检索结果-内蒙古大学图书馆

Neural networks for semantic gaze analysis in XR settings

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Stubbemann, Lena Dürrschnabel, Dominik Refflinghaus, Robert Department of Quality and Process Management University of Kassel Germany Knowledge & Data Engineering Group University of Kassel Germany Interdisciplinary Research Center for Information System Design University of Kassel Germany

Virtual-reality (VR) and augmented-reality (AR) technology is increasingly combined with eye-tracking. This combination broadens both fields and opens up new areas of application, in which visual perception and related cognitive processes can be studied in interactive but still well controlled settings. However, performing a semantic gaze analysis of eye-tracking data from interactive three-dimensional scenes is a resource-intense task, which so far has been an obstacle to economic use. In this paper we present a novel approach which minimizes time and information necessary to annotate volumes of interest (VOIs) by using techniques from object recognition. To do so, we train convolutional neural networks (CNNs) on synthetic data sets derived from virtual models using image augmentation techniques. We evaluate our method in real and virtual environments, showing that the method can compete with state-of-the-art approaches, while not relying on additional markers or preexisting databases but instead offering cross-platform *** Codes 68T45 Copyright © 2021, The Authors. All rights reserved.

关键词： Semantics

A practical mobile computing solution for healthcare institutions

学校读者我要写书评

暂无评论

A practical mobile computing solution for healthcare institu...

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

作者： A. Dwivedi R.K. Bali A.E. James R.N.G. Naguib D. Johnston Data and Knowledge Engineering Research Group (DKERG) Coventry University UK BIOCORE School of Mathematical and Information Sciences Coventry University UK Slough Applied Network Solutions Limited UK

In this paper we look at information technology (IT) trends in the healthcare sector. We analyse recent changes in IT implementations in the healthcare sector to identify critical factors and technologies that are likely to be an integral part of healthcare institutions (HIs) in the new millennium. We contend that the recent advances in Biomedical knowledge coupled with the Genetic engineering revolution are likely to bring about an increased understanding of known diseases and will lead to the identification of new risk factors. We then highlight the fact that, despite appreciating the importance of ensuring integration between different Healthcare Information Systems, HIs are not allocating sufficient funds for this. We highlight the case of US based HIs who face IT challenges in light of a marginal percentage decrease in financial resources for IT purposes. We identify the lack of an Integrated Healthcare Information System to be the most fundamental obstacle that is denying the productivity explosion needed in the healthcare sector. To provide a realistic solution, we look at some of the technologies that together could provide solutions. We use data from our collaborating organization to present a possible low cost IT solution.

关键词： Mobile computing Medical services Information systems Information technology Genetic engineering Diseases Productivity Explosions Collaboration Costs

Towards collaborative conceptual exploration

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Hanika, Tom Zumbrägel, Jens Knowledge and Data Engineering Group University of Kassel Germany Interdisciplinary Research Center for Information System Design University of Kassel Germany Faculty of Computer Science and Mathematics University of Passau Germany

In domains with high knowledge distribution a natural objective is to create principle foundations for collaborative interactive learning environments. We present a first mathematical characterization of a collaborative learning group, a consortium, based on closure systems of attribute sets and the well-known attribute exploration algorithm from formal concept analysis. To this end, we introduce (weak) local experts for subdomains of a given knowledge domain. These entities are able to refute and potentially accept a given (implicational) query for some closure system that is a restriction of the whole domain. On this we build up a consortial expert and show first insights about the ability of such an expert to answer queries. Furthermore, we depict techniques on how to cope with falsely accepted implications and on combining counterexamples. Using notions from combinatorial design theory we further expand those insights as far as providing first results on the decidability problem if a given consortium is able to explore some target domain. Applications in conceptual knowledge acquisition as well as in collaborative interactive ontology learning are at *** Codes 03G10 68T27 Copyright © 2017, The Authors. All rights reserved.

关键词： Learning systems

Simple and Deep Graph Convolutional Networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Chen, Ming Wei, Zhewei Huang, Zengfeng Ding, Bolin Li, Yaliang School of Information Renmin University of China China Gaoling School of Articial Intelligence Renmin University of China China Beijing Key Lab of Big Data Management and Analysis Methods China MOE Key Lab of Data Engineering and Knowledge Engineering China School of Data Science Fudan University China Alibaba Group

Graph convolutional networks (GCNs) are a powerful deep learning approach for graph-structured data. Recently, GCNs and subsequent variants have shown superior performance in various application areas on real-world datasets. Despite their success, most of the current GCN models are shallow, due to the over-smoothing problem. In this paper, we study the problem of designing and analyzing deep graph convolutional networks. We propose the GCNII, an extension of the vanilla GCN model with two simple yet effective techniques: Initial residual and Identity mapping. We provide theoretical and empirical evidence that the two techniques effectively relieves the problem of over-smoothing. Our experiments show that the deep GCNII model outperforms the state-of-the-art methods on various semi- and full-supervised tasks. Code is available at https://***/chennnM/GCNII. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolutional neural networks

Simulation, comparison and analysis of Wireless Sensor Networks protocols: LEACH, LEACH-C, LEACH-1R, and HEED

学校读者我要写书评

暂无评论

Simulation, comparison and analysis of Wireless Sensor Netwo...

International Conference on Electrical engineering (ICEE)

作者： Mohammed Omari Soumia Laroui Department of Computer Science and Engineering Shahid Beheshti University Tehran Iran Knowledge and Data Engineering Group Trinity College Dublin LDDI Laboratory Computer Science Department University of Colonel Ahmed Draya Adrar 01000 Algeria

Wireless Sensor Networks (WSNs) are made up of tiny sensor nodes which sense the data and communicate to the base station via other nodes. These sensor nodes are inexpensive portable devices with limited processing power and energy resources which make them in need of smart clustering protocols. Many clustering and routing protocols were proposed in the literature to serve large networks of such tiny devices. In this paper, we have implemented and analyzed different clustering protocols, namely LEACH, LEACH-C, LEACH-1R, and HEED using MATLAB environment. These clustering protocols are compared in different terms such as residual energy, data delivery to the base station, maximum number of rounds and the number of live nodes. Experimental results showed a better performance of the LEACH protocols when compared to the different versions of HEED. Moreover, LEACH-1R proved to be efficient in terms of network lifetime.

关键词： Wireless sensor networks Base stations Mathematical model Energy consumption Batteries Routing protocols

A review of possible effects of cognitive biases on interpretation of rule-based machine learning models

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Kliegr, Tomáš Bahník, Štěpán Fürnkranz, Johannes Department of Information and Knowledge Engineering Prague University of Economics and Business Czech Republic The Prague College of Psychosocial Studies Czech Republic Johannes Kepler University Computational Data Analytics Group Linz Austria

While the interpretability of machine learning models is often equated with their mere syntactic comprehensibility, we think that interpretability goes beyond that, and that human interpretability should also be investigated from the point of view of cognitive science. In particular, the goal of this paper is to discuss to what extent cognitive biases may affect human understanding of interpretable machine learning models, in particular of logical rules discovered from data. Twenty cognitive biases are covered, as are possible debiasing techniques that can be adopted by designers of machine learning algorithms and software. Our review transfers results obtained in cognitive psychology to the domain of machine learning, aiming to bridge the current gap between these two areas. It needs to be followed by empirical studies specifically focused on the machine learning domain. Copyright © 2018, The Authors. All rights reserved.

关键词： Machine learning

What is the intrinsic dimension of your binary data? - and how to compute it quickly

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hanika, Tom Hille, Tobias Intelligent Information Systems University of Hildesheim Hildesheim Germany Knowledge & Data Engineering Group University of Kassel Kassel Germany Interdisciplinary Research Center for Information System Design University of Kassel Kassel Germany

Dimensionality is an important aspect for analyzing and understanding (high-dimensional) data. In their 2006 ICDM paper Tatti et al. answered the question for a (interpretable) dimension of binary data tables by introducing a normalized correlation dimension. In the present work we revisit their results and contrast them with a concept based notion of intrinsic dimension (ID) recently introduced for geometric data sets. To do this, we present a novel approximation for this ID that is based on computing concepts only up to a certain support value. We demonstrate and evaluate our approximation using all available datasets from Tatti et al., which have between 469 and 41271 extrinsic *** Codes 68T05 06-08 68T01 68T09 Copyright © 2024, The Authors. All rights reserved.

关键词： Clustering algorithms

Temporal reasoning on Twitter streams using semantic web technologies

学校读者我要写书评

暂无评论

Temporal reasoning on Twitter streams using semantic web tec...

IEEE Annual Conference on Pervasive Computing and Communications Workshops (PerCom)

作者： Meng Cui Wei Tai Declan O'Sullivan Trinity College Dublin School of Computer Science & Statistics Dublin Ireland Knowledge and Data Engineering Group School of Computer Science & Statistics Dublin Ireland University of Dublin Trinity College Dublin IE

There has been a significant increase in recent years in the volume and diversity of streams of data, data streams from sensors, data streams arising from the analysis of content or data mining, right through to user generated Twitter streams. There has been a corresponding increase in demand for more real-time analysis of these streams in order to spot significant events and trends of interest to an individual or business. This has resulted in an increased need to achieve efficient temporal reasoning upon the streams. In this paper, we present a novel approach to perform temporal reasoning on real time streams of data using Semantic Web Technologies so that we could derive more valuable information by taking account of the time dimension. Moreover, in order to deal with such high-frequency data, several filter mechanisms have been implemented to, significantly, improve the performance of the reasoning process. In order to illustrate and evaluate the approach, the real-time analysis of Twitter data is taken as a concrete use case for such data streams.

关键词： Cognition Resource description framework Twitter Semantics Real-time systems Filtering theory

Drawing Order Diagrams Through Two-Dimension Extension

学校读者我要写书评

暂无评论

Journal of Graph Algorithms and Applications 2023年第9期27卷 783-802页

作者： Dürrschnabel, Dominik Hanika, Tom Stumme, Gerd Knowledge & Data Engineering Group Research Center for Information System Design & Department of Electrical Engineering and Computer Science University of Kassel Germany Institute of Computer Science University of Hildesheim Germany Berlin School of Library and Information Science Humboldt-Universität zu Berlin Germany

Ordinal real-world data such as concept hierarchies, ontologies, genealogies, or task dependencies in scheduling often has the property to not only contain pairwise comparable, but also incomparable elements. Order diagrams provide an important tool for understanding and thus discovering knowledge in such data. Easily readable drawings of such order diagrams are hard to come by, even for small ordered sets. Many attempts were made to transfer classical graph drawing approaches to order diagrams. Although these methods produce satisfying results for some ordered sets, they unfortunately perform poorly in general. In this work, we present the novel algorithm DimDraw to decompose an ordered set (e.g., a concept hierarchy) in linear orders and to produce a corresponding order diagram. This algorithm is based on a relation between the dimension of an ordered set and the bipartiteness of its transitive incompatibility graph. To evaluate the quality of the algorithm, a user study was conducted where generated drawings were compared with ones from state-of-the-art drawing algorithms. © 2023 Brown University. All rights reserved.

关键词： Set theory