1. Programirljivo precizno elektronsko breme manjših moči : magistrsko deloAnže Jančič, 2025, master's thesis Abstract: V magistrskem delu smo načrtali, izdelali, sprogramirali ter testirali precizno elektronsko breme manjših moči ter visokega dinamičnega razpona za testiranje napajalnih sklopov IoT in podobnih naprav. Vezje deluje na principu napetostno-tokovne pretvorbe ter povratne vezave preko operacijskega ojačevalnika za natančno regulacijo toka. Ta je izvedena preko padca napetosti na merilnem uporu. Bremenski element je tranzistor MOSFET. Breme ima zaradi visokega dinamičnega območja, ki znaša 10⁶ tri kanale. Ključni elementi v vezju so MOSFET, operacijski ojačevalniki, digitalno analogni pretvorniki, mikrokrmilnik ter modul Bluetooth.
Keywords: breme, programirljivo, MOSFET, IOT, mikrokrmilnik
Published in DKUM: 17.10.2025; Views: 0; Downloads: 7
 Full text (4,03 MB) |
2. Samodejno odkrivanje anomalij v dnevniških zapisih omrežnega stikala z uporabo nevronskih mrež na grafihAnže Dolenc, 2025, master's thesis Abstract: V magistrski nalogi obravnavamo zaznavanje anomalij v dnevniških zapisih omrežnega stikala z uporabo nevronskih mrež nad grafi. Klasične metode analize logov nadomestimo s pristopom Log2Graph, ki dnevniške zapise pretvori v grafe s pomočjo razčlenjevalnika Drain in vektorskih predstavitev GloVe ter TF-IDF. Za učenje uporabljamo model DiGCN in preučimo vpliv vrednosti hiperparametrov, deleža anomalij ter kontaminacije učne množice na uspešnost zaznavanja anomalij. Rezultate ocenimo z metrikami AP, ROC AUC in F1. Pristop izkazuje robustnost in prilagodljivost pri zaznavanju anomalij v realnih omrežnih podatkih.
Keywords: dnevniški zapisi, omrežno stikalo, zaznava anomalij, strojno učenje, Log2Graph
Published in DKUM: 10.07.2025; Views: 0; Downloads: 31
Full text (4,49 MB) |
3. Vpliv napak razpoznavalnika govora na kakovost strojnih prevodov v sistemih prevajanja govora v govor : magistrsko deloKlemen Stanič, 2025, master's thesis Abstract: Magistrsko delo analizira vpliv napak avtomatskega razpoznavalnika govora na kakovost strojnih prevodov v sistemih prevajanja govora v govor. S prevajalnikom smo prevedli več izhodov razpoznavalnika govora, ki so se med seboj razlikovali v kvaliteti razpoznavanja, kot referenčne prevode pa smo vzeli prevod nabora povedi, ki je bil uporabljen na vhodu v razpoznavalnik. Tipi napak, ki smo jih obravnavali, so bili: vstavljanje, brisanje in zamenjava besede. V nadaljevanju smo jih še podrobneje razdelali glede na besedne vrste in obseg spremembe. Vpliv napak na kakovost prevodov smo ocenjevali z metriko BLEU. Ugotovili smo, da določene vrste napak bolj vplivajo na kakovost prevoda kakor druge.
Keywords: razpoznavanje govora, strojno prevajanje, napaka razpoznavalnika, nevronske mreže, BLEU
Published in DKUM: 31.03.2025; Views: 0; Downloads: 32
Full text (2,35 MB) |
4. On the use of morpho-syntactic description tags in neural machine translation with small and large training corporaGregor Donaj, Mirjam Sepesy Maučec, 2022, original scientific article Abstract: With the transition to neural architectures, machine translation achieves very good quality for several resource-rich languages. However, the results are still much worse for languages
with complex morphology, especially if they are low-resource languages. This paper reports the
results of a systematic analysis of adding morphological information into neural machine translation
system training. Translation systems presented and compared in this research exploit morphological
information from corpora in different formats. Some formats join semantic and grammatical information and others separate these two types of information. Semantic information is modeled using
lemmas and grammatical information using Morpho-Syntactic Description (MSD) tags. Experiments
were performed on corpora of different sizes for the English–Slovene language pair. The conclusions
were drawn for a domain-specific translation system and for a translation system for the general
domain. With MSD tags, we improved the performance by up to 1.40 and 1.68 BLEU points in the
two translation directions. We found that systems with training corpora in different formats improve
the performance differently depending on the translation direction and corpora size.
Keywords: neural machine translation, POS tags, MSD tags, inflected language, data sparsity, corpora size
Published in DKUM: 28.03.2025; Views: 0; Downloads: 11
Full text (448,16 KB)
This document has many files! More... |
5. |
6. Navodila za snemanje za portal Govorjena slovenščinaDarinka Verdonik, Andreja Bizjak, Gregor Donaj, Boštjan Makarovič, Cristina Contero Almagro, 2025, treatise, preliminary study, study Keywords: portal Govorjena slovenščina, snemanje govora
Published in DKUM: 04.02.2025; Views: 0; Downloads: 6
Full text (307,37 KB) |
7. Sequence-to-Sequence models and their evaluation for spoken language normalization of SlovenianMirjam Sepesy Maučec, Darinka Verdonik, Gregor Donaj, 2024, original scientific article Abstract: Sequence-to-sequence models have been applied to many challenging problems, including
those in text and speech technologies. Normalization is one of them. It refers to transforming
non-standard language forms into their standard counterparts. Non-standard language forms
come from different written and spoken sources. This paper deals with one such source, namely
speech from the less-resourced highly inflected Slovenian language. The paper explores speech
corpora recently collected in public and private environments. We analyze the efficiencies of three
sequence-to-sequence models for automatic normalization from literal transcriptions to standard
forms. Experiments were performed using words, subwords, and characters as basic units for
normalization. In the article, we demonstrate that the superiority of the approach is linked to the
choice of the basic modeling unit. Statistical models prefer words, while neural network-based
models prefer characters. The experimental results show that the best results are obtained with
neural architectures based on characters. Long short-term memory and transformer architectures
gave comparable results. We also present a novel analysis tool, which we use for in-depth error
analysis of results obtained by character-based models. This analysis showed that systems with
similar overall results can differ in the performance for different types of errors. Errors obtained with
the transformer architecture are easier to correct in the post-editing process. This is an important
insight, as creating speech corpora is a time-consuming and costly process. The analysis tool also
incorporates two statistical significance tests: approximate randomization and bootstrap resampling.
Both statistical tests confirm the improved results of neural network-based models compared to
statistical ones.
Keywords: low-resource language, applications, spoken language, normalization, character unit, subword unit, statistical model, long short-term memory, transformer, error analysis
Published in DKUM: 31.01.2025; Views: 0; Downloads: 8
Full text (437,99 KB)
This document has many files! More... |
8. Analiza algoritmov stiskanja na primeru tekstovnih datotek v različnih jezikihKlemen Arzenšek, 2024, master's thesis Abstract: Magistrsko delo obravnava različne algoritme stiskanja tekstovnih datotek in analizira, ali jezik, v katerem je zapisana vhodna datoteka, vpliva na uspešnost stiskanja z izbranimi algoritmi. Preučeni in predstavljeni bodo izbrani algoritmi stiskanja, ugotovljene prednosti uporabe izbranih algoritmov stiskanja tekstovnih datotek, določene entropije analiziranih jezikov na ravni znakov, izvedeni praktični testi izbranih algoritmov stiskanja tekstovnih datotek s testnimi vzorci različnih jezikov, analizirano in ugotovljeno, ali jezik v izbranih testnih vzorcih vpliva na uspešnost posameznih algoritmov stiskanja tekstovnih datotek. Delo bo iskalo povezave med entropijo jezika in uspešnostjo stiskanja. Na koncu bo na primeru Huffmanovega algoritma, ki kodira posamezne znake, preverjeno, ali kodiranje daljših nizov izboljša učinkovitost kodiranja.
Keywords: naravni jezik, entropija jezika, algoritmi stiskanja, algoritem LZW, tekstovne datoteke
Published in DKUM: 23.12.2024; Views: 0; Downloads: 27
Full text (2,04 MB) |
9. |
10. Implementacija hitre Fouriereve transformacije v digitalnem vezjuMatic Kuhar, 2024, undergraduate thesis Abstract: Diplomsko delo obravnava implementacijo Fouriereve transformacije v digitalnem vezju. Proučuje teoretične osnove Fouriereve transformacije in njeno praktično uporabo pri digitalni obdelavi signalov. Poseben poudarek je na praktičnem delu naloge, ki predstavlja programiranje oziroma kreiranje programa za algoritem FFT z opisnim programskim jezikom Verilog, ki je lahko implementiran v digitalno vezje. Naloga opisuje razvoj in optimizacijo algoritma FFT, vključno z evalvacijo zmogljivosti razvitega sistema v realnih aplikacijah.
Keywords: Implementacija FFT, algoritem FFT, digitalno vezje, DFT, Verilog
Published in DKUM: 22.10.2024; Views: 0; Downloads: 20
Full text (2,14 MB) |
