Article
Computer Science, Information Systems
Zheng-Ming Gao, Juan Zhao, Yu-Rong Hu, Hua-Feng Chen
Summary: With the introduction of symmetry or non-symmetry as a new characteristic affecting the capability of algorithms in optimization, experimental results showed that most of the non-symmetric benchmark functions were difficult to optimize. None of the algorithms involved could optimize all functions, indicating the need for new methods and improvements for nature-inspired algorithms.
Article
Mathematics
Linas Stripinis, Remigijus Paulavicius
Summary: This paper presents an innovative extension of the DIRECT algorithm, specifically designed for global optimization problems involving Lipschitz continuous functions and linear constraints. The approach incorporates novel techniques for partitioning and selecting potential optimal hyper-rectangles, and introduces a new mapping technique to efficiently eliminate the infeasible region. Extensive tests using benchmark problems demonstrate the effectiveness and superiority of the proposed algorithm compared to existing DIRECT solvers, as confirmed by statistical analyses using Friedman and Wilcoxon tests.
Article
Computer Science, Artificial Intelligence
Abhishek Kumar, Guohua Wu, Mostafa Z. Ali, Qizhang Luo, Rammohan Mallipeddi, Ponnuthurai Nagaratnam Suganthan, Swagatam Das
Summary: The article introduces a new benchmark suite RWCMOPs for assessing the performance of Constrained Multi-objective Metaheuristics, consisting of 50 real-world problems and proposing a ranking scheme for comparative analysis.
SWARM AND EVOLUTIONARY COMPUTATION
(2021)
Article
Automation & Control Systems
Saul Zapotecas-Martinez, Abel Garcia-Najera, Adriana Menchaca-Mendez
Summary: Traditionally, novel multi-objective optimization algorithms are evaluated on artificial test problems, which lack the properties of real-world applications. This paper presents a collection of multi-objective real-world problems from different disciplines to complement the evaluation of evolutionary algorithms. The study analyzes the conflict between objectives for each real-world problem and compares the performance of different multi-objective evolutionary algorithms.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Jens Weise, Sanaz Mostaghim
Summary: This article proposes a scalable many-objective route planning optimization problem, covering important features of routing applications based on real-world data. By analyzing different test problem instances and providing the true Pareto front, we are able to evaluate the performance of different optimization algorithms in real-world applications.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2022)
Article
Mathematics, Applied
Abraham P. Vinod, Arie Israel, Ufuk Topcu
Summary: This paper presents two first-order, sequential optimization algorithms for solving constrained optimization problems. The algorithms balance the exploration of the unknown feasible space with the pursuit of global optimality within a finite number of oracle calls. The first algorithm accommodates an infeasible start and provides either a near-optimal global solution or establishes infeasibility, while the second algorithm returns a near-optimal global solution without any constraint violation for a strongly convex constraint function and a feasible initial guess. These algorithms compute global suboptimality bounds at each iteration and can satisfy user-specified tolerances in the computed solution.
SIAM JOURNAL ON OPTIMIZATION
(2022)
Article
Automation & Control Systems
Danial Yazdani, Mohammad Nabi Omidvar, Ran Cheng, Jurgen Branke, Trung Thanh Nguyen, Xin Yao
Summary: This study provides a comprehensive review of existing benchmarks and investigates their shortcomings in capturing different problem features. It then proposes a highly configurable benchmark suite capable of generating problem instances with various characteristics.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Computer Science, Information Systems
Mohammed Qaraad, Souad Amjad, Nazar K. Hussein, Seyedali Mirjalili, Nadhir Ben Halima, Mostafa A. Elhosseini
Summary: The study introduces a new algorithm called SSALEO that combines the Salp Swarm Algorithm (SSA) with a local escaping operator (LEO) to overcome limitations of SSA. Experimental results show that SSALEO performs competitively and often outperforms other algorithms, including specialized state-of-the-art algorithms.
Article
Biotechnology & Applied Microbiology
Zongshan Wang, Hongwei Ding, Jingjing Yang, Peng Hou, Gaurav Dhiman, Jie Wang, Zhijun Yang, Aishan Li
Summary: This paper introduces a bio-inspired algorithm called Salp swarm algorithm (SSA) and proposes an improved strategy combining pinhole-imaging-based learning (PIBL) and orthogonal experimental design (OED). It also designs an effective adaptive conversion parameter method to enhance the algorithm's performance. Comparative experiments show that the algorithm performs well in most benchmark problems.
FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY
(2022)
Article
Engineering, Multidisciplinary
Noha Hamza, Ruhul Sarker, Daryl Essam, Saber Elsayed
Summary: The number of research works on dynamic constrained optimization problems has been increasing rapidly over the past two decades. However, no research on dynamic problems with changes in the coefficients of the constraint functions has been reported. In this paper, a new evolutionary framework with multiple novel mechanisms is proposed to deal with such problems, and the results demonstrate its significant contribution in achieving good quality solutions, high feasibility rates, and fast convergence in rapidly changing environments.
ALEXANDRIA ENGINEERING JOURNAL
(2023)
Article
Computer Science, Artificial Intelligence
Cyril Picard, Jurg Schiffmann
Summary: The article presents a framework called MODAct for designing electro-mechanical actuators and derives 20 constrained multiobjective optimization test problems from it. The effects of constraints on the Pareto front and convergence performance are analyzed, and a constraint landscape analysis approach with three new metrics is utilized to characterize the search and objective spaces. Comparison of MODAct features with existing test suites highlights differences and suggests that design problems are challenging due to constraints.
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2021)
Article
Computer Science, Interdisciplinary Applications
Justin Sirignano, Jonathan MacArt, Konstantinos Spiliopoulos
Summary: Recent research has developed partial differential equation (PDE) models in science and engineering using deep learning. The PDE's functional form is determined by a neural network and calibrated to available data. Gradient descent is used to optimize the neural network parameters in the PDE, with the gradient evaluated using an adjoint PDE. As the number of parameters increases, the PDE and adjoint PDE converge to a non-local PDE system. The adjoint method is then used to train a neural network model for fluid mechanics, acting as a closure model for the Reynolds-averaged Navier-Stokes equations.
JOURNAL OF COMPUTATIONAL PHYSICS
(2023)
Article
Computer Science, Artificial Intelligence
Peilan Xu, Wenjian Luo, Xin Lin, Jiajia Zhang, Xuan Wang
Summary: The complexity of engineering design optimizations arises from the large-scale nature of the problems, which demands high performance from evolutionary algorithms. To compare and analyze large-scale optimization algorithms, benchmarks that simulate real-world features are needed. This paper introduces a new large-scale continuous optimization benchmark suite with 15 test functions and a modular structure. The benchmark suite includes features like heterogeneous design and versatile coupling, making it very challenging for cooperative coevolution frameworks and state-of-the-art large-scale optimization algorithms.
SWARM AND EVOLUTIONARY COMPUTATION
(2023)
Article
Computer Science, Software Engineering
Coralia Cartis, Estelle Massart, Adilet Otemissov
Summary: This paper focuses on the bound-constrained global optimization of functions with low effective dimensionality. The intrinsic low dimensionality of the constrained landscape is explored using feasible random embeddings to improve the scalability of algorithms for these special-structure problems. A reduced subproblem formulation that solves the original problem over a random low-dimensional subspace subject to affine constraints is proposed. The X-REGO algorithmic framework, which uses multiple random embeddings, is introduced and proven to converge globally and linearly in the number of embeddings with a high success probability.
MATHEMATICAL PROGRAMMING
(2023)
Article
Mathematics
Yaohui Li, Jingfang Shen, Ziliang Cai, Yizhong Wu, Shuting Wang
Summary: The study introduces a kriging-assisted multi-objective constrained global optimization method that can generate multiple sampling points at a time and generate the Pareto frontier set through multi-objective optimization, further screening out more promising and valuable sampling points.
Article
Computer Science, Software Engineering
Elif Varol Altay, Bilal Alatas
Summary: A new chaos-enhanced representation scheme based on chaos numbers is proposed for evolutionary optimization methods. This method is designed as a multiobjective rule miner that simultaneously handles different conflicting objectives and finds accurate and comprehensible rules automatically. The performance of this method is promising with respect to different metrics based on real quantitative data sets.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2022)
Article
Energy & Fuels
Elif Varol Altay, Ezgi Gurgenc, Osman Altay, Aydin Dikici
Summary: Due to the increase in global climate change and depletion of fossil fuels, the interest in renewable energy sources is growing in developed countries. Geothermal energy, which can be used for both electricity production and heat energy, holds an important place among renewable energy sources. Machine learning methods were utilized in this study to predict the purpose of geothermal waters based on a geothermal dataset from different regions. Various machine learning methods were employed, and a hybrid metaheuristic artificial neural network model was developed, achieving promising results with a 91.84% accuracy rate.
Article
Computer Science, Artificial Intelligence
Osman Altay, Elif Varol Altay
Summary: This study proposes a new hybrid method, IMP-GWO-MLP, which combines the improved grey wolf optimizer (IMP-GWO) with the multilayer perceptron (MLP) to address the challenging parts of MLP training. Experimental results on multiple datasets show that the proposed method outperforms other state-of-the-art methods and has a high success rate in real-world modeling.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Mathematics, Interdisciplinary Applications
Harun Bingol, Bilal Alatas
Summary: With the development of technology, access methods to information have changed, with internet blogs, news sites, and social media replacing traditional tools like TV and newspapers. Cheaper and faster access, as well as internet availability, are the main factors driving this change. However, information spread on the internet can lack accuracy and be driven by various motives. Detecting deceptive information in textual data is crucial, and this paper proposes a new approach using optimization methods like OIO, GWO, and CBOIOs, which are adapted for the deception detection problem. Experimental results show that CBOIOs are more effective than other machine learning algorithms.
CHAOS SOLITONS & FRACTALS
(2023)
Article
Computer Science, Artificial Intelligence
Hande Yuksel Bayram, Harun Bingol, Bilal Alatas
Summary: This study proposes a tomato leaf disease classification model based on deep learning methods, which utilizes pre-trained convolutional neural network architectures to extract feature maps and employs optimized feature maps for intelligent classification. Experimental results show an average accuracy rate of 99.50% for the proposed model.
TRAITEMENT DU SIGNAL
(2022)
Article
Biology
Sinem Akyol, Muhammed Yildirim, Bilal Alatas
Summary: Quality sleep is crucial for daily life, and sleep disorders can be diagnosed using computer-aided systems. A study utilized 700 sound data samples with three different feature extraction methods and optimized the feature maps using improved metaheuristic algorithms and machine learning methods, achieving a high accuracy rate.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Computer Science, Artificial Intelligence
Hande Yuksel Bayram, Harun Bingol, Bilal Alatas
Summary: Brain tumors are dangerous and can be fatal, occurring in people of all ages. Early detection is crucial for treatment planning and survival. In this study, a hybrid deep model combining Convolutional Neural Network and Support Vector Machine was proposed for accurately classifying brain tumors based on MRI images. The proposed model achieved a high accuracy of 93.2%.
TRAITEMENT DU SIGNAL
(2023)
Article
Construction & Building Technology
Muhammed Ulucan, Gungor Yildirim, Bilal Alatas, Kursat Esat Alyamac
Summary: This study aims to develop a new AI model for predicting mix design and early-age compressive strength of recycled aggregate concrete. The model uses a metaheuristic mechanism to extract interpretable rules from experimental data. The proposed model is tested against other machine learning algorithms and rule-based methods, showing promising results in terms of accuracy and explainability.
STRUCTURAL CONCRETE
(2023)
Article
Green & Sustainable Science & Technology
Shiyuan Gan, Xuejing Yang, Bilal Alatas
Summary: This study aims to address the challenges of continuity and intelligent intervention in English language teaching. By using an autoencoder for interest recognition and comprehensive assessment in online teaching, the research demonstrates high accuracy in identifying student interests and achieves a low error rate compared to teacher grades.
Article
Engineering, Multidisciplinary
Sinem Akyol, Mehmet Das, Bilal Alatas
Summary: A hybrid-optimization-based artificial intelligence classification method is applied for the first time to produce explainable models of compressor energy consumption in a vapor compression refrigeration system. This innovative method determines the energy consumption values of a refrigerant gas based on operating parameters, and allows for automatic identification of the operating conditions with the lowest energy consumption.
Article
Computer Science, Information Systems
G. Sandhya Rani, Sarada Jayan, Bilal Alatas
Summary: This paper studies the application of five chaotic maps in global optimization and proposes a global optimization method, Hybrid Chaotic Pattern Search Algorithm (HCPSA), for multivariable unconstrained optimization problems. Comparative results with other algorithms demonstrate the effectiveness of the proposed algorithm in higher dimensional non-linear functions. Additionally, the paper showcases the use of HCPSA in financial prediction and compares it with other algorithms, showing superior accuracy.
Article
Mathematics, Applied
Lamiaa M. El Bakrawy, Mehmet Akif Cifci, Samina Kausar, Sadiq Hussain, Md Akhtarul Islam, Bilal Alatas, Abeer S. Desuky
Summary: This study proposes a modified antlion optimization (MALO) algorithm to improve the primary antlion optimization algorithm (ALO) for the task of instance reduction. The results show that the MALO algorithm outperforms the basic ALO algorithm and other comparative algorithms in terms of convergence rate and performance measures like Accuracy, Balanced Accuracy (BACC), Geometric mean (G-mean), and Area Under the Curve (AUC). The MALO algorithm offers a potential solution to the problem of local optima stagnation and slow convergence speed.
Article
Computer Science, Information Systems
Tummala. S. L. V. Ayyarao, N. S. S. Ramakrishna, Rajvikram Madurai Elavarasan, Nishanth Polumahanthi, M. Rambabu, Gaurav Saini, Baseem Khan, Bilal Alatas
Summary: This paper proposes a metaheuristic optimization algorithm based on ancient war strategy, which achieves a good balance between exploration and exploitation stages by simulating the strategic movements of army troops during war. The algorithm introduces a novel weight updating mechanism and a weak soldier's relocation strategy to improve its convergence and robustness.
Article
Engineering, Multidisciplinary
Cem Baydogan, Bilal Alatas
Summary: The increasing use of various online social media platforms has led to the sharing of correct or incorrect information by users, particularly during COVID-19. This has resulted in a negative reaction towards East Asia (especially China) on these platforms, with social media users spreading degrading, racist, disrespectful, and offensive posts, accusing Asian people of being responsible for the outbreak of COVID-19. To address this issue, the development of a Hate Speech Detection (HSD) system was necessary to prevent the spread of such posts related to COVID-19. In this article, a textual-based study using Shallow Learning (SL) and Deep Learning (DL) methods was conducted to analyze and detect hate speech sharing in online social networks related to COVID-19.
TEHNICKI VJESNIK-TECHNICAL GAZETTE
(2022)
Article
Physics, Multidisciplinary
Xiaoyu Shi, Jian Zhang, Xia Jiang, Juan Chen, Wei Hao, Bo Wang
Summary: This study presents a novel framework using offline reinforcement learning to improve energy consumption in road transportation. By leveraging real-world human driving trajectories, the proposed method achieves significant improvements in energy consumption. The offline learning approach demonstrates generalizability across different scenarios.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2024)
Article
Physics, Multidisciplinary
Junhyuk Woo, Soon Ho Kim, Hyeongmo Kim, Kyungreem Han
Summary: Reservoir computing (RC) is a new machine-learning framework that uses an abstract neural network model to process information from complex dynamical systems. This study investigates the neuronal and network dynamics of liquid state machines (LSMs) using numerical simulations and classification tasks. The findings suggest that the computational performance of LSMs is closely related to the dynamic range, with a larger dynamic range resulting in higher performance.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2024)
Article
Physics, Multidisciplinary
Yuwei Yang, Zhuoxuan Li, Jun Chen, Zhiyuan Liu, Jinde Cao
Summary: This paper proposes an extreme learning machine (ELM) algorithm based on residual correction and Tent chaos sequence (TRELM-DROP) for accurate prediction of traffic flow. The algorithm reduces the impact of randomness in traffic flow through the Tent chaos strategy and residual correction method, and avoids weight optimization using the iterative method. A DROP strategy is introduced to improve the algorithm's ability to predict traffic flow under varying conditions.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2024)
Article
Physics, Multidisciplinary
Chengwei Dong, Min Yang, Lian Jia, Zirun Li
Summary: This work presents a novel three-dimensional system with multiple types of coexisting attractors, and investigates its dynamics using various methods. The mechanism of chaos emergence is explored, and the periodic orbits in the system are studied using the variational method. A symbolic coding method is successfully established to classify the short cycles. The flexibility and validity of the system are demonstrated through analogous circuit implementation. Various chaos-based applications are also presented to show the system's feasibility.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2024)
Article
Physics, Multidisciplinary
Viorel Badescu
Summary: This article discusses the maximum work extraction from confined particles energy, considering both reversible and irreversible processes. The results vary for different types of particles and conditions. The concept of exergy cannot be defined for particles that undergo spontaneous creation and annihilation. It is also noted that the Carnot efficiency is not applicable to the conversion of confined thermal radiation into work.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2024)
Article
Physics, Multidisciplinary
P. M. Centres, D. J. Perez-Morelo, R. Guzman, L. Reinaudi, M. C. Gimenez
Summary: In this study, a phenomenological investigation of epidemic spread was conducted using a model of agent diffusion over a square region based on the SIR model. Two possible contagion mechanisms were considered, and it was observed that the number of secondary infections produced by an individual during its infectious period depended on various factors.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2024)
Article
Physics, Multidisciplinary
Zuan Jin, Minghui Ma, Shidong Liang, Hongguang Yao
Summary: This study proposes a differential variable speed limit (DVSL) control strategy considering lane assignment, which sets dynamic speed limits for each lane to attract vehicle lane-changing behaviors before the bottleneck and reduce the impact of traffic capacity drop. Experimental results show that the proposed DVSL control strategy can alleviate traffic congestion and improve efficiency.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2024)
Article
Physics, Multidisciplinary
Matthew Dicks, Andrew Paskaramoorthy, Tim Gebbie
Summary: In this study, we investigate the learning dynamics of a single reinforcement learning optimal execution trading agent when it interacts with an event-driven agent-based financial market model. The results show that the agents with smaller state spaces converge faster and are able to intuitively learn to trade using spread and volume states. The introduction of the learning agent has a robust impact on the moments of the model, except for the Hurst exponent, which decreases, and it can increase the micro-price volatility as trading volumes increase.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2024)
Article
Physics, Multidisciplinary
Zhouzhou Yao, Xianyu Wu, Yang Yang, Ning Li
Summary: This paper developed a cooperative lane-changing decision system based on digital technology and indirect reciprocity. By introducing image scoring and a Q-learning based reinforcement learning algorithm, drivers can continuously evaluate gains and adjust their strategies. The study shows that this decision system can improve driver cooperation and traffic efficiency, achieving over 50% cooperation probability under any connected vehicles penetration and traffic density, and reaching 100% cooperation probability under high penetration and medium to high traffic density.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2024)
Article
Physics, Multidisciplinary
Josephine Nanyondo, Henry Kasumba
Summary: This paper presents a multi-class Aw-Rascle (AR) model with area occupancy expressed in terms of vehicle class proportions. The qualitative properties of the proposed equilibrium velocity and the stability conditions of the model are established. The numerical results show the effect of proportional densities on the flow of vehicle classes, indicating the realism of the proposed model.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2024)
Article
Physics, Multidisciplinary
Oliver Smirnov
Summary: This study proposes a new method for simultaneously estimating the parameters of the 2D Ising model. The method solves a constrained optimization problem, where the objective function is a pseudo-log-likelihood and the constraint is the Hamiltonian of the external field. Monte Carlo simulations were conducted using models of different shapes and sizes to evaluate the performance of the method with and without the Hamiltonian constraint. The results demonstrate that the proposed estimation method yields lower variance across all model shapes and sizes compared to a simple pseudo-maximum likelihood.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2024)
Article
Physics, Multidisciplinary
Przemyslaw Chelminiak
Summary: The study investigates the first-passage properties of a non-linear diffusion equation with diffusivity dependent on the concentration/probability density through a power-law relationship. The survival probability and first-passage time distribution are determined based on the power-law exponent, and both exact and approximate expressions are derived, along with their asymptotic representations. The results pertain to diffusing particles that are either freely or harmonically trapped. The mean first-passage time is finite for the harmonically trapped particle, while it is divergent for the freely diffusing particle.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2024)
Article
Physics, Multidisciplinary
Hidemaro Suwa
Summary: The choice of transition kernel is crucial for the performance of the Markov chain Monte Carlo method. A one-parameter rejection control transition kernel is proposed, and it is shown that the rejection process plays a significant role in determining the sampling efficiency.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2024)
Article
Physics, Multidisciplinary
Xudong Wang, Yao Chen
Summary: This article investigates the joint influence of expanding medium and constant force on particle diffusion. By starting from the Langevin picture and introducing the effect of external force in two different ways, two models with different force terms are obtained. Detailed analysis and derivation yield the Fokker-Planck equations and moments for the two models. The sustained force behaves as a decoupled force, while the intermittent force changes the diffusion behavior with specific effects depending on the expanding rate of the medium.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2024)