21. On the influence of aging on classification performance in the visual EEG oddball paradigm using statistical and temporal featuresNina Omejc, Manca Peskar, Aleksandar Miladinović, Voyko Kavcic, Sašo Džeroski, Uroš Marušič, 2023, original scientific article Abstract: The utilization of a non-invasive electroencephalogram (EEG) as an input sensor is a common approach in the field of the brain–computer interfaces (BCI). However, the collected EEG data pose many challenges, one of which may be the age-related variability of event-related potentials (ERPs), which are often used as primary EEG BCI signal features. To assess the potential effects of aging, a sample of 27 young and 43 older healthy individuals participated in a visual oddball study, in which they passively viewed frequent stimuli among randomly occurring rare stimuli while being recorded with a 32-channel EEG set. Two types of EEG datasets were created to train the classifiers, one consisting of amplitude and spectral features in time and another with extracted time-independent statistical ERP features. Among the nine classifiers tested, linear classifiers performed best. Furthermore, we show that classification performance differs between dataset types. When temporal features were used, maximum individuals’ performance scores were higher, had lower variance, and were less affected overall by within-class differences such as age. Finally, we found that the effect of aging on classification performance depends on the classifier and its internal feature ranking. Accordingly, performance will differ if the model favors features with large within-class differences. With this in mind, care must be taken in feature extraction and selection to find the correct features and consequently avoid potential age-related performance degradation in practice. Keywords: aging, elderly, machine learning, visual oddball study, brain-computer interface Published in DiRROS: 01.02.2023; Views: 584; Downloads: 297
Full text (3,50 MB) This document has many files! More... |
22. A data-driven machine learning approach for brain-computer interfaces targeting lower limb neuroprostheticsArnau Dillen, Elke Lathouwers, Aleksandar Miladinović, Uroš Marušič, Fakhreddine Ghaffari, Olivier Romain, Romain Meeusen, Kevin De Pauw, 2022, original scientific article Abstract: Prosthetic devices that replace a lost limb have become increasingly performant in recent years. Recent advances in both software and hardware allow for the decoding of electroencephalogram (EEG) signals to improve the control of active prostheses with brain-computer interfaces (BCI). Most BCI research is focused on the upper body. Although BCI research for the lower extremities has increased in recent years, there are still gaps in our knowledge of the neural patterns associated with lower limb movement. Therefore, the main objective of this study is to show the feasibility of decoding lower limb movements from EEG data recordings. The second aim is to investigate whether well-known neuroplastic adaptations in individuals with an amputation have an influence on decoding performance. To address this, we collected data from multiple individuals with lower limb amputation and a matched able-bodied control group. Using these data, we trained and evaluated common BCI methods that have already been proven effective for upper limb BCI. With an average test decoding accuracy of 84% for both groups, our results show that it is possible to discriminate different lower extremity movements using EEG data with good accuracy. There are no significant differences (p = 0.99) in the decoding performance of these movements between healthy subjects and subjects with lower extremity amputation. These results show the feasibility of using BCI for lower limb prosthesis control and indicate that decoding performance is not influenced by neuroplasticity-induced differences between the two groups. Keywords: neuroprosthetics, brain-computer interface, machine learning, electroencephalography, data-driven learning, lower limb amputation Published in DiRROS: 21.07.2022; Views: 717; Downloads: 531
Full text (858,15 KB) This document has many files! More... |
23. Bringing into play automated electron microscopy data processing for understanding nanoparticulate electrocatalysts’ structure–property relationshipsAna Rebeka Kamšek, Francisco Ruiz-Zepeda, Andraž Pavlišič, Armin Hrnjić, Nejc Hodnik, 2022, review article Keywords: identical location electron microscopy, image analysis, machine learning, electrocatalysis, metallic nanoparticles Published in DiRROS: 01.07.2022; Views: 795; Downloads: 530
Full text (2,76 MB) This document has many files! More... |
24. Teaching and learning the language of the neighbour country : tools for mainstream primary education in the Slovenian-Italian border areaIrina Moira Cavaion, 2022, original scientific article Abstract: The article presents two central tools for teaching neighbour languages in border areas within the didactic framework of the Contact-Based-(Neighbour-)Language-Learning-andTeaching method (CoBLaLT, Cavaion 2015; 2016; 2019), namely a teacher’s guide to contact-based neighbour language teaching and the digital portfolio ‘My multimedia autobiography of crossborder contacts’ for pupils aged 11 to 15. They were developed as part of a postdoctoral project between 2017-2019 in the Italian-Slovenian border region. The article highlights the importance of making language teaching research a collaborative process between a strong scientific and professional community that thus fosters innovation and effectiveness of methods and contents in neighbour language learning. Keywords: neighbourg langages, teaching, learning, multilingual border region, linguistic autobiography, European language policy Published in DiRROS: 12.04.2022; Views: 697; Downloads: 368
Full text (1,32 MB) This document has many files! More... |
25. Automated analysis of proliferating cells spatial organisation predicts prognosis in lung neuroendocrine neoplasmsMatteo Bulloni, Giada Sandrini, Irene Stacchiotti, M. Barberis, Fiorella Calabrese, Lina Carvalho, Gabriella Fontanini, Greta Alì, Francesco Fortarezza, Paul Hofman, Izidor Kern, 2021, original scientific article Keywords: neuroendocrine tumors, lung neoplasms, carcinoma, prognosis, pathology, histology, Ki-67 antigen, machine learning, image enhancement, lung cancer, neuroendocrine neoplasms Published in DiRROS: 09.11.2021; Views: 1001; Downloads: 426
Link to file |
26. Treatment outcome clustering patterns correspond to discrete asthma phenotypes in childrenIvana Banić, Mario Lovrić, Gerald Cuder, Roman Kern, Matija Rijavec, Peter Korošec, Mirjana Kljajić-Turkalj, 2021, original scientific article Abstract: Despite widely and regularly used therapy asthma in children is not fully controlled. Recognizing the complexity of asthma phenotypes and endotypes imposed the concept of precision medicine in asthma treatment. By applying machine learning algorithms assessed with respect to their accuracy in predicting treatment outcome, we have successfully identified 4 distinct clusters in a pediatric asthma cohort with specific treatment outcome patterns according to changes in lung function (FEV1 and MEF50), airway inflammation (FENO) and disease control likely affected by discrete phenotypes at initial disease presentation, differing in the type and level of inflammation, age of onset, comorbidities, certain genetic and other physiologic traits. The smallest and the largest of the 4 clusters- 1 (N = 58) and 3 (N = 138) had better treatment outcomes compared to clusters 2 and 4 and were characterized by more prominent atopic markers and a predominant allelic (A allele) effect for rs37973 in the GLCCI1 gene previously associated with positive treatment outcomes in asthmatics. These patients also had a relatively later onset of disease (6 + yrs). Clusters 2 (N = 87) and 4 (N = 64) had poorer treatment success, but varied in the type of inflammation (predominantly neutrophilic for cluster 4 and likely mixed-type for cluster 2), comorbidities (obesity for cluster 2), level of systemic inflammation (highest hsCRP for cluster 2) and platelet count (lowest for cluster 4). The results of this study emphasize the issues in asthma management due to the overgeneralized approach to the disease, not taking into account specific disease phenotypes. Keywords: asthma, allergy and immunology, pediatrics, machine learning, treatment outcome, phenotypes, childhood asthma, clustering Published in DiRROS: 16.08.2021; Views: 1126; Downloads: 772
Full text (1,32 MB) This document has many files! More... |
27. Additional exergames to regular tennis training improves cognitive-motor functions of children but may temporarily affect tennis technique : a single-blind randomized controlled trialLuka Šlosar, Eling D. de Bruin, Eduardo Bodnariuc Fontes, Matej Plevnik, Rado Pišot, Boštjan Šimunič, Uroš Marušič, 2021, original scientific article Abstract: This study evaluated the effects of an exergame program (TennisVirtua-4, Playstation Kinect) combined with traditional tennis training on autonomic regulation, tennis technique, gross motor skills, clinical reaction time, and cognitive inhibitory control in children. Sixty-three children were randomized into four groups (1st % two exergame and two regular trainings sessions/week, 2nd % one exergame and one regular training sessions/week, 3rd % two regular trainings sessions/week, and 4th % one regular training session/week) and compared at baseline, 6-month immediately post intervention and at 1-year follow-up post intervention. At 6-month post intervention the combined exergame and regular training sessions revealed: higher breathing frequency, heart rate (all ps % 0.001) and lower skin conductance levels (p = 0.001) during exergaming; additional benefits in the point of contact and kinetic chain elements of the tennis forehand and backhand technique (all ps % 0.001); negative impact on the shot preparation and the follow-through elements (all ps % 0.017); higher ball skills (as part of the gross motor skills) (p < 0.001); higher percentages of clinical reaction time improvement (1st %9.7% vs 3rd group %7.4% and 2nd %6.6% vs 4th group %4.4%, all ps % 0.003) and cognitive inhibitory control improvement in both congruent (1st %20.5% vs 3rd group %18.4% and 2nd %11.5% vs 4th group %9.6%, all ps % 0.05) and incongruent (1st group %19.1% vs 3rd group %12.5% and 2nd group %11.4% vs 4th group %6.5%, all ps % 0.001) trials. The 1-year follow-up test showed no differences in the tennis technique, clinical reaction time and cognitive inhibitory control improvement between groups with the same number of trainings per week. The findings support exergaming as an additional training tool, aimed to improve important cognitive-motor tennis skills by adding dynamics to the standardized training process. Caution should be placed to planning this training, e.g., in a mesocycle, since exergaming might decrease the improvement of specific tennis technique parts of the trainees. (ClinicalTrials.gov; ID: NCT03946436). Keywords: tennis, training, performance, children, motor learning, cognitive learning, teaching, strategies Published in DiRROS: 17.03.2021; Views: 1479; Downloads: 1197
Full text (1,81 MB) This document has many files! More... |
28. |
29. A comparison of models for forecasting the residential natural gas demand of an urban areaRok Hribar, Primož Potočnik, Jurij Šilc, Gregor Papa, 2019, original scientific article Abstract: Forecasting the residential natural gas demand for large groups of buildings is extremely important for efficient logistics in the energy sector. In this paper different forecast models for residential natural gas demand of an urban area were implemented and compared. The models forecast gas demand with hourly resolution up to 60 h into the future. The model forecasts are based on past temperatures, forecasted temperatures and time variables, which include markers for holidays and other occasional events. The models were trained and tested on gas-consumption data gathered in the city of Ljubljana, Slovenia. Machine-learning models were considered, such as linear regression, kernel machine and artificial neural network. Additionally, empirical models were developed based on data analysis. Two most accurate models were found to be recurrent neural network and linear regression model. In realistic setting such trained models can be used in conjunction with a weather-forecasting service to generate forecasts for future gas demand. Keywords: demand forecasting, buildings, energy modeling, forecast accuracy, machine learning Published in DiRROS: 15.03.2019; Views: 2482; Downloads: 1144
Full text (968,06 KB) |