Search the digital library catalog

Abstract: The use of large language models with chatbots like ChatGPT has become increasingly popular among students, especially in Computer Science education. However, significant debates exist in the education community on the role of ChatGPT in learning. Therefore, it is critical to understand the potential impact of ChatGPT on the learning, engagement, and overall success of students in classrooms. In this empirical study, we report on a controlled experiment with 182 participants in a first-year undergraduate course on object-oriented programming. Our differential study divided students into two groups, one using ChatGPT and the other not using it for practical programming assignments. The study results showed that the students’ performance is not influenced by ChatGPT usage (no statistical significance between groups with a p-value of 0.730), nor are the grading results of practical assignments (p-value 0.760) and midterm exams (p-value 0.856). Our findings from the controlled experiment suggest that it is safe for novice programmers to use ChatGPT if specific measures and adjustments are adopted in the education process.
Keywords: large language models, ChatGPT, artificial intelligence, controlled experiment, object-oriented programming, software engineering education
Published in DKUM: 12.08.2024; Views: 59; Downloads: 6
Full text (492,37 KB)

Abstract: Traveling Salesman Problems (TSPs) have been a long-lasting interesting challenge to researchers in different areas. The difficulty of such problems scales up further when multiple objectives are considered concurrently. Plenty of work in evolutionary algorithms has been introduced to solve multi-objective TSPs with promising results, and the work in deep learning and reinforcement learning has been surging. This paper introduces a multi-objective deep graph pointer network-based reinforcement learning (MODGRL) algorithm for multi-objective TSPs. The MODGRL improves an earlier multi-objective deep reinforcement learning algorithm, called DRL-MOA, by utilizing a graph pointer network to learn the graphical structures of TSPs. Such improvements allow MODGRL to be trained on a small-scale TSP, but can find optimal solutions for large scale TSPs. NSGA-II, MOEA/D and SPEA2 are selected to compare with MODGRL and DRL-MOA. Hypervolume, spread and coverage over Pareto front (CPF) quality indicators were selected to assess the algorithms’ performance. In terms of the hypervolume indicator that represents the convergence and diversity of Pareto-frontiers, MODGRL outperformed all the competitors on the three well-known benchmark problems. Such findings proved that MODGRL, with the improved graph pointer network, indeed performed better, measured by the hypervolume indicator, than DRL-MOA and the three other evolutionary algorithms. MODGRL and DRL-MOA were comparable in the leading group, measured by the spread indicator. Although MODGRL performed better than DRL-MOA, both of them were just average regarding the evenness and diversity measured by the CPF indicator. Such findings remind that different performance indicators measure Pareto-frontiers from different perspectives. Choosing a well-accepted and suitable performance indicator to one’s experimental design is very critical, and may affect the conclusions. Three evolutionary algorithms were also experimented on with extra iterations, to validate whether extra iterations affected the performance. The results show that NSGA-II and SPEA2 were greatly improved measured by the Spread and CPF indicators. Such findings raise fairness concerns on algorithm comparisons using different fixed stopping criteria for different algorithms, which appeared in the DRL-MOA work and many others. Through these lessons, we concluded that MODGRL indeed performed better than DRL-MOA in terms of hypervolumne, and we also urge researchers on fair experimental designs and comparisons, in order to derive scientifically sound conclusions.
Keywords: multi-objective optimization, traveling salesman problems, deep reinforcement learning
Published in DKUM: 28.03.2024; Views: 184; Downloads: 26
Full text (7,89 MB)
This document has many files! More...

Abstract: Športniki, sploh vrhunski so vsakodnevno izpostavljeni stresu, ki dolgoročno ne prinaša pozitivnih posledic. Zato je bil namen naše diplomske naloge raziskati in pojasniti načine, ki bi lahko športniku pozitivno pripomogli pri borbi s stresom. Prav tako je namen tega dela, da bi športniki le tega prebrali in se v primeru stresa odločili za strategije in tehnike, ki so opisane v nalogi, ter bi si pobližje pogledali kako slabo je ne ukrepati, med tem ko že vse kaže na, da je čas, da nekaj ukrenejo.
Keywords: Strategije, tehnike, stres, športniki, premagovanje stresa
Published in DKUM: 25.09.2023; Views: 536; Downloads: 40
Full text (2,91 MB)

Abstract: V diplomskem delu smo opisali razvoj produkta TRONintegration. Produkt služi kot orodje za izdelavo integracije dveh sistemov (na primer TRONoffice in spletne trgovine Shopify). Orodje v osnovi temelji na podobnih funkcionalnostih obstoječega produkta Tray.io, vendar z veliko več možnostmi in dodelavami ter samostojno implementacijo. Opisali smo uporabljene tehnologije, raziskali smo knjižnico Syncfusion, ki nam je zelo pripomogla pri vizualnem prikazu diagrama. Ta najbolj pomembni del predstavlja potek same integracije in je sestavljen iz gradnikov: vozlišč in povezav. Raziskali smo področje orkestracije mikrostoritev in nato razvijali produkt po fazah ter ga na koncu testirali. S pomočjo dokumentacije smo uspešno izdelali orodje, ki omogoča izdelavo integracije dveh sistemov na intuitiven vizualen način in zanj ni potrebno veliko predznanja.
Keywords: integracija, diagram, korak, Angular, Syncfusion
Published in DKUM: 12.07.2023; Views: 679; Downloads: 124
Full text (2,64 MB)

Abstract: V magistrskem delu smo primerjali rezultate implementacij algoritmov ABC in WOA, napisanih v različnih programskih jezikih. Primerjali in analizirali smo vsega skupaj osem implementacij, ki so bile napisane v petih programskih jezikih. Rezultate za primerjavo implementacij smo pridobivali z desetimi optimizacijskimi funkcijami. Glavni cilj je bil odkriti in odpraviti razlike v izvornih kodah implementacij algoritmov, zaradi katerih je prihajalo do razlik v rezultatih. Tako smo dobili rezultate, v katerih so bile vse implementacije enako uspešne.
Keywords: evolucijski algoritmi, primerjava rezultatov, optimizacijske funkcije, ABC, WOA
Published in DKUM: 25.10.2022; Views: 595; Downloads: 55
Full text (3,49 MB)