Article
Computer Science, Interdisciplinary Applications
Dongmei Liu, Haibin Ouyang, Steven Li, Chunliang Zhang, Zhi-Hui Zhan
Summary: This paper proposes a method to automatically optimize CNN hyperparameters based on the local autonomous competitive harmony search (LACHS) algorithm. By using parameter dynamic adjustment strategy, autonomous decision-making search strategy, and local competition mechanism, it effectively improves the performance of CNN and the efficiency of hyperparameter configuration. In addition, the feasibility of LACHS algorithm in configuring CNN hyperparameters is verified through experiments on Fashion-MNIST dataset, CIFAR10 dataset, and expression recognition.
JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING
(2023)
Review
Computer Science, Artificial Intelligence
Feng Qin, Azlan Mohd Zain, Kai-Qing Zhou
Summary: This article systematically reviews the harmony search (HS) algorithm and its variants from three aspects: describing the basic HS principle, discussing the impact of HS improvement on algorithm performance, and analyzing the characteristics and applications of HS variants. It is found that the improvement of HS mainly focuses on parameter enhancement and the integration with other metaheuristic algorithms, providing future directions for enhancing HS.
SWARM AND EVOLUTIONARY COMPUTATION
(2022)
Article
Computer Science, Interdisciplinary Applications
Shubham Gupta
Summary: The modified harmony search algorithm (MHSA) improves the efficiency and accuracy of the search process by utilizing valuable information stored in harmony memory and modifying the search strategy through new formulations. Experimental validation and comparativeperformance study show that MHSA outperforms conventional HSA and other metaheuristic algorithms in terms of search efficiency as a global optimizer.
ENGINEERING WITH COMPUTERS
(2022)
Article
Engineering, Mechanical
Cheng Lu, Da Teng, Behrooz Keshtegar, Abdulaziz S. Alkabaa, Osman Taylan, Cheng-Wei Fei
Summary: In complex aeroengine structures, it is important to consider multi-physical loads for safe design. This study proposes hybrid artificial neural network (ANN) models to simulate the failure modes of turbine blisk, using machine learning approaches. The accuracy of ANN-based models is discussed using six music-inspired optimization algorithms. The Gaussian GHS algorithm shows superior performance with the highest accuracy and tendency among the other optimization algorithms.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Engineering, Civil
Reza Javanmardi, Behrouz Ahmadi-Nedushan
Summary: This paper presents a combined method using optimized neural networks and optimization algorithms to solve structural optimization problems. It trains an optimized artificial neural network (OANN) as a surrogate model to reduce computations for structural analysis. The main optimization problem is solved using the OANN and a population-based algorithm, and then the problem is further solved using the optimal point obtained and the pattern search (PS) algorithm.
FRONTIERS OF STRUCTURAL AND CIVIL ENGINEERING
(2023)
Article
Mathematics
Konstantin Barkalov, Ilya Lebedev, Marina Usova, Daria Romanova, Daniil Ryazanov, Sergei Strijhak
Summary: This paper considers the simulation of slope flow and the optimization of parameter values in the mathematical model. The finite volume method is used to model the slope flow, applying the Reynolds-averaged Navier-Stokes equations and the k-omega SST turbulence model with closure. The global search algorithm is used to find the optimal values of turbulence model coefficients for free surface gravity multiphase flows, and calibration is performed to increase the similarity between experimental and calculated velocity profiles.
Article
Computer Science, Interdisciplinary Applications
Hongquan Guo, Jian Zhou, Mohammadreza Koopialipoor, Danial Jahed Armaghani, M. M. Tahir
Summary: This study developed a deep neural network (DNN) model to predict flyrock induced by blasting, which showed a significant increase in prediction accuracy compared to an artificial neural network (ANN) model. The DNN model, optimized using the whale optimization algorithm (WOA), successfully minimized flyrock resulting from blasting and provided a suitable pattern for blasting operations in mines.
ENGINEERING WITH COMPUTERS
(2021)
Article
Multidisciplinary Sciences
Deniz Demircioglu Diren, Neslihan Ozsoy, Murat Ozsoy, Huseyin Pehlivan
Summary: Optimizing cutting parameters is crucial for cost, energy, and time efficiency in milling processes. Through response surface methodology, the optimal parameters for milling AISI 321 material were determined. The study identified that depth of cut was the most influential parameter, affecting cutting forces and surface roughness.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2023)
Article
Materials Science, Multidisciplinary
Ali Cakmak, Abdulkadir Malkocoglu, Sukru Ozsahin
Summary: This study aims to determine the optimal CNC machining conditions using an artificial neural network. Wood samples of Fagus orientalis, Castanea sativa, Pinus sylvestris, and Picea orientalis at different moisture content (MC) were machined on a CNC router in both across and along the grain directions. Based on the experimental data of surface roughness and cutting power analyses, 16 models were selected out of hundreds of models with the lowest error to determine the optimum machining parameters for each wood MC.
MATERIALS SCIENCE AND TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Mohd Sazli Saad, Azuwir Mohd Nor, Irfan Abd Rahim, Muhammad Ariffin Syahruddin, Intan Zaurah Mat Darus
Summary: This paper presents the integration of an artificial neural network (ANN) and symbiotic organism search (SOS) to model and minimize the surface roughness of the FDM process. The results show that ANN-SOS can accurately predict surface roughness and improve surface quality by adjusting input parameters.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Mathematics
Esra Uray, Serdar Carbas, Zong Woo Geem, Sanghun Kim
Summary: This study focuses on the statistical investigation of the optimum values for the control parameters of the harmony search algorithm and their effects on the best solution. The Taguchi method integrated hybrid harmony search algorithm was proposed as an alternative method for optimization analyses. The results showed that this method is reliable and efficient in parameter optimization.
Article
Multidisciplinary Sciences
Asad Ullah, Tmader Alballa, Waseem, Hamiden Abd El-Wahed Khalifa, Haifa Alqahtani
Summary: In this study, an artificial neural network based on the Cuckoo search algorithm is implemented for solving squeezing flow problems. By transforming the problems into L2 norms of minimization problems, the best set of weights for the neural network is obtained using the Cuckoo search algorithm. The experimental results demonstrate the high accuracy and effectiveness of the proposed method in solving squeezing flow problems.
Article
Computer Science, Artificial Intelligence
Mehmet Ozcalici, Mete Bumin
Summary: In this study, filter rule parameters were optimized using genetic algorithms and stock selection was performed with artificial neural networks to achieve excess returns over the market average. The results suggest that Borsa Istanbul may be a weak form efficient market, but utilizing artificial neural networks can lead to higher profits for investors.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Mehmet Ozcalici, Mete Bumin
Summary: The study explores the use of filter rule and genetic algorithm for identifying profitable trading points in stock markets, and utilizes artificial neural networks for stock selection. The results demonstrate significantly higher returns for the selected stocks compared to the buy and hold strategy.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Yiying Zhang
Summary: NNA is a metaheuristic algorithm with strong global search ability, but its drawbacks include slow convergence and premature convergence when solving complex optimization problems. To overcome these issues, an improved algorithm CCLNNA is introduced, which utilizes competitive learning and chaos theory to enhance optimization performance. Experimental results demonstrate the superiority of CCLNNA in solving complex optimization problems with multimodal properties.
KNOWLEDGE-BASED SYSTEMS
(2021)