Search

Demand for perishable food is sensitive to product prices and is affected by the prices of similar or alternative products. While brand loyalty influences the demand for products, determining a reasonable price requires a precise pricing strategy. In this paper, a pricing model for perishable food is presented in which the brand value of the product and the price of other manufacturers as competitors are considered. To this end, this study first predicts the price of competitors using a combination of optimized Neural Networks and presents an optimized model using a Genetic Algorithm. This algorithm combines a Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and a Genetic Algorithm (GA). The proposed model is then used to merge with a game-theory model for the pricing of perishable foods. In this game-theory model, pricing approaches are developed based on identified prices of competitors. In the coordination contract game-theory model, Multi Retailer- one Supplier and Price-sensitive demand of Perishable product are developed with and without quantity discount contract. Obtained results indicate that independent procurement provides retailers with higher profit, while lower profit will be presented when coordination is not considered. Also, with coordination, the ordering cycle increases, and the ordering frequency decrease. [ABSTRACT FROM AUTHOR]

In order to regulate work in process (WIP) to the desired value in the job shop production control system, capacity adjustment as an effective and efficient measure, which is typically achieved by flexible staffs and working time. In this paper, instead of traditional labour-oriented approaches, we consider a machinery-based capacity adjustment via reconfigurable machine tools (RMTs) to compensate for unpredictable events. To this end, we employ model predictive control (MPC) in combination with genetic algorithm (GA) to explicitly consider complex reconfiguration strategies and address the related integer assignment optimisation problems. To further reduce energy consumption and avoid frequent and unnecessary reconfigurations while keeping a certain level of performance, we adopt an event-triggered MPC scheme with the proposed 'Double-layer event-triggering conditions'. Through extensively illustrated simulations, we demonstrate the effectiveness and plug-and-play availability of the proposed method for a six-workstation four-product job shop system and compare it to a state-of-the-art method. [ABSTRACT FROM AUTHOR]

In this study, a realistic model of the respiratory tract obtained from CT medical images was used to solve the flow field and particle motion using the Eulerian–Lagrangian approach to obtain the maximum particle deposition in the bronchial tree for the main purpose of optimizing the performance of drug delivery devices. The effects of different parameters, including particle diameter, particle shape factor, and air velocity, on the airflow field and particle deposition pattern in different zones of the lung were investigated. In addition, a genetic algorithm was employed to obtain the maximum particle deposition in the bronchial tree and the effect of the aforementioned parameters on particle deposition. Reverse flow, vortex formation, and laryngeal jet all affect the airflow structure and particle deposition pattern. The mouth–throat region had the highest deposition fraction at various flow rates. A change in the deposition pattern with an increased deposition fraction in the throat was observed owing to the increased diameter and shape factor of the particles, resulting from the higher inertia and drag force, respectively. The particle deposition analysis showed that three parameters, shape factor, diameter, and velocity, are directly related to particle deposition, and the diameter is the most effective parameter for particle deposition, with an effect of 60% compared to the shape factor and velocity. Finally, the prediction of the genetic algorithm reported a maximum particle deposition in the bronchial tree of 17%, whereas, based on the numerical results, the maximum particle deposition was reported to be 16%. Therefore, there is a 1% difference between the prediction of the genetic algorithm and the numerical results, which indicates the high accuracy of the prediction of the genetic algorithm. [ABSTRACT FROM AUTHOR]

In the realm of analog integrated circuit (IC) design, due to the intricate nonlinear relationships between circuit performance metrics and design variables, as well as the complex interdependencies and trade‐offs between various performance criteria, it is difficult to determine the appropriate geometric width and length of the circuit components to meet all performance specifications. This difficulty makes the task of designing analog IC challenging. To address the challenge of analog IC design, this paper introduces a machine learning methodology—specifically employing the genetic algorithm (GA)—to automate the selection of circuit components' geometrical parameters, aiding the work of analog circuit designers in determining the appropriate dimensions for transistors within the charge‐pump circuit. The GA, implemented in Python and integrated with a script program written in the OCEAN language, synergistically collaborates in the GA‐OCEAN framework. The result, which ensures compliance with all specifications with remarkably low error margins, ranging as low as 0.03% and as high as 1.24%, highlights the proposed GA‐OCEAN framework's remarkable capacity to determine optimal dimensions for components inside the charge‐pump circuit. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

A significant advancement in wireless communication has occurred over the past couple of decades. Nowadays, people rely more on services offered by the Internet of Things, cloud computing, and big data analytics-based applications. Higher data rates, faster transmission/reception times, more coverage, and higher throughputs are all necessary for these emerging applications. 5G technology supports all these features. Antennas, one of the most crucial components of modern wireless gadgets, must be manufactured specifically to meet the market's growing demand for fast and intelligent goods. This study reviews various 5G antenna types in detail, categorizing them into two categories: conventional design approaches and machine learning-assisted optimization approaches, followed by a comparative study on various 5G antennas reported in publications. Machine learning (ML) is receiving a lot of emphasis because of its ability to identify optimal outcomes in several areas, and it is expected to be a key component of our future technology. ML is demonstrating an evident future in antenna design optimization by predicting antenna behavior and expediting optimization with accuracy and efficiency. The analysis of performance metrics used to evaluate 5G antenna performance is another focus of the assessment. Open research problems are also investigated, allowing researchers to fill up current research gaps. [ABSTRACT FROM AUTHOR]

With the rapid development of renewable energy sources such as wind and solar, the net load characteristics of power systems have undergone fundamental changes. This paper defines quantitative analysis indicators for net load characteristics and examines how these characteristics evolve as the proportion of wind and solar energy increases. By identifying inflection points in the system's adjustment capabilities, we categorize power systems into low, medium, and high renewable energy penetration. We then establish adjustment models that incorporate traditional coal power, hydropower, natural gas generation, adjustable loads, system interconnections, pumped-storage hydroelectricity, and new energy storage technologies. A genetic algorithm is employed to optimize and balance the net load curves under varying renewable energy proportions, analyzing the mechanism behind net load balance. A case study, based on real operational data from 2023 for a provincial power grid in western China, which is rich in renewable resources, conducts a quantitative analysis of the system's adjustment capability inflection point and net load balancing strategies. The results demonstrate that the proposed method effectively captures the evolution of the system's net load and reveals the mechanisms of net load balancing under different renewable energy penetration levels. [ABSTRACT FROM AUTHOR]

Low inertia poses a significant challenge to the widespread integration of photovoltaic (PV) systems into the grid, particularly affecting frequency stability. This paper addresses this challenge by proposing an advanced hybrid inertia (AHI) approach, characterized by the integration of real and virtual inertia, combined with the application of intelligent control techniques, to enhance the primary frequency response of a PV system. Internal inertia is provided by a synchronous generator (SG) acting as a compensator, while virtual inertia is generated through a real-time deloading strategy in the PV plant. The AHI is implemented on an isolated grid, utilizing various intelligent control techniques to improve frequency stability. The intelligent techniques employed include genetic algorithms (GA) and fuzzy logic controllers (FLC), which do not require mathematical modeling. This allows them to overcome the nonlinear dynamics of the PV plant and the uncertainties associated with climatic changes. These techniques are applied to the nonlinear components on the generator side, including the governor loop, DC-DC converter loop, and power reserve injection management loop. A frequency fluctuation scenario, induced by generating power perturbations in the proposed system, demonstrates and validates the improvement in frequency stability achieved by the HI and intelligent techniques. All tests are conducted using MATLAB Simulink. Various simulation results show a significant improvement in frequency stability through the incorporation of HI and intelligent control techniques. [ABSTRACT FROM AUTHOR]

Many text mining methods use statistical information as a text- and language-independent approach for sentiment analysis. However, text mining methods based on stochastic patterns and rules require many samples for training. On the other hand, deterministic and non-probabilistic methods are easier and faster to solve than other methods, but they are inefficient when dealing with Natural Language Processing (NLP) data. This research presents a novel hybrid solution based on two mathematical approaches combined with a heuristic approach to solve unbalanced pseudo-linear algebraic equation systems that can be used as a sentiment word scoring system. In its first step, the proposed solution uses two mathematical approaches to find two initial populations for a heuristic method. The heuristic solution solves a pseudo-linear NLP scoring scheme in a polarity detection method and determines the final scores. The proposed solution was validated using three scenarios on the SemEval-2013 competition, the ESWC dataset, and the Taboada dataset. The simulation results revealed that the proposed solution is comparable to the best state-of-the-art methods in polarity detection. [ABSTRACT FROM AUTHOR]

Accurate diagnosis and effective treatment of thyroid conditions, such as hypothyroidism and hyperthyroidism, are crucial due to their wide-ranging symptoms and consequences. However, conventional back-propagation neural networks have limitations, including slow convergence and susceptibility to local minima. To deal with these problems, the paper suggests an integrated strategy that includes back-propagation (BP) and genetic algorithms (GA). The suggested method uses evolutionary algorithms to investigate various weight combinations and back-propagation to modify weights in response to the discrepancy between expected and actual results. The study evaluated the method using three steps of experimentation, including network building, local search and optimization, and evaluation, on a real-world dataset of thyroid illnesses. The obtained results are very satisfying and promising, indicating that the MLP-GA/BP model is robust enough to detect and categorize thyroid disorders effectively and efficiently. This makes it a reliable diagnostic tool for medical practitioners, allowing them to effectively diagnose and treat patients with thyroid diseases. [ABSTRACT FROM AUTHOR]

A sustainable city is a smart city with a minimal impact on the environment, by incorporating technologies to reduce pollution. Traffic congestion which is a major concern contributes to global warming and climate change. Traffic forecasting projects future traffic patterns, using historical and current data to enhance traffic flow management. We propose a whole novel approach for predicting traffic congestion rate based on air quality data. We developed a new ensemble voting model based on Long Short Term Memory (LSTM) and Polynomial Regression (PolReg) models that use a new voting thresholded algorithm instead of the existing voting ones. The hyperparameters were optimized with the Genetic Agorithm, to overcome the non-stationarity of time series. A comparative study with the literature confirmed that our framework outperforms existing researches by keeping an absolute effectiveness according to learning curves, with Mean Absolute Error of 0.04, R-Squared of 0.93, and Root Mean Square Error (RMSE) of 0.05. [ABSTRACT FROM AUTHOR]

Summary: The existing single‐phase grounding (SPG) fault section location methods typically suffer from difficulty in feature selection, limited feeder terminal units (FTUs) configuration, and excessive dependence on communication, which weaken their generalization and robustness. To overcome these challenges, an SPG fault section location approach based on feature subset optimization is proposed. First, the relation between the position of FTU and its three‐phase current variation is analyzed, and its fault features are extracted to construct the candidate feature sets as feature subset optimization objects. Then, genetic algorithm and support vector machine (SVM) are combined to select the optimal feature subset with small dimensions and recognition error, which avoids the empirical errors of artificial feature selection. To reduce the cumulative errors, the SVM hyperparameters are simultaneously optimized. Finally, the SVM model is trained based on the optimal feature subset and hyperparameters. In the absence of zero‐sequence current measurement, three‐phase currents measured by FTU are locally processed to locate the fault section by the trained SVM. The experimental results verified the effectiveness and feasibility of the proposed method. [ABSTRACT FROM AUTHOR]

The article introduces a newer hybrid method (HAIS-GA) of optimizing and choosing the ideal machining parameters for cryogenic processing. It depends on two late methodologies genetic algorithm (GA) and artificial immune system (AIS), which are connected to numerous troublesome combinatorial streamlining issues with specific qualities and shortcomings. These developmental calculations are proposed to find the best arrangement of process factors for the clashing prerequisites in multi objective capacities. Hybrid model optimization also comes with challenges, such as selecting the right combination of techniques, tuning parameters, potential increases in complexity, and the need for expertise in multiple optimization methods. The key reason for this hybrid approach (HAIS-GA) is the improvement in the results that is achieved due to the characteristics of GA and AIS. Three test functions are employed to compare the outcomes in terms of these functions' ability to achieve the lowest value. Cryogenic processing is used to validate the optimised values that were obtained. The attained results showcase that HAIS-GA approach, in conclusion exhibits a more favourable minimal objective function within a reasonable duration. Due to the nature of Unrestricting to local optima, and it being self-adaptive HAIS-GA provides better result compared to GA and AIS. Based on the least value of the objective function and time for each method. [ABSTRACT FROM AUTHOR]

Vertical axis wind turbine (VAWT) has a rotating axis perpendicular to the wind direction. This type of wind turbine that is suitable for urban environments has low wind direction dependency and noise. In this research, a novel surrogated approach for optimizing a VAWT is proposed, used, tested, and verified, which is not reported in literature. The proposed method consisted of 3D computational fluid dynamics (CFD) analysis of wind flow through the wind turbine with FLUENT software by solving the unsteady turbulent equations. However, 3D CFD analysis was time and cost consuming to obtain the output result (power coefficient) from input values (airfoil chord length, pitch angle, and tip speed ratio as turbine design variables). Thus, artificial neural network (ANN) was applied to obtain weight functions to correlate FLUENT software inputs and outputs after learning process. Finally, genetic algorithm was used for maximizing the turbine power coefficient considering three defined design variables. The optimum value of power coefficient was improved to 0.244, and the optimum values of design variables for blade chord length, blade pitch angle, and blade tip speed ratio were 0.218, −0.453, and 1.24, respectively. This novel surrogated method reduced the computational time and cost of VAWT optimizing considerably. [ABSTRACT FROM AUTHOR]

Beam–slab structures account for 50–65% of a building's total dead load and contribute to 20% of the overall cost and CO2 emissions. Despite their importance, conventional beam–slab structural optimization methods often lack search efficiency and accuracy, making them less effective for practical engineering applications. Such limitations arise from the optimization problem involving a complex solution space, particularly when considering components' arrangement, dimensions, and load transfer paths simultaneously. To address the research gap, this study proposes a novel two-stage genetic algorithm, optimizing beam–slab layout in the first stage and component topological relationships and dimensions in the second stage. Numerical experiments on the prototype case indicate that the algorithm can generate results that meet engineering accuracy requirements within 100 iterations, outperforming comparable algorithms in both efficiency and accuracy. Additionally, this heuristic approach stands out for its independence from prior dataset training and its minimal parameter adjustment requirement, making it highly accessible to engineers without programming expertise. Statistical analysis of the algorithm's optimization process and case studies demonstrate its robustness and adaptability to various beam–slab structural optimization problems, revealing its significant potential for practical engineering scenarios. [ABSTRACT FROM AUTHOR]

This paper addresses a class of uncertain nonlinear systems with disturbances that are challenging to model by proposing a novel model-free adaptive sliding mode control (MFASMC) scheme based on a discrete-time extended state observer (DESO). Initially, leveraging the pseudo partial derivative (PPD) concept in the model-free adaptive control (MFAC) framework, the discrete-time nonlinear model is converted into a full-form dynamic linearization (FFDL) model. Secondly, using the FFDL data model, a discrete sliding mode controller is designed. A discrete integral sliding mode surface is chosen to mitigate chattering during the reaching phase, and a hyperbolic tangent function with minimal slope variation is selected for smoother switching control. Furthermore, a DESO is designed to estimate uncertainties in the discrete system, enabling real-time compensation for the controller. Finally, a genetic optimization algorithm is employed for parameter tuning to minimize the time cost associated with selecting control parameters. The design process of this scheme relies solely on the data of the controlled system, without depending on a mathematical model. The proposed DESO-MFASMC scheme is tested through simulations using a typical numerical equation and the existing EFG-BC/320 electric heavy-duty forklift from the Quzhou Special Equipment Inspection Center. Simulation results show that the proposed method is significantly superior to the traditional MFAC and PID control methods in tracking accuracy and robustness when dealing with nonlinear disturbance of the system. The DESO-MFASMC scheme proposed in this paper not only shows its advantages in theory but also verifies its effectiveness and practicability in engineering through practical application. [ABSTRACT FROM AUTHOR]

In the pursuit of improved productivity and efficiency, the search for alternative fuels that reduce dependence on fossil fuels is of utmost importance. This research study aims to investigate the influence of process parameters, namely blend percentage, fuel injection pressure, exhaust gas recirculation (EGR) rate, and engine load, on various engine performance parameters such as torque, brake thermal efficiency (BTE), brake mean effective pressure (BMEP), hydrocarbon emissions (HC), and mechanical efficiency. The experiments are conducted following the Taguchi orthogonal array (L25) design of experiments. Additionally, grey relational analysis, a multi-objective optimization technique, is applied to identify the optimal levels of the process variables that optimize all the response parameters. The optimal values obtained through grey relational analysis are determined as 0% blend, 600 bar fuel injection pressure, 12% EGR rate, and 12 kg engine load. Moreover, the Genetic Algorithm-based Multi-Objective Genetic Algorithm (MOGA) is employed for multi-objective optimization of the engine input variables, yielding optimal levels of 19.45% blend, 594.35 bar fuel injection pressure, 14.12% EGR rate, and 12 kg engine load. Furthermore, multivariable regression models are developed to predict the response variables within the experimental domain. These models are validated through a confirmation test. The findings of this study provide insights into the optimization of process variables for enhanced engine performance, with the developed models serving as valuable tools for future predictions and optimization. [ABSTRACT FROM AUTHOR]

In this article, a special type of fault isolation problem is reported where temporal information is required for the estimation of parameters from susceptible fault sub-space. Any physical system always obeys certain mathematical constraints under the normal operating condition, and that is incorporated in a behavioral model, which is essentially flowing and force or moment balance. In a fault detection and identification (FDI) model, only concurrent states are known. In FDI, the constraint relationships need to be derived only in terms of known variables, i.e., the measurements and nominal parameters, which are termed analytical redundancy relations (ARRs). The numerical evaluation of ARRs is residuals, and those oscillate within a definite bound of error when computed using test data. In this work, a novel function is formulated using the ARRs at different time instants and that function is minimized to estimate the suspected parameter values belonging to the non-isolable sub-space. Single-fault hypothesis is considered, and a genetic algorithm (GA) is used for the optimization. This FDI analysis may be beneficial for power hydraulic-driven heavy machinery such as hydraulic excavators, dumpers, and front-end loaders, which are mostly used in mines and construction sites. [ABSTRACT FROM AUTHOR]

Evaluating the degradation of hull and ship performance and exploring their degradation pathways is crucial for developing scientific and reasonable ship maintenance plans. This paper proposes a two-stage optimization (TSO) algorithm that combines the Genetic Algorithm (GA) and Long Short-Term Memory (LSTM) network, capable of simultaneously optimizing input features and model parameters to enhance the accuracy and generalization ability of speed prediction models. Additionally, a performance degradation assessment method based on speed loss is provided, aimed at evaluating the degradation of hull and propeller performance, as well as extracting the performance degradation paths. The results indicated that the proposed TSO-LSTM-GA algorithm significantly outperformed existing baseline models. Furthermore, the provided performance degradation assessment method demonstrated certain effectiveness on the target ship data, with a measured degradation rate of 0.00344 kn/d and a performance degradation of 9.569% over 478 days, corresponding to an annual speed loss of 1.257 kn. [ABSTRACT FROM AUTHOR]

Robots assist emergency responders by collecting critical information remotely. Deploying multiple cooperative unmanned ground vehicles (UGVs) for a response can reduce the response time, improve situational awareness, and minimize costs. Reliable communication is critical for multiple UGVs for environmental response because multiple robots need to share information for cooperative navigation and data collection. In this work, we investigate a control policy for optimal communication among multiple UGVs and base stations (BSs). A multi-agent deep deterministic policy gradient (MADDPG) algorithm is proposed to update the control policy for the maximum signal-to-interference ratio. The UGVs communicate with both the fixed BSs and a mobile BS. The proposed control policy can navigate the UGVs and mobile BS to optimize communication and signal strength. Finally, a genetic algorithm (GA) is proposed to optimize the hyperparameters of the MADDPG-based training. Simulation results demonstrate the computational efficiency and robustness of the GA-based MADDPG algorithm for the control of multiple UGVs. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this study is to formulate a new class of vehicle routing problem with an objective to minimise the total cost of raw material collection and derive a new approach to solve optimization problems. This study can help to select the optimum number of suppliers based on cost. Design/methodology/approach: To model the raw material vehicle routing problem, a mixed integer linear programming (MILP) problem is formulated. An interesting phenomenon added to the proposed problem is that there is no compulsion to visit all suppliers. To guarantee the demand of semiconductor industry, all visited suppliers should reach a given raw material capacity requirement. To solve the proposed model, the authors developed a novel hybrid approach that is a combination of block and edge recombination approaches. To avoid bias, the authors compare the results of the proposed methodology with other known approaches, such as genetic algorithms (GAs) and ant colony optimisation (ACO). Findings: The findings indicate that the proposed model can be useful in industries, where multiple suppliers are used. The proposed hybrid approach provides a better sequence of suppliers compared to other heuristic techniques. Research limitations/implications: The data used in the proposed model is generated based on previous literature. The problem derives from the assumption that semiconductor industries use a variety of raw materials. Practical implications: This study provides a new model and approach that can help practitioners and policymakers select suppliers based on their logistics costs. Originality/value: This study provides two important contributions in the context of the supply chain. First, it provides a new variant of the vehicle routing problem in consideration of raw material collection; and second, it provides a new approach to solving optimisation problems. [ABSTRACT FROM AUTHOR]

Soil–structure interaction (SSI) is a well-established phenomenon with significant implications for the dynamic response of structures subjected to earthquake loads. This study aimed to find the optimum stiffness of a lead rubber bearing (LRB) isolator within a multi-degree-of-freedom (MDOF) structure using a genetic algorithm (GA) while accounting for SSI effects through analytical formulation and numerical simulation. The simplified linear cone model was utilized to model the SSI effect, with two degrees of freedom of the soil: sway and rocking. Analytically, the main contribution is the presentation of an equivalent frequency formula for both the structure and the isolation layer, allowing the presentation of these later with respect to dimensionless parameters. Numerically, the displacement of the base level was targeted as the response to be reduced through the GA optimization, which is a further contribution of this work. To achieve this, 28 earthquake records with two components each were used during the optimization procedure. These records were regarded as near-field excitations, and 14 of them had pulse-like characteristics while the other 14 did not. The obtained results showed a local optimum of isolator stiffness for each earthquake and soil type. Owing to the stochastic nature of earthquakes, a weighted averaging method was used to obtain the global optimum isolator stiffness for each soil type, which is a novelty in this work. Further investigation of the local and general optima in the time and frequency domains showed a significant reduction in response in terms of base-level displacement, root-mean square (RMS) of top-floor acceleration, and strain energy of the entire structure. These findings may represent added values for designers working on base isolation (BI) devices in various soil conditions. [ABSTRACT FROM AUTHOR]

Copyright of Fly Ash Comprehensive Utilization is the property of Hebei Fly Ash Comprehensive Utilization Magazine Co., Ltd. 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.)

ABSTRACT Vertical axis wind turbine (VAWT) has a rotating axis perpendicular to the wind direction. This type of wind turbine that is suitable for urban environments has low wind direction dependency and noise. In this research, a novel surrogated approach for optimizing a VAWT is proposed, used, tested, and verified, which is not reported in literature. The proposed method consisted of 3D computational fluid dynamics (CFD) analysis of wind flow through the wind turbine with FLUENT software by solving the unsteady turbulent equations. However, 3D CFD analysis was time and cost consuming to obtain the output result (power coefficient) from input values (airfoil chord length, pitch angle, and tip speed ratio as turbine design variables). Thus, artificial neural network (ANN) was applied to obtain weight functions to correlate FLUENT software inputs and outputs after learning process. Finally, genetic algorithm was used for maximizing the turbine power coefficient considering three defined design variables. The optimum value of power coefficient was improved to 0.244, and the optimum values of design variables for blade chord length, blade pitch angle, and blade tip speed ratio were 0.218, −0.453, and 1.24, respectively. This novel surrogated method reduced the computational time and cost of VAWT optimizing considerably.

In this study, an Artificial Neural Network-Genetic Algorithm (ANN-GA) approach was successfully applied to optimise the physicochemical factors influencing the synthesis of unsaturated fatty acids (UFAs) in the microalgae P. kessleri UCM 001. The optimized model recommended specific cultivation conditions, including glucose at 29 g/L, NaNO3 at 2.4 g/L, K2HPO4 at 0.4 g/L, red LED light, an intensity of 1000 lx, and an 8:16-h light-dark cycle. Through ANN-GA optimisation, a remarkable 66.79% increase in UFAs production in P. kessleri UCM 001 was achieved, compared to previous studies. This underscores the potential of this technology for enhancing valuable lipid production. Sequential variations in the application of physicochemical factors during microalgae culture under mixotrophic conditions, as optimized by ANN-GA, induced alterations in UFAs production and composition in P. kessleri UCM 001. This suggests the feasibility of tailoring the lipid profile of microalgae to obtain specific lipids for diverse industrial applications. The microalgae were isolated from a high-mountain lake in Colombia, highlighting their adaptation to extreme conditions. This underscores their potential for sustainable lipid and biomaterial production. This study demonstrates the effectiveness of using ANN-GA technology to optimise UFAs production in microalgae, offering a promising avenue for obtaining valuable lipids. The microalgae's unique origin in a high-mountain environment in Colombia emphasises the importance of exploring and harnessing microbial resources in distinctive geographical regions for biotechnological applications.

Features within the dataset carry a significant role; however, resource utilization, prediction-time, and model weight are increased by utilizing high-dimensional data in intrusion-detection paradigm. This paper aims to design a novel lightweight intrusion detection system in two phases utilizing a swarm intelligence-based technique. In 1st-phase, essential features are selected using particle swarm optimization algorithm by considering imbalanced dataset. Ant colony optimization algorithm is utilized in 2nd-phase for extracting information-rich and uncorrelated features. Additionally, genetic algorithm is employed for fine-tuning each detection model. Proposed model's performance is evaluated on different base and ensemble classifiers, and it is observed that xgboost achieves best accuracy with 90.38%, 92.63%, and 97.87% on NSL-KDD, UNSW-NB15, and CSE-CIC-IDS2018 datasets, respectively. The proposed model also outperforms other traditional dimensionality reduction and state-of-the-art approaches with statistical validation. This paper also analyses objective function of each metaheuristic algorithm used in this paper, applying convergence graphs, box, and swarm plots. [ABSTRACT FROM AUTHOR]

Silicon wafers find applications in manufacturing large-scale micro-components widely available in consumer-based electronic devices. The milling-electrochemical spark micromachining (Milling-ECSMM) process is popular nowadays as an advanced micromanufacturing process for creating microchannels and several other geometric features. This paper presents a parametric effect of voltage, tool rotation, electrolyte concentration, and duty cycle on MRR, Ra, and TWR, using a tungsten carbide (WC) two-fluted flat-end milling cutter. The experimental model was developed using response surface methodology (RSM), and parametric multi-objective optimization was carried out using desirability function analysis (DFA) and genetic algorithm (GA). SEM and optical images were taken to identify the surface quality of the machined microchannel. The optimal combination of parameters obtained from GA as 90 V, 13 rpm, 64 g/l, and 40% DC gives better convergence and multi-objective response for MRR, TWR, and Ra as 0.409 mg/min, 0.0428 mg/min, and 0.572 µm, respectively. [ABSTRACT FROM AUTHOR]

A product recovery system is proposed to reduce the bulk of waste sent to landfills by retrieving materials and parts of obsolete products for using them in remanufacturing and recycling. Product recovery is a significant strategy for enhancing customer satisfaction with regard to environmental concerns. Considering the fact that some products are returned, it becomes challenging to analyse whether to manufacture a new product or to rework the returned product at every step of the product recovery chain. Our approach uses a mixed integer linear programming model with the genetic algorithm and particle swarm optimisation, where two meta-heuristic algorithms are introduced for solving the MILP problem. Here, a recovery scenario is modelled, subject to the time and type of product to be processed. The study is intended to enhance the overall productivity of the product recovery chain. To demonstrate the approach, a case study is presented in the fast-moving consumer goods industry in which the proposed model demonstrates a reduction in the overall cost in the product recovery chain. [ABSTRACT FROM AUTHOR]

The field of medicine is witnessing rapid development of AI, highlighting the importance of proper data processing. However, when working with medical data, there is a problem of class imbalance, where the amount of data about healthy patients significantly exceeds the amount of data about sick ones. This leads to incorrect classification of the minority class, resulting in inefficient operation of machine learning algorithms. In this study, a hybrid method was developed to address the problem of class imbalance, combining oversampling (GenSMOTE) and undersampling (ENN) algorithms. GenSMOTE used frequency oversampling optimization based on a genetic algorithm, selecting the optimal value using a fitness function. The next stage implemented an ensemble method based on stacking, consisting of three base (k-NN, SVM, LR) and one meta-model (Decision Tree). The hyperparameters of the meta-model were optimized using the GridSearchCV algorithm. During the study, datasets on diabetes, liver diseases, and brain glioma were used. The developed hybrid class balancing method significantly improved the quality of the model: the F1-score increased by 10-75%, and accuracy by 5-30%. Each stage of the hybrid algorithm was visualized using a nonlinear UMAP algorithm. The ensemble method based on stacking, in combination with the hybrid class balancing method, demonstrated high efficiency in solving classification tasks in medicine. This approach can be applied for diagnosing various diseases, which will increase the accuracy and reliability of forecasts. It is planned to expand the application of this approach to large volumes of data and improve the oversampling algorithm using additional capabilities of the genetic algorithm.

Studying the order delivery strategy considering urban traffic restrictions to reduce the average delivery time of orders, improve the consistency of delivery time and customer satisfaction is of great significance. A steering-restricted distribution network was constructed by setting up steerable nodes. And with the goal of minimizing the average delivery time, a multi-vehicle real-time pickup and delivery path optimization model was established considering the dynamics of the orders based on the turn restriction network. And two delayed distribution strategies, IGNORE and wait & return (W&R), were designed to solve the problem. In the study analysis, the number and distance of steerable nodes were adjusted to simulate two kinds of road networks: dense and sparse. Through numerical simulation and genetic algorithm solution, the stability of the model and the applicability of the strategy were verified, the average delivery time of IGNORE and W&R strategies under these two networks, different order quantities, the number of delivery personnel and lengths of rolling time domains were obtained, and the reasons for the fluctuation of the average delivery time were analyzed. The results show that the IGNORE strategy is applicable to the case of small network with few orders, and the average delivery time of orders decreases as the rolling time domain time shortens. The W&R strategy is suitable for larger distribution networks, and the more the number of steerable nodes in the network, the average delivery time of orders decreases. The research conclusion has certain reference significance for the real-time delivery platform to optimize the delivery strategy and improve customer satisfaction. [ABSTRACT FROM AUTHOR]

FDM is the world's most widely used and certified additive manufacturing technology because of its simplicity of use and production flexibility compared to other additive manufacturing techniques. Several input process variables impact the surface quality of manufactured components. The present study investigated the effect of print speed, acceleration, and jerk on the surface roughness of FDM-fabricated parts. The surface roughness of PLA-fabricated items is minimized by optimizing all three input parameters. To investigate the effect of input variables on surface roughness, a total of 20 test specimens were developed and fabricated using a face-centered central composite design technique. The surface roughness has been measured on the lateral sides of components in two directions (along the x-axes and y-axes). Further, the hybrid genetic algorithms-artificial neural networks (GA-ANN) heuristic optimization tool, in which GA is integrated with ANN, is employed to find the best feasible combination of input variables. It is observed that the surface roughness obtained for the x-axis direction is 0.0551512 μm at (speed: 20 mm/s; acceleration: 1137 mm/s2; jerk: 29.36 mm/s) and for the y-axis direction is 11.8919 μm at (speed: 98.60 mm/s; acceleration: 988.35 mm/s2; jerk: 16.508 mm/s). The optimized values are validated experimentally. [ABSTRACT FROM AUTHOR]

Shafting alignment plays an important role in the marine propulsion system, which affects the safety and stability of ship operation. Air spring vibration isolation systems (ASVISs) for marine shafting can not only reduce mechanical noise but also help control alignment state by actively adjusting air spring pressures. Alignment prediction is the first and a key step in the alignment control of ASVISs. However, in large-scale ASVISs, due to factors such as strong interference and raft deformation, alignment prediction faces problems such as alignment measurement sensors failure and difficulty in establishing a mathematical model. To address this problem, a data model for predicting alignment state is developed based on a back propagation (BP) neural network, fully taking advantage of its self-learning and self-adaption abilities. The proposed model exploits the collected data in the ASVIS instead of the alignment measurement data to calculate the alignment state, providing another alignment prediction approach. Then, in order to solve the local optimum issue of BP neural network, we introduce the genetic algorithm (GA) to optimize the weights and thresholds of the BP neural network, and an improved GA-BP model is designed. The GA-BP model can leverage the advantages of the global search capability of GA as well as the BP neural network's fast convergence in local search. Finally, we conduct experiments on a real ASVIS and evaluate the prediction models using different criteria. The experimental results show that the proposed prediction model with the GA-BP neural network can accurately predict the alignment state, with a mean-square error (MSE) of 0.0114 . And compared to the BP neural network, the GA-BP neural network reduces the MSE by approximately 74 % . [ABSTRACT FROM AUTHOR]

Based on the experimental results, this study develops a multi-objective optimization scheme to obtain the set of optimal process parameters for pulsed laser direct cutting of non-oriented silicon steel sheets for manufacturing motor core laminations. The experiments were conducted in the nital solvent, which was the one with the smallest thermal effect of laser cutting among the candidate environments of air, deionized water, alcohol, lubricant oil, sodium chloride solution, and nital solution. The laser was a pulsed Nd:YAG nanosecond laser and the thickness of the silicon steel was 100 μm. The effects of three laser process parameters, laser power (P), cutting speed (v), and pulse repetition rate (f) on the cutting qualities of the heat-affected zone (HAZ), cutting time (TC), and multiple dimensional accuracies of the cut core lamination were examined. The inspected geometric accuracies included the errors in inner and outer core diameters (ED1 and ED2), the error in tooth width (EL), and the roundness of inner and outer diameters (C1 and C2). The developed multi-objective optimization model was a PSI-based ELM-GA scheme consisting of the extreme learning machine (ELM) model for connecting the inputs and the outputs, the preference selection index (PSI) method for obtaining the weighted multi-objective function, and the genetic algorithm (GA) for process optimization. Through employing the predicted optimal process parameter set, the validation experiment showed that the errors between the prediction and the experimental result for the seven qualities of HAZ, ED1, ED2, C1, C2, EL, and TC were 4.04%, 6.25%, 4.02%, 0.48%, 2.14%, 5.09%, and 1.25%, respectively. The HAZ and geometric accuracy of the cut core laminations were qualified for the subsequent lamination assembly. Consequently, the merit of direct formation of ready-for-assembly core laminations without the need for any post-processing renders the proposed laser cutting scheme an economical and effective approach for manufacturing motor core laminations from thin silicon steel sheets. [ABSTRACT FROM AUTHOR]

Memristor crossbars offer promising low-power and parallel processing capabilities, making them efficient for implementing convolutional neural networks (CNNs) in terms of delay time, area, etc. However, mapping large CNN models like ResNet-18, ResNet-34, VGG-Net, etc., onto memristor crossbars is challenging due to the line resistance problem limiting crossbar size. This necessitates partitioning full-image convolution into sub-image convolution. To do so, an optimized mapping of memristor crossbars should be considered to divide full-image convolution into multiple crossbars. With limited crossbar resources, especially in edge devices, it is crucial to optimize the crossbar allocation per layer to minimize the hardware resource in term of crossbar area, delay time, and area–delay product. This paper explores three optimization scenarios: (1) optimizing total delay time under a crossbar's area constraint, (2) optimizing total crossbar area with a crossbar's delay time constraint, and (3) optimizing a crossbar's area–delay-time product without constraints. The Lagrange multiplier method is employed for the constrained cases 1 and 2. For the unconstrained case 3, a genetic algorithm (GA) is used to optimize the area–delay-time product. Simulation results demonstrate that the optimization can have significant improvements over the unoptimized results. When VGG-Net is simulated, the optimization can show about 20% reduction in delay time for case 1 and 22% area reduction for case 2. Case 3 highlights the benefits of optimizing the crossbar utilization ratio for minimizing the area–delay-time product. The proposed optimization strategies can substantially enhance the neural network's performance of memristor crossbar-based processing-in-memory architectures, especially for resource-constrained edge computing platforms. [ABSTRACT FROM AUTHOR]

In today's electric power network, fast changes are the norm, and auxiliary services such as automatic generation control (AGC) play a crucial role in maintaining the quality of the power supply. AGC ensures a balance between power generation, demand, and losses to sustain frequency stability and variation in tie‐line power within a set limit, even when the load changes. To accomplish this, it is always beneficial to consider new approaches to controlling the situation. This paper introduces the design of new AGC regulators that consider deviation in DC tie‐line power as an extra control variable for the turbine controller. In this study, three different deregulated power systems (containing two control areas), namely three thermal generations, the combination of one thermal and two hydro generations, and three hydro generations, including two power distribution companies (DISCOs) in each control area. These optimal AGC regulators are implemented in the proposed thermal–thermal–thermal system to carry out the various power contracts. The results have shown that the dynamic outcomes meet the AGC standards. To improve further dynamic results and the proposed systems' stability margins by incorporating redox flow batteries (RFB). In actual operating conditions, the system parameters do not remain constant due to the aging effect, assumptions made in simplifying the mathematical model, etc. Thus, ±50% deviations in the nominal value of system parameters to assess how well the optimal AGC regulators perform in the system under investigation. The suggested realistic AGC system incorporates many parameter fluctuations and works well with the optimal AGC regulators developed for the proposed plans. This study expanded to include a two‐area, thermal‐hydro‐hydro (THH) system under a deregulated framework connected via an asynchronous transmission link with or without a thyristor‐controlled phase shifter (TCPS) and RFB. The genetic algorithm (GA) can solve many issues and has global search, flexibility to varied problem types, intrinsic parallelism, and the ability to handle massive, complex search spaces. Thus, a two‐area deregulated hydro‐hydro‐hydro system with parallel tie‐lines utilizes GA‐PID, GA‐FOPID, and GA‐(1 + PI)‐FOPID controllers. Moreover, a random load disturbance (RLD) is employed in each section of the offered approach to show the resilience and elite performance of the proposed control strategy. To produce various dynamic reactions in the plans, MATLAB software version R2013a is employed. [ABSTRACT FROM AUTHOR]

The study aims to improve the surface finish of monocrystalline silicon wafer Si (100) with single-pole magnetic abrasive finishing along with slurry of alumina (1200 mesh) and chemical oxidizers (mixture of Marshall's acid salt (K2S2O8, 1.5%wt/wt), Caro's acid salt (KSHO5, 1.5%wt/wt), Sodium Hydroxide (NaOH, 1.5%wt/wt) and Hydrogen peroxide (H2O2, 0.5%wt/wt). The alumina slurry mixed with oxidizer flowed in the working-gap (the gap between the polishing tool and workpiece Si wafer) ranging between 6 to 8 mm. The process of polishing was conducted under different sets of conditions using three parameters, i.e., polishing-speed (X1), working-gap (X2) and workpiece feed-rate (X3). With Response Surface Methodology (RSM) using the above-mentioned parameters, 20 sets of experiments were conducted and two responses i.e., surface roughness (Ra) and work brush temperature (WBT) variation were recorded during the process. The obtained data was examined using Analysis of Variance (ANOVA) and the optimum process parameters of surface roughness and work-brush temperature were determined. A statistical model was created for surface roughness and work brush temperature in terms of the process parameters. After eliminating non-significant terms, the Genetic Algorithm (GA) toolkit, which is a component of the MATLAB 13 package, was employed to optimize the model. The theoretical results were validated through a confirmation experiment conducted under optimal conditions. The study also investigated the surface morphology of unpolished samples and polished samples obtained at optimal parameters with the help of images from AFM and SEM. The chemically assisted process for finishing silicon wafer improved the finishing efficacy to 1.076, nanometers suitable for silicon and other such materials for industrial applications. [ABSTRACT FROM AUTHOR]

Previous research in millimeter-wave antenna technology has focused on designs for specific frequency bands, such as 28 GHz, 32 GHz, 60 GHz, and 78 GHz. This paper analyzes an asymmetric dual-step antipodal petunia-shaped antenna capable of operating across the entire mm-wave frequency range from 30 GHz to 300 GHz. In the initial phase, a K-Band antenna is designed using various single radiators, including shapes such as a ball, balloon, axle, and petunia, in conjunction with a rectangular ground structure. A single radiator petunia design is enhanced to become a dual antipodal petunia radiator to achieve higher operating frequencies. This antipodal design generates multiple resonances at adjacent frequencies, resulting in broadband characteristics. To further improve performance, modifications are made to the ground structure. A novel technique inspired by radiation contouring of the antenna is proposed, which enhances impedance matching and overall antenna performance. Subsequently, a dual antipodal petunia radiator with an asymmetric step ground is optimized using the particle swarm optimization method to cover the entire millimeter-wave band (30-300 GHz). The antenna's physical dimensions are 30x30 mm², with a peak gain of 6 dBi and radiation efficiency ranging from 89% to 92% across the entire mm-wave spectrum. Notably, this proposed antenna exhibits an exceptionally low level of side lobes and excellent cross-polar discrimination, showcasing its unique design. The potential applications of this antenna span various fields, including military and imaging systems, automotive radar, telecommunications, remote sensing, security screening, and energy harvesting technology. [ABSTRACT FROM AUTHOR]

In an antenna array, the radiations characteristics may be disturbed by some failed elements out of total antenna elements that caused increase of side lobe level power and ultimately reduces the efficiency or performance of an antenna system. In this work, computationally efficient brain storm optimization algorithm technique has been employed to recover the original characteristics of antenna array system. The normalized excitation coefficients (amplitude values of all elements) of 32 × 1 and 16 × 1 elements of linear antenna array design has been re-computed with the help of proposed technique to regain original features of antenna. The results has been validated by analyzing the various antenna parameters such as half power beam width, first null beam width, side lobe level etc. Secondly, two nulls have been incorporated in the radiation characteristics of antenna array in order to suppress the unwanted signals that reaching to the system from specific directions. The performance of antenna system for nulls has been verified through parameter such as null depressed level. The work has been compared with other computationally efficient techniques (Biogeography-based optimization and genetic algorithm). [ABSTRACT FROM AUTHOR]

Mountain cities with complex topographies have always been highly vulnerable areas to global environmental change, prone to geological hazards, climate change, and human activities. Exploring and analyzing the vulnerability of coupling systems in mountain cities is highly important for improving regional resilience and promoting sustainable regional development. Therefore, a comprehensive framework for assessing the spatial vulnerability of mountain cities is proposed. A vulnerability assessment index system is constructed using three functional systems, ecological protection, agricultural production, and urban construction. Subsequently, the BP neural network and the genetic algorithm (GA) are combined to establish a vulnerability assessment model, and geographically weighted regression (GWR) is introduced to analyze the spatial influence of one-dimensional systems on the coupling system. Linzhou, a typical mountain city at the boundary between China's second- and third-step terrains, was selected as a case study to demonstrate the feasibility of the framework. The results showed that the vulnerability of the ecological protection system was highly aggregated in the east–central region, that of the agricultural production system was high in the west, and that of the urban construction system was low in the central region and high in the northwestern region. The coupling system vulnerability was characterized by multispatial distribution. The complex topography and geomorphology and the resulting natural hazards are the underlying causes of the vulnerability results. The impact of ecological and urban systems on the coupling system vulnerability is more prominent. The proposed framework can serve as a reference for vulnerability assessments of other similar mountain cities with stepped topographies to support the formulation of sustainable development strategies. [ABSTRACT FROM AUTHOR]

The field of medicine is witnessing rapid development of AI, highlighting the importance of proper data processing. However, when working with medical data, there is a problem of class imbalance, where the amount of data about healthy patients significantly exceeds the amount of data about sick ones. This leads to incorrect classification of the minority class, resulting in inefficient operation of machine learning algorithms. In this study, a hybrid method was developed to address the problem of class imbalance, combining oversampling (GenSMOTE) and undersampling (ENN) algorithms. GenSMOTE used frequency oversampling optimization based on a genetic algorithm, selecting the optimal value using a fitness function. The next stage implemented an ensemble method based on stacking, consisting of three base (k-NN, SVM, LR) and one meta-model (Decision Tree). The hyperparameters of the meta-model were optimized using the GridSearchCV algorithm. During the study, datasets on diabetes, liver diseases, and brain glioma were used. The developed hybrid class balancing method significantly improved the quality of the model: the F1-score increased by 10-75%, and accuracy by 5-30%. Each stage of the hybrid algorithm was visualized using a nonlinear UMAP algorithm. The ensemble method based on stacking, in combination with the hybrid class balancing method, demonstrated high efficiency in solving classification tasks in medicine. This approach can be applied for diagnosing various diseases, which will increase the accuracy and reliability of forecasts. It is planned to expand the application of this approach to large volumes of data and improve the oversampling algorithm using additional capabilities of the genetic algorithm. [ABSTRACT FROM AUTHOR]

In this paper, the notion of a cohesive and self-sufficient grid is proposed. Based on a cohesive and self-sufficient virtual microgrid, an active distribution network is optimally planned, and an optimal configuration of demand-side resources, distributed generations, and energy storage systems are generated. To cope with stochastic uncertainty from forecast error in wind speed and load, flexibility reserves are needed. In this paper, the supply relation between flexibility and uncertainty is quantified and integrated in an innovative index which is defined as cohesion. The optimization objectives are a minimized operational cost and system net-ability cohesion as well as self-sufficiency, which is defined as the abilities both to supply local load and to deal with potential uncertainty. After testing the optimal configuration in the PG&E 69 bus system, it is found that with a more cohesive VM partition, the self-sufficiency of VMs is also increased. Also, a case study on uncertainty-caused system imbalance is carried out to show how flexibility resources are utilized in real-time operational balance. [ABSTRACT FROM AUTHOR]

The widely adopted paradigm in brain–computer interfaces (BCIs) involves motor imagery (MI), enabling improved communication between humans and machines. EEG signals derived from MI present several challenges due to their inherent characteristics, which lead to a complex process of classifying and finding the potential tasks of a specific participant. Another issue is that BCI systems can result in noisy data and redundant channels, which in turn can lead to increased equipment and computational costs. To address these problems, the optimal channel selection of a multiclass MI classification based on a Fusion convolutional neural network with Attention blocks (FCNNA) is proposed. In this study, we developed a CNN model consisting of layers of convolutional blocks with multiple spatial and temporal filters. These filters are designed specifically to capture the distribution and relationships of signal features across different electrode locations, as well as to analyze the evolution of these features over time. Following these layers, a Convolutional Block Attention Module (CBAM) is used to, further, enhance EEG signal feature extraction. In the process of channel selection, the genetic algorithm is used to select the optimal set of channels using a new technique to deliver fixed as well as variable channels for all participants. The proposed methodology is validated showing 6.41% improvement in multiclass classification compared to most baseline models. Notably, we achieved the highest results of 93.09% for binary classes involving left-hand and right-hand movements. In addition, the cross-subject strategy for multiclass classification yielded an impressive accuracy of 68.87%. Following channel selection, multiclass classification accuracy was enhanced, reaching 84.53%. Overall, our experiments illustrated the efficiency of the proposed EEG MI model in both channel selection and classification, showing superior results with either a full channel set or a reduced number of channels. [ABSTRACT FROM AUTHOR]

The design procedure of a novel compact ultra-wideband (UWB) filter with high selectivity and low insertion loss is presented in this paper. The proposed filter consists of a simple planar combline filter at the top of a substrate and a non-intuitive shape of the defected ground structure (DGS) on the other side. The UWB filter is obtained by optimizing the shape of DGS and the combline parameters with a mixed integer genetic algorithm. The mixed integer genetic algorithm optimizes both continuous and binary values simultaneously. The continuous values define the combline parameters while the binary values define the shape of DGS. The detail of the design procedure is presented and validated by fabricating a prototype of the proposed filter. The measured insertion loss of the proposed filter in the mid-band frequency is less than 0.5 dB. The measurement results also show that the proposed UWB filter with a very compact structure has five transmission zeroes at the upper and lower stop bands. [ABSTRACT FROM AUTHOR]

In this paper, a 3D conformal meta-lens designed for manipulating electromagnetic beams via height-to-phase control is proposed. The structure consists of a 40 × 20 array of tunable unit cells fabricated using 3D printing, enabling full 360° phase compensation. A novel automatic synthesizing method (ASM) with an integrated optimization process based on genetic algorithm (GA) is adopted here to create the meta-lens. Simulation using CST Microwave Studio and MATLAB reveals the antenna's beam deflection capability by adjusting phase compensations for each unit cell. Various beam scanning techniques are demonstrated, including single-beam, dual-beam generation, and orbital angular momentum (OAM) beam deflection at different angles of 0°, 10°, 15°, 25°, 30°, and 45°. A 3D-printed prototype of the dual-beam feature has been fabricated and measured for validation purposes, with good agreement between both simulation and measurement results, with small discrepancies due to 3D printing's low resolution and fabrication errors. This meta-lens shows promise for low-cost, high-gain beam deflection in mm-wave wireless communication systems, especially for sensing applications, with potential for wider 2D beam scanning and independent beam deflection enhancements. [ABSTRACT FROM AUTHOR]

This study introduces an asymmetric V-shaped interior permanent magnet synchronous motor (AVIPMSM) by modifying the conventional flux barrier of a V-shaped interior permanent magnet synchronous motor (VIPMSM) including optimization-based finite element analysis (FEA). Nowadays usage of VIPMSM is increasing where higher torque density with high efficiency by decreasing the torque ripple factor is required. To improve these properties, flux barriers are modified in VIPMSM by applying optimization methods. For each pole of VIPMSM, modification has been depleted based on symmetric and asymmetric barriers. It introduces the magnetic field shifting effect in the motor. After deciding the flux barrier in the rotor, an optimized method is applied for achieving the proper dimensions of each barrier to estimate the maximum torque and other performances of the motor. Here, a 24/4 pole VIPMSM is considered for design and analysis. ANSYS Maxwell platform is chosen for performance analysis of motor. In addition to using the inbuilt minimum function optimization techniques of ANSYS, genetic algorithm (GA)/particle swarm optimization (PSO) in MATLAB is applied in the proposal to optimize the flux barriers of the motor. To validate the effectiveness of the proposed method, FEA is adopted by taking into account optimized parameters. The paper also investigates the effect of flux barriers on loss factors to improve the motor efficiency. A comparative study with the benchmark VIPMSM is presented to validate the designed AVIPMSM using optimization and its results are reported. Eventually, the FEA result proves that PSO optimized model is more appropriate for the case understudies. [ABSTRACT FROM AUTHOR]

The bandgap properties of elastic metamaterials can be efficiently utilized to tailor the propagation characteristics of elastic and acoustic waves, which have promising applications in noise and vibration reduction and isolation. In this paper, an elastic metamaterial with a multilayered honeycomb structure (EMHS) is proposed to enlarge the bandgaps in the low-frequency range and its bandgap properties are analyzed. To meet the requirement of the lightweight design, an optimization model for maximizing the total relative bandgap width with a mass constraint is established. A novel optimization approach combining the Kriging surrogate model with the genetic algorithm (GA) is proposed to reduce the huge computational cost of the corresponding optimization problem. In the Kriging-GA approach, a high-precision Kriging-based surrogate model with addition of supplementary points is constructed to predict the bandgap objective function value, and the GA is employed to search for the optimal parameters. The performance of the proposed Kriging-GA approach is investigated by numerical examples, and the results are compared with those obtained by the commonly used FEM-GA method. The results show that the proposed Kriging-GA approach is highly efficient for the design optimization of the EMHS and can remarkably reduce the computational cost of the considered optimization problem, which has promising prospects in a wide range of engineering applications. [ABSTRACT FROM AUTHOR]

Copyright of Systems Engineering & Electronics is the property of Journal of Systems Engineering & Electronics Editorial Department 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.)

The use of MRI analysis for BTD and tumor type detection has considerable importance within the domain of machine vision. Numerous methodologies have been proposed to address this issue, and significant progress has been achieved in this domain via the use of deep learning (DL) approaches. While the majority of offered approaches using artificial neural networks (ANNs) and deep neural networks (DNNs) demonstrate satisfactory performance in Bayesian Tree Descent (BTD), none of these research studies can ensure the optimality of the employed learning model structure. Put simply, there is room for improvement in the efficiency of these learning models in BTD. This research introduces a novel approach for optimizing the configuration of Convolutional Neural Networks (CNNs) and Artificial Neural Networks (ANNs) to address the BTD issue. The suggested approach employs Convolutional Neural Networks (CNN) for the purpose of segmenting brain MRIs. The model's configurable hyper-parameters are tuned using a genetic algorithm (GA). The Multi-Linear Principal Component Analysis (MPCA) is used to decrease the dimensionality of the segmented features in the pictures after they have been segmented. Ultimately, the segmentation procedure is executed using an Artificial Neural Network (ANN). In this artificial neural network (ANN), the genetic algorithm (GA) sets the ideal number of neurons in the hidden layer and the appropriate weight vector. The effectiveness of the suggested approach was assessed by utilizing the BRATS2014 and BTD20 databases. The results indicate that the proposed method can classify samples from these two databases with an average accuracy of 98.6 % and 99.1 %, respectively, which represents an accuracy improvement of at least 1.1 % over the preceding methods.