检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Sousa, Samuel Kern, Roman Know-Center GmbH Institute of Interactive Systems and Data Science Graz University of Technology Graz Austria

Deep learning (DL) models for natural language processing (NLP) tasks often handle private data, demanding protection against breaches and disclosures. data protection laws, such as the European Union's General data Protection Regulation (GDPR), thereby enforce the need for privacy. Although many privacy-preserving NLP methods have been proposed in recent years, no categories to organize them have been introduced yet, making it hard to follow the progress of the literature. To close this gap, this article systematically reviews over sixty DL methods for privacy-preserving NLP published between 2016 and 2020, covering theoretical foundations, privacy-enhancing technologies, and analysis of their suitability for real-world scenarios. First, we introduce a novel taxonomy for classifying the existing methods into three categories: data safeguarding methods, trusted methods, and verification methods. Second, we present an extensive summary of privacy threats, datasets for applications, and metrics for privacy evaluation. Third, throughout the review, we describe privacy issues in the NLP pipeline in a holistic view. Further, we discuss open challenges in privacy-preserving NLP regarding data traceability, computation overhead, dataset size, the prevalence of human biases in embeddings, and the privacy-utility tradeoff. Finally, this review presents future research directions to guide successive research and development of privacy-preserving NLP models. © 2022, CC BY.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Architecture of Modern E-Learning Management System

Architecture of Modern E-Learning Management System

引用

Communications, Information, Electronic and Energy systems (CIEES), International Conference on

作者： Nikolai Scerbakov Alexander Schukin Eugenia Rezedinova Institute of Interactive Systems and Data Science Graz University of Technology Graz Austria Institute of Computer Science and Cybersecurity Peter the Great St. Petersburg Polytechnic University St. Petersburg Russia

Abstract-In contemporary educational institutions, a robust Learning Management System (LMS) plays an important role within the E-Learning infrastructure. An LMS serves as an organized repository for course materials while also incorporating vital communication features like discussion forums, annotations, and chats. The LMS encompasses tools designed to monitor students’ advancement through course materials and assess the knowledge they acquire during their learning journey. Since the LMS is a complex software application, which operates for extended periods of time, it needs a careful consideration of its design in terms of functionality, dependability, and lifecycle management. In this paper, we present the architecture of a modern LMS called WBT-Master. This architectural framework is referred to as CDAT, representing Controller, data, Activity, and Template. The "Activity" assumes a central role within the application. It processes the incoming data according to its designated purpose, and visualizes the data on the user’s screen. The “Template” element comprises HTML fragments containing placeholders The placeholders are bound to the activity variables. “Controllers” act as event handlers and load the different activities depending on user actions. “data Provider” offer a unified data representation on diverse data sources. We also explore the system’s data organization principles and its seamless integration with popular cloud services.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Survey on Usage of Multimedia databases for Emotion Elicitation: A Quantitative Report on How Content Diversity Can Improve Performance

A Survey on Usage of Multimedia Databases for Emotion Elicit...

引用

Proceedings of the International Convention MIPRO

作者： M. Horvat P. Jerčić Department of Applied Computing Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia Graz University of Technology Institute of Interactive Systems and Data Science Graz Austria

Affective picture databases provide a standardized set of images to elicit controlled and consistent emotional responses in research participants. They are a valuable tool for studying various emotion-related phenomena across several research domains. These domains include emotion perception, emotion regulation, and the neural basis of emotion. However, affective picture databases have diverse schemas, structures, and content, making them difficult to use. Searching and retrieving optimal pictures relevant to affective stimulation may be challenging and time-consuming. In this context, we surveyed domain experts about their practices and experiences working with affective multimedia databases such as IAPS, NAPS, OASIS, GAPED, and others. The survey identified a need for novel data observatory software. This finding motivates the authors’ intention to develop and validate such software platform that relies on AI. Such a platform would describe better, retrieve, and integrate various semi-structured affective multimedia datasets. The results prominently indicate the overwhelming dissatisfaction regarding stimuli content diversity and cultural bias, specifically regarding emotional and semantic context. The main driver of satisfaction from users of existing automated retrieval software is the quality of semantic descriptors available. This points to the direction AI should take in novel data observatory software. This survey follows up on a similar survey conducted ten years ago and explores the differences in researchers’ opinions and experiences during that time. The complete aggregated results are publicly available at https://***/mhorvat/stimdbsurvey.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Counting on AR: EEG responses to incongruent information with real-world context

引用

Computers in Biology and Medicine 2025年 185卷 109483-109483页

作者： Wimmer, Michael Pepicelli, Alex Volmer, Ben ElSayed, Neven Cunningham, Andrew Thomas, Bruce H. Müller-Putz, Gernot R. Veas, Eduardo E. Know Center Research GmbH Graz Austria Institute of Neural Engineering Graz University of Technology Graz Austria Wearable Computer Lab University of South Australia AdelaideSA Australia BioTechMed Graz Austria Institute of Interactive Systems and Data Science Graz University of Technology Graz Austria

Augmented Reality (AR) technologies enhance the real world by integrating contextual digital information about physical entities. However, inconsistencies between physical reality and digital augmentations, which may arise from errors in the visualized information or the user's mental context, can considerably impact user experience. This work characterizes the brain dynamics associated with processing incongruent information within an AR environment. To study these effects, we designed an interactive paradigm featuring the manipulation of a Rubik's cube serving as a physical referent. Congruent and incongruent information regarding the cube's current status was presented via symbolic (digits) and non-symbolic (graphs) stimuli, thus examining the impact of different means of data representation. The analysis of electroencephalographic signals from 19 participants revealed the presence of centro-parietal N400 and P600 components following the processing of incongruent information, with significantly increased latencies for non-symbolic stimuli. Additionally, we explored the feasibility of exploiting incongruency effects for brain-computer interfaces. Hence, we implemented decoders using linear discriminant analysis, support vector machines, and EEGNet, achieving comparable performances with all methods. Therefore, this work contributes to the design of adaptive AR systems by demonstrating that above-chance detection of incongruent information based on physiological signals is feasible. The successful decoding of incongruency-induced modulations can inform systems about the current mental state of users without making it explicit, aiming for more coherent and contextually appropriate AR interactions. © 2024

关键词： Interfaces (computer)

来源：评论

学校读者我要写书评

暂无评论

Multiperspective and Multidisciplinary Treatment of Fairness in Recommender systems Research 30

Multiperspective and Multidisciplinary Treatment of Fairness...

引用

30th ACM Conference on User Modeling, Adaptation and Personalization, UMAP2022

作者： Schedl, Markus Rekabsaz, Navid Lex, Elisabeth Grosz, Tessa Greif, Elisabeth Institute of Computational Perception Multimedia Mining and Search Group Johannes Kepler University Linz Austria Ai Lab Human-centered Ai Group Linz Institute of Technology Austria Institute of Interactive Systems and Data Science Graz University of Technology Austria Institute for Legal Gender Studies Johannes Kepler University Linz Austria

ISBN: (纸本)9781450392327

In the communities of UMAP, RecSys, and similar venues, fairness of recommender systems has primarily been addressed from the perspective of computer science and artificial intelligence, e.g., by devising computational bias and fairness metrics or elaborating debiasing algorithms. In contrast, we advocate taking a multiperspective and multidisciplinary viewpoint to complement this technical perspective. This involves considering the variety of stakeholders in the value chain of recommender systems as well as interweaving expertise from various disciplines, in particular, computer science, law, ethics, sociology, and psychology (e.g., studying discrepancies between computational metrics of bias and fairness and their actual human perception, and considering the legal and regulatory context recommender systems are embedded in). © 2022 Owner/Author.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Improving OCR Quality in 19th Century Historical Documents Using a Combined Machine Learning Based Approach

arXiv

引用

arXiv 2024年

作者： Fleischhacker, David Göderle, Wolfgang Kern, Roman Institute of Interactive Systems and Data Science Graz University of Technology Sandgasse 36 Graz8010 Austria Know Center Sandgasse 36 Graz8010 Austria History Department University of Graz Attemsgasse 8 Graz8010 Austria

This paper addresses a major challenge to historical and fellow humanist research with regard to the long 19th century, as large quantities of sources, frequently printed, have become available for the first time, while extraction techniques are lagging behind. Research has so far neglected the vast majority of these printed serial sources, with the exception of a few high-profile data series, such as census data, which have mainly been laboriously extracted manually. Therefore, we researched machine learning (ML) models to recognise and extract complex data structures in a high-value historical primary source, Habsburg Central Europe’s Hof- und Staatsschematismus, which was published between 1702 and 1918. It records every single person in the Habsburg civil service above a certain hierarchical level and documents the genesis of the central administration over two centuries. Its complex and intricate structure as well as its enormous size have so far made any more comprehensive analysis of the administrative and social structure of the later Habsburg Empire on the basis of this source impossible. We pursued two central objectives: Primarily, the improvement of the OCR quality, for which we considered an improved structure recognition to be essential;in the further course, it turned out that this also made the extraction of the data structure possible. We chose Faster R-CNN as base for the ML architecture for structure recognition. In order to obtain the required amount of training data quickly and economically, we synthesised Hof- und Staatsschematismus-style data, which we used to train our model. The model was then fine-tuned with a smaller set of manually annotated historical source data. We then used Tesseract-OCR, which was further optimised for the style of our documents, to complete the combined structure extraction and OCR process. We then evaluated our model’s performance in two steps, first we compared our fine-tuned Tesseract’s performance with that of a

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Neural and Pupillometric Correlates of Error Perception in an Immersive VR Flight Simulation

Neural and Pupillometric Correlates of Error Perception in a...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Michael Wimmer Nicole Weidinger Eduardo Veas Gernot R. Müller-Putz Know-Center GmbH* Graz Austria Institute of Interactive Systems and Data Science Graz University of Technology Graz Austria Institute of Neural Engineering Graz University of Technology Graz Austria BioTechMed-Graz Graz Austria

Algorithms detecting erroneous events, as used in brain-computer interfaces, usually rely solely on neural correlates of error perception. The increasing availability of wearable displays with built-in pupillometric sensors enables access to additional physiological data, potentially improving error detection. Hence, we measured both electroencephalographic (EEG) and pupillometric signals of 19 participants while performing a navigation task in an immersive virtual reality (VR) setting. We found EEG and pupillometric correlates of error perception and significant differences between distinct error types. Further, we found that actively performing tasks delays error perception. We believe that the results of this work could contribute to improving error detection, which has rarely been studied in the context of immersive VR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Federated Learning Solution Blueprints for Use Cases Surveyed in Austrian Industries

Federated Learning Solution Blueprints for Use Cases Surveye...

引用

IEEE Conference on Commerce and Enterprise Computing, CEC

作者： Thomas Blumauer-Hiessl Angela Fessl Gert Breitfuss Daniel Schall Stefan Schulte TU Wien and Siemens Technology Vienna Austria Know-Center GmbH Graz University of Technology Institute of Interactive Systems and Data Science Graz Austria Know-Center GmbH Graz Austria Siemens Technology Vienna Austria Christian Doppler Laboratory for Blockchain Technologies for the Internet of Things Institute for Data Engineering TU Hamburg Hamburg Germany

ISBN: (数字)9798331529093

ISBN: (纸本)9798331529109

Federated Learning (FL) holds immense potential for transforming the industrial landscape by leveraging distributed data to solve Artificial Intelligence (AI) use cases with collectively trained models in a privacy-preserving way. In this regard, Industrial FL (IFL) arose as a collaborative approach for training AI models between multiple industry partners and devices without the need to share the actual training data. However, despite its promising prospects, the transition and successful implementation of FL in practice is currently lagging behind, posing challenges for industrial companies. To address this, it is of crucial relevance to analyze different business types and involved stakeholders to be able to design FL-based solutions tailored to the industries needs. This paper presents the results of 13 semi-structured interviews conducted in Austrian industries, involving 11 companies from different domains. We identify AI applications, pain points, and attitudes towards AI and FL. Based on the interviews, three industry personas are derived, namely, service business, production optimization, and complex product and project business. To address the needs of these personas, three collaborative FL solution blueprints are proposed. The blueprints include system architectures, implementation steps, and collaboration modes for the involved parties. The blueprints are discussed based on dimensions such as FL paradigm, collaboration mode, key benefits, main addressed needs, and challenges.

关键词： Industries Pain Collaboration systems architecture Production Companies Artificial intelligence Interviews Optimization Business

来源：评论

学校读者我要写书评

暂无评论

4.2 Collaborating in a research and development project: Knowledge protection practices applied in a co-opetitive setting

4.2 Collaborating in a research and development project: Kno...

引用

2019 Knowledge Management in Digital Work Environments State-of-the-Art and Outlook, WM 2019

作者： Kaiser, Rene Thalmann, Stefan Pammer-Schindler, Viktoria Fessl, Angela Know-Center - Research Center for Data-Driven Business and Big Data Analytics Graz Austria University of Graz Institute for Interactive Systems and Data Science Graz University of Technology Austria Know-Center and Institute for Interactive Systems and Data Science Graz University of Technology Austria

ISBN: (纸本)9783885796978

Organisations participate in collaborative projects that include competitors for a number of strategic reasons, even whilst knowing that this requires them to consider both knowledge sharing and knowledge protection throughout collaboration. In this paper, we investigated which knowledge protection practices representatives of organizations employ in a collaborative research and innovation project that can be characterized as a co-opetitive setting. We conducted a series of 30 interviews and report the following seven practices in structured form: restrictive partner selection in operative project tasks, communication through a gatekeeper, to limit access to a central platform, to hide details of machine data dumps, to have data not leave a factory for analysis, a generic model enabling to hide usage parameters, and to apply legal measures. When connecting each practice to a priori literature, we find three practices focussing on collaborative data analytics tasks had not yet been covered so far. © 2020 Gesellschaft fur Informatik (GI). All rights reserved.

关键词： data Analytics

来源：评论

学校读者我要写书评

暂无评论

#StayHome playing LoL - Analyzing players' activity and social bonds in league of legends during covid-19 lockdowns

arXiv

引用

arXiv 2021年

作者： Petrosino, Simone Loria, Enrica Pirker, Johanna Institute of Interactive Systems and Data Science Graz University of Technology Graz Austria

Humans are social beings. It is therefore not surprising that the social distancing and movement restrictions associated with the Covid-19 pandemic had severe consequences for the well-being of large sections of the population, leading to increased loneliness and related mental diseases. Many people found emotional shelter in online multiplayer games, which have already proven to be great social incubators. While the positive effect games had on individuals has become evident, we are still unaware of how and if games fostered the fundamental need for connectedness that people sought. In other words: how have the social bonds and interaction patterns of players changed with the advent of the pandemic? For this purpose, we analyzed one year of data from an online multiplayer game (League of Legends) to observe the impact of Covid-19 on player assiduity and sociality in three different geographical regions (i.e., Europe, North America, and South Korea). Our results show a strong relationship between the development of Covid-19 restrictions and player activity, together with more robust and recurrent social bonds, especially for players committed to the game. Additionally, players with reinforced social bonds-i.e., people played with similar teammates-were more likely to stay in the game even once the restrictions were lifted. Copyright © 2021, The Authors. All rights reserved.

关键词： Geographical regions

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：