Automated-tuned hyper-parameter deep neural network by using arithmetic optimization algorithm for Lorenz chaotic system

Deep neural networks (DNNs) are very dependent on their parameterization and require experts to determine which method to implement and modify the hyper-parameters value. This study proposes an automated-tuned hyper-parameter for DNN using a metaheuristic optimization algorithm, arithmetic optimizat...

Full description

Bibliographic Details
Main Authors: Nurnajmin Qasrina Ann, ., Pebrianti, Dwi, Mohammad Fadhil, Abas, Bayuaji, Luhur
Format: Article
Language:English
Published: Institute of Advanced Engineering and Science (IAES) 2023
Subjects:
Online Access:http://umpir.ump.edu.my/id/eprint/36943/
http://umpir.ump.edu.my/id/eprint/36943/1/Automated-tuned%20hyper-parameter%20deep%20neural%20network%20by%20using%20arithmetic%20optimization%20algorithm%20for%20Lorenz%20chaotic%20system.pdf
_version_ 1848825125586075648
author Nurnajmin Qasrina Ann, .
Pebrianti, Dwi
Mohammad Fadhil, Abas
Bayuaji, Luhur
author_facet Nurnajmin Qasrina Ann, .
Pebrianti, Dwi
Mohammad Fadhil, Abas
Bayuaji, Luhur
author_sort Nurnajmin Qasrina Ann, .
building UMP Institutional Repository
collection Online Access
description Deep neural networks (DNNs) are very dependent on their parameterization and require experts to determine which method to implement and modify the hyper-parameters value. This study proposes an automated-tuned hyper-parameter for DNN using a metaheuristic optimization algorithm, arithmetic optimization algorithm (AOA). AOA makes use of the distribution properties of mathematics’ primary arithmetic operators, including multiplication, division, addition, and subtraction. AOA is mathematically modeled and implemented to optimize processes across a broad range of search spaces. The performance of AOA is evaluated against 29 benchmark functions, and several real-world engineering design problems are to demonstrate AOA’s applicability. The hyper-parameter tuning framework consists of a set of Lorenz chaotic system datasets, hybrid DNN architecture, and AOA that works automatically. As a result, AOA produced the highest accuracy in the test dataset with a combination of optimized hyper-parameters for DNN architecture. The boxplot analysis also produced the ten AOA particles that are the most accurately chosen. Hence, AOA with ten particles had the smallest size of boxplot for all hyper-parameters, which concluded the best solution. In particular, the result for the proposed system is outperformed compared to the architecture tested with particle swarm optimization.
first_indexed 2025-11-15T03:23:57Z
format Article
id ump-36943
institution Universiti Malaysia Pahang
institution_category Local University
language English
last_indexed 2025-11-15T03:23:57Z
publishDate 2023
publisher Institute of Advanced Engineering and Science (IAES)
recordtype eprints
repository_type Digital Repository
spelling ump-369432023-02-07T01:24:18Z http://umpir.ump.edu.my/id/eprint/36943/ Automated-tuned hyper-parameter deep neural network by using arithmetic optimization algorithm for Lorenz chaotic system Nurnajmin Qasrina Ann, . Pebrianti, Dwi Mohammad Fadhil, Abas Bayuaji, Luhur TK Electrical engineering. Electronics Nuclear engineering Deep neural networks (DNNs) are very dependent on their parameterization and require experts to determine which method to implement and modify the hyper-parameters value. This study proposes an automated-tuned hyper-parameter for DNN using a metaheuristic optimization algorithm, arithmetic optimization algorithm (AOA). AOA makes use of the distribution properties of mathematics’ primary arithmetic operators, including multiplication, division, addition, and subtraction. AOA is mathematically modeled and implemented to optimize processes across a broad range of search spaces. The performance of AOA is evaluated against 29 benchmark functions, and several real-world engineering design problems are to demonstrate AOA’s applicability. The hyper-parameter tuning framework consists of a set of Lorenz chaotic system datasets, hybrid DNN architecture, and AOA that works automatically. As a result, AOA produced the highest accuracy in the test dataset with a combination of optimized hyper-parameters for DNN architecture. The boxplot analysis also produced the ten AOA particles that are the most accurately chosen. Hence, AOA with ten particles had the smallest size of boxplot for all hyper-parameters, which concluded the best solution. In particular, the result for the proposed system is outperformed compared to the architecture tested with particle swarm optimization. Institute of Advanced Engineering and Science (IAES) 2023 Article PeerReviewed pdf en cc_by_sa_4 http://umpir.ump.edu.my/id/eprint/36943/1/Automated-tuned%20hyper-parameter%20deep%20neural%20network%20by%20using%20arithmetic%20optimization%20algorithm%20for%20Lorenz%20chaotic%20system.pdf Nurnajmin Qasrina Ann, . and Pebrianti, Dwi and Mohammad Fadhil, Abas and Bayuaji, Luhur (2023) Automated-tuned hyper-parameter deep neural network by using arithmetic optimization algorithm for Lorenz chaotic system. International Journal of Electrical and Computer Engineering (IJECE), 13 (2). pp. 2167-2176. ISSN 2088-8708. (Published) http://doi.org/10.11591/ijece.v13i2.pp2167-2176 http://doi.org/10.11591/ijece.v13i2.pp2167-2176
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
Nurnajmin Qasrina Ann, .
Pebrianti, Dwi
Mohammad Fadhil, Abas
Bayuaji, Luhur
Automated-tuned hyper-parameter deep neural network by using arithmetic optimization algorithm for Lorenz chaotic system
title Automated-tuned hyper-parameter deep neural network by using arithmetic optimization algorithm for Lorenz chaotic system
title_full Automated-tuned hyper-parameter deep neural network by using arithmetic optimization algorithm for Lorenz chaotic system
title_fullStr Automated-tuned hyper-parameter deep neural network by using arithmetic optimization algorithm for Lorenz chaotic system
title_full_unstemmed Automated-tuned hyper-parameter deep neural network by using arithmetic optimization algorithm for Lorenz chaotic system
title_short Automated-tuned hyper-parameter deep neural network by using arithmetic optimization algorithm for Lorenz chaotic system
title_sort automated-tuned hyper-parameter deep neural network by using arithmetic optimization algorithm for lorenz chaotic system
topic TK Electrical engineering. Electronics Nuclear engineering
url http://umpir.ump.edu.my/id/eprint/36943/
http://umpir.ump.edu.my/id/eprint/36943/
http://umpir.ump.edu.my/id/eprint/36943/
http://umpir.ump.edu.my/id/eprint/36943/1/Automated-tuned%20hyper-parameter%20deep%20neural%20network%20by%20using%20arithmetic%20optimization%20algorithm%20for%20Lorenz%20chaotic%20system.pdf