Indexing:

Call for papers for a Special Issue

Long title

Predictive Analysis of Real-time Strategy using Graph Mining

Acronym

PARSGM-2021

Short description

In any science and industrial field, such as social networks, economic networks, information networks, biomedical knowledge graphs, and internet graphs, the graph provides a natural way to represent and model the structure or link properties of data. Due to the widespread prevalence of graphs, graph representation and predictive learning play an important role in machine learning, with applications in clustering, classification, retrieval of information, recommendation, exploration of knowledge and others. The methods of machine learning and pattern recognition have had a huge influence on the study of large-scale financial, medical, gaming and social media data sets. However, most of the analytical approaches used to date have concentrated on the use of traditional vector methods and data from the time series. Recently, however, attention has shifted to the use of data representations based on relational and similarity. This is primarily due to improvements in the sophistication of the methods available, including graph embedding, graph kernels and deep graph convolutional neural networks. This has resulted in a range of remarkable implementations of graph-based data analysis approaches across the various industries. The aim of this issue is to give an introduction to the mathematical machinery behind the real time strategy prediction using graph mining. The purpose of this issue is to summarize the research techniques related to the future trends in computational engineering, information science, graph analytics and machine learning. This issue tends to present several interesting open problems with future research directions for architecture design, computational engineering, real time prediction, pattern reduction and multimedia analysis.

Potential topics include but are not limited to the following:
‑     Applications of graph data processing
‑     Complex Networks
‑     Classical signal and image processing assisted by graph theory
‑     Deep learning methods on graphs/manifolds for multimedia analysis
‑     Graph-based Deep Learning
‑     Graph-based Feature Selection
‑     Graph convolution networks for multimedia analysis
‑     Graph and graph-based data classification and clustering
‑     Representation Learning on Graph Structured Data
‑     Theoretical analysis of deep learning models for graphs/manifolds
‑     Unsupervised/semi-supervised graph/manifold learning on multimedia data

Guest editor(s)

 

Dr. Prabu S.
Professor & HoD, Department of ECE
Mahendra Institute of Technology
Namakkal, Tamil Nadu, India
Email: vsprabu4u@outlook.com

Dr. Hemalatha KL
Professor & HOD, Department of ISE
Sri Krishna Institute of Technology
Bangalore, India
Email: hema.skit@gmail.com

Important dates

Submission deadline:          21th March 2021
Interim decision:                  25th April 2021
Revised paper submission:  25th May 2021
Final Acceptance decision:  25th June 2021

Email for submission of papers

vsprabu4u@outlook.com