Machine Learning Optimization Research Articles

Ensemble of optimised machine learning algorithms for predicting surface soil moisture content at a global scale

Abstract. Accurate information on surface soil moisture (SSM) content at a global scale under different climatic conditions is important for hydrological and climatological applications. Machine-learning-based systematic integration of in situ hydrological measurements, complex environmental and climate data, and satellite observation facilitate the generation of reliable data products to monitor and analyse the exchange of water, energy, and carbon in the Earth system at a proper space–time resolution. This study investigates the estimation of daily SSM using 8 optimised machine learning (ML) algorithms and 10 ensemble models (constructed via model bootstrap aggregating techniques and five-fold cross-validation). The algorithmic implementations were trained and tested using International Soil Moisture Network (ISMN) data collected from 1722 stations distributed across the world. The result showed that the K-neighbours Regressor (KNR) had the lowest root-mean-square error (0.0379 cm3 cm−3) on the “test_random” set (for testing the performance of randomly split data during training), the Random Forest Regressor (RFR) had the lowest RMSE (0.0599 cm3 cm−3) on the “test_temporal” set (for testing the performance on the period that was not used in training), and AdaBoost (AB) had the lowest RMSE (0.0786 cm3 cm−3) on the “test_independent-stations” set (for testing the performance on the stations that were not used in training). Independent evaluation on novel stations across different climate zones was conducted. For the optimised ML algorithms, the median RMSE values were below 0.1 cm3 cm−3. GradientBoosting (GB), Multi-layer Perceptron Regressor (MLPR), Stochastic Gradient Descent Regressor (SGDR), and RFR achieved a median r score of 0.6 in 12, 11, 9, and 9 climate zones, respectively, out of 15 climate zones. The performance of ensemble models improved significantly, with the median RMSE value below 0.075 cm3 cm−3 for all climate zones. All voting regressors achieved r scores of above 0.6 in 13 climate zones; BSh (hot semi-arid climate) and BWh (hot desert climate) were the exceptions because of the sparse distribution of training stations. The metric evaluation showed that ensemble models can improve the performance of single ML algorithms and achieve more stable results. Based on the results computed for three different test sets, the ensemble model with KNR, RFR and Extreme Gradient Boosting (XB) performed the best. Overall, our investigation shows that ensemble machine learning algorithms have a greater capability with respect to predicting SSM compared with the optimised or base ML algorithms; this indicates their huge potential applicability in estimating water cycle budgets, managing irrigation, and predicting crop yields.

Recent advances in the interface structure prediction for heteromaterial systems

The atomic structures of solid-solid interfaces in materials are of fundamental importance for understanding the physical properties of interfacial materials, which is, however, difficult to determine both in experimental and theoretical approaches. New theoretical methodologies utilizing various global optimization algorithms and machine learning (ML) potentials have emerged in recent years, offering a promising approach to unraveling interfacial structures. In this review, we give a concise overview of state-of-the-art techniques employed in the studies of interfacial structures, e.g., ML-assisted phenomenological theory for the global search of interface structure (ML-interface). We also present a few applications of these methodologies.

Development of hybrid models based on deep learning and optimized machine learning algorithms for brain tumor Multi-Classification

Accurate classification of magnetic resonance imaging (MRI) images of brain tumors is crucial for early diagnosis and effective treatment in clinical studies. In these studies, many models supported by artificial intelligence (AI) have been proposed as assistant systems for experts. In particular, state-of-the-art deep learning (DL) models that have proven themselves in different fields have been effectively used in the classification of brain MRI images. However, the low accuracy of multiple classification of these images still leads researchers to conduct different studies in this field. Especially there is a need to develop models that achieve high accuracy on original images, and it is believed that this need can be met not only by DL models but also by classical machine learning (ML) algorithms. However, it is critical to choose the hyperparameters correctly for the hybrid use of ML algorithms with DL models. This study proposes a powerful new hybrid method to perform multiple classifications of brain tumors with high accuracy. This method also uses a novel convolutional neural network (CNN) model for feature extraction, and ML algorithms are used for feature classification. In addition, nine state-of-the-art CNN models are used for CNN performance comparison. The Bayesian optimization algorithm is used to obtain the optimal hyperparameter values of ML algorithms. The results obtained from the experimental studies show that the proposed hybrid model achieved 97.15% mean classification accuracy and 97% recall, precision, and F1-score values. Other hybrid models, including DarkNet19-SVM, DarkNet53-SVM, DenseNet201-SVM, EfficientNetB0-SVM, InceptionV3-SVM, NasNetMobile-SVM, ResNet50-SVM, ResNet101-SVM, and Xception-SVM, achieved mean classification accuracies of 95.01%, 95.58%, 96.87%, 97.01%, 95.3%, 95.01%, 96.3%, 95.87%, and 96.23%, respectively. Additionally, the proposed hybrid model exhibited remarkable time efficiency, accomplishing the classification process in a mere 67 min. Conversely, the model that exhibited the lowest time efficiency was the InceptionV3, with a processing time of 370 min. In terms of computational complexity, the EfficientNetB0 model is the most efficient. Despite the higher computational complexity of the proposed CNN model compared to some other models, it achieves the second-best classification accuracy. These results show that the proposed method performs better than previous studies on the same dataset. Especially in the classification problem, the optimized ML algorithms were superior to CNN classifiers. Finally, except for one, the proposed CNN model achieved better classification accuracies than the state-of-the-art CNN models.

Machine learning in optimization of nonwoven fabric bending rigidity in spunlace production line

Spunlace nonwoven fabrics have been extensively employed in different applications such as medical, hygienic, and industrial due to their drapeability, soft handle, low cost, and uniform appearance. To manufacture a spunlace nonwoven fabric with desirable properties, production parameters play an important role. Moreover, the relationship between the primary response and input parameter and the relationship between the secondary response and primary responses of spunlace nonwoven fabric were modeled via an artificial neural network (ANN). Furthermore, a multi-objective optimization via genetic algorithm (GA) to find a combination of production parameters to fabricate a sample with the highest bending rigidity and lowest basis weight was carried out. The results of optimization showed that the cost value of the best sample is 0.373. The optimized set of production factors were Young’s modulus of fiber of 0.4195 GPa, the line speed of 53.91 m/min, the average pressure of water jet 42.43 bar, and the feed rate of 219.67 kg/h, which resulted in bending rigidity of 1.43 mN {mathrm{cm}}^{2}/cm and basis weight of 37.5 gsm. In terms of advancing the textile industry, it is hoped that this work provides insight into engineering the final properties of spunlace nonwoven fabric via the implementation of machine learning.

Machine learning enhanced characterization of surface defects using ultrasonic Rayleigh waves

Rayleigh waves are successfully employed for the characterization of surface defects through the utilization of both time and frequency domain analysis. However, a significant challenge arises when attempting to cover a broad range of the defect depth to Rayleigh wavelength ratio with a single method. This paper presents an enhanced methodology that integrates optimized machine learning (ML) algorithms to expand the coverage of defect depth assessment. An experimentally validated numerical model is firstly established to simulate the interaction of Rayleigh waves with surface defects and utilized to generate a significant quantity of labeled Rayleigh wave signals. The features of received Rayleigh wave patterns are effectively extracted and serve as indicators of defect parameters. The ML framework encompasses the extraction and selection of optimal features, the construction of model architecture, and the tuning of hyperparameters. Three dimensionality optimization techniques—principal component analysis, correlation coefficient analysis, and expert knowledge integration—are compared. Additionally, six machine learning models (decision tree, support vector machine, k-nearest neighbors, random forest, gradient-boosting machine, and artificial neural network) are optimized using particle swarm optimization and subjected to comparison. The results reveal that: (1) principal component analysis yields the highest performance, suggesting the potential for feature dimensionality reduction without relying on expert knowledge; (2) among the models examined, the random forest model and artificial neural network with hyperparameter tuning demonstrate superior performance in predicting defect depth; and (3) the optimized machine learning methods consistently outperform empirical approaches in accurately predicting defect depths across a wide range. Furthermore, the proposed method shows promise for extension to determine additional parameters associated with surface defects, including their width and angle of inclination.

Evaluating the tensile strength of reinforced concrete using optimized machine learning techniques

Many environmental issues have arisen as a result of the widespread usage of concrete, which has led to a reduction of river sand. The excessive extraction of river sand has led to various negative consequences, such as ecosystem disruption, groundwater depletion, coastal erosion, and biodiversity loss. Manufactured sand (MS) from waste deposits may be used in lieu of river sand to address this problem. In this study, to facilitate the production of manufactured sand concrete (MSC), the potential of twelve machine learning (ML)-based models was examined. These models were trained and tested on 248 and 62 laboratory datasets containing nine features effective on the mechanical properties of MSC. MSC's splitting tensile strength (STS) was considered the model's target. The influences that the water-to-cement (W/C) ratio, the stone nano-powder content (SNPC), and the curing age (CA) have on the STS of MSC were also analyzed. Detailed analysis of the results revealed that all the well-tuned ML models have acceptable potential for estimating the STS of MSC; however, the extra tree regressor (ETR) model was in the highest agreement with the laboratory results. Both the ML and laboratory findings showed that MSC with 10% SNPC benefits the long-term STS of MSC. A graphical user interface for the ML-based models was also developed to further aid in the estimation of STS for engineering challenges.The proposed models can be a suitable alternative to time-consuming, expensive, and complex laboratory methods to facilitate the MSC production.

Secure localization techniques in wireless sensor networks against routing attacks based on hybrid machine learning models

The identification and localization of malicious nodes in wireless sensor networks (WSNs) is a hot area of research that can considerably extend the network's lifetime and make it more valuable. We use sensors whose positions are known, or anchor nodes, to make educated guesses about the positions of the unknown nodes. Several localization methods have been developed for precise estimation of the unknowable nodes. So, during the network setup process, finding suitable network parameters for node localization with the requisite accuracy in a short amount of time remains a tough task. Due to the fact that they manipulate network resources and routing protocols, routing assaults like wormhole attacks, Sybil attacks, blackhole attacks, and replay attacks are just a few examples of the types of attacks that have the potential to hinder the accuracy of localization and the quality of service provided by WSNs. This work proposes safe localization and detection of routing threats in wireless sensor networks by utilizing hybrid optimized machine learning approaches for optimal distance, position, and data communication. These approaches aim to find the optimal distance between sensors and the optimal position of sensors. Calculating the average localization accuracy and finding malicious nodes both need the use of the benchmark datasets CICIDS2017 and UNSW NB15. The machine learning algorithms that have been provided can be utilized with these datasets. The cluster labelling K-means clustering technique is applied to binary classification in the system that has been proposed. As a consequence, the system achieves an average detection accuracy of 100%. The findings of the simulation indicate that the proposed hybrid strategy is capable of achieving a higher level of localization accuracy of the unknown nodes, with an average localization error of 0.191.

Enhancing Apple Leaf Disease Identification through Optimized Machine Learning Algorithms

Enhancing Apple Leaf Disease Identification through Optimized Machine Learning Algorithms

Machine learning approach to evaluate TdP risk of drugs using cardiac electrophysiological model including inter-individual variability.

Introduction: Predicting ventricular arrhythmia Torsade de Pointes (TdP) caused by drug-induced cardiotoxicity is essential in drug development. Several studies used single biomarkers such as qNet and Repolarization Abnormality (RA) in a single cardiac cell model to evaluate TdP risk. However, a single biomarker may not encompass the full range of factors contributing to TdP risk, leading to divergent TdP risk prediction outcomes, mainly when evaluated using unseen data. We addressed this issue by utilizing multi-in silico features from a population of human ventricular cell models that could capture a representation of the underlying mechanisms contributing to TdP risk to provide a more reliable assessment of drug-induced cardiotoxicity. Method: We generated a virtual population of human ventricular cell models using a modified O'Hara-Rudy model, allowing inter-individual variation. and Hill coefficients from 67 drugs were used as input to simulate drug effects on cardiac cells. Fourteen features (, , , , , , , , , , , , qNet, qInward) could be generated from the simulation and used as input to several machine learning models, including k-nearest neighbor (KNN), Random Forest (RF), XGBoost, and Artificial Neural Networks (ANN). Optimization of the machine learning model was performed using a grid search to select the best parameter of the proposed model. We applied five-fold cross-validation while training the model with 42 drugs and evaluated the model's performance with test data from 25 drugs. Result: The proposed ANN model showed the highest performance in predicting the TdP risk of drugs by providing an accuracy of 0.923 (0.908-0.937), sensitivity of 0.926 (0.909-0.942), specificity of 0.921 (0.906-0.935), and AUC score of 0.964 (0.954-0.975). Discussion and conclusion: According to the performance results, combining the electrophysiological model including inter-individual variation and optimization of machine learning showed good generalization ability when evaluated using the unseen dataset and produced a reliable drug-induced TdP risk prediction system.

Prediction of milled surface characteristics of carbon fiber-reinforced polyetheretherketone using an optimized machine learning model by gazelle optimizer

Motivated by the nonlinear behavior of composite materials under different machining operations, this work aims at developing an optimized artificial intelligence model to predict milled surface characteristics of carbon fiber-reinforced polyetheretherketone (CFRPEEK). The milling operations were carried out under high-speed dry-cutting conditions. The developed model was employed to predict fractal dimension and surface roughness as functions of cutting speed, cutting width, feed per tooth, and orientation of fibers. The model is composed of an adaptive network-based fuzzy inference system (ANFIS) optimized by a gazelle optimizer (GO). The performance of the model was compared with five other optimized ANFIS models. ANFIS-GO showed outperformance compared with other models to predict milled surface characteristics. The root-mean-square deviation and determination coefficient of predicted data by ANFIS-GO compared with experimental ones are 0.002 and 0.911 for fractal dimension and 0.129 and 0.998 for surface roughness, respectively.

Predicting compressive strength of RCFST columns under different loading scenarios using machine learning optimization

Accurate bearing capacity assessment under load conditions is essential for the design of concrete-filled steel tube (CFST) columns. This paper presents an optimization-based machine learning method to estimate the ultimate compressive strength of rectangular concrete-filled steel tube (RCFST) columns. A hybrid model, GS-SVR, was developed based on support vector machine regression (SVR) optimized by the grid search (GS) algorithm. The model was built based on a sample of 1003 axially loaded and 401 eccentrically loaded test data sets. The predictive performance of the proposed model is compared with two commonly used machine learning models and two design codes. The results obtained for the axial loading dataset with R2 of 0.983, MAE of 177.062, RMSE of 240.963, and MAPE of 12.209%, and for the eccentric loading dataset with R2 of 0.984, MAE of 93.234, RMSE of 124.924, and MAPE of 10.032% show that GS-SVR is the best model for predicting the compressive strength of RCFST columns under axial and eccentric loadings. It is an effective alternative method that can be used to assist and guide the design of RCFST columns to save time and cost of some laboratory experiments. Additionally, the impact of input parameters on the output was investigated.

Evolution, Design, and Future Trajectories on Bipedal Wheel-legged Robot: A Comprehensive Review

This comprehensive review delves into the realm of bipedal wheel-legged robots, focusing on their design, control, and applications in assistive technology and disaster mitigation. Drawing insights from various fields such as robotics, computer science, and biomechanics, it offers a holistic understanding of these robots' stability, adaptability, and efficiency. The analysis encompasses optimization techniques, sensor integration, machine learning, and adaptive control methods, evaluating their impact on robot capabilities. Emphasizing the need for adaptable, terrain-aware control algorithms, the review explores the untapped potential of machine learning and soft robotics in enhancing performance across diverse operational scenarios. It highlights the advantages of hybrid models combining legged and wheeled mobility while stressing the importance of refining control frameworks, trajectory planning, and human-robot interactions. The concept of integrating soft and compliant mechanisms for improved adaptability and resilience is introduced. Identifying gaps in current research, the review suggests future directions for investigation in the fields of robotics and control engineering, addressing the evolution and terrain adaptability of bipedal wheel-legged robots, control, stability, and locomotion, as well as integrated sensory and perception systems, microcontrollers, cutting-edge technology, and future design and control directions.

A Stochastic Algorithm Based on Cable-stayed Bridges Model for Stochastic Optimization in Machine Learning

This paper takes the economic cost of road design as the objective function to study the optimization of road construction cost. It is well-know that stochastic optimization is widely regarded as one of the most important and difficult problems in optimization and machine learning. It is noted that various methods for stochastic optimization problems are sensitive to the learning rate (step-size), which is usually underestimated. Therefore, two new stochastic conjugate gradient algorithms are proposed in this paper. We adapt two modified line search techniques to set the stochastic optimization. One uses the modified Armijo line search technology, the other uses the modified weak Wolfe-Powell line search technology. The new search direction has the properties of sufficient descent and trust region, which makes the establishment of global convergence of the two algorithms very understandable and clear. Finally, numerical experiments show that the two new stochastic conjugate gradient methods are competitive compared with other classical methods.

An evaluation of nature-inspired optimization algorithms and machine learning classifiers for electricity fraud prediction

<span>This study evaluated the nature-inspired optimization algorithms to improve classification involving imbalanced class problems. The particle swarm optimization (PSO) and grey wolf optimizer (GWO) were used to adaptively balance the distribution and then four supervised machine learning classifiers artificial neural network (ANN), support vector machine (SVM), extreme gradient-boosted tree (XGBoost), and random forest (RF) were applied to maximize the classification performance for electricity fraud prediction. The imbalance data was balanced using random undersampling (RUS) and two nature-inspired algorithm techniques (PSO and GWO). Results showed that for the data balanced using random undersampling, ANN (Sentest = 50.31%), and XGBoost (Sentest = 66.32%) has better sensitivity than SVM (Sentest = 23.61%), while RF exhibits overfitting (Sentrain = 100%, Sentest = 71.25%). The classification performance of RF model hybrid with PSO improved tremendously (AccTest = 96.98%, Sentest = 94.87%, Spectest = 99.16%, Pretest = 99.14%, F1 Score = 96.96%, and area under the curve (AUC) = 0.989). This was closely followed by hybrid of XGBoost with PSO. Moreover, RF and XGBoost hybrid with GWO also showed an improvement and promising results. This study has showed that nature-inspired optimization algorithms (PSO and GWO) are effective methods in addressing imbalanced dataset.</span>

Hybrid Quantum-Enhanced Machine Learning for Supply Chain Optimization

Abstract: Modern supply chains face intricate challenges demanding sophisticated optimization strategies.This research presents a pioneering approach, combining quantum computing and machine learning, to revolutionize supply chain optimization. A hybrid framework harmonizes the power of quantum computing, including quantum annealers and gate-based quantum devices, with classical machine learning techniques. This synthesis aims to surmount the limitations of conventional optimization methods. Through rigorous experimentation on real-world supply chain scenarios, our approach demonstrates substantial efficiency gains and enhanced solution quality in comparison to classical methods. The implications are far- reaching, promising substantial cost reductions, streamlined resource allocation, and sustainability improvements for industries relying on supply chain management. Our study contributes to the burgeoning field of quantum machine learning and offers immediate value to supply chain professionals grappling with complexity. As supply chains evolve, our research sets the stage for innovative solutions in the quest for optimization.

Integrating machine learning and mathematical programming for efficient optimization of electric discharge machining technique

This study focuses on predictive modeling in machining, specifically material removal rate (MRR), tool wear rate (TWR), and surface roughness (Ra) prediction using regression analysis. The research employs electrical discharge machining (EDM) experiments to validate the proposed unified predictive model. The approach involves varying machining parameters systematically and collecting empirical data. The dataset is split for training and testing, and advanced regression techniques are used to formulate the model. Evaluation metrics such as R-squared and mean-squared error (MSE) are employed to assess the model’s accuracy. Notable findings include accurate predictions for MRR, TWR, and Ra. This approach demonstrates the potential for real-world application, aiding decision-making processes and enhancing machining efficiency. The research underscores the importance of predictive modeling in manufacturing optimization, offering insights into refining model architectures, data preprocessing techniques, and feature selection. The findings affirm the relevance and applicability of predictive modeling in manufacturing, emphasizing its potential to elevate precision and efficiency

Seamless Connections: Harnessing Machine Learning for MAC Optimization in Home Area Networks

The latest technologies and communication protocols are arousing a keen interest in automation, in which the field of home area networks is the most prominent area to work upon toward solving the issues and challenges faced by wireless home area networks regarding adaptability, reliability, cost, throughput, efficiency, and scalability. However, managing the immense number of communication devices on the premises of a smart home is a challenging task. Moreover, the Internet of Things (IoT) is an emerging global trend with billions of smart devices to be connected in the near future resulting in a huge amount of diversified data. The continuous expansion of the IoT network causes complications and vulnerabilities due to its dynamic nature and heterogeneous traffic. In the applications of IoT, the wireless sensor network (WSN) plays a major role, and to take benefits from WSN, medium access control (MAC) is the primary protocol to optimize, which helps in allocating resources to a huge number of devices in the smart home environment. Furthermore, artificial intelligence is highly demanded to enhance the efficiency of existing systems and IoT applications. Therefore, the purpose of this research paper is to achieve an optimized medium access control protocol through machine learning. The machine learning classifier, e.g., random forest (RF) and linear regression model, is adopted for predicting the features of home area networks. The proposed technique is helpful and could overcome the demerits of existing protocols in relation to scalability, throughput, access delay, and reliability and help in achieving an autonomous home area network (HAN).

Direct speech reconstruction from sensorimotor brain activity with optimized deep learning models.

Objective.Development of brain-computer interface (BCI) technology is key for enabling communication in individuals who have lost the faculty of speech due to severe motor paralysis. A BCI control strategy that is gaining attention employs speech decoding from neural data. Recent studies have shown that a combination of direct neural recordings and advanced computational models can provide promising results. Understanding which decoding strategies deliver best and directly applicable results is crucial for advancing the field.Approach.In this paper, we optimized and validated a decoding approach based on speech reconstruction directly from high-density electrocorticography recordings from sensorimotor cortex during a speech production task.Main results.We show that (1) dedicated machine learning optimization of reconstruction models is key for achieving the best reconstruction performance; (2) individual word decoding in reconstructed speech achieves 92%-100% accuracy (chance level is 8%); (3) direct reconstruction from sensorimotor brain activity produces intelligible speech.Significance.These results underline the need for model optimization in achieving best speech decoding results and highlight the potential that reconstruction-based speech decoding from sensorimotor cortex can offer for development of next-generation BCI technology for communication.

LQMPCS: Design of a Low-Complexity Q-Learning Model based on Proof-of-Context Consensus for Scalable Side Chains

Single-chained blockchains are being rapidly replaced by sidechains (or sharded chains), due to their high QoS (Quality of Service), and low complexity characteristics. Existing sidechaining models use context-specific machine-learning optimization techniques, which limits their scalability when applied to real-time use cases. Moreover, these models are also highly complex and require constant reconfigurations when applied to dynamic deployment scenarios. To overcome these issues, this text proposes design of a novel low-complexity Q-Learning Model based on Proof-of-Context (PoC) consensus for scalable sidechains. The proposed model initially describes a Q-Learning method for sidechain formation, which assists in maintaining high scalability even under large-scale traffic scenarios. This model is cascaded with a novel Proof-of-Context based consensus that is capable of representing input data into context-independent formats. These formats assist in providing high-speed consensus, which is uses intent of data, instead of the data samples. To estimate this intent, a set of context-based classification models are used, which assist in representing input data samples into distinctive categories. These models include feature representation via Long-Short-Term-Memory (LSTM), and classification via 1D Convolutional Neural Networks (CNNs), that can be used for heterogeneous application scenarios. Due to representation of input data samples into context-based categories, the proposed model is able to reduce mining delay by 8.3%, reduce energy needed for mining by 2.9%, while maintaining higher throughput, and lower mining jitters when compared with standard sidechaining techniques under similar use cases.

Use of modern algorithms for multi-parameter optimization and intelligent modelling of sustainable battery performance

The focus of this computational work is to predict and optimize the battery thermal performance indicators for its sustainable operation using different meta-heuristic optimization algorithms and machine learning models. The contribution of this work is two-fold, first, the heat removal ability from battery indicated by average Nusselt number (Nuavg) and hotspots (MaxT) to avoid battery thermal runaway are optimized as single objective optimization (SOO) and as multi-level objective optimization (MOO) problem. Second, intelligent algorithms: Gradient boosting (GB) algorithm and Gaussian process regressor (GPR) algorithm are used for modelling of Nuavg and MaxT. For SOO, Multi-verse optimization (MVO) and Grey wolf optimization (GWO) algorithms are used for individual battery performance indicators. Similarly, the enhanced version of MVO and GWO for MOO (MMVO and MGWO) algorithms is customized. Each algorithm is operated for five cycles and 100 iterations in each cycle of execution. In GB algorithm the effect of different loss functions and in GPR algorithm the effect of parameter alpha (α) is analyzed. SOO gives highest fitness of Nuavg and lowest hotspots occurrence from both the algorithms with same converged positions of operating parameters. MMVO and MGWO relatively provide lower Nuavg with MaxT in the same range of SOO. The MOO provides different set of particle positions compared to SOO. MGWO algorithm has outperformed in providing the best non-dominated solution. The GB and GPR algorithm are good enough for the forecasting of battery thermal parameters. GPR is even accurate, however the range of α is important during training and testing. The best Nuavg obtained from SOO using MVO algorithm is around 82.06 while MaxT is 0.34. The same from GWO algorithm is 82.05 and 0.33 respectively. MGWO algorithm in MOO provides Nuavg and MaxT around 75.57 and 0.34 while MMWO provides 66.76 and 0.33 respectively. GPR algorithm gives accuracy as close as 98 % for MaxT while it gives 94 % accuracy for Nuavg. On the other hand GB algorithm gives 99 % and 97.5 % accuracy for MaxT and Nuavg respectively.