Abstract Announcement for International Journal of Swarm Intelligence Research (IJSIR)

HOME    News    Abstract Announcement for International Journal of Swarm Intelligence Research (IJSIR)

The contents of the latest issue of:

International Journal of Swarm Intelligence Research (IJSIR)

Volume 9, Issue 3, July - September 2018

Indexed by: INSPEC, SCOPUS, Web of Science Emerging Sources Citation Index (ESCI)

For a complete list of indexing and abstracting services that include this journal, please reference the bottom of this announcement.

Published: Quarterly in Print and Electronically

ISSN: 1947-9263; EISSN: 1947-9271;

Published by IGI Global Publishing, Hershey, USA


Editor-in-Chief: Yuhui Shi (Southern University of Science and Technology (SUSTech), China)

Note: The International Journal of Swarm Intelligence Research (IJSIR) has an Open Access option, which allows individuals and institutions unrestricted access to its published content. Unlike traditional subscription-based publishing models, open access content is available without having to purchase or subscribe to the journal in which the content is published. All IGI Global manuscripts are accepted based on a double-blind peer review editorial process.


Comparing Spark with MapReduce: Glowworm Swarm Optimization Applied to Multimodal Functions

Goutham Miryala (North Dakota State University, Fargo, USA), Simone A. Ludwig (Department of Computer Science, North Dakota State University, Fargo, USA)

Glowworm swarm optimization (GSO) is one of the optimization techniques, which need to be parallelized in order to evaluate large problems with high-dimensional function spaces. There are various issues involved in the parallelization of any algorithm such as efficient communication among nodes in a cluster, load balancing, automatic node failure recovery, and scalability of nodes at runtime. In this article, the authors have implemented the GSO algorithm with the Apache Spark framework. Even though we need to address how to distribute the data in the cluster to improve the efficiency of algorithm, the Spark framework is designed in such a way that one does not need to deal with any actual underlying parallelization details. For the experimentation, two multimodal benchmark functions were used to evaluate the Spark-GSO algorithm with various sizes of dimensionality. The authors evaluate the optimization results of the two evaluation functions as well as they will compare the Spark results with the ones obtained using a previously implemented MapReduce-based GSO algorithm.

To obtain a copy of the entire article, click on the link below.

To read a PDF sample of this article, click on the link below.


Swarm-Inspired Routing Algorithms for Unstructured P2P Networks

Vesna Šešum-Cavic (Vienna University of Technology, Vienna, Austria), Eva Kuehn (Vienna University of Technology, Vienna, Austria), Stefan Zischka (Vienna University of Technology, Vienna, Austria)

Due to extreme complexity in nowadays networks, routing becomes a challenging task. This problem is especially delicate in unstructured P2P networks, as there is neither a global view on the network nor a global address mapping. Although different conventional solutions are commercially available, swarm-intelligent approaches are promising in case of frequently changing conditions in P2P networks. In this article, an approach inspired by Dictyostelium discoideum slime molds and bees with distributive and autonomous properties is proposed. Both bio-mechanisms are “tailored” for routing in unstructured P2P systems, resulting in swarm-inspired routing algorithms, SMNet and BeeNet. They are compared with three swarm-based routing algorithms and two conventional approaches. The benchmarks include parameter sensitivity-, comparative-, statistical- and scalability-analysis. SMNet outperforms the other algorithms in the comparative analysis regarding the average data packet delay, especially for bigger network sizes and data packet traffic levels. Both algorithms show good scalability.

To obtain a copy of the entire article, click on the link below.

To read a PDF sample of this article, click on the link below.


Capacitor Placement in Radial Distribution System Using Oppositional Cuckoo Optimization Algorithm

Sneha Sultana (Dr. B. C. Roy Engineering College, Durgapur, India), Provas Kumar Roy (Kalyani Government Engineering College, Kalyani, India)

Capacitors in distribution systems are used to supply reactive power to minimize power loss. This article presents an efficient optimization algorithm named oppositional cuckoo optimization algorithm (OCOA) for optimal allocation of capacitor in radial distribution systems to determine the optimal locations and sizes of capacitors with an objective of reduction of total cost considering different constraints. To test feasibility and effectiveness of the proposed OCOA, it is applied on 22-bus, 69-bus, 85-bus and 141-bus radial distribution systems as test studies and the results are compared with other methods available in literature. Comparison between the proposed method in this article and similar methods in other research works shows the effectiveness of the proposed method for solving optimum capacitor planning problem in radial distribution system.

To obtain a copy of the entire article, click on the link below.

To read a PDF sample of this article, click on the link below.

For full copies of the above articles, check for this issue of the International Journal of Swarm Intelligence Research (IJSIR) in your institution's library. This journal is also included in the IGI Global aggregated "InfoSci-Journals" database: www.igi-global.com/isj.


Mission of IJSIR:

The mission of the International Journal of Swarm Intelligence Research (IJSIR) is to become a leading international and well-referred journal in swarm intelligence, nature-inspired optimization algorithms, and their applications. This journal publishes original and previously unpublished articles including research papers, survey papers, and application papers, to serve as a platform for facilitating and enhancing the information shared among researchers in swarm intelligence research areas ranging from algorithm developments to real-world applications.

Indices of IJSIR:

  • ACM Digital Library

  • Bacon's Media Directory

  • Cabell's Directories

  • DBLP

  • Google Scholar


  • JournalTOCs

  • MediaFinder


  • The Standard Periodical Directory

  • Ulrich's Periodicals Directory

  • Web of Science

  • Web of Science Emerging Sources Citation Index (ESCI)

Coverage of IJSIR:

Topics to be discussed in this journal include (but are not limited to) the following:

  • Ant colony optimization

  • Applications in bioengineering

  • Applications in bioinformatics

  • Applications in business

  • Applications in control systems

  • Applications in data mining and data clustering

  • Applications in decision making

  • Applications in distributed computing

  • Applications in evolvable hardware

  • Applications in finance and economics

  • Applications in games

  • Applications in graph partitioning

  • Applications in information security

  • Applications in machine learning

  • Applications in planning and operations in industrial systems, transportation systems, and other systems

  • Applications in power system

  • Applications in supply-chain management

  • Applications in wireless sensor networks

  • Artificial immune system

  • Constrained optimization

  • Culture algorithm

  • Differential Evolution

  • Foraging algorithm

  • Large scale optimization problems

  • Modeling and analysis of biological collective systems such as social insects colonies, school, and flocking vertebrates

  • Multi-objective optimization

  • Optimization in dynamic and uncertain environment

  • Particle swarm optimization

  • Scheduling and timetabling

  • Swarm robotics

  • Other nature-inspired optimization algorithms

Interested authors should consult the journal's manuscript submission guidelines www.igi-global.com/calls-for-papers/international-journal-swarm-intelligence-research/1149

2018-09-19 10:51

Welcome to Swarm Intelligence community

Swarm Intelligence is a field of Computer science. It is a form of Artificial intelligence. Some animals, mostly insects like ants, or bees form large colonies. These colonies are made of many animals that communicate with each other. Each animal is relatively simple, but by working together with other animals it is able to solve complex tasks.


Powered by CloudDream