Search the digital library catalog

Abstract: Nowadays, technological progress has promoted the integration of artificial intelligence into modern human lives rapidly. On the other hand, extreme weather events in recent years have started to influence human well-being. As a result, these events have been addressed by artificial intelligence methods more and more frequently. In line with this, the paper focuses on searching for predicting the air temperature in a particular Slovenian micro-location by using a weather prediction model Maximus based on a longshort term memory neural network learned by the long-term, lower-resolution dataset CERRA. During this huge experimental study, the Maximus prediction model was tested with the ICON-D2 general-purpose weather prediction model and validated with real data from the mobile weather station positioned at a specific micro-location. The weather station employs Internet of Things sensors for measuring temperature, humidity, wind speed and direction, and rain, while it is powered by solar cells. The results of comparing the Maximus proposed prediction model for predicting the air temperature in micro-locations with the general-purpose weather prediction model ICON-D2 has encouraged the authors to continue searching for an air temperature prediction model at the micro-location in the future.
Keywords: long short-term memory neural networks, air temperature, micro-location, prediction, weather, Internet of Things
Published in DKUM: 25.09.2025; Views: 0; Downloads: 3
Full text (8,81 MB)

Abstract: The thesis explores the theme of nostalgia in George Orwell’s novel Coming Up for Air from various analytical perspectives. The research is made possible by the novel’s detailed story, which captures the tensions between the individual and a rapidly modernising world in pre-World War II Britain. The work is structured into three main sections. First, the theoretical framework provides an overview of different definitions and interpretations of nostalgia from literature, history, and cultural studies. Second, various philosophical perspectives examine the relationship between nostalgia, personal identity, and the individuals’ ways of approaching the memory. From the standpoint of existentialism and the self, the thesis investigates how the protagonist, George Bowling, experiences nostalgia as a mechanism for self-definition. The thesis argues that nostalgia distorts the temporal order, merging past and present into a seamless but fictional continuum. The political philosophy and modernity perspectives place the main character’s nostalgia within the broader socio-political status of 20th century Britain. Orwell employs nostalgia to critique the oppressive forces of industrialisation, totalitarian governance, and capitalist consumerism. Third, the linguistic analysis applies Systemic Functional Linguistics (SFL), using the discourse system framework developed by authors Martin and Rose (2007), to examine how Orwell’s language constructs the protagonist’s nostalgic experience. The analysis looks at how Orwell’s linguistic features show Bowling’s emotional attachment to the past and his disappointment with the present. Engagement is analysed to reveal how the protagonist’s reflections position the reader within his subjective perspective.
Keywords: Nostalgia, George Orwell, Coming Up for Air, Existentialism, Memory, Self-Identity, Political Philosophy, Systemic Functional Linguistics, Time, History.
Published in DKUM: 29.05.2025; Views: 0; Downloads: 29
Full text (2,45 MB)

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...

Abstract: This article approaches personal memory travels with the aim of investigating people’s encounters with the changing environment in relation to time. It centers on the intra-actions with perceptual ephemera as immaterial non-solid entities to argue that our relational reality is a cyclical, dis-continuous process of past and present encounters. The study is grounded in the post-humanist performativ-ity approach and based on personal life histories of memory trips gathered in Slovenia with the help of in-depth interviews and photo-elicitation. Findings suggest that travelers’ engagements with ephemera at site illustrate complex entanglements between human and other (immaterial) entities as co-constituted in time and from within time, provoking the production of situated and temporally sensitive knowledge about the more-than-human world. The article endorses the significance of memory work and human engagements with absences and resonances, both allusions to other (past) contexts, as fundamental for cultivating post-anthropocentric attitudes and advancing the habit of timefulness.
Keywords: personal memory travel, encounters, environment, absence, anthropocene, ephemera, memory, time, trave
Published in DKUM: 16.02.2024; Views: 255; Downloads: 21
Full text (1,42 MB)
This document has many files! More...

Abstract: Working memory is important for a number of higher cognitive functions such as problem solving, reasoning, reading and language comprehension. Moreover, working memory measures are significantly correlated with measures of intellectual abilities. Investigating the neural basis of working memory provides the opportunity to gain a deeper understanding of individual differences in general cognitive ability. This thesis aimed to elucidate the roles of brain oscillations in working memory, with a particular focus on theta and gamma frequency bands. Two techniques were employed that are best suited for the non-invasive study of brain oscillations: scalp recorded EEG and transcranial alternating current stimulation (tACS). In the first step, correlational studies were conducted followed by neuromodulatory studies in the next step. The results showed that individuals with high working memory capacity, contrasted against individuals with low working memory capacity, display stronger alpha and gamma band desynchronisation and increased coherence in the theta frequency band between fronto- parietal areas during maintenance and between frontal brain areas during retrieval. The results further demonstrated that interactions between theta and gamma frequency bands are related to individual differences in working memory capacity. The neuromodulatory studies showed that theta tACS applied over parietal brain areas can be used to enhance performance on working memory tasks, thereby providing support for the causal role of theta band oscillations in working memory.
Keywords: working memory, brain oscillations, capacity, electroencephalograpy, tACS, theta, gamma
Published in DKUM: 28.07.2017; Views: 2099; Downloads: 216
Full text (3,46 MB)