scholarly journals Integrating Historical Person Registers as Linked Open Data in the WarSampo Knowledge Graph

2020 ◽  
pp. 118-126
Author(s):  
Mikko Koho ◽  
Petri Leskinen ◽  
Eero Hyvönen
Keyword(s):  
Data Integration ◽  
Record Linkage ◽  
Open Data ◽  
Knowledge Graph ◽  
Distributed Data ◽  
Application Development ◽  
Named Entities ◽  
Domain Experts ◽  
World War 2 ◽  
Semantic Data

Abstract Semantic data integration from heterogeneous, distributed data silos enables Digital Humanities research and application development employing a larger, mutually enriched and interlinked knowledge graph. However, data integration is challenging, involving aligning the data models and reconciling the concepts and named entities, such as persons and places. This paper presents a record linkage process to reconcile person references in different military historical person registers with structured metadata. The information about persons is aggregated into a single knowledge graph. The process was applied to reconcile three person registers of the popular semantic portal “WarSampo – Finnish World War 2 on the Semantic Web”. The registers contain detailed information about some 100 000 people and are individually maintained by domain experts. Thus, the integration process needs to be automatic and adaptable to changes in the registers. An evaluation of the record linkage results is promising and provides some insight into military person register reconciliation in general.

Semantic Data Integration for Knowledge Graph Construction at Query Time

2017 ◽  
Author(s):  
Diego Collarana ◽  
Mikhail Galkin ◽  
Ignacio Traverso-Ribon ◽  
Christoph Lange ◽  
Maria-Esther Vidal ◽  
...  
Keyword(s):  
Data Integration ◽  
Query Time ◽  
Knowledge Graph ◽  
Semantic Data ◽  
Semantic Data Integration

scholarly journals A Review of Recent Deep Learning Approaches in Human-Centered Machine Learning

Sensors ◽  
2021 ◽  
Vol 21 (7) ◽  
pp. 2514
Author(s):  
Tharindu Kaluarachchi ◽  
Andrew Reis ◽  
Suranga Nanayakkara
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Review Paper ◽  
Learning Systems ◽  
Learning Approaches ◽  
Application Development ◽  
Research Gaps ◽  
Domain Experts ◽  
Working Definition ◽  
Real World Application

After Deep Learning (DL) regained popularity recently, the Artificial Intelligence (AI) or Machine Learning (ML) field is undergoing rapid growth concerning research and real-world application development. Deep Learning has generated complexities in algorithms, and researchers and users have raised concerns regarding the usability and adoptability of Deep Learning systems. These concerns, coupled with the increasing human-AI interactions, have created the emerging field that is Human-Centered Machine Learning (HCML). We present this review paper as an overview and analysis of existing work in HCML related to DL. Firstly, we collaborated with field domain experts to develop a working definition for HCML. Secondly, through a systematic literature review, we analyze and classify 162 publications that fall within HCML. Our classification is based on aspects including contribution type, application area, and focused human categories. Finally, we analyze the topology of the HCML landscape by identifying research gaps, highlighting conflicting interpretations, addressing current challenges, and presenting future HCML research opportunities.

scholarly journals Development of Knowledge Graph for Data Management Related to Flooding Disasters Using Open Data

2021 ◽  
Vol 13 (5) ◽  
pp. 124
Author(s):  
Jiseong Son ◽  
Chul-Su Lim ◽  
Hyoung-Seop Shim ◽  
Ji-Sun Kang
Keyword(s):  
Artificial Intelligence ◽  
Domain Knowledge ◽  
Open Data ◽  
Heterogeneous Data ◽  
Big Data Analysis ◽  
Knowledge Graph ◽  
Cross Domain ◽  
Disaster Data ◽  
Knowledge Graphs ◽  
Open Datasets

Despite the development of various technologies and systems using artificial intelligence (AI) to solve problems related to disasters, difficult challenges are still being encountered. Data are the foundation to solving diverse disaster problems using AI, big data analysis, and so on. Therefore, we must focus on these various data. Disaster data depend on the domain by disaster type and include heterogeneous data and lack interoperability. In particular, in the case of open data related to disasters, there are several issues, where the source and format of data are different because various data are collected by different organizations. Moreover, the vocabularies used for each domain are inconsistent. This study proposes a knowledge graph to resolve the heterogeneity among various disaster data and provide interoperability among domains. Among disaster domains, we describe the knowledge graph for flooding disasters using Korean open datasets and cross-domain knowledge graphs. Furthermore, the proposed knowledge graph is used to assist, solve, and manage disaster problems.

Knowledge Graph Completion to Solve University Campus Issues

2020 ◽  
Vol 1 (3) ◽  
pp. 333-350
Author(s):  
Yuto Tsukagoshi ◽  
Takahiro Kawamura ◽  
Yuichi Sei ◽  
Yasuyuki Tahara ◽  
Akihiko Ohsuga
Keyword(s):  
Data Integration ◽  
Conventional Method ◽  
Current Literature ◽  
Statistical Data ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Knowledge Graph ◽  
University Campus ◽  
Combining Data ◽  
Conventional Methods

A number of urban challenges are encountered by modern societies. Governments, businesses and public bodies need to make statistical data widely available in order to tackle these challenges. Nonetheless, current literature and data are problematic; they have inaccuracies which lead to less effective methods of resolving these issues. This research aims to solve this challenge by thinking of a university campus as a microcosm of society, implementing a data integration schema, and combining data into a knowledge graph. Existing completion methods will then be applied and updated. Especially in regards to bicycle environment, our knowledge graph was tailored and evaluated in line with conventional methods, and secondly with our proposed derivative methods. Roughly 650 pieces of parking data, with various dates and times, was contrasted with each time's mean absolute error. Our approach accurately projected 54.5 more bicycles than the conventional method.

CIM Dictionaries: An Evolutionary Approach to CIM Data Integration

1991 ◽  
Author(s):  
Uwe Weissflog
Keyword(s):  
Data Integration ◽  
Added Value ◽  
Heterogeneous Environments ◽  
Semantic Data ◽  
Application Systems ◽  
Homogeneous Set ◽  
Semantic Data Model ◽  
Additional Service ◽  
Product Definition

Abstract This paper provides an overview of methods and ideas to achieve data integration in CIM. It describes a dictionary approach allowing participating applications to define their common constructs gradually as an additional service across application systems. Because of the importance of product definition data, the role of PDES/STEP as part of this dictionary approach is also described. The technical concepts of the dictionary, such as schema mapping, semantic data model, user methods and the required additions within participating applications are explained. Problems related to data integrity, data redundancy, performance and binding of dissimilar software components are discussed as well as the deficiencies related to today’s data modelling capabilities. The added value an active dictionary can provide to a CIM environment consisting of established applications in heterogeneous environments, where migration into one standardized homogeneous set of CIM applications is not likely, is also explained.

Enhancing transparency through open government data: the case of data portals and their features and capabilities

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Martin Lněnička ◽  
Renata Machova ◽  
Jolana Volejníková ◽  
Veronika Linhartová ◽  
Radka Knezackova ◽  
...  
Keyword(s):  
Open Data ◽  
Open Government ◽  
Data Sets ◽  
Web Content ◽  
Content Type ◽  
Domain Experts ◽  
Computer Mediated ◽  
Open Government Data ◽  
Decision Making Processes ◽  
Government Data

PurposeThe purpose of this paper was to draw on evidence from computer-mediated transparency and examine the argument that open government data and national data infrastructures represented by open data portals can help in enhancing transparency by providing various relevant features and capabilities for stakeholders' interactions.Design/methodology/approachThe developed methodology consisted of a two-step strategy to investigate research questions. First, a web content analysis was conducted to identify the most common features and capabilities provided by existing national open data portals. The second step involved performing the Delphi process by surveying domain experts to measure the diversity of their opinions on this topic.FindingsIdentified features and capabilities were classified into categories and ranked according to their importance. By formalizing these feature-related transparency mechanisms through which stakeholders work with data sets we provided recommendations on how to incorporate them into designing and developing open data portals.Social implicationsThe creation of appropriate open data portals aims to fulfil the principles of open government and enables stakeholders to effectively engage in the policy and decision-making processes.Originality/valueBy analyzing existing national open data portals and validating the feature-related transparency mechanisms, this paper fills this gap in existing literature on designing and developing open data portals for transparency efforts.

Sign in / Sign up

Export Citation Format

Share Document