MITS5002: Research Report on Evolutionary Artificial Neural Networks

This report presents a review of an academic paper focused on evolutionary artificial neural networks (ANNs). The study explores the concept of ANNs, highlighting their potential when combined with evolutionary algorithms (EAs) to optimize performance and address design issues. The paper discusses the intention, research methods (qualitative design, secondary data), findings, and issues such as overfitting. The analysis reveals that ANNs and EAs, both AI technologies, draw inspiration from behavioral characteristics. The report concludes that EAs are effective in enhancing ANNs and solving design challenges, offering insights for students studying software engineering and AI.

Software
Engineering
Methodologies

Introduction
• This study focuses on the artificial neural networks and review
a research paper based on ANNs.
• The title of the article is evolutionary artificial neural
networks: a review which will be discussed in this report [4].
• The aim of this presentation is to describe the concept of
artificial neural networks.
• This study divided into several sections such as intention of
the paper, research methods, findings, issues highlighted by
author and results.

Intention and content of the paper
• The objective of this article is to demonstrate the principle of
artificial neural network and use of evolutionary algorithms in
ANNs.
• The authors identified that benefits of the artificial neural
networks are represented by the network architecture and the
source code [1].
• EAs play a major role in the field of ANNs where it optimize
the performance of neural networks.
• The EAs processes are used for selecting the effective input
variables for neural networks from raw data which is included
in the input features [2].

Research methodologies
• There are various kinds of research methods used by the
authors which are described below:
• Research design (Qualitative)
• Research strategy
• Data collection process (Secondary)
• Data analysis technique (Descriptive content analysis)

Issues highlighted by the researchers
• It is highlighted that over-fitting is one of the common
problem associated with the artificial neural networks.
• Solving practical issues is another problem highlighted by the
authors.
• The main problem of EA is that it is less effective and
performance may not be equal with the special algorithms.

Results and findings
• From this paper, it has found that the artificial neural network
has the potential to combine the various processing units with
the real-time learning system.
• The evolutionary algorithm is one of the best approaches for
artificial neural networks that optimize the overall
performance of the system [3].
• After analysing this paper it has identified that ANNs and EAs
both are the AI technologies which borrow thoughts from
behaviour characteristics.

Conclusion
• It is concluded that the evolutionary algorithm is an effective
technique for improving the overall performance of ANNs and
also solve the designing issues faced by ANNs.
• This study identified the key features of ANNs and reviewed
the process of EA for optimizing the performance of neural
networks.
• This paper is completely related to the Unit of study and
students can gain their skills because the authors provided in-
depth analysis about ANNs and software engineering.

References
1. M.A., Ahmadi, M., Ebadi, A. Shokrollahi and, S.M.J., Majidi, “Evolving
artificial neural network and imperialist competitive algorithm for
prediction oil flow rate of the reservoir,” Applied Soft
Compauting, vol. 13, no. 2, pp.1085-1098, 2013.
2. D.Z., Antanasijević, V.V., Pocajt, D.S., Povrenović, M.Đ. Ristić and,
A.A., Perić-Grujić, “PM10 emission forecasting using artificial neural
networks and genetic algorithm input variable optimization,” Science
of the Total Environment, vol. 443, no. 5, pp.511-519, 2013.
3. E., Asadi, M.G., da Silva, C.H., Antunes, L. Dias and, L., Glicksman,
“Multi-objective optimization for building retrofit: A model using
genetic algorithm and artificial neural network and an application,”
Energy and Buildings, vol. 81, no. 6, pp.444-456, 2014. S.,
4. Ding, H., Li, C., Su, J. Yu and, F., Jin, “Evolutionary artificial neural
networks: a review,” Artificial Intelligence Review, vol. 39, no. 3,
pp.251-260, 2013