Search

With the service level playing an increasingly essential role in the service-oriented manufacturing (SOM) supply chain, the distribution network design can be heavily affected by the customer behaviour based on their satisfaction of services. In this paper, we consider the service level for service time and delivery quantity separately. A novel mixed integer non-linear programming model is proposed to design the multi-period distribution network from a fourth-party logistics (4PL) perspective. The customer satisfaction based on prospect theory is maximised while considering the investment budget and the service level. A scenario-based linear reformulation is proposed to find the optimal solution when the problem scale is small. For a large-scale problem, we propose an individual-driven Q-learning based memetic particle swarm optimisation algorithm. Numerical experiments are conducted to demonstrate the effectiveness and efficiency of the proposed algorithm. Furthermore, the impact of service modes, different customer behaviour, and customer satisfaction evaluation periods on distribution network is investigated. We find that the length of evaluation periods leads to differences in customer satisfaction due to different perceptions of 'small loss' and 'big gain' by boundedly rational customers. [ABSTRACT FROM AUTHOR]

After the expiration of each lease, lessees may return leased equipment on schedule, renew the lease or purchase it according to the equipment status and their demands. By considering lessees' uncertain options and equipment status difference, the pricing and inventory decision-makings of leased equipment are explored. A mixed-integer nonlinear programming model by maximising the net present value of lessor's profit is presented with respect to constraints like rental revenue, manufacturing, lessees' credit check, transportation, maintenance, upgrade and inventory costs. The rental price and inventory decisions are obtained by solving the problem with a particle swarm optimisation algorithm. We also analyse the impacts of purchasing cost of old equipment from a third-party supplier on lessor's inventory, renewal price or purchasing price of leased equipment on lessees' options and lessor's profit. The results show: (1) with the extension of lease period, the rental price increases while the growth rate decreases; (2) the maintenance cost accounts for about 20% of total cost, and the preventive maintenance strategy can reduce excess maintenance cost as lease period increases; (3) the lessor shall set moderate renewal price discount coefficient and purchasing price coefficient, and analyse purchasing cost of old equipment to manage inventory timely. [ABSTRACT FROM AUTHOR]

As a high-energy density material, polymeric nitrogen has attracted considerable attention, while the exceptionally high synthesis pressure hinders its studies and applications. A significant discovery indicates that the insertion of noble gas elements can effectively reduce the synthesis pressure of polymeric nitrogen compounds. This work utilized the particle swarm optimization algorithm and first-principles calculations to extensively explore the stoichiometry of Xe–N compounds under high pressures. Two phases of XeN14, P6mm and P-62m, have been discovered, which are energetically more stable than the basic mixture of Xe and N2. Evidence of charge transfer between Xe and N was found, verifying that Xe plays a crucial role in forming polymeric nitrogen compounds. These two compounds are kinetically stable at pressures ranging from 50 to 200 GPa and exhibit semiconductor properties. A unique channel-like structure was discovered in the P6mm phase. The energy densities of P6mm and P-62m phases are 7.39 and 7.59 kJ/g, respectively, significantly exceeding those of TNT (Trinitrotoluene) and HMX (Octogen), indicating their potential as high-energy density materials. [ABSTRACT FROM AUTHOR]

Using the particle swarm optimization algorithm, we conducted an extensive search for the high-pressure stable structure of technetium diboride (TcB2) within the pressure range of 0–400 GPa. At zero pressure, the P63/mmc (hP6-TcB2) structure is considered the ground state configuration. As the pressure increases, a structural transition from hP6-TcB2 to P6/mmm (hP3-TcB2) occurs at approximately 174.9 GPa. We discuss the bonding between the two distinct phases and analyze the contribution of different atomic bonds to maintaining their structural stability. Meanwhile, the temperature–pressure phase diagram of TcB2 was successfully determined for the first time through the quasi-harmonic approximation method. It is predicted that the transition pressure from hP6-TcB2 to hP3-TcB2 can be reduced to about 164 GPa at a room temperature of 300 K. These results provide valuable insights into the behavior of TcB2 under different temperature and pressure conditions and open up new possibilities for exploring its potential applications in a variety of environments. [ABSTRACT FROM AUTHOR]

Changes to components, known as engineering changes (ECs), rarely occur on their own. In fact, in complex assembly systems, most ECs are introduced in batches to ensure that changed components match. As a result, to implement ECs optimally, multiple component's stock must be considered until the change is executed on the EC effectivity date. This problem is known as the EC effectivity date optimisation problem, a variation of the general inventory control problem with deterministic and dynamic demand. As optimisation and monitoring of this problem is computationally expensive, research has suggested to investigate whether metaheuristics can provide adequate support. To fill this research gap, we present the results of a benchmark on basic metaheuristics for EC effectivity date optimisation. To do so, we have compared five common metaheuristics in their basic form (Ant Colony Optimisation, Genetic Algorithm, Particle Swarm Optimisation, Tabu Search, and Simulated Annealing) on a real-world test set. Of the tested algorithms the Genetic Algorithm identified most best solutions and returned good average results for the test cases. However, as its reliability was comparatively low, our research suggests a sequential application of the Genetic Algorithm and Tabu Search. [ABSTRACT FROM AUTHOR]

With the fierce competition in e-commerce, e-tailers are required to rapid responses to a variety of customised orders with multiple frequencies and strict delivery times. The delay or insufficient supply caused by disruptions might result in lost sales during long-term processes. To address this problem, a two-stage stochastic programming model considering profits, consumer service level (CSL) as well as market priorities is developed to manage long-term disruptions. We analyse multi-period consumer transaction data and formulate geographical relevance (GR) to link each marketplace with historical data in related regions and then prioritise market segments. A GR-based two-stage stochastic programming with multi-period is proposed, which (1) considers both proactive mitigation decisions before disruption and reactive recovery plans after disruption; (2) collaborates three resilience strategies; (3) optimises the e-tailer's profits considering market priorities during long-term disruptions. Using a real case of Chinese e-commerce under the COVID-19 pandemic, it is illustrated (1) the applicability and performance of the proposed GR-based model for multi-period resilience optimisation improving both the CSL and the total profit; (2) the efficiency and robustness of the developed sequential particle swarm optimisation with social structures algorithm. The proposed method could optimise e-tailers' response strategies for managing long-term disruptions in practice. [ABSTRACT FROM AUTHOR]

This paper proposes a white-box perspective that portrays a supply chain delivery process as a network of related activities which remains to be improved. It addresses a critical disadvantage of supply chain delivery performance models, namely considering a delivery process as a whole and ignoring characteristics and relationships between activities in the delivery process. A delivery process is modeled using the Graphical Evaluation and Review Technique based on the characteristic function (CF-GERT). Based on the CF-GERT model, a framework for applying managerial effort to activities to improve overall delivery performance is proposed. Then, particle swarm optimization (PSO) based on the penalty function is used to solve the delivery performance improvement framework. Finally, a numerical case shows how applying efforts to activities can effectively improve delivery performance and demonstrates the influence of several parameters on the related costs. [ABSTRACT FROM AUTHOR]

This paper introduces a methodology designed to augment the inverse design optimization process in scenarios constrained by limited compute, through the strategic synergy of multi-fidelity evaluations, machine learning models, and optimization algorithms. The proposed methodology is analyzed on two distinct engineering inverse design problems: airfoil inverse design and the scalar field reconstruction problem. It leverages a machine learning model trained with low-fidelity simulation data, in each optimization cycle, thereby proficiently predicting a target variable and discerning whether a high-fidelity simulation is necessitated, which notably conserves computational resources. Additionally, the machine learning model is strategically deployed prior to optimization to compress the design space boundaries, thereby further accelerating convergence toward the optimal solution. The methodology has been employed to enhance two optimization algorithms, namely Differential Evolution and Particle Swarm Optimization. Comparative analyses illustrate performance improvements across both algorithms. Notably, this method is adaptable across any inverse design application, facilitating a synergy between a representative low-fidelity ML model, and high-fidelity simulation, and can be seamlessly applied across any variety of population-based optimization algorithms.

• A phase error correction method (IFOA-JMEC) for InIRA images is proposed. • Ionospheric scintillation and atmospheric turbulence are main errors source for InIRA. • Correcting spatial-variant Error in range by dividing subblocks and interpolating. • Background atmosphere has little influence on InIRA height measurement accuracy. • Phase screen models for ionospheric scintillation and atmospheric turbulence. The interferometric imaging radar altimeter (InIRA) is a newly developed microwave remote sensing system in recent years. It is of great significance to analyze the main sources of its height measurement error through simulation, and to develop the corresponding image phase error correction methods. This can provide basis and reference for the subsequent correction of the real images phase error. In this study, according to the interaction principle between atmospheric interference and InIRA radar electromagnetic waves, the influence of background ionosphere and background troposphere on height measurement error is analyzed by introducing ionosphere and troposphere delays into echo signals respectively. The impact of ionospheric scintillation and atmospheric turbulence on the height measurement error is analyzed by building multi-layer phase screen models. Then according to the analysis results, a phase error correction method for InIRA images combined by the improved fruit fly optimization algorithm (IFOA) and the joint minimum entropy criterion (JMEC) is proposed. The image is divided into several sub-images with negligible spatial variation of phase error according to the principle of first range and then azimuth. IFOA is used to search the optimal phase compensation values iteratively to compensate the phase of all sub-images. When the joint entropy of the sub-images reaches the minimum value, the phase error correction of the whole InIRA image is completed. Experimental results show that the proposed method can correct the phase of InIRA images with inconspicuous features and polluted by weak ionospheric scintillation and atmospheric turbulence relatively quickly. After correction, the height measurement error can be reduced from decimeter level to centimeter level. The correction accuracy and efficiency of the proposed method are superior to those of the method combined by particle swarm optimization algorithm and joint minimum entropy criterion (PSO-JMEC), the method combined by genetic algorithm and joint minimum entropy criterion (GA-JMEC), the method combined by phase gradient autofocus and Map Drift (PGA-MD), and improved PGA-MD algorithm. [ABSTRACT FROM AUTHOR]

Diabetes is a chronic medical condition that disrupts the body's normal blood sugar levels. It is essential to detect this disease at an early stage in order to prevent organ and tissue injury. This study focuses on diagnosing diabetes by leveraging ensemble learning methods, which involve combining various machine learning techniques. The goal is to create an ensemble learning model that achieves the best classification performance by employing different classifiers and combining techniques. The study explores boosting, bagging, voting, and stacking ensemble learning methods, while also introducing an approach called PSO-GWO (Particle Swarm Optimization and Grey Wolf Optimization) hybrid method for optimizing the model's hyperparameters. The model consisting of combining various classifiers in the stacking ensemble learning method provided the highest classification performance in diagnosing diabetes. The 5-fold cross-validation method is used in the study. Within the scope of the study, the highest accuracy with (98.10%) is obtained with the random forest classifier. The results of the study are presented in comparison with other studies in the literature. These findings contribute to the field of diabetes diagnosis and highlight the potential for developing more accurate and reliable diagnostic systems in the future. [ABSTRACT FROM AUTHOR]

Producing liquid hydrogen (LH 2) is an energy-intensive process as 30% of the LH 2 energy is consumed during liquefaction in the existing commercial plants. Thus, numerous innovative liquefaction processes were proposed to achieve a significant reduction in the specific energy consumption (SEC) of the LH 2 production systems. In particular, single-mixed refrigerant (SMR) and dual-mixed refrigerant (DMR) hydrogen precooling processes were introduced as efficient alternatives for conventional precooling processes. However, the SEC of the SMR is still high (>2 kWh/kg H2) and lacks efficient and practical optimization. On the other hand, the DMR demonstrates efficient operation (SEC close to 1.0 kWh/kg H2) but with a more complex configuration and higher capital cost. To address these gaps, this study (i) presents a new dual-pressure SMR precooling process (DP-SMR) that combines the simplicity of the SMR process and efficient operation of the DMR process, (ii) proposes a new optimization method for the cryogenic process with systematic implementation on the SMR, DMR, and the proposed DP-SMR processes, and (iii) conducts systematic thermoeconomic assessment for the optimized cases of the precooling processes. The proposed optimization method integrates knowledge-based optimization (KBO) procedures with other efficient optimization algorithms including genetic algorithm optimization (GAO), particle swarm optimization (PSO), and Bayesian optimization (BO). This method fosters the optimization process and ensures the achievement of optimal performance that satisfies all design constraints without performing penalty functions. The results show that the SEC of the proposed DP-SMR process is 1.29 kWh/kg H2 , which is 6%–10% lower than all SMR processes available in the literature. In addition, the levelized precooling cost of the DP-SMR process is 2.15% and 16.00% lower than that of the optimized DMR and SMR processes, respectively. The proposed optimization procedures in this study will facilitate the achievement of robust optimization performance for any cryogenic process including hydrogen, nitrogen, and natural gas liquefaction systems. • A new dual-pressure single mixed-refrigerant hydrogen precooling process is proposed. • A new optimization method for the cryogenic process is introduced. • Systematic thermoeconomic analysis for three H2 precooling processes is conducted. • The energy consumption of the proposed process is reduced by 10%. • The H 2 precooling cost is reduced by 16% compared to conventional SMR processes. [ABSTRACT FROM AUTHOR]

To reduce carbon emissions, hydrogen is a clean energy as fuel to co-combustion with natural gas. This experimental work focuses on studying the effects of hydrogen addition to methane on combustion performance and emissions in non-premixed coaxial burners, establishing performance prediction models and optimizing operation conditions involving fuel velocity, hydrogen blending ratio and equivalence ratio. The global sensitivity and analysis of variance were adopted to quantify the contributions of independent variables on the output responses of temperature, O 2 , NO, CO and CO 2 emissions. The hydrogen blending ratio is the most influential parameter, whose total effects of NO and CO 2 emissions are 64.6% and 83.5%, respectively. The equivalence ratio is not significant to NO and CO 2 emissions, and the adjusted determination coefficient of the reduced prediction model is 0.9707 and 0.9360, demonstrating a better goodness of fit. Based on the response surface model and particle swarm optimization algorithm, a Pareto was solved showing NO and CO 2 emissions decrease by 42.0%–73.6% and 60.8%–89.5%, and peak temperature in the chamber centerline increases by 1.02%–3.61%. The research results provide a profound guide to predict and optimize combustion performance and emissions for methane-hydrogen non-premixed flame. [Display omitted] • Prediction models of CH 4 –H 2 non-premixed burner were built by response surface method. • Total effects of hydrogen blending ratio on NO and CO 2 emissions are 64.6% and 83.5%. • Equivalence ratio is not significant to flue gas temperature, NO and CO 2 emissions. • A Pareto set was obtained by optimizing flame temperature and pollutants via PSO. • Peak temperature increases by 2.30%, NO and CO 2 decrease by 59.4% and 78.3%. [ABSTRACT FROM AUTHOR]

AbstractThe flame temperature is a crucial parameter in combustion, indicating heat generation and transfer. However, determining the correct temperature becomes challenging when flame emissivity is unknown. This article presents a multispectral 2D temperature field reconstruction method using particle swarm optimization and the Broyden–Fletcher–Goldfarb–Shanno algorithm, combined with multivariate extreme-value optimization. This method establishes an objective function based on the correlation between the true temperature and spectral data. The objective function was minimized by adjusting the emissivity, enabling the reconstruction of 2D temperature and emissivity images without assuming an emissivity model. Calibration with a multispectral camera yielded the spectral response coefficients, and three-time spline interpolation was used to verify the calibration data. The reconstructed 2D temperature field showed a mean absolute error (MAE) of 4.61 and structural similarity (SSIM) of 0.995. The reconstructed emissivity image had an MAE range of 0.04 to 0.053 and an SSIM range of 0.897 to 0.915. The system, tested on a butane flame, showed a temperature range of 1001 K to 1356 K, with an average temperature of 1194 K and emissivity values ranging from 0.3166 to 0.8621. The results align with the expected combustion process and radiation characteristics distribution of the butane flame. [ABSTRACT FROM AUTHOR]

Skin cancer is one of the most common types of cancer in the world. If skin cancer is not treated early, it also affects the diseased area under the skin and this threatens the treatment of the disease. In recent years, many diseases have been rapidly detected with high accuracy with artificial intelligence methods, and the treatment process has accelerated. Convolutional neural networks, one of the artificial intelligence methods, provide very detailed information about images, and extremely successful results are obtained in classifying images. In this study, first the data set was trained with the EfficientNetB0 model, which is one of the convolutional neural networks models. Then, with the fully connected layer of this model, deep features of the images were obtained. These deep features were obtained by selecting Particle Swarm Optimization and Genetic Algorithm optimization, and different feature combinations were created. Each of these selected feature sets was classified by the support vector machines method, and the best performance results were tried to be obtained. As a result, the success of the proposed model has been proven by obtaining an accuracy rate of 89.17%. [ABSTRACT FROM AUTHOR]

Shear strength parameters play a crucial role in the design and construction of rock slopes, underground openings, tunnels, excavations, and foundations. Determination of cohesion (c) and angle of internal friction (φ) through laboratory tests (e.g., triaxial tests) and in situ tests is time-consuming and expensive; therefore, it is valuable to accurately predict the shear strength parameters of rock materials using less expensive and more reliable methods. In this study, 4 artificial intelligence models, namely group method of data handling (GMDH), gene expression programming (GEP), bidirectional long short-term memory network (BILSTM), and random forest (RF), are proposed to predict the rock shear strength parameters c and φ. A database of 199 sets of experimental data from 4 rock types was used to construct the proposed models. The results show that the accuracy of the RF model is superior to the other three models, with coefficients of determination of 0.9933 (c) and 0.9727 (φ) on all datasets, respectively. To further improve the prediction accuracy of the RF model, six metaheuristic algorithms, namely particle swarm optimization (PSO), bald eagle search (BES), marine predators algorithm (MPA), northern goshawk optimization (NGO), golden jackal optimization (GJO), and dung beetle optimizer (DBO), were used to optimize the hyperparameters of the model. The results show that the accuracy of the six hybrid RF models is higher than that of the single RF model. Among the 6 hybrid RF models, the hybrid DBO–RF model is superior to the other hybrid RF models. In addition, the factors affecting the shear strength of rock materials are analyzed through the parameter sensitivity analysis. Highlights: Four artificial intelligence models are used to predict the shear strength parameters of rock materials. Six metaheuristic algorithms are used to optimize the hyperparameters of the random forest model. The prediction performance of the six hybrid random forest models is compared. The factors influencing the shear strength of rock materials are analyzed by parameter sensitivity analysis. [ABSTRACT FROM AUTHOR]

ABSTRACT In this brief, an optimal active fuzzy fault‐tolerant control (OAFFTC) scheme is proposed for a class of unknown perturbed multi‐input multi‐output (MIMO) nonlinear systems with nonaffine nonlinear actuator faults and time‐varying sensor faults. The control strategy can handle automatically (online updating) with three additives (bias, drift, and loss of accuracy) along with one multiplicative (loss of effectiveness) sensor faults and nonlinear state‐dependent actuator faults. In order to deal with uncertain system dynamics, sensor and actuator faults, and external disturbances, fuzzy systems (FSs) and backstepping techniques were combined to provide the adaptive control term as well as a robust control term. Butterworth filter is used to get rid the algebraic loop problem. The suggested robust term, can deal with approximation errors of the fuzzy systems (FSs). To automatically optimize the adaptive parameters and the starting conditions, particle swarm optimization (PSO) approach is introduced. The Lyapunov approach is employed to demonstrate the closed‐loop system's stability. To assess the efficacy and correctness of the suggested scheme, quadrotor dynamic model is performed on the simulation part. [ABSTRACT FROM AUTHOR]

Based on Keynesian macroeconomic theory, this paper introduces economic indicators with Chinese characteristics, and constructs a multivariate grey machine learning forecasting model (IGM (1, N, X1 (0))-IPSO-LSTM) to predict China's GDP growth. Firstly, IGM (1, N) model is constructed by changing the background value construction method of GM (1, N) model and introducing grey action constant A which reflects the change from the grey differential equation to the difference equation. Secondly, due to the low frequency and small amount of GDP data, constructing a two-layer LSTM model to increase the model complexity, so that the data can be fully trained. In addition, this paper uses nonlinear descending function instead of w to construct Improved Particle Swarm Optimization algorithm (IPSO), and adds Genetic Algorithm (GA) to IPSO to reduce the risk of particles falling into the local optimal solution. Finally, using IPSO to find the optimal parameters of LSTM model to predict China's GDP growth. By comparing the prediction accuracy of IGM (1, N, X1 (0))-IPSO-LSTM model with other benchmark models, the prediction result of IGM (1, N, X1 (0))-IPSO-LSTM model is the best. It is predicted that China's GDP growth rate in 2024 is 5.18% and in 2025 is 5.12%. By analyzing the trend development of China's economic, it is found that the forecast results are consistent with the expected trend of macro economy, which increases the credibility of the forecast results. [ABSTRACT FROM AUTHOR]

Rising coal price and increasingly stringent emission policy highlight the importance of balancing economic benefit and sustainable development of coal-fired power plants. In order to make the power plant operate economically and safely, and reduce the emission of pollutants as much as possible, this paper proposed a coal blending optimization framework for coal-fired power plants. This framework constructs a set of mathematical model based on the minimization objective function, including the economy, safety and environmental protection of coal. And a multi-strategy fusion multi-objective particle swarm optimization (MSF-MOPSO) method is proposed to optimize the coal blending model. The feasibility, effectiveness and superiority of the method are theoretically verified by convergence analysis and several sets of simulation experiments. And the practical application of this framework shows that under the coal blending strategy based on different weight combinations, the algorithm proposed in this paper can produce high-quality Pareto spatial distribution. Comparing with other state-of-the-art coal blending algorithms, this method can reduce the coal purchase cost by 4.42% and ${\rm{S}}{{\rm{O}}_{\rm{2}}}$ S O 2 emission by 5.11% at least under the same condition. It has significant environmental protection and economic benefit. [ABSTRACT FROM AUTHOR]

To improve the probability analysis efficiency of slope, this paper proposes an improved particle swarm optimization (IPSO) method to determine the critical sliding surface (CSS) and its corresponding minimum safety factor, which is used to calculate the failure probability of slope. Based on the random fields generated by using Karhunen-Loève (KL) expansion method, the simplified Bishop's method combined with the entry and exit method, the particle swarm optimization (PSO) method, and the IPSO method is used to determine the CSS and its corresponding minimum factor of safety. Then, Monte Carlo simulation is used to estimate the failure probability of slope. The application potential of the IPSO method is demonstrated by re-analyzing two examples. Meaningful comparisons are made to demonstrate the calculating accuracy and calculating efficiency of the IPSO method in searching for the minimum safety factor of slope. Results show that the IPSO can accurately and efficiently determine the minimum safety factor in slope probability analysis considering the spatially variable soils. The IPSO method provides a promising tool for an efficient slope probability analysis. [ABSTRACT FROM AUTHOR]

The converter is a complex, high temperature, high pressure reactor with limited internal moitoring. At present, data‐driven models mainly focus on the prediction differences between algorithms, and there is relatively little analysis of the impact of different hyperparameters on prediction accuracy. Taking a 120 t converter in a Chinese steel plant as an example, this paper explores the application of particle swarm optimization‐back propagation neural network (PSO‐BP) in converter temperature prediction. First, the Pauta criterion or Box plot method was used to preprocess the data by prescreening. Subsequently, the influence of the activation function, learning rate, and number of hidden layer nodes of BP on the prediction accuracy of the endpoint temperature were explored. Then we investigated the influence of PSO parameters on the optimal result of BP initial value. Comparing the temperature prediction hit rate before and after optimization, the BP model has hit rates of 63.64%, 79.22%, and 87.45% within ±10, ±15, and ±20 °C, respectively, and the PSO‐BP model has hit rates of 68.40%, 84.85%, and 94.81%, respectively. In comparison, PSO‐BP extracts data features more accurately, has higher stability, and has better accuracy in predicting the endpoint temperature of the converter. [ABSTRACT FROM AUTHOR]

This document is a list of references to research papers and articles that focus on machining processes, specifically the machining of superalloy Inconel 718. The papers cover a range of topics including tool wear reduction, surface integrity evaluation, optimization techniques, and prediction models using artificial intelligence and machine learning. The research explores different lubrication techniques, nanofluid additives, and cutting parameters to improve the machinability of Inconel 718. The papers utilize various methodologies such as neural networks, fuzzy logic, response surface methodology, and genetic algorithms to optimize machining parameters and predict tool wear, surface roughness, and material removal rate. [Extracted from the article]

Healthcare stands out as a critical domain profoundly impacted by Internet of Things (IoT) technology, generating vast data from sensing devices as IoT applications expand. Addressing security challenges is paramount for a successful IoT healthcare framework, with blockchain technology offering a decentralized structure for robust data protection and secure data exchange within multi-node IoT networks. The research introduces a secure IoT healthcare diagnostic model empowered by deep neural networks, emphasizing encryption, safe transactions, and healthcare diagnostics as key components. Notably, the model incorporates innovative techniques like the orthogonal particle swarm optimization algorithm for sharing medical images and a neighborhood indexing sequence method for hash value encryption. The development of an optimized deep neural network-based classification model for illnesses, validated through extensive trials, demonstrates superior performance metrics compared to existing decision-making techniques, with significant improvements in f-Measure (96.25%), sensitivity (93.26%), specificity (94.26%), and accuracy (93.26%). This study's scientific contribution lies in its innovative approach to securing IoT-healthcare diagnosis models, validated performance enhancements using real-world datasets, and insightful recommendations for future research directions, fostering advancements in healthcare technology for enhanced patient care and system efficiency. [ABSTRACT FROM AUTHOR]

A parametric Adaptive Model Predictive Controller (AMPC) based on Particle Swarm Optimization-Back Propagation (PSO-BP) neural network has been developed in this paper, the primary focus is on improving the trajectory tracking performance of autonomous vehicles under varying road conditions. The PSO-BP neural network is employed for real-time adjustment of the controller's predictive horizon and sampling time. A vehicle dynamics model is established and an improved tracking control algorithm involving road curvature feedforward is proposed. In the design of AMPC, the real-time update of tire lateral stiffness is achieved through the adoption of the Recursive Least Squares (RLS) method, ensuring the precision of trajectory tracking for the vehicle under varying operating conditions. The simulation platform, which combines Carsim and Simulink, was employed for validating the proposed approach. The findings reveal that the proposed controller can promptly adjust the predictive horizon and sampling time according to the vehicle's state. Through the employed estimation strategy, real-time adjustments of tire lateral stiffness are achieved, allowing for dynamic alterations of vehicle speed and front wheel angle in response to road curvature. As a result, this approach significantly enhances control accuracy and lateral steering stability, especially in large curvature conditions. [ABSTRACT FROM AUTHOR]

This paper introduces a comprehensive three-step framework for fault classification in underground cable systems. The first step involves the implementation of the Cumulative Sum (CUSUM) technique to detect the fault instances, which will help in precisely tracking the affected portions. The second step focuses on parameter estimation techniques, followed by the third step, which incorporates classification techniques. The study employs a range of evolutionary optimization algorithms, including Ant Colony Optimization, Bacteria Foraging Optimization, Simulated Annealing, Genetic Algorithm, and Particle Swarm Optimization. These algorithms are effectively employed to track and estimate parameters like amplitude, phase, frequency, and damping factor associated with various types of permanent faults, such as L-G fault, L-L fault, L-L-G fault, and L-L-L-G fault generated in the underground cable. The optimized parameters extracted through these algorithms are utilized as features within a Support Vector Classifier for fault classification. The overall accuracy of the classifier using these features is reported to be 0.944, which is quite high and indicates a strong performance in classifying faults. The study includes a brief comparison of the performance of these bio-inspired algorithms. The effectiveness of the tracking algorithms is validated through the use of laboratory-tested current signals. In addition, the signals are subjected to varying signal-to-noise ratios to evaluate the robustness of the tracking algorithm. A comparative analysis is performed to estimate the accurate parameters and highlights the significant tracking ability of the Particle Swarm Optimization (PSO) algorithm, which outperforms other algorithms.The Root Mean Squared Percentage Error (RMSPE) for the L-G fault in PSO is 0.3082, showing superior performance compared to other algorithms. [ABSTRACT FROM AUTHOR]

With the advancement of Industry 4.0, Time-Sensitive Networking (TSN) has become essential for ensuring prompt and reliable data transmission. As an augmentation of Ethernet, TSN aims to supply services capable of low latency, minimal jitter, and low packet loss for urgent data in decentralized, user-oriented networks. Efficient detection techniques are integral to TSN for swiftly determining the practicability of network configurations, as existing schedulability analysis proves insufficient. This paper delves into the potential of backpropagation neural networks (BPNN) in schedulability analysis efficiency. We optimize BPNN using spearman correlation feature selection combined with a voting ensemble method and Particle Swarm Optimization (PSO), forming two models: Spearman-Vote-BPNN and Spearman-PSO-BPNN. Testing on 5,000 network configurations in computer simulations, both models demonstrated high generalization accuracy, around 97.4%. Spearman-Vote-BPNN achieved the fastest training speed at 0.63 s and an accuracy of 98.2%. Meanwhile, Spearman-PSO-BPNN showed the highest accuracy (98.5%) with the quickest detection speed (5.6 ms). The outcomes of this research significantly advance the efficacy and precision of TSN network configuration detection and establish a formidable groundwork for future scholarly pursuits in this area. [ABSTRACT FROM AUTHOR]

Efficient energy conservation to maximize the network lifetime is always the most critical challenge in wireless sensor networks due to their energy-constrained nodes and harsh working environments. Clustering routing is considered the most popular method to lessen energy utilization at present. In this paper, a fuzzy logic and particle swarm optimization-based clustering routing protocol called PFCRE is proposed to improve energy efficiency, mitigate the energy holes and enhance the network lifetime as well. The proposed PFCRE considers energy minimum and balance to form clusters by using an improved particle swarm optimization algorithm. Moreover, a fuzzy inference system is employed to find the optimal route for each CH, which considers effective parameters including residual energy, distance to base station and number of being selected as relay so as to not only minimize energy consumption but also balance traffic load. Especially, the rules of the fuzzy inference system are tuned by another particle swarm optimization algorithm. Furthermore, an adaptive maintenance mechanism is used to organize the clusters instead of periodic clustering to further diminish computation and message overheads. The performance of PFCRE is evaluated by extensive experiments, and the results indicate that it outperforms IBRE-LEACH, EAUCA, DAPFL, IPSOGWO along with FMSFLA in terms of network lifetime, throughput, energy consumption, and standard deviation of CH's traffic load. [ABSTRACT FROM AUTHOR]

Meta-heuristic algorithms, due to their high search speed and strong generalization ability, are frequently applied in programs mainly to discover the corresponding optimal strategy for any problem in view of their defined rules. After years of collision evolution, they have been continuously used to solve the complex, unordered and diverse optimization problems and improve efficiency. Aiming at the problems of low convergence accuracy and easy to fall into local optima of the traditional Harris hawks optimization algorithm, a compound improved Harris Hawks Optimization algorithm (CIHHO) is proposed. Firstly, the early circling exploration and later attack exploitation phase of the dynamic adjustment algorithm for environmental factors is introduced to regulate the energy of Harris hawks; Secondly, the concept of Versoria function is introduced to modify the random jump strength and raise the data grabbing ability of local space; Introducing the Levy flight function to adjust the factor and reduce the disturbance impact of Levy flight is beneficial for getting rid of the local space after entering the exploitation phase, and introducing random white noise to reduce step size and improve algorithm accuracy. Taking CEC 2017 test function suite set as the core, the performance of CIHHO algorithm is analyzed. Firstly, the performance of CIHHO algorithm is compared with HHO, HHO_JOS, LHHO, LMHHO and NCHHO. Secondly, the performance of unimodal function, multimodal function, mixed function and compound function is compared with other 7 improved algorithms. Finally, ablation experiments are carried out. The convergence value of the iterative curve obtained is more quantitative than the improved algorithm, The generality of the improved CIHHO algorithm in solving multiple optimization problems with different dimensions is verified. Further applying the CIHHO algorithm to three different engineering experiments, the minimum cost calculation results directly demonstrate that the CIHHO algorithm obtained has certain advantages in dealing with search space problems. [ABSTRACT FROM AUTHOR]

Recent years have seen an exponential rise in data produced by Internet of Things (IoT) applications. Cloud servers were not designed for such extensive data, leading to challenges like increased makespan, cost, bandwidth, energy consumption, and network latency. To address these, the cloud–fog environment has emerged as an extension to cloud servers, offering services closer to IoT devices. Scheduling workflow applications to optimize multiple conflicting objectives in cloud fog is an NP-hard problem. Particle Swarm Optimization (PSO) is a good choice for multi-objective solutions due to its simplicity and rapid convergence. However, it has shortcomings like premature convergence and stagnation. To address these challenges, we formalize a theoretical background for scheduling workflow applications in the cloud–fog environment with multiple conflicting objectives. Subsequently, we propose an adaptive particle swarm optimization (APSO) algorithm with novel enhancements, including an S-shaped sigmoid function to dynamically decrease inertia weight and a linear updating mechanism for cognitive factors. Their integration in cloud–fog environments has not been previously explored. This novel application addresses unique challenges of workflow scheduling in cloud–fog systems, such as heterogeneous resource management, energy consumption, and increased cost. The effectiveness of APSO is evaluated using a real-world scientific workflow in a simulated cloud–fog environment and compared with four meta-heuristics. Our proposed workflow scheduling significantly reduces makespan and energy consumption without compromising overall cost compared to other meta-heuristics. [ABSTRACT FROM AUTHOR]

With the development of artificial intelligence and unmanned technology, unmanned vehicles have been utilized in a variety of situations which may be hazardous to human beings, even in real battle fields. An intelligent unmanned vehicle can be aware of surrounding situations and make appropriate responding decisions. For this purpose, this paper applies Multi-agent Deep Deterministic Policy Gradient (MADDPG) algorithm for vehicle's of situation awareness and decision making, inside which a Fast Particle Swarm Optimization (FPSO) algorithm is proposed to calculate the optimal vehicle attitude and position; therefore, an improved deep reinforcement learning algorithm FPSO-MADPPG is formed. A specific advantage function is designed for the FPSO portion, which considers angle, distance, outflanking encirclement. A dedicated reward is designed for the MADPPG portion, which considers key factors like angle, distance, and damage. Finally, FPSO-MADPPG is then used in a combat game to operate unmanned tanks. Simulation results show that our method not only can obtain higher winning rate, but also higher reward and faster convergence than DDPG and MADPPG algorithms. [ABSTRACT FROM AUTHOR]

In the application of decision-making systems in the field of healthcare, with advancing technology, the outputs of direct analysis devices have become usable. As the dataset becomes richer, the accuracy of models also increases. The parameters of the dataset used in this study contain raw data closer to real conditions in terms of both quantity and quality compared to previous studies. When examining the models established to identify liver diseases, it is observed that besides the model performance, the performance of experts also affects due to the use of parameters containing expert opinions. The data set used in this study did not include subjective data other than class values, and only expert opinions were used in training the model. Thus, the model performance will be less dependent on the dataset compared to other studies. Real-life data has been worked on with different models to see which structures are better. Artificial neural networks and particle swarm optimization methods were trained to solve the classification problem and results were analyzed by testing with training and test data in the study. [ABSTRACT FROM AUTHOR]

Calculating the composition of the combustion products serves as the starting point for the high-area ratio (HAR) rocket nozzle. The HAR rocket nozzle finds application in next-generation hypersonic vehicles and missiles. The gas dynamics, gas radiation, and turbulence-chemistry interactions (TCI) play a crucial role in simulations of hypersonic turbulent reactive flows through a rocket nozzle. The interaction of turbulence and chemistry leads to random species mixing and enhanced heat transfer. The k-omega shear stress transport (SST) model is employed to calculate the average flow fields. The eddy dissipation concept (EDC) with reduced chemistry is applied to capture the TCI in the nozzle. The spectral properties of H 2 O are calculated using the full spectrum k -distribution (FSK) model in conjunction with the first-order spherical harmonics method. The mass fractions of combustion products obtained from Particle Swarm Optimization (PSO) and Monte Carlo (MC) methods agree well with the Chemical Equilibrium with Applications (CEA) code. The flow fields obtained with the current solver are validated with the published experimental data. A significant rise and fall of 7–8% have been observed in the centerline flow properties when not including the TCI models in the flow solver. The centerline flow fields obtained with different discretization schemes are in good agreement. The radiative heat flux from the H 2 O species is more dominant than the convective. • Calculate the chemical equilibrium composition of product species for the H 2 –O 2 combustion using the Monte Carlo and PSO methods. • Modeling of the hypersonic turbulent reacting flow of a high-area-ratio (HAR) rocket nozzle in OpenFOAM. • Developed and implemented a spectral model to calculate the radiative properties of H 2 O gas in OpenFOAM. • Effects of turbulence-chemistry interactions (TCI) on the flow fields are analyzed. • Radiative and convective heat transfers are more significant near the throat area. [ABSTRACT FROM AUTHOR]

In many countries, residential energy consumption constitutes a significant portion of total energy usage, making it a crucial focus for power systems and urban planners. Addressing energy consumption in buildings involves two primary facets: accurately predicting and optimizing load demand. This research aims to address the challenges of load demand prediction in the context of building energy consumption. It introduces innovative approaches, including optimized support vector regression (SVR), temperature factor consideration, and the integration of Trombe walls (TW), ultimately contributing to more accurate load demand forecasts and enhanced energy efficiency. To enhance the precision of load demand prediction, we introduce a novel variable that quantifies deviation from the ideal temperature; a key factor in energy usage. This innovative temperature factor plays a pivotal role in forecasting the load demand more accurately. Leveraging this novel approach, we employ an optimized (SVR) that considers weather conditions. The parameters of a radial basis function kernel-based support vector regression (RBF-SVR) method are fine-tuned through an improved particle swarm optimization algorithm (IPSO). In addition, installed TW prove highly effective in reducing building energy consumption by harnessing and redistributing heat, consequently improving the load demand profile. We employ mathematical models to analyze the impact of Trombe walls on predicted load demands, demonstrating that our proposed method yields low mean absolute percentage error (MAPE) when applied to sample buildings. The findings reveal that our method significantly enhances the accuracy of energy usage prediction, while the installation of Trombe walls results in a remarkable reduction of load demand – by 19.32% in winter and 16.24% in summer, thereby promoting energy efficiency and sustainability. [ABSTRACT FROM AUTHOR]

With the increase of the complexity of space environment and the improvement of satellite maneuverability, the satellite maneuver game has become the focus of space research. In view of the need for pre-observation during debris removal or on-orbit maintenance missions, a scenario of observation and counter-observation similar to the pursuit-evasion game is proposed. In this paper, the impulsive observation and counter-observation game (OCOG) of two satellites is comprehensively investigated using a multi-objective optimization method. A sequential decision impulsive maneuver model is constructed and the impulsive OCOG is transformed into a bilateral optimization problem in terms of multiple constraints such as maneuverability, illumination angle, and fuel consumption, etc. To determine the optimal impulsive maneuvers for both satellites, the ring topology multi-objective particle swarm optimization (RTMOPSO) is designed. This novel algorithm uses adjacent particles to form multiple small populations to make the population converge in multiple directions during the optimization process, avoiding the single convergence of the population. Compared with non-dominated sorting genetic algorithm II (NSGA-II) and self-organized speciation based multi-objective particle swarm optimization (SSMOPSO) in the OCOG scenario, proposed method always has superiority in the game. Additional simulation is conducted and shows that the proposed algorithm is also applied for the case of non-maneuvering satellites. This research provides an effective maneuver strategy for future space game. [ABSTRACT FROM AUTHOR]

Streamflow estimation is necessary to develop sustainable water management strategies that balance the needs of various water users while protecting the ecological health of the watershed. This study presents a comprehensive analysis of river flow data in Turkey's Meriç basin using long-term daily data spanning the years 2001–2011. Within the scope of forecasting of daily river flows, 80% of dataset was used for training stage and the 20% of dataset was used for testing. The performance of four different models, including Extreme Gradient Boosting (XGBoost) benchmark model, Linear Regression, Long Short-Term Memory Network (LSTM), and proposed Particle Swarm Optimization (PSO)—XGBoost hybrid model, was evaluated using several statistical evaluation criteria such as RMSE, MAPE, MAE, SD, NSE, KGE, and model success was assessed based on determination coefficient (R2) values. The forecasting results of the models were evaluated with statistical metrics. The proposed PSO-XGBoost model outperformed all models with R2 values of 0.7460 at the Babaeski FMS station, 0.9582 at the Meriç FMS station, and 0.8116 at the Hayrabolu FMS station, respectively. It has been found that when the parameters of the XGBoost model are optimized with the meta-heuristic PSO algorithm, the daily flow prediction accuracy is significantly increased in the Meriç River basin, which has a pluviozonal River regime. The results demonstrate that the proposed hybrid model produces precise and reliable estimations for daily river flow analysis in the Meriç basin. The findings derived from the proposed model demonstrate its promising potential for water resource management and decision-making in the region. [ABSTRACT FROM AUTHOR]

Uncertainty analysis is crucial before hydrological simulation to address model vulnerability in snow-covered mountainous river basins, ensuring effective soil conservation and water resource management planning. The present study is conducted on Sutlej River Basin, which is located in Western Himalayas and originated from Manasarovar Lake at Tibetans platue in China. The Soil and Water Assessment Tool (SWAT) model is calibrated; the parameter sensitivity and uncertainty of the SWAT were quantified using four optimization methods such as (i) sequential uncertainty fitting (SUFI-2), (ii) particle swarm optimization (PSO), (iii) generalized likelihood uncertainty estimation (GLUE), and (iv) parameter solution (ParaSol). The model is performed with calibration period (1982–2000) and validation period (2001–2013), using monthly observed streamflow at the Bhakra gauging station. The statistical performance criteria such as Nash–Sutcliffe efficiency coefficient (NSE) and coefficient of determination (R2), values showing all four models, performed very well in the model calibration and validation. During the calibration period, SUFI-2 and ParaSol algorithms show higher performance with NSE and R2 values of 0.82 and 0.83. In the validation period, SUFI-2 shows high accuracy with NSE and R2 values of 0.77 and 0.78, while ParaSol also performed well with NSE and R2 values of 0.71 and 0.76. These results highlighted the superior performance of SUFI-2 and ParaSol compared to the other two (PSO, GLUE) techniques. Further, the values of p-factor and r-factor reveal that ParaSol method performed poor during both the calibration period (p-factor: 0.25, r-factor: 0.32) and the validation period (p-factor: 0.26, r-factor: 0.38). These results suggest that while ParaSol was effective in optimizing parameter sets, it fails in providing accurate estimates of uncertainty during both model calibration and validation, whereas other three methods perform very well in the model uncertainty analysis. This study fills a significant research gap by offering guidance on adjusting sensitive parameters, reducing uncertainty in streamflow simulation, and addressing the challenges specific to hydrological modeling in mountainous river basins, which is different from the previous studies conducted in plain river basins. [ABSTRACT FROM AUTHOR]

Internet Protocol version 6 (IPv6) is the most recent iteration of IP, designed to accommodate hundreds of thousands of devices with unique IP addresses. IPv6 introduces new features, such as the Neighbor Discovery Protocol (NDP) and Address Auto-configuration Scheme. For its effective operation, IPv6 relies on several protocols, including ICMPv6, which carries significant responsibilities. Similar to IPv4, IPv6 is susceptible to various attacks, including newer types like DDoS attacks executed via ICMPv6 messages, posing serious security and financial threats. Consequently, an Intrusion Detection System (IDS) is essential to safeguard against these attacks. IDS continuously evolve to incorporate features that can accurately detect such threats. However, feature selection strategies, particularly bio-inspired algorithms, often yield incorrect subsets of features. During machine learning processes, these inaccuracies impede the detection accuracy of DDoS attacks using ICMPv6. Many Optimization Search Algorithms become trapped in local minima and fail to consider multi-objective approaches, resulting in suboptimal feature selection. To address this, optimizing a bio-inspired algorithm within an IPv6 network has been proposed. Specifically, hybridizing the MFPA algorithm with the PSO algorithm is suggested to enhance detection accuracy. The selected features are used to train the dataset with a Support Vector Machine (SVM) classifier. The proposed approach is evaluated using the ICMPv6 dataset on various attacks, demonstrating superior classification accuracy of 97.99 %. It also reduced the number of features from 19 to 8, showcasing its efficiency. [ABSTRACT FROM AUTHOR]

Fraud detection in banking systems is crucial for financial stability, customer protection, reputation management, and regulatory compliance. Machine Learning (ML) is vital in improving data analysis, real-time fraud detection, and developing fraud techniques by learning from data and adjusting detection strategies accordingly. Feature Selection (FS) is essential for enhancing fraud detection through ML to achieve optimal model accuracy. This is because it helps to eliminate the negative impact of redundant and irrelevant attributes. To enhance the accuracy of the given dataset, the researchers utilized multiple methods to determine the most fitting features. However, it is important to note that when implementing these methods on datasets with larger feature sizes, they may encounter issues with local optimality. Despite this, the researchers continue to work on improving the effectiveness of these methods. This study presents an effective methodology based on the Brown-Bear Optimization (BBO) algorithm to enhance the capacity to accurately identify financial CCF transactions by recognizing pertinent features. BBO has balanced capabilities to reduce dimensionality while enhancing classification accuracy. It is improved by adjusting the positions randomly to enhance exploration and exploitation capabilities, and then it is cloned into a binary variant named Binary BBOA (BBBOA). The Support Vector Machine (SVM), k-nearest Neighbor (k -NN), and Xgb-tree are the ML classifiers used with the suggested methodology. On the Australian credit dataset, the proposed methodology is compared with the basic BBOA and ten current optimizers, such as Binary African Vultures Optimization (BAVO), Binary Salp Swarm Algorithm (BSSA), Binary Atom Search Optimization (BASO), Binary Henry Gas Solubility Optimization (BHGSO), Binary Harris Hawks Optimization (BHHO), Binary Bat Algorithm (BBA), Binary Particle Swarm Optimization (BPSO), Binary Grasshopper Optimization Algorithm (BGOA), and Binary Sailfish Optimizer (BSFO). Regarding Wilcoxon's rank-sum test (α = 0. 05), the superiority and effective consequence of the presented methodology are clear on the utilized dataset and got an accuracy of classification up to 91% in the utilized dataset combined with an attribute reduction length down to 67%. The proposed methodology is further validated using 10 benchmark datasets and outperformed its competitors in most utilized datasets regarding different performance measures. In the end, the proposed methodology is further validated using ten benchmark datasets from the UCI repository. It outperformed its competitors in most of the utilized datasets regarding different performance measures. [ABSTRACT FROM AUTHOR]

Improvement of particle swarm optimization (PSO) is relevant to solving the inherent local optima and premature convergence problem of the PSO. In this paper, a novel improvement of the particle swarm optimization is provided to curb the problem of the classical PSO. The proposed improvement modifies the updating velocity function of the PSO, and it uses a local best murmuration particle which is found using the k-means clustering technique. In this contribution, each particle moves towards the global best position by not only using the personal best and global best, but particles are modelled to move in murmuration towards the global best using the personal best, global best and a local best particle known as the local best murmuration particle. The improved model was tested against the traditional PSO and two other variants of the PSO and genetic algorithm (GA) using 18 benchmark test functions. The proposed improvement demonstrated superior exploration abilities by achieving the best optimum values in 15 out of 18 functions, particularly in the multimodal functions, where it achieved the best optimum value in all 6 cases. It also achieved the best worst-case values in 12 out of 18 functions, especially in the variable-dimension functions, where other algorithms showed significant escalation, indicating the proposed improvement's reliability and robustness. In terms of convergence, the proposed improvement exhibited the best convergence rate in all 18 functions. These findings highlight the impressive ability of the proposed improvement to converge swiftly without compromising accuracy. [ABSTRACT FROM AUTHOR]

Copyright of Light Industry Machinery is the property of Light Industry Machinery Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Shanghai Jiaotong University (Science) is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Accurate short-term photovoltaic (PV) power prediction helps to improve the economic efficiency of power stations and is of great significance to the arrangement of grid scheduling plans. In order to improve the accuracy of PV power prediction further, this paper proposes a data cleaning method combining density clustering and support vector machine. It constructs a short-term PV power prediction model based on particle swarm optimization (PSO) optimized Long Short-Term Memory (LSTM) network. Firstly, the input features are determined using Pearson's correlation coefficient. The feature information is clustered using density-based spatial clustering of applications with noise (DBSCAN), and then, the data in each cluster is cleaned using support vector machines (SVM). Secondly, the PSO is used to optimize the hyperparameters of the LSTM network to obtain the optimal network structure. Finally, different power prediction models are established, and the PV power generation prediction results are obtained. The results show that the data methods used are effective and that the PSO-LSTM power prediction model based on DBSCAN-SVM data cleaning outperforms existing typical methods, especially under non-sunny days, and that the model effectively improves the accuracy of short-term PV power prediction. [ABSTRACT FROM AUTHOR]

The sample data for reinforcement learning algorithms often exhibit sparsity and instability, making the training results susceptible to falling into local optima. Mini-Max-Multi-agent Deep Deterministic Policy Gradient (M3DDPG) algorithm is a multi-agent reinforcement learning algorithm, which introduces the minimax theorem into Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm. It also has unstable convergence caused by sparse sample data and randomization. However, the Particle Swarm Optimisation (PSO) algorithm, unlike traditional reinforcement learning methods, involves the construction of independent populations of policy networks to generate sample data, followed by training the reinforcement learning algorithm. PSO optimizes and updates the policy population based on a fitness function, aiming to enhance the efficiency and convergence speed of the algorithm in learning from the sample data. In order to address the multi-agent pursuit-evasion problem, we propose the PSO-M3DDPG algorithm, which combines the PSO algorithm with the M3DDPG algorithm. Through experimental simulations, the improved algorithm demonstrates superior training results and faster convergence speeds, thus validating its effectiveness. [ABSTRACT FROM AUTHOR]

Aiming at the electric vehicle charging pile control system has the characteristics of multi-parameter, strong coupling and non-linearity, and the existing traditional PID control and fuzzy PID control methods have the problems of slow charging speed, poor control performance and anti-interference ability, as well as seriously affecting the service life of the battery, this paper designs a kind of improved particle swarm algorithm to optimize the PID controller of the charging control system for electric vehicle charging piles, and utilizes the improved particle swarm algorithm to Adaptive and precise adjustment of proportional, integral and differential parameters, so that the system quickly reaches stability, so as to improve the accuracy of the system control output current or voltage. Simulation results show that the optimized system response speed of the improved particle swarm algorithm is improved by 3.077 s, the overshooting amount is reduced by 1.01%, and there is no oscillation, which has strong adaptability and anti-interference ability, and can significantly improve the control accuracy and charging efficiency of the charging pile control system. [ABSTRACT FROM AUTHOR]

Engineering projects must meet quality and schedule requirements during construction. This is a typical multi-objective problem and a difficult point in the management of engineering enterprises. To address these issues, a research study proposes an intelligent multi-objective optimisation technique. First, analyse the optimisation objectives of the enterprise in the context of digitalisation. Then, construct a multi-objective cost optimisation model for engineering enterprises. Second, the Multi-Objective Particle Swarm Optimisation (MOPSO) algorithm is introduced to solve multi- objective problems. To improve the multi-objective optimisation effect of the model, the inertia weight parameters and particle learning behaviour are optimised and adjusted, as the model is prone to getting stuck in local optima. In the performance test of the algorithm model, the optimised MOPSO model can accurately search for the minimum value of 0 at the position (0, 0) under the Rastrig in function, and at the same time, the number of iteration convergence is the least. The GA, ACOM, and traditional MOPSO models have more iterative convergence times, and the optimisation results are 0.10, 0.15, and 0.14, respectively. It can be seen that the performance of the optimised MOPSO model is better. In the specific example analysis, using the optimised MOPSO solution, the project cost was reduced from 31 million yuan in the contract to 30.52 million yuan, and the construction period was shortened from 588 days to 540 days, and met the environmental protection and quality requirements. The research content can provide important decision support for engineering project managers. [ABSTRACT FROM AUTHOR]

Phishing could be considered a worldwide problem; undoubtedly, the number of illegal websites has increased quickly. Besides that, phishing is a security attack that has several purposes, such as personal information, credit card numbers, and other information. Phishing websites look like legitimate ones, which makes it difficult to differentiate between them. There are several techniques and methods for phishing detection. The authors present two machine-learning algorithms for phishing detection. Besides that, the algorithms employed are XGBoost and random forest. Also, this study uses particle swarm optimization (PSO) and grey wolf optimizer (GWO), which are considered metaheuristic algorithms. This research used the Mendeley dataset. Precision, recall, and accuracy are used as the evaluation criteria. Experiments are done with all features (111) and with features selected by PSO and GWO. Finally, experiments are done with the most common features selected by both PSO and GWO (PSO n GWO). The result demonstrates that system performance is highly acceptable, with an F-measure of 91.4%. [ABSTRACT FROM AUTHOR]

The surge in adoption of electric vehicles (EVs) within the transportation sector can be attributed to the growing interest in sustainable transportation initiatives. It is imperative to position electric vehicle charging stations (EVCS) strategically and distribute generations (DGs) to mitigate the effects of electric vehicle loads. This research employs the whale optimization algorithm (WOA) to optimize the placement of EVCS and DGs alongside network reconfiguration. The backward-forward sweep (BFS) power flow technique is utilized to compute load flow under varying load conditions. The primary objective of this investigation is to minimize power losses and enhance the voltage profile within the system. The proposed approach was tested on IEEE-33 and 69 bus systems and compared with particle swarm optimization (PSO) and genetic algorithm (GA) techniques. The simulation outcomes affirm the effectiveness of whale optimization algorithm in determining that integrating 3 EVCS with 3 DGs yields optimal outcomes following network reconfiguration, resulting in a 56.22% decrease in power losses for the IEEE-33 bus system and a 76.13% reduction for the IEEE-69 bus system. The simulation results indicate that the proposed approach enhances system performance across all metrics, showcasing the superior performance of WOA compared to PSO and GA in accomplishing set objectives. [ABSTRACT FROM AUTHOR]

The impact of drought builds on all three fronts of economy, environment, and society is devastating. Predicting its arrival and duration is highly important to arrange any sort of mitigation plans. The association of detailed relationship between multiple variables makes drought prediction a highly complex task. Especially influence of global warming, polar sea extent variations and their influence on overall ocean temperature have altered the seasonal rainfall behaviors all over the world. In the midst of it, predictions centered on the history of rainfall levels become inaccurate. The proposed system is an optimized deep learning prediction model integrating indigenous knowledge (IK) is proposed to predict the drought. IK expressed in human language is translated using fuzzy function and fed to an improved Long Short Term Memory (LSTM) model. The LSTM model hyperparameters are optimized using a hybrid of Particle Swarm Optimization (PSO) with firefly to produce the meta-heuristics algorithm which will provide the best performance in presence of integration of IK features into modern meteorological features which solves the problem of local minima in LSTM hyperparameter optimization. The performance of the proposed results were tested compared with the meteorological information gathered by the Karnataka Natural Disaster Monitoring Centre (KNDMC) for the district named Chitradurga of the Karnataka state in India. The proposed system which is Indigenous Knowledge merged along the cross model attention network can produce at least 1.4% higher Nash-Sutcliffe model efficiency coefficient (NSE) and 30% lower Mean Absolute Error (MAE) in the prediction of Standard Precipitation Index (SPI) compared to Convolution Neural Networks (CNN) and LSTM based time series prediction models. [ABSTRACT FROM AUTHOR]

The Mixed Radial Basis Function Neural Network (MRBFNN) is an artificial neural network that employs Radial Basis Functions (RBFs) as activation functions in its hidden layer. The number of neurons in the hidden layer and the choice of RBF functions used in these neurons significantly affect the convergence of MRBFNN learning algorithms and impact the overall performance of neural networks. This article presents a nonlinear optimization model and an algorithm to select an appropriate architecture and learning strategy for MRBFNN. To approximate the solution of our model, we utilized an algorithm based on Particle Swarm Optimization (PSO) techniques. We will apply our approach in Medical Diseases Diagnosis (MDD). The numerical results obtained demonstrate the effectiveness of the proposed theoretical approach and underscore the advantages of the new modeling methodology. [ABSTRACT FROM AUTHOR]

In addressing the critical challenge of developing sustainable energy solutions for electric vehicle (EV) battery charging, this study introduces an innovative direct current (DC) microgrid system optimized for areas with high solar irradiance, such as Ain El Ibel, Djelfa. The research confronts two primary difficulties: maximizing solar energy utilization in the microgrid system and ensuring system stability and response accuracy for reliable EV charging. To tackle these challenges, the study presents two original achievements. Firstly, it develops a neural network-enhanced Maximum Power Point Tracking (MPPT) controller, which is further optimized with Particle Swarm Optimization (PSO) to increase the efficiency of solar energy capture. Secondly, it refines the system's reliability through the advanced calibration of a Fractional Order Proportional-Integral (FOPI) controller using the Grey Wolf Optimization (GWO) technique, marking a notable improvement in microgrid system stability and response accuracy. The integration of a solar panel array, battery storage, and a supercapacitor, coupled with these advanced optimization techniques, exemplifies a significant leap forward in enhancing efficiency and reliability of EV battery charging through renewable energy sources. Comprehensive simulation and evaluation of the system underscore its superiority over conventional methods, demonstrating the effectiveness of combining neural network-based optimization with PSO and GWO. This breakthrough not only advances the field of renewable energy, particularly for solar-powered EV charging stations, but also aligns with global efforts towards sustainable transportation solutions. [ABSTRACT FROM AUTHOR]

In the 21st century, the software industry has achieved great development, and the development complexity and volume of software projects are also continuously increasing. Therefore, the design of software engineering supervision network plans is becoming increasingly important. The Pareto optimal solution set construction method, global extremum selection method, and fitness value determination method of the multi-objective particle swarm optimization algorithm have been improved in response to the poor optimization performance and poor convergence and distribution of optimal solutions in existing network planning algorithms. However, traditional methods only optimize one or two objectives of network planning, resulting in inconsistency with actual engineering. Thus, this study establishes a multiobjective model based on resources, duration, cost, and quality for comprehensive optimization. Based on the results, the Pareto optimal solution curves obtained by the proposed algorithm on three classic test functions were consistent with the actual theoretical Pareto frontier curves. The proposed method was applied to engineering project examples. 10 solutions that met the schedule requirements were obtained. Most engineering projects had a quality of over 80%, which verified the practicality of the algorithm. The algorithm has achieved good results in optimizing engineering quality. Therefore, this model can consider various indicators such as resources and costs to obtain software engineering quality improvement plans. It has certain application potential. [ABSTRACT FROM AUTHOR]