Special issue on ' Managing Complex Computational Challenges' in

Journal of Computational Methods in Sciences and Engineering


Managing Complex Computational Challenges

A huge body of methods for making large-scale simulations and analyses are produced, which are more computationally efficient, enabling a wide range of research to be less time- and memory-intensive. The proposed methods and systems can synthesize domains that integrate many concepts from deep learning, machine learning, AI and other computational techniques. Keeping the scientific value while designing computational approaches that leverage increased computational power is essential. Developing one system identifies a few significant features or facets. However, generating a large model uses innumerable parameters and infinite indicators to bring broad models that analyse multidimensional patterns and function as generic with permissible customization. The future computational system can build newer interfaces with computers on one side, people, technologies, and domains on the other, and produce modalities. Robust techniques with insights create solution spaces with fewer computational complexities.

Advanced big data analytics offer solutions to research questions in many different disciplines. Computational techniques coupled with intelligence are more successful for complex processes in many domains, and the refining activities lead to domain precision. In recent years efficient machine learning models have been recorded that solve many complex issues in other fields.

Many approaches in research currently warrant intensive computational methods and have become more inevitable to solve research questions. Research can generate unique and highly objective scalable solutions to the complexity and understanding of how the different propositions can help product possible systems to solve the tasks with domain knowledge.

Complexity reduction leads to robustness, structured results, higher accuracy, and resolved issues and is mainly achieved by applying computational methods. The proposed special issue will address many agendas codified in the above description and, more specifically, but not limited to the below themes.

Neural models
Spatio-temporal data modelling
DL approaches to analyse patterns
Convolutional Long Short-Term Memory network
Data Transfer Framework
Data security
Data correlational dependencies
Knowledge-driven machine learning
Information and Systems Intelligence
Computational Modelling
Intelligent agent-supported processing
Intelligent control systems
Domain-specific smart models and architectures
Complex data and sparse modelling
Semantics-induced segmentation and clustering
Edge Intelligence

The important dates

Submission of Papers: June 15, 2023

Acceptance/Rejection Notification: July 10, 2023

Revised version: August 25, 2023

Issue Publication: (will be notified later)


Special Issue Editors

Pit Pichappan, PhD,
Senior Scientist
Digital Information Research Labs
Chennai. India

Ezendu Ariwa, PhD,
Warwick University

Fouzi Harrag, PhD
Associate Professor
Computer Science,
Ferhat Abbas University,
Setif, Algeria

Editorial Board:

Ricardo Jorge, UJEP, Czech Republic
Adriana Mexicano, Tecnológico Nacional de Mexico, Mexico
Jonathan Villanueva, Mexico
Ales Prochazka, VSCHT, Czech Republic
Dimitrios Karras, CIT, Albania
Fouzi Harrag, Ferhat Abbas University, Algeria
Pit Pichappan, Digital Information Research Labs, India
Adrian Florea, "Lucian Blaga" University of Sibiu, Romania
Arpad Gellert, "Lucian Blaga" University of Sibiu, Romania
Yao Liang, National Taiwan Ocean University, Taiwan
Pavel Losket, Swansea University, UK
Simon Fong, University of Macau, Macau
Daisy Jacobs, University of Zululand, South Africa

For further queries, please contact

For Author guidelines, please visit before submission-

Submission of papers   SUBMIT HERE