Metaheuristic Model Research Articles

Cost prediction for product development using hybrid deep learning model: a meta-heuristic model

Cost prediction for product development using hybrid deep learning model: a meta-heuristic model

Harmony search algorithm to enhance approach to permutation flow shop scheduling problem

The permutation flow-shop scheduling problem (PFSP) is one of the widely analysed and investigated problems within the general field of scheduling, as its major focus is on the allocation and sequencing of a set of jobs across a set of machines in order to minimize the makespan or satisfy other criteria. This paper further generalizes the problem to the distributed permutation flow-shop scheduling problem (DPFSP), namely in a manufacturing system with multiple factories, where every factory employs identical machines; with the objective of achieving the least makespan at the worst factory in terms of processing time. We resolve the issue through a Harmony Search Algorithm (HSA), a metaheuristic model developed from the musical harmonisation concept, together with constraint programming techniques, including interval variables and non-adjacent constraints. The problemsolving algorithm incorporates a lower bound estimation heuristic for efficiently directing the search in the right possible solution zone. Performance evaluation on both the small benchmark and the large benchmark data set showed the ability of the HSA to perform the different assignment in various problem scenarios that include the different number of jobs, machines and factories to support them. Comparisons with the best-known values established the performance of the HSA algorithm in identifying high quality solutions for the PFSP in less computation time.

Enhancing thermal management systems: a machine learning and metaheuristic approach for predicting thermophysical properties of nanofluids

Abstract In thermal engineering, predicting nanofluid thermophysical properties is essential for efficient cooling systems and improved heat transfer. Traditional methods often fall short in handling complex datasets. This study leverages machine learning (ML) and metaheuristic algorithms to predict key nanofluid properties, such as specific heat capacity (SHC), thermal conductivity (TC), and viscosity. By utilizing Artificial Neural Networks (ANN), Support Vector Regression (SVR), Gradient Boosting (GB), and Linear Regression (LR), alongside metaheuristic models like Differential Evolution (DE) and Particle Swarm Optimization (PSO), we achieve superior prediction accuracy compared to traditional models. The integration of these computational techniques with empirical data demonstrates their effectiveness in capturing the complex dynamics of thermofluids. Our results validate the precision of ML and metaheuristic models in predicting nanofluid properties and underscore their potential as robust tools for researchers and practitioners in thermal engineering. This work paves the way for future exploration of ML algorithms in thermal management, marking a significant advancement in optimizing nanofluid applications in industry and research.

Predictive Analysis of Students’ Learning Performance Using Machine Learning

Several researchers and educational institutions got attracted to the domain of predicting the performance of the students to classify the educational level of student performance. Though the educational sector uses several techniques for extracting useful information about them and the measures to be undertaken in the learning process, it is necessary to develop a student performance assessment model to assist the students as well as faculty members to improve their performance to the next level. This research work majorly concentrates to examine and identify useful rules and patterns to motivate the students for handling their education as well as career in a better way and also to improve the functioning of academics to supervise the policies for students’ benefit. Here, EDM is employed to identify the effective data which helps in applying the active learning in technical applications. Initially, a review of different DM, machine learning (ML), and meta-heuristic models to assess the performance of the students. the proposed models can be employed as an appropriate tool for mining educational data to achieve effective performance assessment of the students.

Estimation of shifted weibull distribution parameters using optimization algorithms for optimal investment decisions making

This study examines the estimation of parameters for the Shifted Weibull Distribution (SWD) using several robust metaheuristic algorithms, with a focus on enhancing precision and reliability in investment data analysis. Utilizing investment return data from the Malaysian property sector, we evaluate the performance of five metaheuristic models: Election Algorithm (EA), Artificial Dragonfly Algorithm (ADA), Genetic Algorithm (GA), Differential Evolution (DE), and Ant Colony Optimization (ACO). The evaluation criteria include Bayesian Information Criterion (BIC), Root Mean Squared Error (RMSE), and accuracy. Results reveal that EA consistently outperforms other models, achieving the lowest BIC value of 147.2 and an impressive accuracy rate of 94.90% at a sample size of 1,000. The Genetic Algorithm (GA) shows the lowest RMSE of 0.99, indicating strong predictive performance. Tukey's HSD test highlights significant accuracy variations among the models, with EA and GA notably outperforming ACO and DE. However, RMSE and BIC metrics do not demonstrate clear variations among the models. These findings underscore the superior performance of the EA model in the context of SWD parameter estimation, making it the preferred choice for modeling investment return data. Future research should explore additional factors influencing model performance and validate these models with diverse real-world datasets to further enhance their applicability in financial decision-making.

Assessing the impact of water scarcity on thermoelectric and hydroelectric potential and electricity price under climate change: Implications for future energy management

This study investigates the impact of water resource restrictions on thermoelectric and hydroelectric stations, analyzing its influence on demand and electricity prices. It uses General Circulation Models (GCMs) and Soil and Water Assessment Tools (SWAT) to forecast future temperature trends and estimate river flow patterns. The research provides insights into climate change's potential effects on water resources and electricity potential. The study shows a significant decrease in river flow, indicating potential issues with hydroelectric and thermoelectric systems. The study also uses an optimized Echo State Network (ESN) for accurate electricity demand, using the Modified Snow Leopard Optimization (MSLO) algorithm as a new metaheuristic model. The simulation results show a consistent increase in electricity demand scenarios, which is expected to lead to higher supply prices due to decreased production capacity. This could have significant economic effects. The investigation provides a comprehensive understanding of water resource management challenges in power production, aiding in informed decisions in the future energy industry.

Evaluation of renewable energy technologies in Colombia: comparative evaluation using TOPSIS and TOPSIS fuzzy metaheuristic models

The study investigates the weighting and hierarchization of renewable energy sources in specific geographical regions of Colombia using the TOPSIS and Diffuse TOPSIS metaheuristic models. 5 regions were analyzed, two of them with different scenarios: Caribbean 1 and 2, Pacific 1 and 2, Andean, Amazonian and Orinoquia. The results reveal significant differences in the evaluation of technologies between the two models. In the Caribbean 1, Diffuse TOPSIS gave a higher score to Solar Photovoltaics, while TOPSIS favored Hydropower. In the Caribbean 2, Solar Photovoltaic obtained similar scores in both models, but Wind was rated better by TOPSIS. In the Pacific Region 1, Biomass and large-scale Hydropower led according to both models. In the Pacific 2, Solar Photovoltaic was better evaluated by TOPSIS, while Wind was preferred by Diffuse TOPSIS. In the Andean Region, large-scale hydroelectric and Solar photovoltaic plants obtained high scores in both models. In the Amazon, Biomass led in both models, although with differences in scores. In Orinoquia, Solar Photovoltaic was rated higher by both models. The relevance of this research lies in its ability to address not only Colombia's immediate energy demands, but also in its ability to establish a solid and replicable methodological framework. The application of metaheuristic methods such as TOPSIS and TOPSIS with fuzzy logic is presented as a promising strategy to overcome the limitations of conventional approaches, considering the complexity and uncertainty inherent in the evaluation of renewable energy sources. By achieving a more precise weighting and hierarchization, this study will significantly contribute to strategic decision-making in the implementation of sustainable energy solutions in Colombia, serving as a valuable model for other countries with similar challenges.

Optimal adaptive coordination of overcurrent relays in power systems protection using a new hybrid metaheuristic algorithm

AbstractAdvent of distributed generation and progression towards an intelligent grid infrastructure within the domain of contemporary electrical power systems have created dynamic load profiles. Accompanying these developments, protective relays are faced with an evolving electrical load landscape and variable fault current conditions, resulting in disparate operational timings throughout the diurnal cycle. In light of these challenges, this paper delineates the formulation and simulation of a novel adaptive protection strategy for overcurrent relays, meticulously tailored to accommodate the fluctuations in electrical load. To construct a robust framework for this adaptive mechanism, a series of hypothetical fault current scenarios are meticulously crafted to activate the relays within the briefest time interval feasible. Further innovating within this sphere, this paper introduces a new hybrid algorithm, deftly amalgamating the strengths of three preeminent metaheuristic models: Improved Harmony Search, Particle Swarm Optimization, and Differential Evolution. Simulations and analyses substantiate the efficacy of the algorithm in optimizing the coordination among overcurrent relays aiming to uphold the overarching protective imperatives of the grid. For the IEEE 6‐bus system, the mean value of the objective function during 24 h in Monte Carlo is 292.6607 and very close to 272.0758 in the simulation of eight stochastic scenarios, which contributes to the validity of the approach in practical settings. Also, in the IEEE 30‐bus system, the results of the mean relay operation time set for the hours with the lowest and highest consumption load are 17.1297 and 14.8049 s, which reveals the increase in the operation speed of the relays.

Fine-tuning inflow prediction models: integrating optimization algorithms and TRMM data for enhanced accuracy.

This research explores machine learning algorithms for reservoir inflow prediction, including long short-term memory (LSTM), random forest (RF), and metaheuristic-optimized models. The impact of feature engineering techniques such as discrete wavelet transform (DWT) and XGBoost feature selection is investigated. LSTM shows promise, with LSTM-XGBoost exhibiting strong generalization from 179.81 m3/s RMSE (root mean square error) in training to 49.42 m3/s in testing. The RF-XGBoost and models incorporating DWT, like LSTM-DWT and RF-DWT, also perform well, underscoring the significance of feature engineering. Comparisons illustrate enhancements with DWT: LSTM and RF reduce training and testing RMSE substantially when using DWT. Metaheuristic models like MLP-ABC and LSSVR-PSO benefit from DWT as well, with the LSSVR-PSO-DWT model demonstrating excellent predictive accuracy, showing 133.97 m3/s RMSE in training and 47.08 m3/s RMSE in testing. This model synergistically combines LSSVR, PSO, and DWT, emerging as the top performers by effectively capturing intricate reservoir inflow patterns.

Implementation of Hybridized Meta-Heuristic Model for Feature Selection in Sentiment Analysis

Implementation of Hybridized Meta-Heuristic Model for Feature Selection in Sentiment Analysis

Prediction of drought hydrological and water scarcity based on optimal artificial intelligence by developing a metaheuristic optimization algorithm

This study presents a novel approach to predicting water stress in Yichang City, China, through an optimized Capsule Neural Network (CapsNN) model enhanced by the Improved Aquila Optimization (IAO) algorithm. The model, applied to monthly water stress data from 2000 to 2022, is gauged using the Streamflow Drought Index (SDI). When compared to traditional metaheuristic models, our CapsNN/IAO framework demonstrates superior accuracy in drought forecasting across various time scales with significant reductions in The Mean Absolute Error is 0.1021, the Root Mean Square Error is 0.1824, and good the Nash-Sutcliffe Efficiency is 0.75, the coefficient of determination R2 is 0.89, and the Willmott's Index is 0.93. Notably, the model predicts short-term water shortages with greater frequency at the SDI3 scale, while identifying the most severe drought conditions at the SDI6 scale. These insights are critical for enhancing water resource management.

Development of ANN-based metaheuristic models for the study of the durability characteristics of high-volume fly ash self-compacting concrete with silica fume

The construction of durable and sustainable infrastructure requires the use of industrial byproducts such as fly ash (FA) and silica fume (SF) to enhance strength and durability. This study introduces novel machine learning models to forecast the results of rapid chloride penetration test (RCPT) for self-compacting concrete (SCC) containing high volumes of FA and SF. This study assessed the effects of supplementary cementitious materials (SCMs) and elevated temperature curing on the RCPT outcomes for SCC. Various metaheuristic algorithms including teaching–learning-based optimization (TLBO), ant colony optimization (ACO), the imperialist competitive algorithm (ICA), and shuffled complex evolution (SCE)—optimize the learning rate, weights, and biases of artificial neural network (ANN) models. A dataset of 360 experimental RCPT data points with seven input parameters was used to train and test the hybrid models. The accuracy of these models was assessed using eight performance indices, and the results were further analyzed through rank analysis, scatter plots, and error matrices. The training and testing sets for the AI models, specifically ANN-TLBO, exhibit a strong correlation between the experimental and predicted RCPT values, with R2 values of 0.9962 for training and 0.9676 for testing, compared to the R2 values of the other proposed models. Consequently, the results of this study suggest that the ANN-TLBO model is the optimal hybrid ANN model for predicting RCPT values in SCC. Verified experimental results and external validation indicate that the ANN-TLBO model is an effective alternative for accurately predicting real-time RCPT in SCC.

An efficiency metaheuristic model to predicting customers churn in the business market with machine learning-based

Metaheuristics is an optimization method that improves and completes a task in a short period of time based on its objective function. The goal of metaheuristics is to search the search space for the best solution. Machine learning detects patterns in large amounts of data. Machine learning encourages enterprise automation in a variety of areas in order to improve predictive ability without requiring explicit programming to make decisions. The percentage of customers who leave the company or stop using the service is referred to as churn. The purpose of this research is to forecast customer churn in the market business. Particle swam optimization (PSO) was used in this study as a metaheuristic method to provide a strategy to guide the search process for new customers and obtain parameters for processing by support vector regression (SVR). SVR predicts the value of a continuous variable by determining the best decision line to find the best value. The number of transactions, the number of periods, and the conversion value are the parameters that are visible. Efficiency models are added to improve prediction results through two optimizations: prediction flexibility and risk minimization. The findings demonstrate the effectiveness of prediction in reducing customer churn.

Novel neural network-based metaheuristic models for the stability prediction of rectangular trapdoors in anisotropic and non-homogeneous clay

The problem of trapdoor stability is a crucial problem in geotechnical engineering. This study is the first to introduce novel neural network-based metaheuristic models for the stability prediction of 3D rectangular trapdoors in anisotropic and nonhomogeneous clays. However, no researcher has considered such trapdoor problems in the past. In this study, the dataset is obtained by using finite element limit analysis (FELA). The proposed hybrid machine learning models based on artificial neural networks (ANNs) and various types of optimization algorithms (OAs), namely, ant colony optimization (ACO), artificial lion optimization (ALO), the imperialist competition algorithm (ICA), and shuffled complex evolution (SCE), are also proposed in this paper by undergoing rigorous optimization to ensure accuracy and efficiency in capturing the intricate dynamics of the stability investigations from the models. The performance of the proposed ANN-based models is assessed using several performance metrics, regression plots, and rank analysis. The proposed ANN-SCE model outperforms the other proposed models in predicting trapdoor stability, where the ANN-SCE model achieved the highest rank, with a score of 58, followed by the ANN-ALO (47), ANN-ICA (33), and ANN-ACO (22) models. The proposed neural network-based metaheuristic models deliver precise and effective forecasts of trapdoor stability to make informed decisions concerning road design and mitigation tactics, ultimately improving the robustness of infrastructure facing geotechnical challenges.

Improving security performance of Internet of Medical Things using hybrid metaheuristic model

Improving security performance of Internet of Medical Things using hybrid metaheuristic model

Multi-Objective Prediction of Drilling EMS-45 with Finite Element, Backpropagation Neural Network, and Metaheuristic Model

Multi-Objective Prediction of Drilling EMS-45 with Finite Element, Backpropagation Neural Network, and Metaheuristic Model

Comparative Analysis of Shear Strength Prediction Models for Reinforced Concrete Slab–Column Connections

This research focuses on a comprehensive comparative analysis of shear strength prediction in slab–column connections, integrating machine learning, design codes, and finite element analysis (FEA). The existing empirical models lack the influencing parameters that decrease their prediction accuracy. In this paper, current design codes of American Concrete Institute 318-19 (ACI 318-19) and Eurocode 2 (EC2), as well as innovative approaches like the compressive force path method and machine learning models are employed to predict the punching shear strength using a comprehensive database of 610 samples. The database consists of seven key parameters including slab depth (ds), column dimension (cs), shear span ratio (av/d), yield strength of longitudinal steel (fy), longitudinal reinforcement ratio (ρl), ultimate load-carrying capacity (Vu), and concrete compressive strength (fc). Compared with the design codes and other machine learning models, the particle swarm optimization-based feedforward neural network (PSOFNN) performed the best predictions. PSOFNN predicted the punching shear of flat slab with maximum accuracy with R2 value of 99.37% and least MSE and MAE values of 0.0275% and 1.214%, respectively. The findings of the study are validated through FEA of slabs to confirm experimental results and machine learning predictions that showed excellent agreement with PSOFNN predictions. The research also provides insight into the application of metaheuristic models along with ANN, revealing that not all metaheuristic models can outperform ANN as usually perceived. The study also highlights superior predictive capabilities of EC2 over ACI 318-19 for punching shear values.

Predicting Confinement Effect of Carbon Fiber Reinforced Polymers on Strength of Concrete using Metaheuristics-based Artificial Neural Networks

This article deals with the study of predicting the confinement effect of carbon fiber reinforced polymers (CFRPs) on concrete cylinder strength using metaheuristics-based artificial neural networks. A detailed database of 708 CFRP confined concrete cylinders is developed from previously published research with information on eight parameters, including geometrical parameters like the diameter (d) and height (h) of a cylinder, unconfined compressive strength of concrete (f_co^'), thickness (nt), the elastic modulus of CFRP (Ef), unconfined concrete strain (?_co), confined concrete strain (?_cc) and the ultimate compressive strength of confined concrete (f_cc^'). Three metaheuristic models are implemented, including particle swarm optimization (PSO), grey wolf optimizer (GWO), and bat algorithm (BA). These algorithms are trained on the data using an objective function of mean square error, and their predicted results are validated against experimental studies and finite element analysis. The study shows that the hybrid PSO model predicted the strength of CFRP-confined concrete cylinders with a maximum accuracy of 99.13% and GWO predicted the results with an accuracy of 98.17%. The high accuracy of axial compressive strength predictions demonstrated that these prediction models are a reliable solution to the empirical methods. The prediction models are especially suitable for avoiding full-scale, time-consuming experimental tests that make the process quick and economical.

A Hybrid Bio-inspired Fuzzy Feature Selection Approach for Opinion Mining of Learner Comments

AbstractWith more and more teaching learning activities being shifted to online mode, the education system has seen a drastic paradigm shift in the recent times. Learner opinion has emerged as an important metric for gaining valuable insights about teaching–learning process, student satisfaction, course popularity, etc. Traditional methods for opinion mining of learner feedback are tedious and require manual intervention. The author, in this work has proposed a hybrid bio-inspired metaheuristic feature selection approach for opinion mining of learner comments regarding a course. Experimental work is conducted over a real-world education dataset comprising of 110 K learner comments (referred to as Educational Dataset now onwards) collected from Coursera and learner data from academic institution MSIT. Based on the experimental results over the collected dataset, the proposed model achieves an accuracy of 92.24%. Further, for comparative analysis, results of the proposed model are compared with the ENN models for different embeddings, viz., Word2Vec, tf-idf and domain-specific embedding for the SemEval-14 Task 4. The hybrid bio-inspired metaheuristic model outperforms the pre-existing models for the standard dataset too.

Self Adaptive Meta Heuristic Model for Floor Planning in Very Large Scale Integration

Self Adaptive Meta Heuristic Model for Floor Planning in Very Large Scale Integration