检索结果-内蒙古大学图书馆

Natural language processing methods for knowledge management-Applying document clustering for fast search and grouping of engineering documents

引用

CONCURRENT ENGINEERING-RESEARCH AND APPLICATIONS 2021年第2期29卷 142-152页

作者： Arnarsson, Ivar Orn Frost, Otto Gustavsson, Emil Jirstrand, Mats Malmqvist, Johan Chalmers Univ Technol Dept Ind & Mat Sci Chalmersplatsen 4 S-41296 Gothenburg Sweden Fraunhofer Chalmers Ctr Gothenburg Sweden

Product development companies collect data in form of Engineering Change Requests for logged design issues, tests, and product iterations. These documents are rich in unstructured data (e.g. free text). Previous research affirms that product developers find that current IT systems lack capabilities to accurately retrieve relevant documents with unstructured data. In this research, we demonstrate a method using Natural Language processing and document clustering algorithms to find structurally or contextually related documents from databases containing Engineering Change Request documents. The aim is to radically decrease the time needed to effectively search for related engineering documents, organize search results, and create labeled clusters from these documents by utilizing Natural Language processing algorithms. A domain knowledge expert at the case company evaluated the results and confirmed that the algorithms we applied managed to find relevant document clusters given the queries tested.

关键词： natural language processing document clustering semantic data processing knowledge management engineering change request

来源：评论

学校读者我要写书评

暂无评论

Usage of Regular Features of Partially Defined Functional Neural Networks to Find a Solution

引用

AUTOMATIC DOCUMENTATION AND MATHEMATICAL LINGUISTICS 2024年第2期58卷 100-107页

作者： Betin, V. N. Ivashchenko, V. F. Suprun, A. P. Int Ctr Informat & Elect Moscow Russia Starovoytov Ctr Informat Technol & Syst Execut Pow Moscow Russia Russian Technol Univ MIREA Moscow Russia

In this paper, we propose techniques to improve the efficiency of systems acting with knowledge bases and based on functional neural networks (FN-networks) formalism due to the use of their structural features. The article addresses the case of partially defined FN-networks, which have a regular structure and are set as lists of multiple similar objects and fragments with common structure such that their number is unknown and may be unlimited. It offers an algorithm to find solution, which is based on dynamic formation of limited, fully determined local fragments of partially defined network and subsequent transfer of the results to the entire FN-network, which may be endless.

关键词： artificial intelligence decision support systems FN-network automated decision making automated algorithm synthesis text comprehension systems semantic data processing information-analytic systems inferencing machinery consolidation of knowledge knowledge bases

来源：评论

学校读者我要写书评

暂无评论

A Multi-Stage Advanced Deep Learning Graphics Pipeline 21

A Multi-Stage Advanced Deep Learning Graphics Pipeline

引用

SIGGRAPH Asia Conference on Technical Communications

作者： Harris, Mark Wesley Semwal, Sudhanshu Kumar Univ Colorado Colorado Springs CO 80907 USA

ISBN: (纸本)9781450390736

In this paper we propose the Advanced Deep Learning Graphics Pipeline (ADLGP). ADLGP is a novel approach that uses existing deep learning architectures to convert scene data into rendered images. Our goal of generating frames from semantic data has produced successful renderings with similar structures and composition as target frames. We demonstrate the success of ADLGP with side-by-side comparisons of frames generated through standard rendering procedures. We assert that a fully implemented ADLGP framework would reduce the time spent in visualizing 3D environments, and help selectively offload the requirements of the current graphics rendering pipeline.

关键词： Graphics pipeline rendering pipeline rendering technologies machine learning generative adversarial networks text-to-image super resolution semantic data processing image processing

来源：评论

学校读者我要写书评

暂无评论

KSD: An Ontology-Driven Yet semantically Transparent Application Development Tool

KSD: An Ontology-Driven Yet Semantically Transparent Applica...

引用

OnTheMove (OTM) International Federated Conference

作者： Jaiswal, Dibyanshu Dey, Sounak TCS Res & Innovat Labs Kolkata India

ISBN: (纸本)9783319559612;9783319559605

To come up with a semantic web application, it requires skills from two major backgrounds: (a) domain experts to model and populate a semantic knowledge base;and (b) application developers to understand the domain ontology and then build an interface for end users. Learning and using such tools is an overhead and slows down the development process. To address these problems, our paper proposes KSD - Knowledge Serializer and De-serializer tool, that takes an ontology as an input and represents it in a structured form (like JSON, XML) while preserving the underlying semantic information. This format is adaptable to the changes in the underlying ontology and can be used to create user interface, web services and other application modules.

关键词： Serialization semantic user interface Ontology-driven user interface semantic data processing

来源：评论

学校读者我要写书评

暂无评论

Researching North Korean Historiography with Digital Humanities Methodologies

引用

KOREA JOURNAL 2023年第4期63卷 16-53页

作者： Ryu, Intae Hong, Jong-wook Korea Univ Inst Sinog Literatures & Philol Seoul South Korea Seoul Natl Univ Inst Humanities Seoul South Korea

The purpose of this article is to attempt to combine North Korean humanities research with digital humanities methods, using the North Korean Humanities data Archive (NKHDA) project as an example, and to report on a newly constructed semantic data processing model. Although NKHDA targeted the entire scope of North Korean humanities, it mainly focused on the field of historiography, which has a relatively large accumulation of scholarly information. This article focuses on North Korean historiography to discuss the following three points. Firstly, the theoretical and technical background of the NKHDA is summarized. Secondly, the trial -and -error process of constructing NKHDA is described. Thirdly, the process of creating a new model of semantic data processing by combining wiki documentation and triple data/ visualization is described. A new model was made possible by embedding triple data lists and network graphs into wiki pages and developing a data entry tool for triple data generation. Also described is the NKHDAs' use as an educational platform for the digital humanities.

关键词： North Korean historiography digital humanities NKHDA (North Korean Humanities data Archive) semantic data processing triple data network graph wiki database

来源：评论

学校读者我要写书评

暂无评论

A Method for Continuous Clustering and Querying of Moving Objects 3rd

A Method for Continuous Clustering and Querying of Moving Ob...

引用

3rd International Conference on Advanced Informatics for Computing Research (ICAICR)

作者： Nishad, A. Abraham, Sajimon Mahatma Gandhi Univ Kottayam Kerala India

ISBN: (纸本)9789811501081;9789811501074

Location sensing moving objects generate a continuous stream of spatio-temporal data. Querying and analysis of this data can give more inference on the mobility patterns of the objects. In this paper, we are proposing a method for evaluating spatio-temporal aggregate queries. For the effective processing of queries continuous clustering is employed on moving objects. The frequency of clustering is determined by the semantic properties of the travel network. Moving objects and queries are combined together and processed incrementally all through the travel network. The cluster membership of an object may change during the course of the journey. By analyzing this, the pattern of the movement of object can be ascertained. Special data structures are maintained to keep track clusters to answer spatio-temporal aggregate queries. We prove that our system can deliver answers to spatio-temporal aggregate queries effectively without processing the entire records of the moving objects.

关键词： Location based systems Moving objects semantic data processing Spatio-temporal data mining Spatio-temporal aggregate queries

来源：评论

学校读者我要写书评

暂无评论

Functorial Model Management

引用

Proceedings of the Design Society: International Conference on Engineering Design 2019年第1期1卷 1963-1972页

作者： Spencer Breiner Blake Pollard Eswaran Subrahmanian National Institute of Standards and Technology (NIST) Carnegie Mellon University

In this paper we use formal tools from category theory to develop a foundation for creating and managing models in systems where knowledge is distributed across multiple representations and formats. We define a class of models which incorporate three different representations---computations, logical semantics, and data--as well as model mappings (functors) to establish relationships between them. We prove that our models support model merge operations called colimits and use these to define a methodology for model integration.

关键词： semantic data processing Systems Engineering (SE) Information management Model management data integration

来源：评论

学校读者我要写书评

暂无评论

EFFECTS OF BIOPHILIC RESTORATIVE EXPERIENCES ON DESIGNERS' BODIES, BRAINS, AND MINDS

引用

Proceedings of the Design Society 2023年 3卷 1565-1574页

The research presented in this paper explores a novel method for assessing the effects of biophilic restorative experiences on designers’ cognition by combining the use of physiological, neurocognitive and semantic measures. A total of 12 engineering graduate students participated in a three-step pilot experiment that consisted of (1) a stressor (the Trier Social Stress Test), (2) a destressing intervention (biophilic sound experience), and (3) a design task. Heart rate variability (HRV) was used to track subjects’ autonomic nervous system (ANS) activity. Functional near-infrared spectroscopy (fNIRS) was used to track patterns of brain activation in subjects’ prefrontal cortex (PFC). Changes in design quality were assessed by the semantic space they explored, measured through a natural language processing (NLP) technique. Preliminary findings suggest that an auditory biophilic restorative experience can change designers’ bodies, brains, and minds. Results from this pilot study encourage further exploration of the use of exposure to nature-based stimuli as a method to help enhance engineering design cognition.

关键词： Bio-inspired design / biomimetics Design cognition semantic data processing neurocognition biophilia

来源：评论

学校读者我要写书评

暂无评论

Towards an Approach Integrating Various Levels of data Analytics to Exploit Product-Usage Information in Product Development

引用

Proceedings of the Design Society: International Conference on Engineering Design 2019年第1期1卷 2627-2636页

作者： Patrick Klein Wilhelm Frederik van der Vegte Karl Hribernik Thoben Klaus-Dieter University of Bremen Delft University of Technology BIBA - Bremer Institut für Produktion und Logistik GmbH

By applying data analytics to product usage information (PUI) from combinations of different channels, companies can get a more complete picture of their products’ and services’ Mid-Of-Life. All data, which is gathered within the usage phase of a product and which relates to a more comprehensive understanding of the usability of the product itself, can become valuable input. Nevertheless, an efficient use of such knowledge requires to setup related analysis capabilities enabling users not only to visualize relevant data, but providing development related knowledge e.g. to predict product behaviours not yet reflected by initial *** paper elaborates on explorations to support product development with analytics to improve anticipation of future usage of products and related services. The discussed descriptive, predictive and prescriptive analytics in given research context share the idea and overarching process of getting knowledge out of PUI data. By implementation of corresponding features into an open software platform, the application of advanced analytics for white goods product development has been explored as a reference scenario for PUI exploitation.

关键词： Analytics Simulation Design methods semantic data processing User centred design

来源：评论

学校读者我要写书评

暂无评论

PROBLEMS: EASY TO SAY BUT DIFFICULT TO WRITE

引用

Proceedings of the Design Society 2023年 3卷 2945-2954页

Patents are an invaluable source of data that can be beneficial for Engineering Design (ED). Patenting is one of the main means for disclosing the inventive process. For this reason, the description of the problem solved should also be included in any patents. The ED literature lacks a proper definition of a problem, resulting in a fragmented scenario. Prior studies have employed Text Mining (TM) to extract problems from patents. We argue that TM can assist ED researchers in understanding how problems are articulated in text. Based on the literature, we propose two hypotheses: (1) problem-related text exhibits a negative sentiment polarity compared to other sections of patents; (2) problem-related keywords identified in the literature are predominantly used to describe problems rather than other aspects. We analyse Japanese patents to validate our hypotheses, since they explicit Problem and Solution in the abstract. Finally, we compare our results with a set of problem-related sentences extracted from USPTO patents. Our study reveals a higher positive sentiment in problem-related sentences compared to solution-related ones and highlights the inadequacy of using problem-related keywords alone to differentiate between the two.

关键词： Patent Analysis Text mining Knowledge management semantic data processing Conceptual design

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：