International Journal of Computer Networks & Communications (IJCNC)

ISSN: 0974 - 9322 (Online) ; 0975 - 2293 (Print)

Special Issue on : "Shaping up the Innovations in Graph Theory to measure linearity of data"

Guest Editors:

Waqas Nazeer
Government College University, Pakistan

Ebenezer Bonyah
Akenten Appiah-Menka University of Skills Training and Entrepreneurial Development, Ghana

MerveIlkhan Kara
Düzce University, Konuralp Campus, Turkey

Theme and Scope

Knowledge graphs are an innovative paradigm for encoding, accessing, combining, and interpreting data from heterogeneous and multimodal sources beyond simply a combination of technology. In a shorter time, knowledge graphs have been identified as an important component of modern search engines, intelligent assistants, and corporate intelligence. Geospatial data science, cognitive neuroscience, and machine learning emerge together in geospatial knowledge graphs symbolic of spatiality, attributes, and interactions. These knowledge graphs can be used for many geospatial applications, including geographic information retrieval, geospatial interoperability, and geographic information systems knowledge discovery. Nevertheless, Geospatial Knowledge Graphs rarely reach their maximum potential in geospatial and downstream applications since most conventional data warehouses and system elements in KGs need to account for the specialty of geographical information. A geospatial graph's linear relationship between the measurement and true values cannot effectively represent the bias component of measuring the linearity of GeoKGs. A measurement technique is linear when the relationship between the measurement and true values is a linear data function that can be analytically verified. It is a major variable because it allows data to be linearly extended across points. A linear fit of geographic knowledge graphs characterizes a relationship when the measurement system is linear. When the measurement system is linear, the connection is represented by a polynomial approximation. A linear polynomial approximation is compared with a linear data fitting to evaluate linearity.

Geographic knowledge graphs are a combination of database representation and management that have the potential to optimize and resolve the challenges relating to data interoperability, semi-automated knowledge thinking, and retrieval of information. Geospatial knowledge graphs are forms of applied semantics that provide a domain of geographical information context. This prototype uses several development tools to build an architecture of the system in line with those goals and is entirely made up of open-source and free software. The challenges are to acquire and recognize the geospatial semantics inherent in the data sources, align such graph systems with standards, test systematic computations, and visualize data using a spatial analysis user interface. Questions about reasoning and competency were used to validate the systems and ontologies design, but the user-based design needed customization.

This Special Issue intends to combine researchers required to work in the knowledge graphs with linearity researchers to present original research findings or cutting-edge applications. To encourage research in these fields, we invite papers on various knowledge graph technology-related topics for this Special Issue from multiple domains. Focused on the increasing demands for the efficient and effective development, management, and utilization of geospatial technology within KGs, this Special Issue on Geospatial Knowledge Graphs aims to address this problem. The researchers should contribute papers describing substantial and unpublished work.

Possible topics include but are not limited to:

• Improving geospatial knowledge graphs based on machine learning
  
• Standards and data vocabularies for linked geospatial knowledge graphs
  
• Knowledge graphs on reasoning and geospatial-specific querying
  
• Ranking techniques and benchmarking of applications on querying GeoKGs
  
• Survey of tools for geospatial knowledge graphs
  
• Reinforcement learning and deep learning on geospatial knowledge graphs
  
• Geographic ontology alignment and gazetteer data management for geographic entities
  
• Recommendation and personalization of knowledge graph interaction and navigation
  
• Edge computing and deep learning graph mining
• Relationship discovery and rule in knowledge graph computing
• A measure of non-linearity of geospatial knowledge graphs
• Knowledge graphs on the linearity of statistical evaluation in assay validation
• Natural language processing and information extraction for knowledge graphs

Notes for Prospective Authors

Submissions must be original and should not have been published previously or be under consideration for publication while being evaluated for this Issue. Manuscripts should be written in English and strictly follow the guideline of the Journal IJCNC. The manuscripts should be submitted to one of the guest editors through email graph23@aircconline.com.

Tentative timeline for this special issue:

For more details please visit: http://airccse.org/journal/ijcnc.html