1. Materials for HybridNeuro webinar titled "Validation of results: statistical models and MU identification accuracy"Aleš Holobar, Nina Murks, 2024, zaključena znanstvena zbirka raziskovalnih podatkov Opis: This dataset contains a collection of teaching materials that were used in the HybridNeuro project webinar titled "Validation of results: statistical models and MU identification accuracy". The webinar was presented by Aleš Holobar and covered the complexities of motor unit (MU) identification accuracy, regression analysis and Bayesian models. The primary aim of the webinar was to spark a robust discussion within the scientific community, particularly focusing on the application and implications of linear mixed models and Bayesian regression in the realm of MU identification. The teaching materials include Matlab and R source code for statistical analysis of the included data, as well as three examples of MU identification results in CSV format (from both synthetic and experimental HDEMG signals). The presentation slides in PDF format are also included. The dataset is approximately 9 MB in size.
Ključne besede: HybridNeuro, webinar, teaching materials, statistical models, regression analysis, motor unit identification, matlab, rstudio, statistics, surface high density electromyogram (HDEMG), tibialis anterior, dataset
Objavljeno v DKUM: 30.05.2024; Ogledov: 221; Prenosov: 25
 Celotno besedilo (108,35 KB)
Gradivo ima več datotek! Več... |
2. Simulated and experimental HDEMG signals of biceps brachii muscle for analysis of motor unit mergingAleš Holobar, Jakob Škarabot, Dario Farina, 2024, zaključena znanstvena zbirka raziskovalnih podatkov Opis: This dataset contains a collection of simulated and experimental surface HDEMG recordings of the biceps brachii muscle during the isometric elbow flexion. Simulated data contains 50 recordings: 5 subjects and 5 excitation levels, each with and without added noise. Experimental data contains 16 recordings: 2 subjects with 4 excitation levels and 2 repetitions of each level. Synthetic data was simulated using the cylindrical volume conductor model [1] and the motor unit recruitment and firing modulation model proposed in [2]. Each recording is 20 seconds in length with 90 HDEMG channels sampled at 2048 Hz and is stored as a 2D matrix of raw EMG values in Matlab’s MAT format. Experimental surface EMG data was recorded on two volunteers during isometric contractions at constant force level. Each recording is 25 seconds in length with 64 HDEMG channels sampled at 2048 Hz and is also stored as a 2D matrix of raw EMG values in Matlab’s MAT format. The dataset is approximately 1.5 GB in size.
Ključne besede: surface high density electromyogram (HDEMG), motor unit, spike train, motor unit merging, simulated data, experimental data, biceps brachii, dataset
Objavljeno v DKUM: 30.05.2024; Ogledov: 172; Prenosov: 20
Celotno besedilo (125,29 KB)
Gradivo ima več datotek! Več... |
3. |
4. |
5. The psychological science accelerator’s COVID-19 rapid-response datasetErin M. Buchanan, Saša Zorjan, 2023, izvirni znanstveni članek Opis: In response to the COVID-19 pandemic, the Psychological Science Accelerator coordinated three large-scale psychological studies to examine the efects of loss-gain framing, cognitive reappraisals, and autonomy framing manipulations on behavioral intentions and afective measures. The data collected (April to October 2020) included specifc measures for each experimental study, a general questionnaire examining health prevention behaviors and COVID-19 experience, geographical and cultural context characterization, and demographic information for each participant. Each participant started the study with the same general questions and then was randomized to complete either one longer experiment or two shorter experiments. Data were provided by 73,223 participants with varying completion rates. Participants completed the survey from 111 geopolitical regions in 44 unique languages/ dialects. The anonymized dataset described here is provided in both raw and processed formats to facilitate re-use and further analyses. The dataset ofers secondary analytic opportunities to explore coping, framing, and self-determination across a diverse, global sample obtained at the onset of the COVID-19 pandemic, which can be merged with other time-sampled or geographic data.
Ključne besede: covid-19, responses, online experiments, dataset, dataset descriptions
Objavljeno v DKUM: 09.04.2024; Ogledov: 295; Prenosov: 240
Celotno besedilo (1,57 MB)
Gradivo ima več datotek! Več... |
6. UAV Thermal Imaging for Unexploded Ordnance Detection by Using Deep LearningMilan Bajić, Jr., Božidar Potočnik, 2023, izvirni znanstveni članek Opis: A few promising solutions for thermal imaging Unexploded Ordnance (UXO) detection were proposed after the start of the military conflict in Ukraine in 2014. At the same time, most of the landmine clearance protocols and practices are based on old, 20th-century technologies. More than 60 countries worldwide are still affected by explosive remnants of war, and new areas are contaminated almost every day. To date, no automated solutions exist for surface UXO detection by using thermal imaging. One of the reasons is also that there are no publicly available data. This research bridges both gaps by introducing an automated UXO detection method, and by publishing thermal imaging data. During a project in Bosnia and Herzegovina in 2019, an organisation, Norwegian People's Aid, collected data about unexploded ordnances and made them available for this research. Thermal images with a size of 720 x 480 pixels were collected by using an Unmanned Aerial Vehicle at a height of 3 m, thus achieving a very small Ground Sampling Distance (GSD). One of the goals of our research was also to verify if the explosive war remnants' detection accuracy could be improved further by using Convolutional Neural Networks (CNN). We have experimented with various existing modern CNN architectures for object identification, whereat the YOLOv5 model was selected as the most promising for retraining. An eleven-class object detection problem was solved primarily in this study. Our data were annotated semi-manually. Five versions of the YOLOv5 model, fine-tuned with a grid-search, were trained end-to-end on randomly selected 640 training and 80 validation images from our dataset. The trained models were verified on the remaining 88 images from our dataset. Objects from each of the eleven classes were identified with more than 90% probability, whereat the Mean Average Precision (mAP) at a 0.5 threshold was 99.5%, and the mAP at thresholds from 0.5 to 0.95 was 87.0% up to 90.5%, depending on the model's complexity. Our results are comparable to the state-of-the-art, whereat these object detection methods have been tested on other similar small datasets with thermal images. Our study is one of the few in the field of Automated UXO detection by using thermal images, and the first that solves the problem of identifying more than one class of objects. On the other hand, publicly available thermal images with a relatively small GSD will enable and stimulate the development of new detection algorithms, where our method and results can serve as a baseline. Only really accurate automatic UXO detection solutions will help to solve one of the least explored worldwide life-threatening problems.
Ključne besede: unmanned aerial vehicle, unexploded ordnance, thermal imaging, UXOTi_NPA dataset, convolutional neural networks, deep learning
Objavljeno v DKUM: 12.02.2024; Ogledov: 389; Prenosov: 26
Celotno besedilo (16,94 MB)
Gradivo ima več datotek! Več... |
7. Uporaba metod zastopanja znanja za preučevanje naprednih sistemov za pomoč voznikom in avtonomne vožnje : masterʹs thesisGregor Ovsenjak, 2021, magistrsko delo Opis: Področje avtonomne vožnje je eno izmed najbolj raziskovanih tem v avtomobilski industriji. Varnost avtonomnih vozil v vsakdanjih situacijah na cesti predstavlja enega izmed glavnih izzivov, zaradi vrste različnih situacij do katerih pride v resničnem svetu. Avtonomna vozila bi morala prevoziti več sto miljard kilometrov, da bi lahko potrdili njihovo zanesljivost pri odločanju v primeru nevarnosti. Zato ima virtualno testiranje scenarijev, kjer lahko simuliramo poljubne situacije, pomembno vlogo pri validaciji in preverjanju delovanja avtonomnih vozil.
Tako virtualno testiranje predstavlja nujen postopek v razvoju naprednih sistemov avtonomne vožnje. Vendar je ustvarjanje raznolikih scenarijev velikokrat okoren in zamuden postopek. Zaradi tega je zaželjena večkratna in ponovna uporaba podatkov iz realnega sveta. Ker ontologije predstavljajo večkrat uporabno zastopanje informacij, so idealen kandidat za ustvarjanje raznolikih scenarijev. V nalogi predstavimo avtomatiziran postopek za razbiranje informacij iz podatkovne baze za namene večkratne in ponovne uporabe le teh v ontologijah. Ključnega pomena za razvoj ontologije je dobro razumevanje strukture podatkovne baze, zato se velik del naloge osredotoča na analizo le te. Podatke z baze je potrebno s pomočjo programske kode razbrati in interpretirati ter šele nato uskladiti ontologijo z bazo. Pri tem razvijemo dve nove metodi, ki temeljita na geometričnih algoritmih. Na podlagi le-teh, raziščemo bazo in zbrane podatke očiščimo s z uporabo statistične analize ter opredelimo v ontologijo. Rezultat naše naloge je ontologija zapolnjena z osnovnimi koncepti, ki so definirani na podlagi podatkov zbranih s podatkovne baze.
Ključne besede: ontologije, avtonomna vožnja, avtomatizacija, Waymo Open Dataset
Objavljeno v DKUM: 20.12.2021; Ogledov: 921; Prenosov: 60
Celotno besedilo (1,95 MB) |
