Search

Feature selection is a real-world problem that finds a minimal feature subset from an original feature set. A good feature selection method, in addition to selecting the most relevant features with less redundancy, can also reduce computational costs and increase classification performance. One of the feature selection approaches is using meta-heuristic algorithms. This work provides a summary of some meta-heuristic feature selection methods proposed from 2018 to 2022 that were designed and implemented on a wide range of different data for solving feature selection problem. Evaluation criteria, fitness functions and classifiers used and the time complexity of each method are also depicted. The results of the study showed that some meta-heuristic algorithms alone cannot perfectly solve the feature selection problem on all types of datasets with an acceptable speed. In other words, depending on dataset, a special meta-heuristic algorithm should be used. The results of this study and the identified research gaps can be used by researchers in this field. [ABSTRACT FROM AUTHOR]

Epilepsy is a long-term neurological condition that disrupts brain function in people of all ages, epilepsy is a condition that is analysed through the brain signals via electroencephalogram (EEG) signal. To analyse epilepsy using spatial and temporal data, various machine-learning-based techniques are used. However, most of the techniques suffer from inaccuracy issues in dealing with the dynamic and raw EEG signal. In this research, an intelligent societal optimisation-driven classifier is introduced based on convolutional neural networks (CNN) for epileptic seizure prediction using EEG signals. To boost predictive accuracy, we extract frequency band features from the EEG signal utilising wavelet decomposition. The frequency band features form the feature vector, is provided smart societal optimisation- CNN such that the prediction performance is enhanced through the optimal tuning of the CNN with the smart societal optimisation. Smart societal optimisation is proposed by integrating the behaviour of the Lobos wolf and the Moggie. The smart societal optimisation-based CNN attains 87.673% accuracy, 84.949% sensitivity91.274%specificity for the K-Fold-10 for CHB-MIT scalp EEG database. [ABSTRACT FROM AUTHOR]

Chronic kidney disease (CKD) one of the most dangerous illnesses. Early detection is vital for improving survival rates and underscoring the need for an intelligent classifier to differentiate between normal and abnormal kidney ultrasound images. Features extracted from an image have a significant impact on classification accuracy. In this study, we present a Binary Coati optimization algorithm (BCOA) for feature selection in CKD, which focuses on reducing the high dimensionality features extracted from ultrasound images, including GLCM, GLRLM, GLSZM, GLDM, NGTDM, and first order, by employing BCOA-S shaped and BCOA-V shaped transfer functions that convert BCOA from a continuous search space to a binary form, which helps in the selection of optimal features to improve the classification performance while reducing the feature dimensionality. The reduced feature was evaluated using six machine-learning classifiers: Random Forest, Support Vector Machine, Decision tree, K-nearest Neighbor, XG-boost, and Naïve Bayes. The efficiency of the proposed framework was assessed based on accuracy, precision, recall, specificity, f1 score and AUC curve. BCOA-V outperformed in terms of accuracy, precision, recall, specificity, F1 score and AUC curve by 99%,100%,97%,100%, 98%, and 98%, respectively. This makes it a superior choice for CKD diagnosis and is a valuable tool for feature selection in medical diagnosis. [ABSTRACT FROM AUTHOR]

Integrating long-term observational data analysis with numerical simulations of dam operations provides an effective approach to dam safety evaluation. However, analytical results are often subject to errors due to challenges in accurately surveying and modeling the foundation, as well as temporal changes in foundation properties. This paper proposes a concrete dam displacement separation model that distinguishes between deformation caused by foundation restraint and that induced by external loads. By combining this model with intelligent optimization techniques and long-term observational data, we can identify the actual mechanical parameters of the dam and conduct structural health assessments. The proposed model accommodates multiple degrees of freedom and is applicable to both two- and three-dimensional dam modeling. Consequently, it is well-suited for parameter identification and health diagnosis of concrete gravity and arch dams with extensive observational data. The efficacy of this diagnostic model has been validated through computational case studies and practical engineering applications. [ABSTRACT FROM AUTHOR]

A multi-fidelity optimisation strategy has been developed in the present work, and its performance is illustrated through a series of test cases. The strategy is based on hybrid methods such that two genetic optimisation algorithms are employed, each coupled to a different fidelity level with transfer of information between them. The aim is that the low fidelity model, being less accurate but with a lower computational cost, performs a comprehensive search along the design space guiding the high fidelity model to the optimum region. This strategy has been shown to reduce the computational time of an optimisation through analytical test cases as well as numerical cases. The analytical cases have been used to tune the parameters that define the multi-fidelity strategy, while the numerical cases are employed to apply the method to engineering problems, focusing on the aerodynamic performance of an airfoil. The speed-up shows a certain dependency to the models relation, both regarding their similarity level as well as the relative computational cost. For cases exhibiting a significant dissimilarity between models, wherein the low fidelity model is notably inaccurate, the attained speed-up diminishes, and numerous instances demonstrate an absence of speed-up. However, for most cases, even with poor model similarity the optimisations are accelerated by an order of 2, while values up to 3–5 were found for higher similarity levels. Hence, the developed strategy shows a relevant decrease of computational cost of an optimisation procedure although its performance is affected by the models relative accuracy. [ABSTRACT FROM AUTHOR]

Epilepsy is a long-term neurological condition that disrupts brain function in people of all ages, epilepsy is a condition that is analysed through the brain signals via electroencephalogram (EEG) signal. To analyse epilepsy using spatial and temporal data, various machine-learning-based techniques are used. However, most of the techniques suffer from inaccuracy issues in dealing with the dynamic and raw EEG signal. In this research, an intelligent societal optimisation-driven classifier is introduced based on convolutional neural networks (CNN) for epileptic seizure prediction using EEG signals. To boost predictive accuracy, we extract frequency band features from the EEG signal utilising wavelet decomposition. The frequency band features form the feature vector, is provided smart societal optimisation- CNN such that the prediction performance is enhanced through the optimal tuning of the CNN with the smart societal optimisation. Smart societal optimisation is proposed by integrating the behaviour of the Lobos wolf and the Moggie. The smart societal optimisation-based CNN attains 87.673% accuracy, 84.949% sensitivity91.274%specificity for the K-Fold-10 for CHB-MIT scalp EEG database.

The purpose of this study is to develop an advanced neural network algorithm as a new optimisation for the optimal design of truss structures. The central concept of the algorithm is based on biological nerve structures and artificial neural networks. The performance of the proposed method is explored in engineering design problems. Two efficient methods for improving the standard neural network algorithm are considered here. The first is an enhanced initialisation mechanism based on opposite-based learning. The second relies on using a few tunable parameters to provide proper exploration and exploitation abilities for the algorithm, enabling better solutions to be found while the required structural analyses are reduced. The new algorithm's performance is investigated by using five well-known restricted benchmarks to assess its efficiency in relation to the latest optimisation techniques. The outcome of the examples demonstrates that the upgraded version of the algorithm has increased efficacy and robustness in comparison with the original version of the algorithm and some other methods. [ABSTRACT FROM AUTHOR]

Introduction: Sleep apnoea syndrome (SAS) is a serious sleep disorder and early detection of sleep apnoea not only reduces treatment costs but also saves lives. Conventional polysomnography (PSG) is widely regarded as the gold standard diagnostic tool for sleep apnoea. However, this method is expensive, timeconsuming and inherently disruptive to sleep. Recent studies have pointed out that ECG analysis is a simple and effective diagnostic method for sleep apnea, which can effectively provide physicians with an aid to diagnosis and reduce patients' suffering. Methods: To this end, in this paper proposes a LightGBM hybrid model based on ECG signals for efficient detection of sleep apnea. Firstly, the improved Isolated Forest algorithm is introduced to remove abnormal data and solve the data sample imbalance problem. Secondly, the parameters of LightGBM algorithm are optimised by the improved TPE (Tree-structured Parzen Estimator) algorithm to determine the best parameter configuration of the model. Finally, the fusion model TPE_OptGBM is used to detect sleep apnoea. In the experimental phase, we validated the model based on the sleep apnoea ECG database provided by Phillips-University of Marburg, Germany. Results: The experimental results show that the model proposed in this paper achieves an accuracy of 95.08%, a precision of 94.80%, a recall of 97.51%, and an F1 value of 96.14%. Discussion: All of these evaluation indicators are better than the current mainstream models, which is expected to assist the doctor's diagnostic process and provide a better medical experience for patients. [ABSTRACT FROM AUTHOR]

Real-time hardware-in-the-loop-(HIL) simulation integration is now a fundamental component of the power electronics control design cycle. This integration is required to test the efficacy of controller implementations. Even though hardware-in-the-loop-(HIL) tools use FPGA devices with computing power that is rapidly evolving, developers constantly need to balance the ease of deploying models with acceptable accuracy. This study introduces a methodology for implementing a full-bridge inverter and buck converter utilising the associate-discrete-circuit-(ADC) model, which is optimised for real-time simulator applications. Additionally, this work introduces a new approach for choosing ADC parameter values by using the artificial-bee-colony-(ABC) algorithm, the firefly algorithm (FFA), and the genetic algorithm (GA). The implementation of the ADC-based model enables the development of a consistent architecture in simulation, regardless of the states of the switches. The simulation results demonstrate the efficacy of the proposed methodology in selecting optimal parameters for an ADC-switch-based full-bridge inverter and buck converter. These results indicate a reduction in overshoot and settling time observed in both the output voltage and current of the chosen topologies. [ABSTRACT FROM AUTHOR]

Abstract This research work aims to study photovoltaic systems that generate energy for self-consumption using different traditional technologies, such as silicon, and emerging technologies, like nanowires and quantum. The photovoltaic system without batteries was implemented in a residential property in three different places, in Portugal. According to Portuguese Law, the sale of surplus energy to the grid is possible but the respective value for its selling is not defined. To evaluate the project viability, two different analyses are considered: with and without the sale of surplus energy to the grid. Results show that if there is no sale of excess energy produced to the grid, the project is not economically viable considering the four different technologies. Otherwise, using traditional technologies, the project is economically viable, presenting a payback time lower than 10 years. This shows that the introduction of nanostructures in solar cells is not yet a good solution in the application of solar systems namely with the current law. Furthermore, independently of the used technology, the current Portuguese law seems to difficult the investment return, which should not be the way to encourage the use of renewable sources.

The increasing penetration of photovoltaic technology in the electricity market requires the development of a methodology that facilitates the optimisation of photovoltaic plants with single-axis trackers. This paper presents an optimisation methodology that takes into account the most important design variables of single-axis photovoltaic plants, including irregular land shape, size and configuration of the mounting system, row spacing, and operating periods (for backtracking mode, limited range of motion, and normal tracking mode). Equations for the determination of the optimal row spacing and operating periods have been developed and is presented in detail. A packing algorithm that takes into account the irregular land shape and the possible configurations of the mounting systems is also presented. The objective function is the total area of the photovoltaic field and the optimisation is performed by a packing algorithm. As the economic aspect of energy generation also plays a key role in decision-making, the levelised cost of energy has been used to assess the economic viability of the optimal layout of the mounting systems. The results show that the proposed methodology and packing algorithm are able to optimise the photovoltaic plant with single-axis solar tracking and provide reliable results after a reasonable computation time. The methodology was demonstrated in detail for a Spanish photovoltaic plant (Granjera photovoltaic power plant), including the optimal layout of the mounting systems and the cost analysis for this layout. The optimal layout of the mounting systems could increase the amount of energy captured by 91.18% in relation to the current of Granjera photovoltaic power plant. The mounting system configuration used in the optimal layout is the one with the best levelised cost of energy efficiency, 1.09. The presented optimisation methodology can be utilised to facilitate the optimal design of commercial photovoltaic plants with single-axis trackers. Therefore, questions such as: what is the optimal distribution of mounting systems?, how much energy will this distribution produce?, and at what cost will it produce it?, can be answered by using the proposed methodology. • The optimal layout of single-axis solar trackers in large-scale PV plants. • A detailed analysis of the design of the inter-row spacing and operating periods. • The optimal layout of the mounting systems increases the amount of energy by 91%. • Also has the best levelised cost of energy efficiency, 1.09. [ABSTRACT FROM AUTHOR]

This work introduces a novel privacy preservation scheme. In large databases, the data sanitisation process preserves the stored sensitive data safely from unauthorised access and users by hiding it. Moreover, the statistical features are extracted. Further, the normalised data and features are processed under the data sanitisation process. For the sanitisation process, the optimal key is produced by utilising the Deep Belief Network (DBN) with Chaotic Map-adopted Poor and Rich Optimisation (CMPRO) model. It is the modified version of the classical PRO algorithm. As a novelty, chaotic map and cycle crossover operation is included in the CMPRO algorithm. Privacy, modification degree, data preservation ratio, and hiding failure are considered as the objectives for the key generation process. Then, the data restoration process restores or recovers the sanitised data, and it is the reverse process. Then, the outcomes of the adopted scheme are analysed over the traditional systems based on certain measures. Especially, the sanitisation effectiveness of the proposed approach for data 1 in test case 2 and it is 54.56%, 51.82%, 47.94%, 49.59%, 18.17%, 43.32%, 47.03%, 47.03%, 55.79%, 21.84%, 47.33%, and 32.13% better than the existing CNN+CMPRO, RNN+CMPRO, LSTM+CMPRO, BiLSTM+CMPRO, DBN+PRO, DBN+SSA, DBN+SMO, DBN+LA, DBN+SSO, DBN+J-SSO, DBN+BS-WOA, and DBN+R-GDA schemes. [ABSTRACT FROM AUTHOR]

Abstract The use of low earth orbit (LEO) satellites to enhance the performance of global navigation satellite system navigation and positioning services has become a popular research topic. In this study, NSGA‐III optimisation algorithm was used to design two hybrid configurations of 177 and 186 LEO constellations for enhancing the BeiDou Satellite Navigation System (BDS). Under the enhanced effect of optimisation constellation, the global average geometric dilution of precision (GDOP) of BDS was reduced to 0.8 ± 0.1, and the maximum GDOP was reduced from 2.4 to less than 1.1 (54.2% reduction). In order to verify the contribution of the two constellations to the convergence time and positioning accuracy of BDS precise point positioning (PPP), a LEO enhanced BDS PPP simulation experiment was carried out using International GNSS Service data from five stations. The results show that after 10 min of static positioning, both LEO constellations improved the positioning accuracy of BDS from the decimetre level to less than 5 cm. The maximum improvement for 177 and 186 LEO was 95.0% and 96.9%, respectively. Additionally, the convergence time for 177 and 186 LEO reduced to less than 3.5 and 3 min, and the maximum improvement was 93.5% and 95.2%, respectively. Overall, both constellations can improve the positioning accuracy and convergence time of BDS PPP.

This research work aims to study photovoltaic systems that generate energy for self-consumption using different traditional technologies, such as silicon, and emerging technologies, like nanowires and quantum. The photovoltaic system without batteries was implemented in a residential property in three different places, in Portugal. According to Portuguese Law, the sale of surplus energy to the grid is possible but the respective value for its selling is not defined. To evaluate the project viability, two different analyses are considered: with and without the sale of surplus energy to the grid. Results show that if there is no sale of excess energy produced to the grid, the project is not economically viable considering the four different technologies. Otherwise, using traditional technologies, the project is economically viable, presenting a payback time lower than 10 years. This shows that the introduction of nanostructures in solar cells is not yet a good solution in the application of solar systems namely with the current law. Furthermore, independently of the used technology, the current Portuguese law seems to difficult the investment return, which should not be the way to encourage the use of renewable sources. [ABSTRACT FROM AUTHOR]

Satellite remote sensing provides a unique opportunity for calibrating land surface models due to their direct measurements of various hydrological variables as well as extensive spatial and temporal coverage. This study aims to apply terrestrial water storage (TWS) estimated from the gravity recovery and climate experiment (GRACE) mission as well as soil moisture products from advanced microwave scanning radiometer–earth observing system (AMSR-E) to calibrate a land surface model using multi-objective evolutionary algorithms. For this purpose, the non-dominated sorting genetic algorithm (NSGA) is used to improve the model's parameters. The calibration is carried out for the period of two years 2003 and 2010 (calibration period) in Australia, and the impact is further monitored over 2011 (forecasting period). A new combined objective function based on the observations' uncertainty is developed to efficiently improve the model parameters for a consistent and reliable forecasting skill. According to the evaluation of the results against independent measurements, it is found that the calibrated model parameters lead to better model simulations both in the calibration and forecasting period. [ABSTRACT FROM AUTHOR]

In power electronics, the alleviation of the converter losses is the major target to accomplish higher efficiency and lower thermal stress that can pave the way to lifetime enhancement of devices. Hence, this paper intends to implement a novel variable switching frequency system for switching loss minimisation in a 3-phase Voltage Source Inverter (VSI). Here, the count of commutations is minimised by varying the switching frequency over the fundamental period. Here, the switching loss is reduced by optimising the modulation index m and the reference angle θ of VSI with a novel hybrid optimisation model. The proposed novel hybrid optimisation model is constructed by hybridising the concept of Group search Algorithm (GSO) and Rider Optimisation Algorithm (ROA) and hence referred to as Bypass updated Group search Algorithm (BU-GSO). Finally, the performance of BU-GSO is evaluated over the traditional models in terms of convergence analysis, Total Harmonic Distortion (THD) as well. Moreover, the evaluation is accomplished with inductive load variation and restive load variation, respectively. [ABSTRACT FROM AUTHOR]

Real-time hardware-in-the-loop-(HIL) simulation integration is now a fundamental component of the power electronics control design cycle. This integration is required to test the efficacy of controller implementations. Even though hardware-in-the-loop-(HIL) tools use FPGA devices with computing power that is rapidly evolving, developers constantly need to balance the ease of deploying models with acceptable accuracy. This study introduces a methodology for implementing a full-bridge inverter and buck converter utilising the associate-discrete-circuit-(ADC) model, which is optimised for real-time simulator applications. Additionally, this work introduces a new approach for choosing ADC parameter values by using the artificial-bee-colony-(ABC) algorithm, the firefly algorithm (FFA), and the genetic algorithm (GA). The implementation of the ADC-based model enables the development of a consistent architecture in simulation, regardless of the states of the switches. The simulation results demonstrate the efficacy of the proposed methodology in selecting optimal parameters for an ADC-switch-based full-bridge inverter and buck converter. These results indicate a reduction in overshoot and settling time observed in both the output voltage and current of the chosen topologies.

Online updating is an important statistical method for the analysis of big data arriving in streams due to its ability to break the storage barrier and the computational barrier under certain circumstances. The quantile regression, as a widely used regression model in many fields, faces challenges in model fitting and variable selection with big data arriving in streams. Chen et al. (2019, Annals of Statistics) has proposed a quantile regression method for streaming data, but a strong additional condition is required. In this paper, renewable optimized objective functions for regression parameter estimation and variable selection in a quantile regression are proposed. The proposed methods are illustrated using current data and the summary statistics of historical data. Theoretically, the proposed statistics are shown to have the same asymptotic distributions as the standard version computed on an entire data stream with the data batches pooled into one data set, without additional condition. Both simulations and data analysis are conducted to illustrate the finite sample performance of the proposed methods. [ABSTRACT FROM AUTHOR]

It is crucial for flood discharge structure vibration safety evaluations to filter low-frequency noise, separate dense-frequency components and obtain high-frequency component accurately from vibration signals. Variational mode decomposition, a novel signal adaptive decomposition method, effectively processes flood discharge structures. However, the mode number and quadratic penalty item uncertainty in variational mode decomposition directly affects the vibration signal decomposition. Therefore, an improved variational mode decomposition method for vibration signal processing is proposed in this study. The proposed method adaptively determines the mode number based on singular entropy and frequency stability to completely separate the structural vibration components (including dense-frequency components and high-frequency components) and noise components from the vibration signal. Next, an objective quadratic penalty item function based on sample entropy and mutual information is proposed to quantify the mode mixing between the structural vibration components. Finally, a particle swarm optimisation algorithm based on beetle antenna search is proposed to optimise the quadratic penalty item, which overcomes the shortcomings of traditional algorithms and suppresses the mode mixing between the structural vibration components. The validity and feasibility of the proposed method was verified by the simulation signal and was applied to a sluice prototype project. The results showed that the method effectively filtered noise, greatly improved the vibration response signal-to-noise ratio and obtained the structural vibration component time history signal, which provides a foundation for flood discharge structure vibration safety evaluation and health monitoring. [ABSTRACT FROM AUTHOR]

The use of low earth orbit (LEO) satellites to enhance the performance of global navigation satellite system navigation and positioning services has become a popular research topic. In this study, NSGA‐III optimisation algorithm was used to design two hybrid configurations of 177 and 186 LEO constellations for enhancing the BeiDou Satellite Navigation System (BDS). Under the enhanced effect of optimisation constellation, the global average geometric dilution of precision (GDOP) of BDS was reduced to 0.8 ± 0.1, and the maximum GDOP was reduced from 2.4 to less than 1.1 (54.2% reduction). In order to verify the contribution of the two constellations to the convergence time and positioning accuracy of BDS precise point positioning (PPP), a LEO enhanced BDS PPP simulation experiment was carried out using International GNSS Service data from five stations. The results show that after 10 min of static positioning, both LEO constellations improved the positioning accuracy of BDS from the decimetre level to less than 5 cm. The maximum improvement for 177 and 186 LEO was 95.0% and 96.9%, respectively. Additionally, the convergence time for 177 and 186 LEO reduced to less than 3.5 and 3 min, and the maximum improvement was 93.5% and 95.2%, respectively. Overall, both constellations can improve the positioning accuracy and convergence time of BDS PPP. [ABSTRACT FROM AUTHOR]

Quality data in manufacture process has the features of mixed type, uneven distribution, dimension curse and data coupling. To apply the massive manufacturing quality data effectively to the quality analysis of the manufacture enterprise, the data pre-processing algorithm based on equivalence relation is employed to select the characteristic of hybrid data and preprocess data. KML-SVM (Optimised kernel-based hybrid manifold learning and support vector machines algorithm) is proposed. KML is adopted to solve the problems of manufacturing process quality data dimension curse. SVM is adopted to classify and predict low-dimensional embedded data, as well as to optimise support vector machine kernel function so that the classification accuracy can be maximised. The actual manufacturing process data of AVIC Shenyang Liming Aero-Engine Group Corporation Ltd is demonstrated to simulate and verify the proposed algorithm. [ABSTRACT FROM PUBLISHER]

Recently, metaheuristics (MHs) have become increasingly popular in real-world engineering applications such as in the design of airframes structures and aeroelastic designs owing to its simple, flexible, and efficient nature. In this study, a novel hybrid algorithm is termed as Ensemble of Genetic algorithm, Grey wolf optimizer, Water cycle algorithm and Population base increment learningusing Weighted sum (E-GGWP-W), based on the successive archive methodology of the weighted population has been proposed to solve the aircraft composite wing design problem. Four distinguished algorithms viz. a Genetic algorithm (GA), a Grey wolf optimizer (GWO), a Water cycle algorithm (WCA), and Population base increment learning (PBIL) were used as ingredients of the proposed algorithm. The considered wing design problem is posed for overall weight minimization subject to several aeroelastic and structural constraints along with multiple discrete design variables to ascertain its viability for real-world applications. The algorithms are validated through the standard test functions of the CEC-RW-2020 test suite and composite Goland wing aeroelastic optimization. To check the performance, the proposed algorithm is contrasted with eight well established and newly developed MHs. Finally, a statistical analysis is done by performing Friedman’s rank test and allocating respective ranks to the algorithms. Based on the outcome, ithas been observed that the suggested algorithm outperforms the others.

While the concept of swarm intelligence was introduced in 1980s, the first swarm optimisation algorithm was introduced a decade later, in 1992. In this paper, nineteen representative original swarm optimisation algorithms are analysed to extract their common features and design a taxonomy for swarm optimisation. We use twenty-nine benchmark problems to compare the performance of these nineteen algorithms in the form they were first introduced in the literature against five state-of-the-art swarm algorithms. This comparison reveals the advancements made in this field over three decades. It reveals that, while the state-of-the-art swarm optimisation algorithms are indeed competitive in terms of the quality of solutions they find, their complexities have evolved to be more computationally demanding when compared to the nineteen original algorithms of swarm optimisation. The investigation suggests that there is an urge to continue to design swarm optimisation algorithms that are simpler, while maintaining their current competitive performance. [ABSTRACT FROM AUTHOR]

In a fuel cell electric vehicle (FCEV) powered by a metal hydride tank, the performance of the tank is an indicator of the overall health status, which is used to predict its behaviour and make appropriate energy management decisions. The aim of this paper is to investigate how to evaluate the effects of charge/discharge cycles on the performance of a commercial automotive metal hydride hydrogen storage system applied to a real FCEV. For this purpose, a mathematical model is proposed based on uncertain physical parameters that are identified using the stochastic particle swarm optimisation (PSO) algorithm combined with experimental measurements. The variation of these parameters allows an assessment of the degradation level of the tank's performance on both the quantitative and qualitative aspects. Simulated results derived from the proposed model and experimental measurements were in good agreement, with a maximum relative error of less than 2 % . The validated model was used to establish the correlations between the observed degradations in a hydride tank recovered from a real FCEV. The results obtained show that it is possible to predict tank degradations by developing laws of variation of these parameters as a function of the real conditions of the use of the FCEV (number of charging/discharging cycles, pressures, mass flow rates, temperatures). [ABSTRACT FROM AUTHOR]

This paper presents the application of a reinforcement learning (RL) algorithm, concretely Q-Learning, as the core of a decision support system (DSS) for a steelmaking subprocess, the Composition Adjustment by Sealed Argon-bubbling with Oxygen Blowing (CAS-OB) from the SSAB Raahe steel plant. Since many CAS-OB actions are selected based on operator experience, this research aims to develop a DSS to assist the operator in taking the proper decisions during the process, especially less experienced operators. The DSS is intended to supports the operators in real-time during the process to facilitate their work and optimise the process, improving material and energy efficiency, thus increasing the operation's sustainability. The objective is that the algorithm learns the process based only on raw data from the CAS-OB historical database, and on rewards set according to the objectives. Finally, the DSS was tested and validated by a developer engineer from the CAS-OB steelmaking plant. The results show that the algorithm successfully learns the process, recommending the same actions as those taken by the operator 69.23% of the time. The algorithm also suggests a better option in 30.76% of the remaining cases. Thanks to the DSS, the heat rejection due to wrong composition is reduced by 4%, and temperature accuracy is increased to 83.33%. These improvements resulted in an estimated reduction of 2% in CO2 emissions, 0.5% in energy consumption and 1.5% in costs. Additionally, actions taken based on the operator's experience are incorporated into the DSS knowledge, facilitating the integration of operators with lower experience in the process. [ABSTRACT FROM AUTHOR]

Satellite remote sensing provides a unique opportunity for calibrating land surface models due to their direct measurements of various hydrological variables as well as extensive spatial and temporal coverage. This study aims to apply terrestrial water storage (TWS) estimated from the gravity recovery and climate experiment (GRACE) mission as well as soil moisture products from advanced microwave scanning radiometer–earth observing system (AMSR-E) to calibrate a land surface model using multi-objective evolutionary algorithms. For this purpose, the non-dominated sorting genetic algorithm (NSGA) is used to improve the model’s parameters. The calibration is carried out for the period of two years 2003 and 2010 (calibration period) in Australia, and the impact is further monitored over 2011 (forecasting period). A new combined objective function based on the observations’ uncertainty is developed to efficiently improve the model parameters for a consistent and reliable forecasting skill. According to the evaluation of the results against independent measurements, it is found that the calibrated model parameters lead to better model simulations both in the calibration and forecasting period.

Thermal plasma reactors offer an environment of high temperature, enthalpy, and reactivity, making them highly efficient for solid waste treatment and promising for clean energy production from municipal and industrial waste. Optimal geometrical parameters of the reactor can enhance waste treatment and reactor performance. This study presents a comprehensive analysis of 11 key geometrical parameters of a thermal plasma reactor. Utilizing CFD Fluent software, numerical simulations were conducted to generate a dataset. Subsequently, a predictive model focusing on the average temperature in the core melt zone was trained using six Machine Learning (ML) algorithms. The Particle Swarm Optimisation (PSO) algorithm optimized the hyperparameters of the Gradient Booster Regression (GBR) model, which was combined with a Genetic Algorithm (GA) to identify the reactor's optimal geometrical parameters. A DC arc plasma torch-solid waste thermal plasma reactor treatment system was established on this basis. The study also explored the effects of gasification coefficient, reaction temperature, and thermal plasma jet mode on system performance. Findings indicate that the PSO-GBR model achieved the highest prediction accuracy, with the temperature in the core reaction zone reaching 3621 K. The deviation between numerical simulations and machine learning predictions was a mere 1.3%. Enhancing syngas yield and energy efficiency is achievable by controlling reaction temperature and increasing the gasification coefficient. A laminar plasma jet mode, at equal power, provides a more effective reaction environment. The accuracy and reliability of the machine learning-driven regression model and optimization results are significant in guiding the optimal design of plasma reactors and advancing waste-to-energy conversion processes. [Display omitted] • Study integrates CFD and ML to predict optimal structural parameters of a thermal plasma reactor. • GBR optimized by PSO was most effective in predicting the reactor core's average temperature. • The theoretical predictions of the CFD-ML framework are validated based on an experimental setup. • Study examines reactor performance under varying conditions, offering insights for waste-to-energy conversion. [ABSTRACT FROM AUTHOR]

Implementing energy storage solutions is crucial to address the intermittency challenges of marine renewable energy. Buoyancy energy storage technology (BEST) holds potential, but its development remains in its infancy. Additionally, optimisation has not been implemented to improve the design. Therefore, a transit search (TS)-based optimisation model is developed to optimise both the small-scale (volume of tank less than 500 m3) and large-scale (volume of tank less than 30,000 m3) fabric BEST to maximise the power density and energy density. The optimisation results obtained through the transit search (TS) algorithm surpass those from the gray wolf (GW), whale, and artificial bee colony (ABC) algorithms in terms of consistency. The optimised large-scale fabric BEST design demonstrates improvements, with a 56% increase in power density from 345 W/m3 to 539 W/m3 and a 58% increase in energy density from 201 Wh/m3 to 318 Wh/m3 compared to the pre-optimised design from the literature. Moreover, linear relationships between the tank's submerged volume-to-water volume ratio and the extra weight limit were investigated through sensitivity analysis. The optimised fabric BEST shows competitive energy density when compared to other emerging energy storage technologies. Lithium-sulphur has higher energy density, but fabric BEST offers better safety and ease of installation. [ABSTRACT FROM AUTHOR]

Recently, metaheuristics (MHs) have become increasingly popular in real-world engineering applications such as in the design of airframes structures and aeroelastic designs owing to its simple, flexible, and efficient nature. In this study, a novel hybrid algorithm is termed as Ensemble of Genetic algorithm, Grey wolf optimizer, Water cycle algorithm and Population base increment learning using Weighted sum (E-GGWP-W), based on the successive archive methodology of the weighted population has been proposed to solve the aircraft composite wing design problem. Four distinguished algorithms viz. a Genetic algorithm (GA), a Grey wolf optimizer (GWO), a Water cycle algorithm (WCA), and Population base increment learning (PBIL) were used as ingredients of the proposed algorithm. The considered wing design problem is posed for overall weight minimization subject to several aeroelastic and structural constraints along with multiple discrete design variables to ascertain its viability for real-world applications. The algorithms are validated through the standard test functions of the CEC-RW-2020 test suite and composite Goland wing aeroelastic optimization. To check the performance, the proposed algorithm is contrasted with eight well established and newly developed MHs. Finally, a statistical analysis is done by performing Friedman's rank test and allocating respective ranks to the algorithms. Based on the outcome, it has been observed that the suggested algorithm outperforms the others. [ABSTRACT FROM AUTHOR]

In a fuel cell electric vehicle (FCEV) powered by a metal hydride tank, the performance of the tank is an indicator of the overall health status, which is used to predict its behaviour and make appropriate energy management decisions. The aim of this paper is to investigate how to evaluate the effects of charge/discharge cycles on the performance of a commercial automotive metal hydride hydrogen storage system applied to a real FCEV. For this purpose, a mathematical model is proposed based on uncertain physical parameters that are identified using the stochastic particle swarm optimisation (PSO) algorithm combined with experimental measurements. The variation of these parameters allows an assessment of the degradation level of the tank’s performance on both the quantitative and qualitative aspects. Simulated results derived from the proposed model and experimental measurements were in good agreement, with a maximum relative error of less than 2%. The validated model was used to establish the correlations between the observed degradations in a hydride tank recovered from a real FCEV. The results obtained show that it is possible to predict tank degradations by developing laws of variation of these parameters as a function of the real conditions of the use of the FCEV (number of charging/discharging cycles, pressures, mass flow rates, temperatures).

One of the main goals of any power grid is sustainability. The given study proposes a new method, which aims to reduce users’ anxiety especially at slow charging stations and improve the smart charging model to increase the benefits for the electric vehicles’ owners, which in turn will increase the grid stability. The issue under consideration is modelled as an optimisation problem to minimise the cost of charging. This approach levels the load effectively throughout the day by providing power to charge EVs’ batteries during the off-peak hours and drawing it from the EVs’ batteries during peak-demand hours of the day. In order to minimise the costs associated with EVs’ charging in the given optimisation problem, an improved version of an intelligent algorithm is developed. In order to evaluate the effectiveness of the proposed technique, it is implemented on several standard models with various loads, as well as compared with other optimisation methods. The superiority and efficiency of the proposed method are demonstrated, by analysing the obtained results and comparing them with the ones produced by the competitor techniques.

This study addresses the pose estimation problem of an aircraft runway using visual observations in a landing approach scenario. The authors utilised the fact that the geodetic coordinates of most runways are known precisely with highly visible markers. Thus, the runway observations can increase the level of situational awareness during the landing approach, providing additional redundancy of navigation and less reliance on global positioning system. A novel pose optimisation algorithm is proposed utilising unit dual quaternion for the runway corner observations obtained from a monocular camera. The estimated runway pose is further fused with an inertial navigation system in an extended Kalman filter. An open-source flight simulator is used to collect and process the visual and flight dataset during the landing approach, demonstrating reliable runway pose estimates and the improved inertial navigation solution.

In this study, the system with fractional power nonlinearity is introduced into the theory of aperiodic stochastic resonance (ASR). The fractional exponent is a key parameter and its effect on the ASR phenomenon excited by aperiodic binary signal is investigated in this system. Compared to the classical bistable system, the system with fractional power nonlinearity shows better performance. It can adjust not only the noise intensity but also the fractional exponent to enhance weak signal. In the field of signal transmission, pure aperiodic binary signal is usually submerged in the noise and the signal is unknown. Thus, an effective method is proposed based on ASR and moving average. By the method, the unknown aperiodic binary signal can be recovered in the noise background. To improve the efficiency of the signal recovery, the adaptive ASR is realised with the help of adaptive particle swarm optimisation (APSO) algorithm to optimise the parameters. The method may provide some reference to the engineering field. [ABSTRACT FROM AUTHOR]

Open‐circuit voltage decay (OCVD) is a method to characterise minority carrier effective lifetime (τeff). It is non‐destructive, simple and low‐cost. It has been mainly used in silicon p‐n junctions. τeff is not only a very important parameter to optimise device design but also to supervise process steps. It is not the only parameter we can obtain by OCVD. Due to the intrinsic space charge region capacitance of a p‐n junction, the doping level of the lowest‐doped region (Nl) and built‐in potential (Vbi) are extractable. Moreover, it is also possible to obtain the shunt resistance (Rsh) value when it has a significant effect on the p‐n junction behaviour. The authors first applied the well‐established one‐diode model in a transient regime to simulate OCVD signal. In a second step, they used an optimisation algorithm to fit the experimental curve of a silicon diode to extract τeff, Nl, Vbi and Rsh. These values were compared to those obtained from C–V and I–V. Results are promising and demonstrate for the first time, the flexibility of the OCVD method. It opens up the perspective for the development of add‐on features of the method and for measuring short lifetime. [ABSTRACT FROM AUTHOR]

Image compression is an intensively studied subject in computer vision. The deep generative model, especially generative adversarial networks (GANs), is a popular new direction for this subject. In this study, the authors propose a new compression method based on a generative model and focus on its application by GANs. The decoder in the proposed method is modified from the GAN generator model, which can produce visually real‐like synthetic images. It is one of the two models in GANs, which is trained through a two‐players' contest game. The encoder is an optimisation algorithm called backpropagation‐to‐the‐input, which derives from an image inpainting algorithm based on generative models. In the proposed method, the authors turn the encoding process into an optimisation task to search for optimal encoded representations. Compared with traditional methods, the proposed method can compress images from certain domains into extremely small and shape‐fixed encoded space but still retain better visual representations. It is easy and convenient to apply without any retraining or additional modification to the generative models. [ABSTRACT FROM AUTHOR]

The Hashin's strength criteria are usually employed in first ply failure and damage-onset analysis of fibre-reinforced composites. This work presents optimality conditions of local material orientations for these criteria, in terms of principal stresses and material strength parameters. Each criterion (matrix tensile/compressive, fibre tensile/compressive modes) has its conditions separately derived, analytically, based on a fixed stress field assumption. The conditions found show that orientations which coincide and do not coincide with principal stress directions may minimise local failure indices. These solutions are employed in a proposed algorithm, named HA-OCM (Hashin Optimality Criteria Method), which selectively satisfies the matrix failure modes (either tensile or compressive), iteratively and finite element-wise in composites. It is demonstrated that the HA-OCM is able to design single-layer plane structures with improved failure loads in comparison with designs following only maximum (in absolute) principal stress orientations. Results show that the material orientations have a trend to end up either aligned or at 90° with maximum in absolute principal stress directions. Global optima for compliance are, however, not guaranteed. To give an idea of gains in terms of failure loads, some HA-OCM designs show improvements of 71% and 140%, for example, in comparison with principal stress design. [ABSTRACT FROM AUTHOR]

For a non-linear anisotropic permanent magnet synchronous machine (PMSM), a prediction model for model predictive control (MPC) considering effects like cross-coupling and saturation is developed in a straight forward procedure. The objective of the designed MPC is either tracking of reference currents or torque tracking. Both approaches use the projected fast gradient method (PFGM) as optimisation algorithm. The latter approach makes look-up-tables for current references obsolete and additionally minimises winding losses. This two approaches are compared in a simulation study with a state of the art PI controller.

The interaction between renewable energy generation and high-voltage direct current (HVDC) transmission system becomes an essential cause of the subsynchronous oscillation (SSO) problem. In this study, the permanent magnet synchronous generator-based wind farm connected to HVDC transmission system is studied. The susceptivity analysis is carried out to find the main influence factors of the SSO problem. Besides, a parameter design method for subsynchronous damping controller is proposed. The configuration and the performance indicator are discussed, and then the optimisation algorithm is developed based on hybrid genetic algorithm and electromagnetic transient simulation. Finally, the proposed design method is validated by simulation in PSCAD/EMTDC.

Introduction: Sleep apnoea syndrome (SAS) is a serious sleep disorder and early detection of sleep apnoea not only reduces treatment costs but also saves lives. Conventional polysomnography (PSG) is widely regarded as the gold standard diagnostic tool for sleep apnoea. However, this method is expensive, time-consuming and inherently disruptive to sleep. Recent studies have pointed out that ECG analysis is a simple and effective diagnostic method for sleep apnea, which can effectively provide physicians with an aid to diagnosis and reduce patients' suffering., Methods: To this end, in this paper proposes a LightGBM hybrid model based on ECG signals for efficient detection of sleep apnea. Firstly, the improved Isolated Forest algorithm is introduced to remove abnormal data and solve the data sample imbalance problem. Secondly, the parameters of LightGBM algorithm are optimised by the improved TPE (Tree-structured Parzen Estimator) algorithm to determine the best parameter configuration of the model. Finally, the fusion model TPE_OptGBM is used to detect sleep apnoea. In the experimental phase, we validated the model based on the sleep apnoea ECG database provided by Phillips-University of Marburg, Germany., Results: The experimental results show that the model proposed in this paper achieves an accuracy of 95.08%, a precision of 94.80%, a recall of 97.51%, and an F1 value of 96.14%., Discussion: All of these evaluation indicators are better than the current mainstream models, which is expected to assist the doctor's diagnostic process and provide a better medical experience for patients., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2024 Xiong, Wang, He, Wang, Liu, Sun, Zhang and Zhang.)

The growing demand for the cloud community market towards attracting and sustaining the incoming and the available cloud users is addressed actively to meet the competitive environment. There is a good scope for improving the provider capabilities in the cloud in order to satisfy the users with attractive benefits. The study introduces an effective virtual machine (VM) migration strategy using an optimisation algorithm in such a way to facilitate the user selection of the providers based on their budgetary requirements in running their own platforms. The constraints associated with the selection of the provider include cost, revenue, and resource, which are altogether confined as an elective factor. The optimisation algorithm employed for the VM migration is referred to as Taylor series‐based salp swarm algorithm (Taylor‐SSA) that is the integration of the Taylor series with SSA. The evaluation of the method is progressed using three setups by varying the number of providers and users. The cost, the revenue, and the resource of the proposed method are analysed and concluded that the proposed method acquired a minimal cost, maximal resource gain and revenue. [ABSTRACT FROM AUTHOR]

For space manufacturers, additive manufacturing promises to dramatically reduce weight and costs by means of integral designs achieved through part consolidation. However, integrated designs hinder the ability to change and service components over time – actually increasing costs – which is instead enabled by highly modular designs. Finding the optimal trade-off between integral and modular designs in additive manufacturing is of critical importance. In this article, a product modularisation methodology is proposed for supporting such trade-offs. The methodology is based on combining function modelling with optimisation algorithms. It evaluates product design concepts with respect to product adaptability, component interface costs, manufacturing costs and cost of post-processing activities. The developed product modularisation methodology is derived from data collected through a series of workshops with industrial practitioners from three different manufacturer companies of space products. The implementation of the methodology is demonstrated in a case study featuring the redesign of a satellite antenna. [ABSTRACT FROM AUTHOR]

For a non-linear anisotropic permanent magnet synchronous machine (PMSM), a prediction model for model predictive control (MPC) considering effects like cross-coupling and saturation is developed in a straight forward procedure. The objective of the designed MPC is either tracking of reference currents or torque tracking. Both approaches use the projected fast gradient method (PFGM) as optimisation algorithm. The latter approach makes look-up-tables for current references obsolete and additionally minimises winding losses. This two approaches are compared in a simulation study with a state of the art PI controller. [ABSTRACT FROM AUTHOR]

A prominent issue in microgrid (MG) cost optimisation is the consideration of variable parameters such as demand, wind speed, sun radiation intensity etc. This study deals with mitigating substantial deviation between study results and actual MG operation indices. The deviation is the result of ignoring the effects of power electronics devices in the optimisation algorithm. A new optimisation model is proposed to involve the main converter's restrictions in the optimisation process. For connecting renewable sources with uncertain outputs such as photovoltaic, wind, and also loads to a MG, using power electronic converters is inevitable. This study proposes an operation cost optimisation development by foreseeing the effects and limitations of power electronic devices, disregarding of which would undoubtedly lead to a notable deviation in optimisation results. [ABSTRACT FROM AUTHOR]