Multi objective optimization machine learning. In this paper, we present a .

Multi objective optimization machine learning May 11, 2019 · The machine learning algorithms exploit a given dataset in order to build an efficient predictive or descriptive model. We consider Jan 4, 2023 · This section presents the GA design choices for a multi-objective approach centered in Green AI. Through a rigorous multi-objective optimization process, the energy efficiency was improved by 126 %, while maintaining battery temperatures below 28. 4 days ago · The outcomes demonstrate that the compressive strength and slump flow of UHPC are correctly predicted by the machine learning models. In this work, we develop a machine learning-based multi-objective optimization framework for improving dimension accuracy of wax pattern by optimizing its process parameters. As a promising AI method, the development and application of Machine Learning (ML) attract increasingly more attention from researchers. In this multi-objective formulation, we will study the tradeoffs among the accuracy, false positive rate, true positive rate, and area under receiver operator characteristic curve objectives (formulae linked here). ’s NSGA-II is commonly applied, but this research applies meta-heuristic algorithms to multi-objective optimization in a cloud production system, incorporating more advanced features. Multi-objective evolutionary optimization assists machine learning algorithms to optimize their hyper-parameters, usually under conflicting Jul 1, 2024 · This optimization problem is like the optimization of parameters of shield machine in the process of digging (Liu et al. We demonstrated the efficacy of the strategy by optimizing the two step aging treatment parameters to enhance the strength and ductility of as-cast ZE62 (Mg-6 wt. This study proposes a novel multi-objective particle swarm optimization (MOPSO) algorithm employing the Gaussian process regression (GPR)-based machine learning (ML) method for multi-variable, multi-level optimization problems with multiple constraints. However, there were few studies that investigated the contradictory of mechanical and magnetic properties to process FeSiCr SMC powders. ,2022a), multi-objective BLO has not received much attention. Our workflow includes assembling building blocks and topologies into an initial set of hypothetical MOFs, using genetic algorithms to optimize this initial set for high CO2/N2 selectivity, and further evaluating the top materials through process-level modeling Apr 15, 2024 · Soft magnetic composite (SMC) products have been widely used in electromagnetic applications due to their unique properties, including extremely low eddy current loss and relatively low total core loss at medium and high frequencies. Amorphous optimization of shading geometries is the optimization of shading devices irregularly, which can suggest solutions that might look May 25, 2024 · Multi-objective optimization and machine learning assisted design and synthesis of magnesium based novel non-equiatomic medium entropy alloy Author links open overlay panel Priyabrata Das , Pulak Mohan Pandey Dec 15, 2023 · This study assesses the use of different computational tools to obtain optimal reservoir operations at the Hatillo dam in the Dominican Republic. Sep 1, 2024 · Our methodology combines the strengths of robust multi-objective optimization techniques with the adaptability of machine learning, an essential blend given the challenges posed by variable weather patterns and their impact on grid operations. Oct 15, 2018 · Feature selection methods are developed to determine the most suitable modes of original time series and the optimal input form of the model, while the optimization forecasting module is applied to model the wind speed series based on the machine learning method and the multi-objective optimization algorithm, then the compromise solution of Oct 15, 2018 · Feature selection methods are developed to determine the most suitable modes of original time series and the optimal input form of the model, while the optimization forecasting module is applied to model the wind speed series based on the machine learning method and the multi-objective optimization algorithm, then the compromise solution of This tutorial aims to provide a comprehensive introduction to fundamentals, recent advances, and applications of multi-objective optimization (MOO), followed by hands-on coding examples. When deciding on the optimal Sep 25, 2024 · In this article, we computationally design a series of metal–organic frameworks (MOFs) optimized for postcombustion carbon capture. Jan 1, 2023 · However, this method was limited to the optimization of a single objective, which restricts the amount of process understanding that can be achieved. In many applications of machine learning such as drug discovery and material design, the goal is to generate candidates which simultaneously optimize a set of potentially conflicting objectives. The microscopic parameters were determined by Pearson correlation analysis and domain knowledge as the key affect factors of tensile strength and Oct 15, 2023 · In recent years, multi-objective optimization (MOO) emerges as a foundational problem underpinning many multi-agent multi-task learning applications. The optimizer was Non-Dominated Sorting Genetic Algorithm version II (NSGA-II), which ensures the approximation of the Pareto front of the multi-objective problem. Download: Download high-res image (710KB) Dec 1, 2023 · This study utilized whole building energy simulation and multi-objective optimization method to conduct the work. In this work, we present a framework called Of course, multiple objectives can in principle be aggregated into a single metric, which converts a multi-objective optimization (MOO) problem to a single-objective optimization problem. A multi-objective optimization approach is applied to models that simulate reservoir operations and three different machine learning (ML) models are employed to learn the real operation of the system. Multi-objective optimization or Pareto optimization (also known as multi-objective programming, vector optimization, multicriteria optimization, or multiattribute optimization) is an area of multiple-criteria decision making that is concerned with mathematical optimization problems involving more than one objective function to be optimized simultaneously. Such complicated systems urgently desire advanced methods to conquer the multi-objective optimization problems (MOPs). In this paper, we Apr 4, 2022 · The ever-increasing growth of semiconductor industries owing to nano sizing of modern electronic devices intensifies the need to handle enormous data. Extensive experiments combine four machine learning and deep learning algorithms with an evolution-ary optimisation algorithm. We know there is a wealth of subtlety and finesse involved in data cleaning and feature engineeri Jul 28, 2022 · The multi-objective evolutionary algorithm is regarded as the most popular and effective algorithm for solving multi-objective optimization problem, which has been used to enhance the performance of machine learning-based model and the quality of their results [45]. Elgendy et al. Oct 23, 2022 · We study the problem of generating diverse candidates in the context of Multi-Objective Optimization. Current Pareto set learning methods for such problems often rely on surrogate models like Gaussian processes to approximate the objective functions. At a fundamental level, his research has focused on Multi- and Many-objective optimization, including, development of Evolutionary Algorithms and their performance enhancement using Machine Learning; Termination criterion for these algorithms; and Decision Support based on objectives and constraints’ relative preferences. 6 kPa. To solve this problem, the difficulty lies not only in the high cost of discipline performance evaluation but also in the complex coupling relationship between different disciplines. This motivates us to propose Mar 3, 2022 · We consider a generic min-max multi-objective bilevel optimization problem with applications in robust machine learning such as representation learning and hyperparameter optimization. The method involves establishing a multi-objective optimization model that considers both optimal electrode design and optimal trajectory planning. To ensure that the parts Jul 7, 2021 · Jul 7, 2021 · post Exploring Multi-Objective Hyperparameter Optimization. There are four steps in this workflow: (1) Extract the structural parameters and properties from simulated structures as the current training set. These surrogate models can become fragmented Dec 28, 2023 · Download Citation | Multi-Disciplinary and Multi-Objective Optimization Method Based on Machine Learning | The optimization of aircraft is a typical multidisciplinary and multi-objective problem. Volume 2A: 42nd Design Automation Conference. In Proceedings of the International Conference on Artificial Neural Networks. In Proceedings of the 2016 IEEE Symposium Series on Computational Intelligence (SSCI’16) . IEEE, Los Alamitos, CA, 1–8. Evolutionary multi-objective optimization (EMO) algorithms are a family of nature-inspired algorithms widely used for solving multi-objective optimization problems (MOPs). Feb 15, 2024 · The approaches of multi-objective optimization (MOO) can be utilized to delicately balance between environmental sustainability and economic viability [5]. Jul 4, 2022 · Realistic problems typically have many conflicting objectives. 1 which means that there are a lot Feb 14, 2021 · Meta learning with multiple objectives can be formulated as a Multi-Objective Bi-Level optimization Problem (MOBLP) where the upper-level subproblem is to solve several possible conflicting targets for the meta learner. . Despite the great success achieved Oct 19, 2023 · Here, we present a data-efficient method for the high-dimensional multi-property optimization of 3D-printed architected materials utilizing a machine learning (ML) cycle consisting of the finite Dec 28, 2023 · The optimization of aircraft is a typical multidisciplinary and multi-objective problem. Oct 15, 2023 · Inspired by the significant development in machine learning technology, we herein propose a multi-objective optimization strategy to search for Fe-based MGs with optimal combinations of critical casting size (D max), B s, and plasticity. In this paper, we propose an end-to-end prediction and multi-objective optimization framework integrating machine learning (ML) and non-dominated sorting genetic algorithm (NSGA-II). More specifically, AutoDL contains a standard process of data preprocessing, optimal hyperparameter tuning, algorithm selection, and model performance Oct 15, 2022 · The main steps include: selecting optimization parameters, establishing sample database, formulating machine learning strategy, conducting automatic design and cost calculation, and optimizing the multi-objective problem through the genetic algorithm. Rong et al. Dec 6, 2023 · Structural optimization is essential to improve the performance of mixing equipment. Several methods have been developed to perform HPO; most of these are focused on optimizing one performance measure (usually an error-based measure), and the literature on such single-objective HPO problems is vast. Nov 1, 2023 · To address this research gap, this work proposes a comprehensive machine learning (ML) aided MPC with multi-objective optimization (MOO) and multi-criteria decision making (MCDM) methodology (abbreviated as ML-aided MPC-MOO-MCDM) for chemical process control. proposed a multi-objective optimization strategy utilizing machine learning for the process parameter optimization in vertical zone refining of 7 N-grade ultra-high purity indium [30]. The performance of the combined training and optimisation pipeline is evaluated by verifying the generated Pareto-optimal results using the ground truth simulations. The major steps are hourly weather files generation, parametric building simulation, the establishment of surrogate model and Multi-objective optimization, respectively. Jan 24, 2024 · Multi/Many-objective approaches: while most hybridization research between optimization and machine learning focuses on single-objective approaches, real-world problems often involve multiple objectives (Kang et al. In multi-task learning (MTL), the optimization problem is a multi-objective problem in nature, but is usually solved by summing the objectives Mar 15, 2023 · Multi-objective Optimization (MOO) nominates the best solutions that provide calculated compromises between objectives and suggests the required decision variables for achieving such objectives [16]. Oct 1, 2023 · To accurately address the fully coupled complex chemical-physical processes occurred in PEM fuel cells and solve the traditional time-consuming and economically unfordable multi-variable and multi-objective optimization of GDL, physics-based simulation and machine-learning-based surrogate modelling are integrated to build a sophisticated M 5 Sep 10, 2024 · In Section “Machine learning approximation models and multi-objective optimization”, basic theories of MLAM and MOOA are introduced, and the basic process for multi-objective optimization design of dump truck carriages is elucidated. 5555/3524938. , before possible alternative solutions are known Jan 1, 2025 · In particular, they proposed the multi-objective particle swarm optimization (MOPSO) [11], the multi-objective firefly algorithm (MOFA) [12] and the multi-objective bat algorithm (MOBAS) [13]. Moreover, these objectives are often imperfect evaluations of some underlying property of interest Multi-Objective Hyperparameter Tuning. (2018) NSGA-II multi-objective optimization was adopted for optimization, which only took into account the multi-objective optimization capability and convergence speed, but did not take into account the parameter sensitivity and Nov 1, 2024 · Multi-objective optimization of engineered cementitious composite based on machine learning and generative adversarial network Author links open overlay panel Yufei Wang a b , Junbo Sun c , Xiangyu Wang b , Shengping Li a , Hongyu Zhao c , Bo Huang d , Yujie Cao b , Mohamed Saafi e Jun 1, 2024 · The multi-objective optimization design of recycled aggregate concrete mixture proportions based on machine learning and NSGA-II algorithm is carried out. However, it is often unclear how a trade-off between different objectives should be defineda priori, i. In order to reduce the computational cost of solving such multi-objective problems, this paper proposes an ARBF-MLPA (Adaptive Radial Basis Function neural network combined with Machine Learning Point Adding) method Dec 24, 2022 · In (general) multi-objective optimization problems, the multiple objectives are often scalarized into one single function, such that the problem can be solved as a single-objec- tive problem. The multi-objective optimization produces Pareto fronts, which illustrate the trade-off between the mix’s compressive strength, slump flow, cost, and environmental sustainability as well as the wide variety of Feb 23, 2024 · Qingquan Zhang, Jialin Liu, Zeqi Zhang, Junyi Wen, Bifei Mao, and Xin Yao. , 2023), and the optimization of speed in the process of ship navigation (Karatug et al. It acts as pseudo-multi-objective optimization since it is transformed into single-objective optimization. Abstract Oct 31, 2024 · This reduces computational overhead and marks a significant advancement in using machine learning to enhance the efficiency and scalability of multi-objective optimization tasks. 3 Multi-Task Learning as Multi-Objective Optimization Consider a multi-task learning (MTL) problem over an input space X and a collection of task spaces {Yt} t2[T], such that a large dataset of i. From the analysis and comparisons conducted in Section 4. However, existing algorithms in MOO literature remain limited to centralized learning settings, which do not satisfy the distributed nature and data privacy needs of such multi-agent multi-task learning applications. Accelerating surrogate assisted evolutionary algorithms for expensive multi-objective optimization via explainable machine learning[J]. These can address different main tasks (i. MOO has wide applications in all industry sectors where decision Jan 15, 2023 · A multi-objective optimization strategy was designed by machine learning with regard to vertical zone refining of ultra-high purity indium. A case study is done for a real waste collection problem in a certain area of Beijing. , 2022a), the optimization of process parameters of blast furnace gas (lv et al. % RE) Mg alloy. Fairer machine learning through multi-objective evolutionary learning. The solution proposed in this work will be part of the development of AutoML framework, which aims to automate model construction process, focusing on HPO and AO/NAS optimization. Such problems find wide Jun 16, 2024 · ABSTRACT. Springer, 111–123. , before possible alternative solutions are known [43]. d. However, much less attention has been paid to the fairness-aware multi-objective optimization, which is indeed commonly seen in real life, such as fair resource allocation problems and data-driven multi-objective Jun 16, 2013 · Evolutionary multi-objective optimization (EMO) algorithms have been used in finding a representative set of Pareto-optimal solutions in the past decade and beyond. In this paper, the two objectives, ROP and MSE, are set to be equal. In this work, we present a framework called Autotune that To reduce the slot torque of the surface attached the PM machine without affecting the maximum torque, Ilka et al. An efficient optimization strategy based on computational fluid dynamics, machine learning, and the multi-objective genetic algorithm was proposed to predict and optimize the performance of the stirred tank. Mar 15, 2024 · This study proposed a procedure to optimize the mixture of RAC using machine learning (ML) and multi-objective optimization (MOO) model, which enhances the compressive strength and chloride ion resistance of RAC while minimizing the effect on environmental impact (EI) and life cycle costs (LCC). The majority of data found in the real world are conflicting in nature and must be optimized to attain the demanded target Jul 15, 2024 · By integrating multi-objective optimization, machine learning, and electric vehicle dynamics, this study addresses a challenge in PHEV adoption. Prior work either demand optimizing a new network for every point on the Pareto front, or induce a large overhead to the number of trainable parameters by using hyper-networks conditioned on modifiable preferences. For example, in [ 129 ] and [ 131 ], we can use different classifications models encoded in the MOO-framework and then select the best model as discussed in Sect. Dec 12, 2023 · Multi-objective parameter configuration of machine learning algorithms using model-based optimization. Sep 5, 2024 · Ouyang et al. The results indicate that the comprehensive dimensions of technical performance, economic performance, and environmental impact of the optimized Automated machine learning has gained a lot of attention recently. 1 Introduction In multi-objective optimization (MOO) one attempts to simultaneously optimize several, poten-tially con icting functions. , 2023). Dec 23, 2024 · Expensive multi-objective optimization problems (EMOPs) are common in real-world scenarios where evaluating objective functions is costly and involves extensive computations or physical experiments. Feb 1, 2023 · Machine learning-assisted multi-objective optimization of battery manufacturing from synthetic data generated by physics-based simulations Author links open overlay panel Marc Duquesnoy a b , Chaoyue Liu a f , Diana Zapata Dominguez a f , Vishank Kumar d , Elixabete Ayerbe b c , Alejandro A. Franco a b e f Jun 1, 2022 · The efficacy of urban mitigation strategies for heat and carbon emissions relies heavily on local urban characteristics. The pareto optimal solution is obtained based on MOO, which can be combined with the technique for order of preference by similarity to ideal solution (TOPSIS) methods to choose the best solution [6]. While BPNNs tune their parameters iteratively with (usually, time-consuming) gradient-based computations, ELMs merely use an analytically determined non-iterative solution as the output weights, together with randomly initialized input weights. So, we start out by computing each of those five objectives for our 84 hyperparameter Jan 1, 2006 · In the layer optimization objective design, machine learning is generally regarded as a multi-objective optimization problem [172]; however, most algorithms optimize a scalarized objective in a Nov 1, 2022 · Afterward, the formation of a squad is based on the predictions and multi-objective evolutionary algorithms. An optimization approach is proposed for the multi-objective optimization design of two-dimensional (2D) hydrofoils by combining a machine learning method XGBoost and an Mar 24, 2021 · Multi-objective optimization (MOO) is a prevalent challenge for Deep Learning, however, there exists no scalable MOO solution for truly deep neural networks. [30], [31] As such, an efficient experimental approach for multi-objective optimization of mixed variable catalytic systems on a substrate-by-substrate basis would be desirable. It needs to be completed four steps for achieving this goal. Apr 15, 2022 · An ELM is a fast training algorithm for single-hidden layer feed-forward neural networks (SLFNs). Sep 1, 2024 · Flowchart of multi-objective optimization for the multi-generation system based on machine learning model. applies gradient-based multi-objective optimization to multi-task learning. Real-time decision-making in dynamic multi-objective optimization problems (DMOPs) is challenging due to constantly changing objectives and constraints. 1. Multi-objective evolutionary optimization assists machine learning Oct 1, 2024 · To investigate the EDM of highly distorted closed surfaces while accounting for multiple factors, this research proposes a machine learning-driven multi-objective optimization method. Jun 27, 2024 · This paper combines the non-dominated sorting genetic algorithm III multi-objective optimization algorithm with the light gradient boosting machine algorithm to optimize the yield strength, ultimate Sep 1, 2022 · To accelerate data-driven studies for various optimization applications in chemical engineering, a comprehensive machine learning aided multi-objective optimization and multi-criteria decision making (abbreviated as ML aided MOO-MCDM) framework is proposed in the present paper. tention recently. However, it is often unclear how a trade-off between different objectives should be defined a priori , i. Sep 20, 2024 · The challenge of optimizing the distribution path for location logistics in the cold chain warehousing of fresh agricultural products presents a significant research avenue in managing the logistics of agricultural products. 1007/978-3-031-22419-5_12 Dec 26, 2024 · Multi-objective optimization: NSGA-II: Deb et al. Oct 10, 2018 · In this paper, we explicitly cast multi-task learning as multi-objective optimization, with the overall objective of finding a Pareto optimal solution. To improve the optimization efficiency, a new optimization method is proposed, including two new algorithms: conditional Of course, multiple objectives can in principle be aggregated into a single metric, which converts a multi-objective optimization (MOO) problem to a single-objective optimization problem. The integration of MaOEA-CSS algorithm with PINN effectively addresses the challenges of traditional optimization methods, demonstrating significant improvements in computational efficiency and Nov 23, 2021 · Hyperparameter optimization (HPO) is a necessary step to ensure the best possible performance of Machine Learning (ML) algorithms. Asphalt mixture proportion design is one of the most important steps in asphalt pavement design and application. , 2023), which are all belong to dynamic multi-objective Feb 27, 2024 · This paper proposes an automated deep learning (AutoDL) framework for dynamic prediction and multi-objective optimization (MOO) on the driving position of the tunnel boring machine (TBM) to enhance tunneling reliability and efficiency. This study proposes an MOO method based on machine learning (ML) and metaheuristic algorithms to optimize concrete mixture proportions. However, most of Pareto domination-based multi-objective optimization evolutionary May 11, 2019 · The machine learning algorithms exploit a given dataset in order to build an efficient predictive or descriptive model. Applications of various multi-objective Jan 4, 2023 · A Multi-objective Hyperparameter Optimization for Machine Learning Using Genetic Algorithms: A Green AI Centric Approach January 2023 DOI: 10. Jul 1, 2024 · The remainder of this paper is structured as follows: Section 2 introduces the preliminary background of expensive multi-objective optimization and explainable machine learning; Section 3 presents the details of the proposed algorithm; Section 4 is devoted to experimental studies. % Zn-2 wt. A commonly used approach is to convert a multi-objective problem into a single-objective problem using weight coefficients, and traditional optimization tools are employed to search for optimal parameters [18], [19], [20]. Nov 1, 2024 · The machine learning algorithms, multi-objective optimization technology, and the concept of main objective optimization are integrated. Aug 1, 2024 · Not only does this study address the existing gap in the literature regarding the multi-objective optimization and predictive modeling of Al-Mg alloys' tensile properties but also it exemplifies the integration of molecular dynamics simulations with machine learning techniques in materials science research. Aug 14, 2019 · Automated machine learning has gained a lot of attention recently. Therefore, we Aug 30, 2020 · The current single-objective optimization models are not applicable to multi-objective optimization (MOO). When using multi-objective optimization algorithms such as NSGA-II and MOPSO to May 20, 2022 · This work provides a new multi-objective optimization strategy that is expected to be used for the development of new steels with excellent comprehensive performance. We use various supervised machine learning algorithms for prediction and multi-objective evolutionary algorithms for squad formation in a generalized manner, which any management can adapt for any franchise-based or international tournament. By Chris and Melanie. General purpose machine learning software that simultaneously supports multiple objectives and constraints is scant, though the potential benefits are great. Oct 1, 2022 · Parameter identification using more than one type of monitoring data requires different objective functions. General purpose machine learning software that simultaneously supports multiple objectives and constraints is scant, though the potential benefits are great. Li B, Yang Y, Liu D, et al. "Multi-Objective Composite Panel Optimization Using Machine Learning Classifiers and Genetic Algorithms. Jan 30, 2023 · Different approaches are being used in the literature to reduce the number of objectives required for optimization. A review of multi-objective optimization Oct 1, 2024 · And the machine learning and genetic algorithms-based approach are introduced for the multi-objective optimization design of the airfoil fin PCHE with tip gap by taking the horizontal number, staggered number, vertical number, and gap number as optimization variables, and the volumetric heat transfer coefficient and Fanning friction factor as UL in equation2. In this work, we present a framework called Autotune that Sep 15, 2024 · The findings indicate that the channel width and coolant velocity play a pivotal role in enhancing BTMS efficiency. Machine learning-based design and optimization have been widely developed in marine engineering fields, achieving higher design efficiency with sufficient accuracy but avoiding complex numerical solution processes. The continuous development and improvement of urban land surface models enable rather accurate assessment of the environmental impact on urban development strategies, whereas physically-based simulations remain computationally costly and time consuming, as a consequence of Dec 24, 2022 · Hyperparameter optimization (HPO) is a necessary step to ensure the best possible performance of Machine Learning (ML) algorithms. But in many applications, we are not only interested in optimizing ML pipelines solely for predictive accuracy; additional May 15, 2023 · Multi-objective optimization problems (MOPs) involve a search for decision variable values that, without loss of generality, minimize a set of objective functions. Some emerging applications of MOO include, hardware-aware neural architecture search; multi-task learning as multi-objective optimization; Jan 1, 2025 · A multi-objective optimal design strategy for automotive seat skeleton based on machine learning regression model, multi-objective optimization algorithm and multi-criteria decision-making method. @article{li2024accelerating, title={Accelerating surrogate assisted evolutionary Nov 23, 2021 · multi-objective hyp erpar ameter optimization for machine learning algorithms, highlighting the approaches curren tly used in the literature, the typical perfor- mance measures used as objectives Jul 12, 2023 · By treating hyperparameter optimization of a machine learning algorithm as a multi-objective optimization problem, our framework allows for generating diverse models that trade off high performance and ease of interpretability in a single optimization run. Graphical abstract Download: Download high-res image (178KB) Nov 1, 2024 · By integrating advanced machine learning models with robust multi-objective optimization techniques, this framework facilitates the prediction of equivalent performance and the meticulous design of the meso‑structure of 3D woven thermal protection composites aimed at thermal protection. To this end, we use algorithms developed in the gradient-based multi-objective optimization literature. (2) Train the machine learning surrogate model to predict target property values. ,2021;Chen et al. Feb 28, 2024 · It has been recently remarked that focusing only on accuracy in searching for optimal Machine Learning models amplifies biases contained in the data, leading to unfair predictions and decision supports. Jan 1, 2016 · Abdolmaleki A Huang S Hasenclever L Neunert M Song H Zambelli M Martins M Heess N Hadsell R Riedmiller M Daumé H Singh A (2020) A distributional view on multi-objective policy optimization Proceedings of the 37th International Conference on Machine Learning 10. The goal of this issue is to identify the optimal location and distribution path for warehouse centers to optimize various objectives. utilized machine learning to predict the thermal conductivity of composites based on cross-sectional images [31] . However, existing studies either apply an inefficient evolutionary algorithm or linearly combine multiple objectives as a single-objective problem with the need to tune Sep 1, 2022 · To accelerate data-driven studies for various optimization applications in chemical engineering, a comprehensive machine learning aided multi-objective optimization and multi-criteria decision making (abbreviated as ML aided MOO-MCDM) framework is proposed in the present paper. Building and selecting the right machine learning models is often a multi-objective optimization problem. Swarm and Evolutionary Computation, 2024, 88: 101610. 3524940 (11-22) Online publication date: 13-Jul-2020 Aug 23, 2023 · Different conflicting optimization criteria arise naturally in various Deep Learning scenarios. Aug 4, 2023 · The best one, LMA was then used to build a proxy model with which multi-objective optimization (maximize FOE and minimize FWPT) was performed. Dec 5, 2021 · Most of the tasks in machine learning have a single objective function, for example, image classification, image captioning, movie rating, etc. While BLO is used in machine learning (Liu et al. " Proceedings of the ASME 2016 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. 4. 2021a. Classification models were established for certain impurities (Si, S, Fe, Zn, Ni, Cu and As). The MOO problem comprises two objective functions: to develop the satellite formation model with FCNNs; and to decrease droplet diameter and increase Oct 1, 2024 · The MOML framework formulates objective functions in meta-learning with multiple objectives as a Multi-Objective Bi-Level optimization Problem (MOBLP), where the lower-level subproblem is to learn the adaptation to a task in a similar way to vanilla meta-learning and the upper-level subproblem minimizes a vector-valued function corresponding to Mar 5, 2024 · In summary, the following research gaps can be drawn as a result of the aforementioned literature review: i) The optimization of the LOS system is a complex multi-objective problem, and even worse it has to be invoked thousands of times by the mechanism models established by the process simulation software to obtain the output parameters Oct 13, 2022 · Multi-objective optimization problems are often accompanied by complex black-box functions which not only increases the difficulty of solving, but also increases the solving time. A regression prediction model of material-thickness-each output index for seat parts with high fitting accuracy was constructed. In this work, we present a framework called Jun 15, 2022 · Hyperparameter optimization constitutes a large part of typical modern machine learning workflows. Sep 1, 2022 · A comprehensive strategy of machine learning (ML) and multi-objective optimization based on thermodynamic simulation data was proposed to accelerate the composition design of Ni-based superalloys. The machine learning life cycle is more than data + model = API. This work aims to propose a machine learning methodology, designated by FS-OPA, to tackle this problem. May 17, 2024 · Wax pattern fabrication in the investment casting of hollow turbine blades directly determines the dimension accuracy of subsequent casting, and therefore significantly affects the quality of final product. Keywords: Multi-Objective Optimization, Pareto Front, Stochastic Gradient Descent, Supervised Machine Learning. Recently, though, algorithms have appeared that Aug 17, 2022 · In order to solve the multiple unmanned aerial vehicles (UAVs) collaborative path planning problem under complex environments with multiple constraints, the multi-objective particle swarm optimization algorithm with multi-mode collaboration based on reinforcement learning (MCMOPSO-RL) is proposed in this paper to find optimal paths and handle constraints simultaneously. Representative algorithms in each category are discussed in depth. Of course, multiple objectives can in principle be aggregated into a single metric, which converts a multi-objective optimization (MOO) problem to a single-objective optimization problem. Jun 1, 2019 · In this paper, a multi-objective optimization (MOO) design method for DOD printing parameters through fully connected neural networks (FCNNs) is proposed in order to solve these challenges. The data expansion is achieved by utilizing the output generated sample in the adversarial learning process of GANs. Recently, though, algorithms have appeared that Apr 13, 2023 · Optimization and learning are two main paradigms of artificial intelligence in addressing complex real-world problems, with their respective focuses but frequently enhanced by each other. Apr 15, 2023 · A scheme of Bayesian optimization loop for multi-objective design task on TPMS design parameters. Dec 5, 2020 · In summary, a machine learning assisted strategy to iteratively recommend the next experiment to accomplish the multi-objective optimization were proposed. Therefore, it is instinctive to look at the engineering problems as multi-objective optimization problems. From the resulting Pareto front, they selected the best design using the technique for order preference by similarity to an ideal solution (TOPSIS). [35 ] Flexible multitask scheduling in cloud manufacturing: Parallel distributed genetic algorithm Dec 5, 2016 · Zeliff, K, Bennette, W, & Ferguson, S. The usual approach is a simple weighting of the criteria, which formally only works in the convex setting. Oct 1, 2023 · (5) In practical applications, various performance requirements of concrete and its economics need to be considered. First, the GPR-based ML Jan 1, 2024 · The present study is focused on multi-objective performance optimization & thermodynamic analysis from the perspectives of energy and exergy for Recompression, Partial Cooling & Main Compression Intercooling supercritical CO 2 (sCO 2) Brayton cycles for concentrated solar power (CSP) applications using machine learning algorithms. Nov 20, 2024 · Recent years have seen the rapid development of fairness-aware machine learning in mitigating unfairness or discrimination in decision-making in a wide range of applications. This arises from the fact that machine learning methods and corresponding preprocessing steps often only yield optimal performance when hyperparameters are properly tuned. It delves into the significance of leveraging V2G technology for energy revenue generation while navigating the balance between revenue generation and preserving the Li-ion batteries' health. This paper briefly explains the multi-objective optimization algorithms and their variants with pros and cons. Charlotte Dec 1, 2023 · Additionally, current algorithms for solving multi-objective optimization problems often convert them into single-objective optimization problems through weighted linear combinations, but this method is difficult to assign weight coefficients to each objective [26]. i. Selected collection of recent research on multi-objective approach to machine learning; Recent developments in evolutionary multi-objective optimization; Applies the concept of Pareto-optimality to machine learning May 28, 2023 · In this paper, we propose a new direction-oriented multi-objective problem by regularizing the common descent direction within a neighborhood of a direction that optimizes a linear combination of objectives such as the average loss in MTL. , in the setting of Multi-Task Learning), but also main and secondary tasks such as loss minimization versus sparsity. This paper integrates machine learning with Non-dominated Sorting Genetic Algorithm II (NSGA-II) to solve DMOPs and make real-time decisions. In this paper, we present a Dec 5, 2023 · Therefore, we applied interpretable machine learning methods in the multi-objective optimization design of SM-HTMs with high hole mobility and stability. e. 4 °C and coolant pressure drops under 3. In this work, we firstly generated quantitative structure-property relationships (QSPR) models to predict μ and η of organic SM-HTMs. Jan 1, 2024 · Shang et al. May 1, 2024 · Furthermore, the application of machine learning and genetic algorithms for multi-objective optimization underscores a departure from traditional mathematical modeling methods, promising heightened accuracy and efficiency in power cycle analysis. This method is applied to six challenging benchmark problems and demonstrates more than a 50% reduction in constraint evaluations, with varying savings across Apr 5, 2024 · Furthermore, multi-objective optimization algorithms were combined to achieve process optimization based on the machine learning framework established for the fusion process big data and mechanism. data points {x i,y 1 i,,y T i} i2[N] is given where T is Jul 5, 2022 · To solve this problem, we propose using a multi-objective optimization; multi-objective evolutionary algorithm based on decomposition (MOEA/D), and non-dominated sorting genetic algorithm (NSGA2 Sep 1, 2021 · Note that all machine learning problems can be converted to multi-objective optimization problems to improve the productivity of the algorithms. We design MORBiT, a novel single-loop gradient descent-ascent bilevel optimization algorithm, to solve the generic problem and present a novel analysis showing that MORBiT converges to the first-order stationary Apr 15, 2022 · Machine learning \Nwp: Numerical weather prediction \PV: Photovoltaic \RbFnn: radial basis function neural network \GWO: Grey wolf optimization \WSI: Whole sky imager \MOgoa: Multi objective grasshopper optimization algorithm \FE: Forecasting effectiveness \MOalo: Multi objective ant lion optimization \GAvmd: Variational model decomposition Apr 1, 2023 · Case d is another method to deal with multi-objective optimization problems, where the objectives are summed with weights to one single objective. Oct 1, 2024 · Multi-objective parameter optimization of large-scale offshore wind Turbine's tower based on data-driven model with deep learning and machine learning methods Author links open overlay panel Biyi Cheng a b , Yingxue Yao b , Xiaobin Qu c , Zhiming Zhou d , Jionghui Wei d , Ertang Liang b , Chengcheng Zhang b , Hanwen Kang a , Hongjun Wang a Mar 15, 2024 · The machine learning proxy (MLP) multi-objective optimization framework consists of three parts: (1) first principles modeling; (2) ML; (3) multi-objective optimization, as shown in Fig. The influence factors on compressive strength of recycled aggregate concrete are analyzed. This framework can have high fidelity and simultaneously predict multiple thermo-mechanical fields of the anisotropic plate-heat source system. [105] proposed a multi-algorithm gene adaptive multi-objective method (AMALGAM), as a multi-objective optimization solver, by incorporating the uncertainty of surrogate modeling into the optimization model through chance-constrained programming (CCP), to solve the groundwater remediation design problem of high-density non-aqueous Jun 1, 2008 · Over the last decade, efforts on solving machine learning problems using the Pareto-based multiobjective optimization methodology have gained increasing impetus, particularly due to the great Jan 1, 2025 · This study presents a novel machine learning-based multi-objective optimization framework for the prestress optimization of suspend dome structures. It is necessary to rely on the process of creating algorithms that extract useful information from data, automatically. Recently, multi-objective hyperparameter optimization has been proposed to search for Machine Learning models which offer equally Pareto-efficient trade-offs between accuracy and fairness May 30, 2024 · A multi-objective optimization algorithm based on machine learning is proposed. 2 , it is evident that the BPNN model is the best machine learning model to predict the proposed system performance. However, the existing machine learning models mainly focus on the optimization of single performance, while the optimization of multi-objective performance has not been sufficiently considered and applied. dtxzfvt rsrak caaa jsqu pgrdbqn qvdqpycg nzpm dahe xva xnlj