ROC scores ranging from 0.829 to 0.999 depend- ing on data preprocessing, with consistently high metric values overall. This demon- strates that ML methods are well suited to distinguishing healthy from patholog- ical tissue. Grade classification achieved AUC-ROC scores ranging from 0.618 to 0.690 using radiomics and between 0.520-0.591 using habitats, with metrics gen- erally above baseline for three-class classification. While performance remains modest, results indicate meaningful correlation between radiomic inputs and FN- CLCC grade. Sub-group classification of bone vs. soft tissue sarcomas achieved AUC-ROC scores of 0.750-0.863 using radiomics and 0.585-0.707 using habitats, indicating that ML methods can effectively aid in sarcoma sub-type differentia- tion. Conclusions: The findings demonstrate that combining multiple image trans- forms with radiomics for diagnostic, characterization and grading classification feasible and effective. Advanced ML models substantially improve performance across diagnostic and prognostic tasks. Furthermore, the habitat generation ap- proach offers additional biological interpretability and can enhance grade and sub- group prediction. These results highlight the promise of AI-driven radiomics pipelines to support clinical decision making in sarcoma diagnosis and hopefully earlier management and extended survival. Keywords: Artificial Intelligence, Machine Learning, Sarcoma, Diagnostics, Sarcoma Grading, Radiomics, Habitats.
The development, implementation and validation of an objective match scoring system for elite netball
(2025) Butterworth, Andrew; Hamblen, Andrew; O’Donoghue, Peter; Department of Sport Science
This study created and empirically validated an objective match scoring system for the dynamic and tactically rich sport of elite netball. Vast data was captured from all matches (488) played over five-seasons in the UK Netball Superleague. This was ordered into evenly weighted segments for each performance indicator, with each segment assigned a 0 to 10 value on a sliding scale, with the lowest segmented performances awarded a 0, and the highest a 10. Next, individual performance indicators for both teams in all 308 matches from seasons 2021, 2022 and 2023 were calculated an out of ten score, based on which segment they fell within. A resultant out of ten score for the overall match performance of each team was then computed, showing its objective strength. Use of this system was then implemented within elite coaches pre- and post-match analysis processes, with mixed methods utilised to ascertain the empirical validity in practice. Quantitative analysis concludes that the system accurately scores the outcome of matches with statistical significance, whilst qualitative data confirms the usefulness for elite coaching practice, specifically as an aid to previewing and reviewing performances. We conclude that the tool is an objective, trustworthy addition to the coaching process.
Pre-trained deep learning space mapping with intermittent model enhancement for fast multi-fidelity microwave design optimization
(2026-09-14) Koziel, Slawomir; Pietrenko-Dabrowska, Anna; Department of Engineering
Parameter tuning is essential in the development of microwave devices. In recent years, a growing interest in formal optimization methods has emerged, driven by their ability to simultaneously adjust multiple decision variables, even under constraints. Their disadvantage is their high computational cost, which is a serious obstacle to the optimization of electromagnetic (EM) models. This difficulty can be alleviated using multi-fidelity simulations. Problem-independent approaches rely on low-fidelity models constructed through coarse-discretization EM analysis (in contrast to problem-specific equivalent network representations), where a critical factor is the appropriate model correction strategy. This paper introduces a versatile deep-learning space mapping (DLSM) strategy that leverages a reusable pre-trained neural network surrogate. The non-parametric DLSM model implements multi-point response correction, applied independently to the real and imaginary components of relevant S-parameter responses. Furthermore, it is trained as a function of the problem's decision variables and response interrelations. It is embedded in a gradient-based optimization loop, where it is locally retrained using intermittent high-fidelity simulations and sample weighting to place greater emphasis on the neighborhood of the current solution. Comprehensive verification of the procedure involving three planar circuits underscores its competitive efficacy, with a mean running cost of 16 high-fidelity simulations and relative savings over the baseline algorithm up to 87%. Meanwhile, consistent results obtained for multiple scenarios targeting diverse performance specifications corroborate DLSM reusability and applicability across broad ranges of operating conditions.
What Static Connectivity Misses : Dynamic Alpha-Band Brain Network States in First-Episode Psychosis
(2026-09-11) Aubonnet, Romain; Hassan, Mahmoud; Gargiulo, Paolo; Seri, Stefano; Di Lorenzo, Giorgio; Department of Engineering
This study investigates resting-state EEG alpha-band connectivity in first-episode psychosis (FEP) using a novel dynamic connectivity pipeline and examines its relationship with cognitive functioning and psychopathological scores. Data from 78 individuals with FEP and 60 healthy controls (CTR) were analyzed. Source estimation was performed using eLORETA, and connectivity was quantified with the weighted phase-lag index. Static connectivity matrices were assessed using graph theory and edge-wise metrics. Dynamic connectivity matrices were clustered into five distinct brain network states (BNS) using a modified k-means algorithm, from which temporal and graph theory metrics were extracted. Static connectivity metrics revealed lower alpha connectivity in FEP than in controls. The dynamic approach identified reduced variability in the characteristic path length within the default mode network–associated BNS 1 in FEP, suggesting diminished adaptive modulation of functional integration. Subgroup analysis by medication status uncovered distinct BNS signatures for medicated and unmedicated FEP. BNS metrics were correlated with social cognition measures in CTR and with positive formal thought disorder in FEP, whereas static metrics showed no such associations. These findings suggest that relative to static connectivity metrics, dynamic connectivity provides non-redundant information and underscores the impact of medication on neural dynamics in psychosis.
Flokkar í Opnum vísindum
Veldu flokk til að skoða.
- University of Iceland
- University of Akureyri
- Bifröst University
- Hólar University College
- IRIS
- Agricultural University of Iceland
- National and University Library of Iceland
- Iceland University of the Arts