Meta tags:

Headings (most frequently used words):

explore, ctu, digital, library, recent, submissions,

Text of the page (most frequently used words):
and (47), the (32), more (15), show (11), for (11), using (10), this (9), that (8), faculty (8), data (7), models (7), thesis (6), learning (6), are (6), these (5), methods (5), alloys (5), mechanical (5), accuracy (5), problems (5), engineering (5), 2026 (4), nuclear (4), with (4), research (4), habilitation (4), communication (4), analysis (4), design (4), from (4), gfms (4), embeddings (4), robotic (4), search (4), gamma (3), radiation (3), dosimetry (3), its (3), work (3), computational (3), experimental (3), measurements (3), such (3), findings (3), disease (3), behavior (3), digital (3), processing (3), machine (3), advanced (3), diagnostic (3), environments (3), resorbable (3), properties (3), framework (3), dataset (3), samples (3), strength (3), particularly (3), property (3), gene (3), dna (3), quality (3), deep (3), training (3), genomic (3), evo2 (3), fusion (3), breakpoints (3), sequences (3), mission (3), planning (3), routing (3), exploration (3), ctu (3), library (3), developed (2), information (2), czech (2), technical (2), university (2), prague (2), prompt (2), important (2), reactor (2), analytical (2), however (2), accurate (2), current (2), libraries (2), therefore (2), stilbene (2), detectors (2), reactors (2), results (2), between (2), calculations (2), study (2), disorders (2), synucleinopathies (2), parkinson (2), multiple (2), system (2), atrophy (2), rem (2), sleep (2), disorder (2), which (2), defined (2), neurodegenerative (2), prodromal (2), approaches (2), even (2), demonstrate (2), support (2), screening (2), both (2), conditions (2), magnesium (2), promising (2), their (2), diluted (2), relationships (2), composition (2), than (2), prediction (2), trained (2), them (2), catboost (2), high (2), predictive (2), revealed (2), robustness (2), was (2), generate (2), journal (2), article (2), sample (2), foundation (2), transformer (2), dnabert2 (2), classification (2), fusionai (2), 000 (2), best (2), performance (2), 967 (2), dedicated (2), baseline (2), required (2), outperform (2), central (2), through (2), studied (2), operations (2), decision (2), making (2), offline (2), strategies (2), can (2), localization (2), acta (2), polytechnica (2), institute (2), sciences (2), about, send, feedback, cookie, settings, provided, computing, centre, load, shielding, techniques, modeling, hindered, inaccuracies, combines, simulations, mcnp6, code, hpge, supplemented, special, setup, neutron, sources, solutions, investigated, materials, consistently, showed, significant, discrepancies, endf, viii, jeff, jendl, provides, crucial, necessary, refining, future, evaluations, simultaneously, confirms, reliability, monitoring, flux, mixed, fields, contribute, reliable, safety, lifetime, assessments, klusoň, jaroslav, krása, antonín, košťál, michal, czakoj, tomáš, studium, promptního, gama, záření, jeho, vlivu, reaktorovou, dozimetrii, effect, doctoral, aim, interdisciplinary, characterize, dementia, lewy, bodies, well, synucleinopathy, often, progresses, into, serves, marker, signal, statistical, identified, distinctive, patterns, acoustic, linguistic, non, verbal, drug, naïve, novo, stage, our, automated, abilities, may, procedures, controlled, clinical, unconstrained, real, world, novotný, 2025, computerized, candidates, temporary, medical, devices, due, biodegradability, favorable, accelerate, implants, driven, elucidate, complex, screens, within, biocompatible, compositional, limits, treating, degradation, constraint, rather, explicit, target, 410, six, different, predict, yield, ultimate, tensile, elongation, among, ensemble, demonstrated, 950, uts, 916, 903, shapley, additive, explanation, thermomechanical, alloying, elements, most, influential, factors, governing, validation, confirmed, generalization, capability, capturing, process, optimized, model, further, employed, maps, visualizing, ductility, trade, off, function, establishes, validated, rapid, silico, targeted, next, generation, tesař, ryjáček, baláž, beneš, nandal, elsevier, accelerating, approach, background, fusions, critical, drivers, oncogenesis, biomarkers, various, cancers, detection, rna, sequencing, when, performed, traditional, encounters, challenges, related, complexity, noise, although, robust, usually, requires, large, labeled, datasets, substantial, resources, pre, pangenome, scale, offer, solution, issues, presents, first, comprehensive, benchmark, four, based, nucleotide, hyenadna, curated, extracted, kilobase, pair, kbp, surrounding, evaluated, representations, qualitatively, sne, visualization, quantitatively, lightweight, classifiers, vector, machines, simple, neural, networks, fixed, achieved, score, result, outperformed, 894, second, performer, 920, demonstrating, derived, evolutionary, pretraining, conversely, failed, compete, 677, 723, furthermore, efficiency, only, 600, reach, peak, whereas, over, conclusions, highly, discriminative, out, box, significantly, baselines, while, requiring, fraction, time, suggests, could, scalable, efficient, way, developing, precise, tools, rare, diseases, klempíř, kollinová, dvorský, komárková, krupička, biomed, benchmarking, binary, surveys, two, decades, unifying, idea, running, formulate, tasks, solve, metaheuristic, resulting, either, established, metaheuristics, adapted, novel, designed, specifically, respective, they, applied, three, classes, missions, inspection, serve, online, solvers, greedy, plans, obtained, continuous, under, realistic, sensor, motion, practical, relevance, formulations, illustrated, diverse, set, application, scenarios, including, aware, micro, aerial, vehicle, long, term, autonomy, human, populated, source, observation, living, honeybee, colonies, route, open, pit, mining, kulich, mobile, robotics, recent, submissions, publishing, activity, proceedings, masaryk, studies, klokner, technology, biomedical, transportation, architecture, physical, electrical, civil, access, publications, theses, academic, works, explore, statistics, browse, communities, collections, log, skip, main, content, dspace, repository, home,

Text of the page (random words):
dspace repository home skip to main content digital library log in communities collections browse statistics search explore ctu s digital library access research publications theses and academic works search faculty of civil engineering faculty of mechanical engineering faculty of electrical engineering faculty of nuclear sciences and physical engineering faculty of architecture faculty of transportation sciences faculty of biomedical engineering faculty of information technology klokner institute masaryk institute of advanced studies central library acta polytechnica acta polytechnica ctu proceedings ctu publishing activity recent submissions habilitation thesis routing problems in mobile robotics 2026 kulich m show more this habilitation thesis surveys more than two decades of my research in robotic mission planning the unifying idea running through this thesis is to formulate mission planning tasks as routing problems studied in operations research and to solve them using metaheuristic methods the resulting methods are either established metaheuristics adapted to robotic problems or novel approaches designed specifically for the respective problems they are applied to three classes of robotic missions exploration inspection and search and serve as both online decision making and offline solvers we show that decision making strategies for exploration and search defined as routing problems can outperform greedy strategies and that high quality offline mission plans can be obtained even in continuous environments and under realistic sensor and motion models the practical relevance of the studied formulations is illustrated through a diverse set of application scenarios including localization aware exploration by a micro aerial vehicle long term autonomy in human populated environments radiation source localization robotic observation of living honeybee colonies and route planning for open pit mining operations show more journal article benchmarking genomic foundation models for binary classification of gene fusion breakpoints from dna sequences biomed central 2026 krupička r komárková m dvorský b kollinová k klempíř o show more background gene fusions are critical drivers of oncogenesis and diagnostic biomarkers in various cancers however their detection from rna or dna sequencing when performed using traditional analytical methods encounters challenges related to sample quality computational complexity and noise although deep learning is more robust it usually requires large labeled datasets and substantial training resources genomic foundation models gfms which are pre trained on pangenome scale data offer a promising solution to these issues methods this study presents the first comprehensive benchmark of four transformer based gfms nucleotide transformer nt evo2 hyenadna and dnabert2 for the classification of gene fusion breakpoints using the curated fusionai dataset of 52 000 sequences we extracted embeddings from 10 kilobase pair kbp dna sequences surrounding fusion breakpoints we evaluated the quality of these representations qualitatively using t sne visualization and quantitatively by training lightweight classifiers support vector machines and simple neural networks on the fixed embeddings results nt achieved the best performance with an accuracy of 0 967 and an f1 score of 0 967 this result outperformed the dedicated deep learning baseline fusionai with an accuracy of 0 894 evo2 was the second best performer accuracy 0 920 demonstrating robustness derived from evolutionary pretraining conversely dnabert2 failed to compete accuracy 0 677 0 723 furthermore sample efficiency analysis revealed that nt required only 2 600 samples to reach 95 of its peak performance whereas the baseline required over 14 000 samples conclusions these findings demonstrate that advanced gfms particularly the nt and evo2 models generate highly discriminative out of the box embeddings these embeddings significantly outperform dedicated deep learning baselines while requiring a fraction of the training data and computational time this suggests that gfms could be a scalable data efficient way of developing precise genomic diagnostic tools particularly for rare diseases show more journal article accelerating the design of resorbable magnesium alloys a machine learning approach to property prediction elsevier 2026 nandal v beneš v baláž p ryjáček j tesař k show more resorbable magnesium mg alloys are promising candidates for temporary medical devices due to their biodegradability and favorable mechanical properties to accelerate the design of diluted mg alloys for implants we developed a data driven framework to elucidate the complex relationships between composition processing and mechanical properties the framework screens mechanical properties within biocompatible compositional limits treating degradation as a design constraint rather than an explicit prediction target using a dataset of 410 samples we trained six different machine learning ml models to predict yield strength ultimate tensile strength and elongation among them ensemble models particularly catboost demonstrated high predictive accuracy r2 ys 0 950 uts 0 916 and el 0 903 shapley additive explanation analysis revealed that thermomechanical processing conditions and alloying elements such as zn mn and gd are the most influential factors governing mechanical behavior in diluted mg alloys validation on the experimental dataset confirmed the models robustness and generalization capability in capturing process property relationships the optimized catboost model was further employed to generate predictive property maps visualizing the strength ductility trade off as a function of zn mn composition this work establishes a validated ml framework for rapid in silico screening and targeted design of next generation resorbable mg alloys show more habilitation thesis computerized analysis of communication disorders in α synucleinopathies 2025 novotný m show more the aim of this interdisciplinary habilitation thesis is to characterize communication disorders in α synucleinopathies such as parkinson s disease dementia with lewy bodies and multiple system atrophy as well as in rem sleep behavior disorder which is an α synucleinopathy that often progresses into a defined neurodegenerative disease and therefore serves as an important prodromal marker using digital signal processing machine learning methods and advanced statistical approaches we identified distinctive patterns in acoustic linguistic and non verbal communication in drug naïve de novo parkinson s disease multiple system atrophy and even in a prodromal neurodegenerative stage of rem sleep behavior disorder our findings demonstrate that automated analysis of communication abilities may support screening and diagnostic procedures both in controlled clinical environments and in unconstrained real world conditions show more doctoral thesis study of prompt gamma radiation and its effect on reactor dosimetry studium promptního gama záření a jeho vlivu na reaktorovou dozimetrii czech technical university in prague czakoj tomáš košťál michal krása antonín klusoň jaroslav show more prompt gamma radiation is important in reactor dosimetry shielding and analytical techniques however its accurate modeling is hindered by inaccuracies in current nuclear data libraries therefore this work combines computational simulations using the mcnp6 2 code with experimental measurements using hpge and stilbene detectors at the lr 0 and vr 1 research reactors supplemented by measurements on a special setup using neutron sources and solutions of the investigated materials the results consistently showed significant discrepancies between measurements and calculations using current nuclear data libraries such as endf b viii 0 jeff 3 3 and jendl 5 this work provides crucial experimental data necessary for refining future evaluations and simultaneously confirms the reliability of stilbene detectors for monitoring gamma flux in mixed fields these findings contribute to more accurate dosimetry calculations and more reliable safety and lifetime assessments of nuclear reactors show more load more 2026 czech technical university in prague developed and provided by computing and information centre cookie settings send feedback about