Linköping Electronic Conference Proceedings
Not a member yet
1113 research outputs found
Sort by
Detecting and Segmenting Solar Farms in Satellite Imagery: A Study of Deep Neural Network Architectures
Get PDFIn line with global sustainability goals, such as the Paris Agreement, accurate mapping, monitoring, and management of solar farms are critical for achieving net zero emissions by 2050. However, many solar installations remain undocumented, posing a challenge. This paper studies semantic segmentation using deep neural networks, including networks constructed using network architecture search (NAS), for solar farm detection. Semantic segmentation has evolved through technologies like Fully Convolutional Networks and U-Net, which have shown strong performance on satellite imagery. For NAS, Differentiable Architecture Search and its variants like Auto-DeepLab have become efficient ways to automate the creation of neural network architectures. This work compares models generated using Auto-DeepLab to Solis-seg, a Deep Neural Network optimized for detecting solar farms in satellite imagery. Solis-seg achieves a mean Intersection over Union (IoU) of 96.26% on a European Sentinel-2 dataset, with Auto-DeepLab models lagging slightly behind. Our results for Solis-seg also challenge the prevailing method of using transfer learning from classification tasks for semantic segmentation. Thus, this work contributes to both the field of earth observation machine learning and the global transition to renewable energy by studying an efficient, scalable approach to tracking solar installations. We believe that this paper offers valuable insights into applying advanced machine learning techniques to solar farm detection and can be useful for further research in earth observation and sustainability
The Social Life of Algorithmic Values: Examining the Impact of Value-Based Frameworks in Everyday Life
Get PDFValue-based frameworks are widely used to guide the design of algorithms, yet their influence in mediating users’ perception and use of algorithm-driven technologies is vastly understudied. Moreover, there is a need to move research beyond a focus on human-algorithm interaction to account for how the values these frameworks promote – algorithmic values – become socialised outside the boundaries of the (human-algorithm) interaction and how they influence everyday practices that are not algorithmically mediated. This paper traces the entanglement of algorithmic values and everyday life by mapping how residents of the Salvadorian town of El Zonte perceive the top-down transition of the town into "Bitcoin Beach" through value-driven transformations to diverse aspects of their material culture and built environment. This approach advances empirical research on the impact of algorithms by acknowledging the myriad ways in which those who won’t or can’t (afford to) interact with algorithm-driven technologies are impacted by the value-based outcomes of their programming and provides novel insights for critically examining the role of algorithm-driven technologies in shaping sustainable futures
A Clearer View on Fairness: Visual and Formal Representations for Comparative Analysis
Get PDFThe opaque nature of machine learning systems has raised concerns about whether these systems can guarantee fairness. Furthermore, ensuring fair decision making requires the consideration of multiple perspectives on fairness.At the moment, there is no agreement on the definitions of fairness, achieving shared interpretations is difficult, and there is no unified formal language to describe them. Current definitions are implicit in the operationalization of systems, making their comparison difficult.In this paper, we propose a framework for specifying formal representations of fairness that allows instantiating, visualizing, and comparing different interpretations of fairness. Our framework provides a meta-model for comparative analysis. We present several examples that consider different definitions of fairness, as well as an open-source implementation that uses the object-oriented functional language Soda
Should You Trust Your Voice Assistant? It’s Complicated, but No
Get PDFThe widespread use of voice-assisted applications using artificial intelligence raises questions about the dynamics of trust and reliance on these systems. While users often rely on these applications for help, instances where users face unforeseen risks and heightened challenges have sparked conversations about the importance of fostering trustworthy artificial intelligence. In this paper, we argue that the prevailing narrative of trust and trustworthiness in relation to artificial intelligence, particularly voice assistants, is misconstrued and fundamentally misplaced. Drawing on insights from philosophy and artificial intelligence literature, we contend that artificial intelligence systems do not meet the criteria for participating in a relationship of trust with human users. Instead, a narrative of reliance is more appropriate. However, we investigate the matter further to explore why the trust/trustworthiness narrative persists, focusing on the unique social dynamics of interactions with voice assistants. We identify factors such as diverse modalities and complexity, social aspects of voice assistants, and issues of uncertainty, assertiveness, and transparency as contributors to the trust narrative. By disentangling these factors, we shed light on the complexities of human-computer interactions and offer insights into the implications for our relationship with artificial intelligence. We advocate for a nuanced understanding of trust and reliance in artificial intelligence systems and provide suggestions for addressing the challenges posed by the dominance of the trust/trustworthiness narrative
Queerlit – a bibliography of Swedish fiction with LGBTQI topics
Get PDFThis paper summarizes the project Queerlit: Metadata and Searchability for LGBTQ+ Literary Heritage 2020-2023 and discusses some challenges in the development of this resource. The Queerlit project consist of four parts: 1. Creating a bibliography of Swedish fiction with LGBTQI themes 2. Creating a Swedish thesaurus (QLIT), adapted from the of the linked open data thesaurus Homosaurus 3. Assigning all material in the bibliography with subject headings from QLIT. 4. A web user interface for searching the material All four parts are integrated with the Swedish union catalog, Libris, making the results of the project available for all under a CC0 license. QLIT is the first external thesaurus integrated in the linked open data framework used in the technical platform of Libris, XL. The bibliography spans from rune stones from the 7th century to recently published fiction. When applying subject headings for the material both general aspects of the work and specific LGBTQI topics are described, making this the most comprehensive retrospective indexing project of Swedish literature to date. The underlying knowledge organization is made a prominent method of interacting with the search interface, which is empirically designed around the needs of various user groups
Collectio: a software especially designed for creating dynamic libraries for fluid and multilingual text traditions
Get PDFThis contribution presents a new software, Collectio, which can be used for creating highly complex relational MySQL databases, or more accurately, dynamic libraries. These libraries prove particularly well-suited for texts where the material has been organized in different ways and thus represents a ‘fluid’ textual tradition, or in traditions transmitted in many languages. So far, two libraries have been created using Collectio: APDB (the Apophthegmata Patrum Database) and HIPPO, which contains pre-modern hippiatric material. The sources included in the libraries are mainly in the form of manuscripts, editions and modern translations. Collectio employs a unique input model, built upon .txt and .csv files stored in an archive in the folder of the library. The contents of the database tables in the master database are generated from these documents. Since not only texts are registered but also the detailed structure and parallel text segments in other sources, both texts and structures can be systematically compared and analysed within and across language boundaries. In addition to the advanced research tools for comparing texts and structures, the application contains search options, indexes of names, places and concepts, metadata on the sources, pre-written SQL commands and more. A new way of encoding text, which can be converted into TEI/XML, is also introduced
STUnD: ett Sökverktyg för Tvåspråkiga Universal Dependencies-trädbanker
Get PDFFöreliggande artikel introducerar STUND, ett Sökverktyg för Tvåspråkiga Universal Dependencies-trädbanker som möjliggör parallella syntaktiska sökningar. Vi demonstrerar dess praktiska tillämpning i en fallstudie på tempusformen presens perfekt i svenska och engelska. Resultaten visar att presens perfekt används i ungefär lika stor utsträckning i båda språken, men att det förekommer viss variation som verkar bero på språkspecifika konventioner och översättningsstrategier
Samförfattande som datadriven tvärvetenskap: Pragmatiska lärdomar från SweTerror-projektet
Get PDFTerrorism i svensk politik (SweTerror) är ett storskaligt tvärvetenskapligt forskningsprojekt med forskare från såväl human- och samhällsvetenskaperna som datavetenskaperna. Samtidigt använder och utvecklar SweTerror nationell forskningsinfrastruktur för riksdagsdata. Detta paper beskriver användningen av samförfattande som en datadriven tvärvetenskaplig praktik för att integrera olika vetenskapliga perspektiv och skapa samsyn i projektforskningen. Vi tar fasta på betydelsen av valet att koncentrera samarbetsformen kring konferenspapers inom specifikt digital humaniora och diskuterar erfarenheten av att samskrivande försvagar vetenskapligt revirtänkande, liksom ett iterativt förhållningssätt till forskningsdata kopplade till forskningsinfrastrukturer under uppbyggnad. Avslutningsvis betonar vi datadrivet samförfattande som en pragmatisk praktik för att stärka kollaborativt samarbete och kunskapsbryggor inom en tvärvetenskaplig forskargrupp
MWE-Finder: An evaluation through three case studies
Get PDFIn this paper we showcase and evaluate MWE-Finder, a system that allows users to search for occurrences of an MWE in a large Dutch text corpus. To this end, we conduct three small case studies, and discuss the results in detail. We make use of the MWEs 0geen *+haan zal naar iets kraaien ‘no one will say anything about something’, iemand zal 0dat *+varken wassen ‘someone will deal with that problem’ and iemand zal iemand het hemd van het lijf vragen ‘someone will want to know all the ins and outs of something from someone’, which are all in canonical form following Odijk (2023) and Odijk and Kroon (2024).
The results show that MWE-Finder is very accurate in retrieving the target MWEs, reaching an accuracy of 93.7%, and an F1-score of 95.2%. The case studies additionally lay bare points of improvement of MWE-Finder, specifically concerning the enrichment of syntactic parses by making the object relation explicit in certain constructions
The LiRI Corpus Platform
Get PDFWe present the LiRI Corpus Platform (LCP), a software system and infrastructure for querying a vast array of corpora of different kinds. It heavily relies on the PostgreSQL relational database management system, employing state-of-the-art data representation and indexing techniques, which lead to significant performance gains when querying, even for structurally complex queries involving nested logical operations and quantifiers. In this work, we describe the requirements that led to the development of this novel system, discuss methods from corpus linguistics and beyond that we considered key for such a system, and provide details on a number of technological features that we take advantage of. Our platform also comes with its own query language tailored both to the requirements in terms of information need and our philosophy of how to define corpora in an abstract way