1,721,167 research outputs found
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Web editor for audio transcripts
No full textV diplomskem delu se ukvarjamo z razvojem urejevalnika zvočnih transkripcij, ki je prilagojen za uporabo v aplikaciji ON (Online Notes).
Urejevalnik mora podpirati številne funkcionalnosti, ki so specifične za urejanje zvočnih transkripcij.
Knjižnica, ki se uporablja v obstoječi različici spletnega portala ON, je zastarela in nima več tehnične podpore.
V diplomskem delu podamo ključne zahteve za tak urejevalnik in preučimo obstoječe rešitve in primerne knjižnice.
Eno od preverjenih knjižnic izberemo in argumentiramo njen izbor ter uporabimo za implementacijo podanih zahtev.
Zahteve, ki predstavljajo tehnične izzive, posebej opišemo in obrazložimo primerne rešitve.
Na koncu rešitev ovrednotimo tako, da primerjamo implementacijo posameznih funkcionalnosti z izhodiščnimi zahtevami.In this thesis we are developing a sound transcription editor.
The editor is designed to be used in the ON (Online Notes) application.
must support the stevile functionalities that are specific to editing audio transcripts.
transcripts. The notebook used in the existing version of the web portal
ON, is outdated and no longer technically supported. In this thesis we give
the key requirements for such an editor and review existing solutions and suitable
libraries. Select one of the proven libraries and justify its selection
and use it to implement the given requirements. Requirements representing
technical challenges, shall be described separately and appropriate solutions shall be explained. Finally
evaluate the solution by comparing the implementation of the individual functionalities.
ctionality with the baseline requirements
Generating light adapted trees using genetic algorithms
Full text linkV sklopu tega diplomskega dela je bila izdelana spletna aplikacija za samodejno generiranje svetlobi prilagojenih dreves. Za prilagajanje dreves svetlobi uporablja genetske algoritme. Za proceduralno generiranje dreves uporablja knjižnico procTree, ki predstavlja primer parametričnega modela za generiranje dreves. V prvem delu diplomskega dela bo predstavljena teorija, na podlagi katere je nastala končna aplikacija. Ta vsebuje: teorijo o generiranju dreves in teorijo o genetskih algoritmih. Temu sledi poglavje, ki opisuje implementacijo aplikacije. Ta poda način uporabe, opiše postopek generiranja dreves ter prilagajanja teh z uporabo genetskih algoritmov. Na kratko je opisana tudi izdelava uporabniškega vmesnika, paralelizacije in prikazovalnika. Zadnje poglavje prikazuje rezultate, dobljene z aplikacijo. Poglavje predstavi nekaj splošnih primerov generiranih dreves, opiše vpliv parametrov na generiranje dreves, prikaže interakcijo med drevesi in na koncu predstavi še nekaj težave ter možnih nadgradenj aplikacije.As a part of this bachelor\u27s theses a web application for automatic generation of light adapted trees was made. Genetic algorithms are used to adapt the trees towards the light source. The library ProcTree, which is an example of a parametric model for generating trees, is used to generate the trees. The first part of the theses contains the theory used in the creation of the application. The chapter consists of the following topics: tree generation theory and genetic algorithm theory. This chapter is followed by descriptions of the implementation of the application. Specifically the chapter talks about the usage of the application, it describes the process of tree generation and how this generation is influenced by genetic algorithms. It also describes the creation of the user interface and the renderer, and how the application is parallelized. The last chapter shows the results of the application. First some basic result are shown, than the effects of some parameters on the generation are explained, after that some interaction between trees are shown. The theses is concluded by a few problems and possible improvements of the application
Web crawler for searching Slovenian audio and video content with transcripts
No full textV Sloveniji primanjkuje gradiva za učenje govornih modelov, kar predstavlja oviro za nadaljnji razvoj tega področja. Rešitev predstavlja razvoj orodja za avtomatizirano iskanje zvočnega gradiva. Diplomsko delo obravnava izbiro orodja Scrapy za spletno pajkanje, napisanega v Pythonu in njegov razvoj. Spletni pajek je program ali programska skripta, ki avtomatizirano brska po spletu in vsebino shranjuje. Cilj našega pajka je iskanje avdio in video virov v slovenskem jeziku. Pri razvoju smo poudarek dali tudi na skladnost z zakonodajo in etičnimi smernicami. Poleg tega smo se poglobili v razvoj skripte za iskanje transkripcij posnetkov.
Raziskovanje temelji na deskriptivni metodi za predstavitev že obstoječih orodij za spletno pajkanje. Uporabljen je pregled pravnih aktov. Osredotočili smo se na Zakon o avtorskih in sorodnih pravicah ter Splošno uredbo o varstvu podatkov. Preučena je bila literatura o etičnih smernicah pajkanja, načinih vključevanja avdio in video vsebin na spletnih straneh ter načinih iskanja podobnosti med besedili.
Rezultati končnega testiranja so pokazali, da lahko spletni pajek uspešno pridobiva večje količine avdio in video virov. Od tega je 63,6 % posnetkov bilo v razločnem slovenskem govoru. Povzamemo lahko, da tudi skripta za iskanje transkripcij uspešno deluje. 16 posnetkom je bila najdena transkripcija s stopnjo podobnosti večjo od 0,9. Dokazali smo, da je z uporabo spletnih pajkov možno avtomatizirati pridobivanje zvočnih posnetkov. Diplomsko delo prispeva k napredku na področju slovenskih govornih tehnologij, saj nakaže kako na hitrejši in enostavnejši način nabrati velike količine zvočnega gradiva. Prav tako navede pogoje, kako to narediti zakonito in na prijazen način do spletnih strežnikov.In Slovenia, there is a shortage of learning material for training speech models, which poses a barrier to the further development of this field. The solution lies in the development of a tool for the automated retrieval of audio material. This thesis discusses the selection of the Scrapy tool for web crawling, written in Python, and its development. A web crawler is a program or script that automatically browses the web and stores its content. The goal of our crawler is to search for audio and video resources in the Slovenian language. During development, we also focused on compliance with legal and ethical guidelines. Additionally, we delved into the development of a script for searching for transcriptions of recordings.
The research is based on the descriptive method to present existing tools for web crawling. A review of legal acts was conducted, focusing on the Copyright and Related Rights Act and the General Data Protection Regulation. We also examined literature on ethical guidelines for web crawling, methods of embedding audio and video content on web pages and methods of finding similarities between texts.
The results of the final testing showed that the web crawler can successfully retrieve large quantities of audio and video resources. Of these, 63,6 % of the recordings were in distinct Slovenian speech. We can conclude that the script for searching for transcriptions also works successfully. Transcriptions with a similarity score greater than 0,9 were found for 16 recordings. We have demonstrated that using web crawlers can automate the retrieval of audio recordings. This thesis contributes to the advancement of Slovenian speech technologies, as it indicates how to collect large quantities of audio material more quickly and easily. It also outlines the conditions for doing so legally and in a server friendly manner
Developing an online platform for creating audiobooks
No full textTa naloga raziskuje načrtovanje, oblikovanje, razvoj in implementacijo spletnega sistema za ustvarjanje zvočnih knjig. Spletna aplikacija omogoča uporabnikom nalaganje besedilnih datotek (specifično dokumentov Microsoft Word), samodejno ekstrakcijo besedila iz naložene datoteke ter preoblikovanje besedila v razčlenjene stavke. Vsak stavek se nato lahko pretvori v avdio format z uporabo integriranega sistema za pretvorbo besedila v govor (TTS). Tehnologije in orodja, ki smo jih uporabili za razvoj spletne aplikacije vključujejo Node.js, JavaScript, MongoDB, Express.js, TTS API, Multer ipd. Projekt si prizadeva poenostaviti ustvarjanje zvočnih knjig z avtomatizacijo postopka pretvorbe in zagotavljanjem prilagodljivosti za uporabnike pri urejanju besedila, izbiri glasov in nadzoru nastavitev, kot so poudarjanje, tempo in normalizacija zvoka. Glavni cilj naloge je ustvariti ustrezno slovensko različico za aplikacije za ustvarjanje zvočnih knjig. Od že obstoječih rešitev, se bo naša aplikacija razlikovala v možnosti shranjevanja različnih verzij stavkov in možnosti izbiranja med njimi.This project explores the planning, design, development, and implementation of a web-based system for creating audiobooks. The web application allows users to upload text files (specifically Microsoft Word documents), automatically extract text from the uploaded file, and transform the text into parsed sentences. Each sentence can then be converted into an audio format using an integrated text-to-speech (TTS) system. The technologies and tools used for developing the web application include Node.js, JavaScript, MongoDB, Express.js, TTS API, Multer, and others. The project aims to simplify the audiobook creation process by automating the conversion process and providing users with flexibility in editing text, selecting voices, and controlling settings such as emphasis, tempo, and audio normalization. The primary goal of this project is to develop a suitable Slovenian version of audiobook creation applications. Compared to existing solutions, our application will stand out by offering the ability to store different versions of sentences and allowing users to choose between them
Automated heat pump control system
Full text linkLjudje že stoletja ogrevamo svoja bivališča na najrazličnejše načine. Sodobnejši in človeku prijaznejši načini so na voljo le s pritiskom na gumb in nastavitvijo željene temparature. Večkrat se bivališča grejejo tudi, ko nas ni doma in na temperature, ki nam ne predstavljajo ugodnega počutja. V magistrskem delu predstavljamo nadgradnjo obstoječega sistema toplotne črpalke, ki spremlja naše gibanje tudi izven naših bivališč, izklaplja naše toplotne sisteme, ko zazna, da bomo odsotni dlje časa in ogreje bivališče na nam ugodno temparaturo točno ob prihodu domov. Tako nam o predhodnih ročnih regulacijah ni potrebno popolnoma nič razmišljati. Poleg tega ohranimo precej nepotrebno potrošene energije in s tem posredno varujemo okolje. Ogrevalni sistem smo nadgradili z avtomatiziranim sistemom, ki je povezan z GPS sistemom mobilne naprave in omogoča strojno učenje glede na predhodne situacije. Rezultati analize delovanja novega sistema so pri povprečnih dnevnih zunanjih temperaturah med 7 in 9 stopinj Celzija pokazali tudi več kot 40 % prihrankov električne energije.For centuries, people have been using different types of heating systems. Modern and user-friendly systems are regulated just by pressing a button and setting the right temperature. Our homes can be heated when we are away and often reach unpleasant temperatures. In our master thesis, we presented an upgrade of the existing heat pump system that tracks our movement even when we are away from home. It recognises when we will be away for a longer period of time, switches off our heating as needed, and sets the right temperature at the exact time of our return. That means we do not have to worry about manual controls. In addition, we are protecting the environment and saving energy. The heating system has been upgraded with an automatic system that is connected to a mobile device through GPS and enables machine learning based on past behaviour. Analyses showed that using the new heating system at average outdoor temperatures between 7 and 9 degrees Celsius can reduce energy consumption for more than 40 %
- …
