Search

In the forthcoming decades, significant advancements will shape the construction and operations of distribution systems. Particularly, the increasing prominence of photovoltaic (PV) systems in the power industry will impact the security of these systems. This study employs Monte Carlo Simulation (MCS) in conjunction with genetic algorithm (GA) and differential evolution (DE) to address uncertainties. The probability density functions (pdf) for total voltage harmonic distortion (UTHD), individual voltage harmonic distortion (UIHDh), and RMS voltage (URMS) have been determined for utilization in chance constrained framework. In addition, the uncertainty effects of PV systems on grid losses for various solar radiation conditions are also investigated. Specifically, the paper aims to evaluate these impacts within the context of stochastic limits. The PV system sizing problem has been addressed inside the distribution system using a chance-constrained framework. A key contribution is the integration of GA, DE, and MCS into a cohesive approach, and the study evaluates the benefits of this approach through an analysis of outcomes derived from the stochastic method. The simulation results illustrate the advantages of the proposed stochastic GA methodology. [ABSTRACT FROM AUTHOR]

3D integration is one of the scalable multiprocessor design solutions. The main challenge in 3D design is temperature traps, especially in the upper layers and hot spots. The current studies present solutions for solving temperature and hotspot problems in topology, routing, and mapping levels. Accordingly, the characteristics of temperature-aware core mapping are beneficial for dealing with the challenges of 3D chips. In this paper, the core temperature is modeled based on processing, communication power, neighbor node temperature, distance from the heat sink, and hotspot node. To find the optimal solution, this paper proposes thermal-aware application mapping techniques using genetic algorithms and fuzzy logic to minimize peak temperatures in 3D network-on-chip (NoC) architectures. Fitness functions include the above parameters with the same weight (GSM) and the fitness function with fuzzy logic by considering the effect of distance from heat sink (GFM1) and heat sink distance and the number of neighbor's core (GFM2). Specifically, the fuzzy logic-based GFM1 algorithm demonstrates superior performance over the genetic algorithm-driven GSM approach in reducing power consumption and energy costs associated with inter-core communication traffic. Across the different traffic patterns tested, GFM1 consistently achieves lower energy expenditure, with reductions upward of 50% compared to GSM. This underlines the strengths of the fuzzy technique in enabling thermal-aware mapping to minimize chip temperatures in the presence of intensive workloads and communication. In essence, the key takeaway is that GFM1 outperforms GSM in the context of power and energy metrics linked to handling on-chip traffic between processing cores. [ABSTRACT FROM AUTHOR]

Power system operators are faced with the problem of unit commitment belonging to mixed integer programming, which becomes very complicated, as units become large-scale and highly constrained. Because unit commitment problem is a binary problem with commitment and de-commitment, a discrete/binary optimization algorithm with superior performance is required. This paper proposes a novel hybrid binary bat algorithm for unit commitment problem, which consists of two process. To begin with, the proposed binary bat algorithm is applied to determining the commitment schedule of unit commitment problem. Specifically, an improved crossover operator based on exponential-logic-modulo map is proposed to enhance the convergence and maintain the diversity of populations. To prevent the algorithm from falling into a local optimum, a local mutation strategy performs local perturbation. Chaotic map is responsible for updating some parameters to increase the performance of the proposed algorithm. Furthermore, Lambda-iteration method is adopted to solve economic load dispatch in continuous space. Constraint handling is performed using the heuristic constraint produce. The effectiveness of the proposed algorithm is verified by benchmark functions and test systems. Additionally, the simulation results are compared with other well-established heuristic and binary approaches. [ABSTRACT FROM AUTHOR]

Logistics distribution is one of the main sources of carbon dioxide emissions at present, and there are also such distribution problems in the shipbuilding process. With the increasing attention paid to environmental problems, how to effectively reduce the energy consumption of block transportation and improve the utilization rate of resources in the factory is the key problem that China's shipbuilding industry needs to solve at present. This article considers the time windows for block transportation tasks, as well as the self-loading constraints of different types of flat cars, and establishes an optimization model that minimizes the empty transport time and energy consumption of the flat cars as the optimization objective. Then, an Improved Genetic Whale Optimization Algorithm is designed, which combines the cross and mutation ideas of genetic algorithms and proposes a whale individual position updating mechanism under a mixed strategy. Furthermore, the performance and computational efficiency of the algorithm are verified through comparative analysis with other classical optimization algorithms on standard test examples. Finally, the shipyard's block transportation example proves that the energy-saving ship block transportation scheduling method can effectively improve the efficiency of shipbuilding enterprise's block transportation and reduce the energy consumption in the block transportation process. It proves the engineering practicality of the green dispatching method proposed in this paper, which can further provide a decision-making method for shipyard managers. [ABSTRACT FROM AUTHOR]

Over the years, there has been a considerable discussion regarding machine learning (ML) techniques to forecast software faults. It can be challenging to choose a suitable machine learning technique for fault prediction modelling because of variations in the prediction performance of machine learning techniques for software systems. The evaluation of previously presented software fault prediction (SFP) approaches revealed that single machine learning-based models that did not deliver the best accuracy and F1-Score in any context, emphasizing the need to use multiple techniques, such as sampling and selection, in addition to the application of machine learning models. In order to address this issue, we present and discuss a method for predicting software faults that rely on choosing the most suitable machine learning and deep learning techniques from a pool of accurate and competitive learning techniques in order to construct a fault prediction model. The presented approach chooses the best features using Mutual Information feature selection technique. Using a hybrid sampling (SMOTE-Tomek) techniques, the issue of class imbalance (CI) is addressed. Then finally a Genetic Algorithm based machine learning (GA-DT) and a deep learning model (ANN-DT) are developed for the purpose for predicting faults in a software. For empirical evaluation, Eclipse version dataset (2.0, 2.1, and 3.0) is considered. Precision, recall, accuracy, and f1-Score are the performance metrics we used to evaluate the effectiveness of the proposed approach. The results demonstrated that the proposed approach (GA-DT and ANN-DT) effectively predicted the software's faults with ANN-DT providing best accuracies for all the three versions of Eclipse dataset. [ABSTRACT FROM AUTHOR]

Aggregate blending is a complex process especially when more sizes of aggregates need to be blended. For rough usage or to offer an initial answer, the conventional approaches are adequate. However, to obtain a cost-effective blend that meets specification requirements, more aggregate sizes must be accommodated. Several methods were investigated by various authors to deal with this complex process. Most of the methods are confined to a blending of three or four sizes of aggregates only. In this study, an attempt has been made to assess various computational techniques for aggregate blending to optimize the aggregate gradation area. Aggregates grading requirements specified for Dense Bituminous Macadam Grade-2 in MORT&H 500-10 was chosen as a reference. For this grading specifications, various methods like trial-and-error, mid-point gradation, least-square optimization, Generalised Reduced Gradient (GRG) non-linear, GRG multi start, simplex linear programming, regression analysis, IRC SP:89-2010, quadratic programming, support vector machines-SMoreg, path variate analysis, interval method, R programming were employed, and optimal proportions for aggregate blending were obtained. Curve fitting along with integration was applied to determine the aggregate gradation area under the combined gradation curve and maximum density line. The existence of a gradation curve between upper and lower limits and close to the mid-point line is considered as the first check and the minimum aggregate gradation area is considered as a second check while evaluating different optimal proportions arrived. Least aggregate gradation area which implies the minimum percentage of air voids was obtained for simplex LP (UL and LL) and evolutionary algorithm (Genetic algorithm) methods, i.e., 6.885. But these two methods yielded a filler of zero percentage which is practically not possible, hence simplex LP (MID) satisfies all the criterion and is adopted as the best method for aggregate blending. [ABSTRACT FROM AUTHOR]

The lower hook mechanism is one of the key mechanisms in netting machine. The weft reel diameter of the new generation netting machine has doubled to the original one, resulting in a large route change of lower hook, thus the lower hook mechanism needs to be redesigned. By comparing the fitting results under different methods, the hook tip trajectory with smaller acceleration is determined. By using the closed vector method, the inverse and forward kinematic models of the mechanism is established and solved. By using NSGA-II genetic algorithm, the transmission performance parameters of the mechanism are effectively optimized. The kinematic simulation of the optimized mechanism is completed in Adams to verify the correctness of kinematic models and the effectiveness of optimization results. The comparison result of the simulated and initial fitted trajectory shows that the lower hook mechanism designed in this paper could meet the technical requirements of the position and posture of the lower hook. [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]

The cubic stiffness force model (CSFM) and Bouc-Wen model (BWM) are introduced and compared innovatively. The unknown coefficients of the nonlinear models are identified by the genetic algorithm combined with experiments. By fitting the identified nonlinear coefficients under different excitation amplitudes, the nonlinear vibration responses of the system are predicted. The results show that the accuracy of the BWM is higher than that of the CSFM, especially in the non-resonant region. However, the optimization time of the BWM is longer than that of the CSFM. [ABSTRACT FROM AUTHOR]

With the increasing integration of renewable energy sources into distribution and transmission networks, the efficiency of cascade H-bridge multilevel inverters (MLIs) in power control applications has become increasingly significant for sustainable electricity generation. Traditionally, obtaining optimal switching angles of MLIs to minimize total harmonic distortion (THD) requires solving the selective harmonic elimination equations. To this end, this research aims to use two recently developed intelligent optimization algorithms, dandelion optimizer and gold rush optimizer, to solve this problem. To evaluate the effectiveness of the proposed algorithms, an eleven-level cascaded H-bridge MLI (CHB-MLI) was considered in the study. Simulation results for different modulation indices were obtained, and the accuracy and solution quality were compared with genetic algorithm and particle swarm optimization algorithms. MATLAB/Simulink-based models were used to verify numerical computations, ensuring the reliability of the findings. This research contributes to the field by providing insights into obtaining optimal switching angles and minimizing THD in MLIs by applying intelligent optimization algorithms. [ABSTRACT FROM AUTHOR]

The Analytic Hierarchy Process (AHP) is a multi-criteria decision-making method that relies on constructing a pairwise comparison matrix (PCM) based on decision-makers' (DMs) judgments regarding alternatives and criteria. The objective is to obtain weights and ultimately rank and select alternatives. However, in some cases, DMs may not provide judgments due to a lack of experience, knowledge, or reluctance to express opinions on the subject, resulting in missing pairs in the PCM. Existing techniques for filling these missing pairs have inherent limitations. This paper demonstrates the application of the pymissingAHP algorithm, implemented in Python and available at https://bit.ly/3UFdqSZ, to address missing pairs using mono and multiobjective approaches. The pymissingAHP algorithm employs a Genetic Algorithm (GA) featuring a specialized encoding to address this issue. Our approach can handle mono or multiple objective scenarios, which involve minimizing the consistency index and maintaining the ranking of weights as defined by experts. Additionally, the algorithm accommodates fuzzy numbers within the AHP framework (FAHP). PCMs containing numerous missing values may yield multiple solutions and not accurately reflect experts' opinions. Although our approach can solve entirely depleted PCMs, obtaining as many comparisons as possible is recommended to ensure a faithful representation of expert opinions for the decision-makers. The pymissingAHP algorithm provides a significant advantage: the capacity to seek solutions that address single or multiple objectives, utilizing continuous or discrete values, and additionally, the ability to solve FAHP problems. [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]

Choosing a shrinkage method can be done by selecting a penalty from a list of pre-specified penalties or by constructing a penalty based on the data. If a list of penalties for a class of linear models is given, we introduce a predictive stability criterion based on data perturbation to select a shrinkage method from the list. Simulation studies show that our predictive method identifies shrinkage methods that usually agree with existing literature and help explain heuristically when a given shrinkage method can be expected to perform well. If the preference is to construct a penalty customized for a given problem, then we propose a technique based on genetic algorithms, again using a predictive criterion. We find that, in general, a custom penalty never performs worse than any commonly used penalties and there are cases the custom penalty reduces to a recognizable penalty. Since penalty selection is mathematically equivalent to prior selection, our method also constructs priors. Our methodology allows us to observe that the oracle property typically holds for penalties that satisfy basic regularity conditions and therefore is not restrictive enough to play a direct role in penalty selection. In addition, our methodology, can be immediately applied to real data problems, and permits us to take model mis-specification into account. [ABSTRACT FROM AUTHOR]

Feature selection (FS) is a crucial preprocessing step that aims to eliminate irrelevant and redundant features, reduce the dimensionality of the feature space, and enhance clustering efficiency and effectiveness. FS is categorized as NP-Hard due to the high number of existing solutions. Various metaheuristic methods have been developed to address the FS problem, yielding promising results. Particularly, particle swarm optimization (PSO), an evolutionary computing (EC) approach guided by swarm intelligence, has gained widespread adoption owing to its implementation simplicity and potential for global search. This paper analyzes several variants of PSO algorithms and introduces a new FS method called HPSO. The proposed approach utilizes an asynchronously adaptive inertia weight and an improved constriction factor. Additionally, it incorporates a chaotic map and a MAD fitness function with a feature count penalty to tackle the clustering FS problem. The efficiency of the developed method is evaluated against the genetic algorithm (GA) and well-known variants of PSO algorithms, including PSOs with fixed inertia weights, PSOs with improved inertia weights, PSOs with fixed constriction factors, PSOs with improved constriction factors, PSOs with adaptive inertia weights, and PSO's includes advanced learning exemplars and sophisticated structure topologies. This paper assesses two different reference text data sets, Reuters-21578 and Webkb. In comparison with competitive methods, the proposed HPSO method achieves higher clustering precision and selects a more informative feature set. [ABSTRACT FROM AUTHOR]

Optimal portfolio selection—composing a set of stocks/assets that provide high yields/returns with a reasonable risk—has attracted investors and researchers for a long time. As a consequence, a variety of methods and techniques have been developed, spanning from purely mathematics ones to computational intelligence ones. In this paper, we introduce a method for optimal portfolio selection based on multi-objective evolutionary algorithms, specifically Nondominated Sorting Genetic Algorithm-II (NSGA-II), which tries to maximize the yield and minimize the risk, simultaneously. The system, named EvoFolio, has been experimented on stock datasets in a three-years time-frame and varying the configurations/specifics of NSGA-II operators. EvoFolio is an interactive genetic algorithm, i.e., users can provide their own insights and suggestions to the algorithm such that it takes into account users' preferences for some stocks. We have performed tests with optimizations occurring quarterly and monthly. The results show how EvoFolio can significantly reduce the risk of portfolios consisting only of stocks and obtain very high performance (in terms of return). Furthermore, considering the investor's preferences has proved to be very effective in the portfolio's composition and made it more attractive for end-users. We argue that EvoFolio can be effectively used by investors as a support tool for portfolio formation. [ABSTRACT FROM AUTHOR]

Grid computing is the aggregation of the power of heterogeneous, geographically distributed computing resources to provide high-performance computing. To benefit from the grid computing capabilities, effectual scheduling algorithms are primarily essential. This paper presents a GA-based approach, called Grid Workflow Tasks Scheduling Algorithm (GWTSA), for scheduling workflow tasks on grid services based on users' QoS (quality of service) constraints in terms of cost and time. For a given set of inter-dependent workflow tasks, it generates an optimal schedule, which minimizes the execution time and cost, such that the optimized time be within the time constraints (deadline) imposed by the user. In GWTSA, the workflow tasks are modeled as a DAG, which is divided, then the optimal sub-schedules of all task divisions are computed and used to obtain the execution schedule of the entire workflow. A GA-based technique is employed in GWTSA to compute the optimal execution sub-schedule for each branch division that consists of a set of sequential tasks. In this technique, the chromosome represents a branch division, where each gene holds the id of the service provider chosen to execute the corresponding task in the branch; and the fitness function is formulated as a multi-objective function of time and cost, this gives users the ability to determine their requirements if speed against cost or vice versa, by changing the weighting coefficients in the fitness function. The paper also exhibits the experimental results of assessing the performance of GWTSA with workflow samples of different sizes. [ABSTRACT FROM AUTHOR]

Performance-Aware Blockchains (PABs) are the highly optimized version of regular blockchains, capable of mining blocks with low delay and low energy. To incorporate performance awareness, researchers have proposed various lightweight consensus models that depend on single-chained blockchains, which limits their scalability performance after several blocks. To overcome this limitation, sharded blockchains were introduced, but very few of these sharded chains use lightweight consensus models. Hence, in this work, we propose a novel incremental learning model with light-weighted consensus for shard management in performance-aware blockchains. By using incremental learning, the model could continuously learn from the changing characteristics of the blockchain and make informed decisions about shard size adjustments to optimize performance. Further, to optimize shard size and ensure mining operates with lower delay and lower energy consumption, we use a hybrid combination of Genetic Algorithm and the Learner-based Elephant Herd Optimizer (GA-TLEHO) method. The reason for this hybrid combination of optimization methods is to enhance convergence by leveraging both exploration and exploitation. It is evident from the simulation analysis that the proposed method potentially mitigates Masquerading, Distributed Denial-of-Service (DDoS), and Finney attacks with higher efficiency and lower delay when compared with other state-of-the-art blockchain methods. [ABSTRACT FROM AUTHOR]

This paper proposes a fuzzy clustering model for probability density functions (PDFs) using the two-objective genetic algorithm. In this model, the L 1 -distance is used to evaluate the similarity of PDFs, and new two indexes that relate to the similarity of PDFs and clusters are proposed as the objective functions of genetic algorithm. Moreover, the operators for crossover, mutation, and selection are also updated to improve the quality of fuzzy clustering according to the corrected rand, the partition entropy, and the partition coefficients. By combining these improvements, we have an effective automatic fuzzy clustering algorithm for PDFs that can determine the appropriate number of clusters, the elements in each cluster, and the probability belonging to clusters of each element. The proposed model is tested through experiments using the established Matlab procedure, and it is also applied effectively to image data. These experiments demonstrate the superiority of the proposed model compared to other models. [ABSTRACT FROM AUTHOR]

It is crucial to optimize energy consumption in buildings while considering thermal comfort. The first step here involved an EnergyPlus simulation on a trade center building located in Tehran, Bandar Abbas, and Tabriz, Iran. A multi-objective optimization was then performed based on non-dominated sorting genetic algorithm II (NSGA-II) in jEPlus + EA to establish the building in the selected city where would benefit the most from implementing the radiant ceiling cooling system. Efforts were undertaken to choose environmentally-friendly materials. The final solution by Pareto charts resulted in a 52% reduction in energy consumption, a 37.3% decrease in cooling load, and a 17.4% improvement in comfort hours compared to the original design. Annual emission of greenhouse gas reduced as 167.67 tone of CO2 equivalent emission, 25.77 ton of CH4, and 0.2 ton of NO2. The mentioned algorithm was conducted for the first time on a trade center, including a DOAS system and radiant ceiling cooling system. Simultaneously, the environmental-friendly materials were dealt with. The procedure holds significant relevance for the design and optimization of buildings in Iran, especially wherever the climate is hot and humid. This approach offers advantages to the environment by reducing the impact on energy resources and utilizing environmentally-friendly materials. [ABSTRACT FROM AUTHOR]

The location planning of relief distribution centres (DCs) is crucial in humanitarian logistics as it directly influences the disaster response and service to the affected victims. In light of the critical role of facility location in humanitarian logistics planning, the study proposes a two-stage relief distribution location problem. The first stage of the model determines the minimum number of relief DCs, and the second stage find the optimal location of these DCs to minimize the total cost. To address a more realistic situation, restrictions are imposed on the coverage area and capacity of each DCs. In addition, for optimally solving this complex NP-hard problem, a novel two-phase algorithm with exploration and exploitation phase is developed in the paper. The first phase of the algorithm i.e., exploration phase identifies a near-optimal solution while the second phase i.e. exploitation phase enhances the solution quality through a close circular proximity investigation. Furthermore, the comparative analysis of the proposed algorithm with other well-known algorithms such as genetic algorithm, pattern search, fmincon, multistart and hybrid heuristics is also reported and computationally tested from small to large data sets. The results reveal that the proposed two-phase algorithm is more efficient and effective when compared to the conventional metaheuristic methods. [ABSTRACT FROM AUTHOR]

Fog computing has evolved as a promising computing paradigm to support the execution of latency-sensitive Internet of Things (IoT) applications. The mobile devices connected to the fog environment are resource constrained and non-stationary. In such environments, offloading mobile user's computational task to nearby fog servers is necessary to satisfy the QoS requirements of time-critical IoT applications. Moreover, the fog servers are also susceptible to numerous attacks which induce security and privacy issues.Offloading computation task to a malicious fog node affects the integrity of users' data. Despite the fact that there are many integrity-preserving strategies for fog environments, the majority of them rely on a reliable central entity that might have a single point of failure. Blockchain is a promising strategy that maintains data integrity in a decentralized manner. The state-of-art blockchain offloading mechnanisms have not considered the mobility during secure offloading process. Besides, it is necessary to ensure QoS constraints of the IoT applications while considering mobility of user devices. Hence, in this paper, Blockchain assisted Mobility-aware Secure Computation Offloading (MSCO) mechanism is proposed to choose the best authorized fog servers for offloading task with minimal computational and energy cost. To address the optimization issue, a hybrid Genetic Algorithm based Particle Swarm Optimization technique is employed. Experimental results demonstrated the significant improvement of MSCO when compared to the existing approaches in terms of on average 11 % improvement of total cost which includes the parameters of latency and energy consumption. [ABSTRACT FROM AUTHOR]

As pharmaceutical analysis progresses towards environmental sustainability, there is a growing need to enhance the safety and health conditions for analysts. Consequently, the incorporation of chemometrics into environmentally friendly analytical methods represents a promising approach. Favipiravir, cefixime, and moxifloxacin hydrochloride have been currently used in COVID-19 treatment. In this study, we develop spectrophotometric methods depending on chemometric based models to measure the levels of favipiravir, cefixime, and moxifloxacin hydrochloride in pharmaceutical preparations and spiked human plasma. It is challenging to determine favipiravir, cefixime, and moxifloxacin simultaneously because of overlap in their UV absorption spectra. Two advanced chemometric models, partial least square (PLS) and genetic algorithm (GA), have been developed to provide better predictive abilities in spectrophotometric determination of the drugs under study. The described models were created using a five-level, three-factor experimental design. The outcomes of the models have been thoroughly assessed and interpreted, and a statistical comparison with recognized values has been taken into consideration. The analytical eco-scale and the green analytical procedure index (GAPI) evaluation methods were also utilized to determine how environmentally friendly the mentioned models were. The outcomes demonstrated how well the models described complied with the environmental requirements. [ABSTRACT FROM AUTHOR]

This paper focuses on building a ground motion model (GMM) using artificial neural network technique driven by a synthetically generated database in a data poor region. A hybrid simulated method considering nonlinear site response is used to generate potential ground motions in Tianjin area. The synthetic database containing a total of 9267 ground motion records from 93 simulated earthquake events are utilized to develop the model. A back propagation neural network developed by genetic algorithm (GA-BPNN) is used to obtain the optimal weights and biases that most fit the target dataset without overfitting. The structure of GA-BPNN model consists of 322 unknowns including weights and biases that connect input and output parameters. The model is developed to predict PGA and 5% damped spectral acceleration (periods from 0.01 to 10 s). The input parameters consist of moment magnitude (Mw), strike (φ), dip (δ), rake angle (λ), focal depth (h), epicenter distance (R) and azimuth (θ). The model performance is observed to be within the appropriate error limits. It is found that the model has the ability to capture the parametric variation relationship. Additionally, the synthetically based model is compared with empirically based GMM relations derived from NGA-West2, finding it has similar performance and behavior to leading GMMs. The model application in Tianjin area demonstrates that this paper provides a scheme to utilize synthetic database and build GMMs in data poor regions. [ABSTRACT FROM AUTHOR]

Multiphysical optimization is particularly challenging when involving fluid–solid interactions with large deformations. While analytical approaches are commonly computational inexpensive but lack of the necessary accuracy for many applications, numerical simulations can provide higher accuracy but become very fast extremely costly. Experimental optimization approaches promise several benefits which can allow to overcome these issues in particular for application which bear complex multiphysics such as fluid–structure interactions. Here, we propose a method for an experimental optimization using genetic algorithms with a custom optimizer software directly coupled to a fully automatized experiment. Our application case is a biomimicking fish robot. The aim of the optimization is to determine the best swimming gaits for high propulsion performance in combination with low power consumption. The optimization involves genetic algorithms, more precise the NSGA-II algorithm and has been performed in still and running water. The results show a negligible impact of the investigated flow velocity. A subsequent spot analysis allows to derive some particular characteristics which leads to the recommendation to perform two different swimming gaits for cruising and for sprinting. Furthermore, we show that Exp-O techniques enable a massive reduction in the evaluation time for multiphysical optimization problems in realistic scenarios. [ABSTRACT FROM AUTHOR]

Ultra-high-pressure (UHP) water jetting is commonly used to remove rust from ship hulls. However, few studies have been undertaken to optimize the topology of reaction rotating sprinklers (RRS) using UHP. This work proposes two contributions aimed at optimizing the RRS topology and maximizing the efficiency of rust removal. The first contribution is a novel accumulative impinging-duration model, which can accurately quantify the spiral trajectory density of multiple water jets and provide a practical means to evaluate the feasibility of RRS topology. The second contribution is the development of a new meta-heuristic algorithm called adaptive genetic algorithm (AGA), which offers high-quality solutions for the combinatorial topology optimization problem associated with RRS. The AGA converges significantly faster than the conventional genetic algorithm (CGA) and avoids being trappped at a local optimum. The effectiveness of the proposed topology optimization method is demonstrated through two case studies involving RRS with different model specifications. The AGA significantly increases the utilization ratio of water-jet energy by more than 50.6 %, outperforming CGA. The rust-removal efficiency of AGA-optimized RRS is theoretically predicted by analyzing the maximal translation speed and further validated through field experiments. Results show that the rust-removal efficiency of AGA-optimized RRS for ship hulls is greatly improved, with improvements of over 50 % and 43 % in theoretical and practical verification, respectively. This research introduces a unique quantization method and an efficient optimization algorithm for practical RRS design. [ABSTRACT FROM AUTHOR]

Surface wave inversion is a key step in the application of surface waves to soil velocity profiling. Currently, a common practice for the process of inversion is that the number of soil layers is assumed to be known before using heuristic search algorithms to compute the shear wave velocity profile or the number of soil layers is considered as an optimization variable. However, an improper selection of the number of layers may lead to an incorrect shear wave velocity profile. In this study, a deep learning and genetic algorithm hybrid learning procedure is proposed to perform the surface wave inversion without the need to assume the number of soil layers. First, a deep neural network is adapted to learn from a large number of synthetic dispersion curves for inferring the layer number. Then, the shear-wave velocity profile is determined by a genetic algorithm with the known layer number. By applying this procedure to both simulated and real-world cases, the results indicate that the proposed method is reliable and efficient for surface wave inversion. [ABSTRACT FROM AUTHOR]

This paper tackles the influence of the functionalization of polystyrene and graphene oxide (GO) composites on the flammability characteristics. A microscale combustion calorimeter (MCC) was used to experimentally determine the heat release capacity (HRC), the specific heat release rate (HRR) and the total heat released (THR). Neural models were designed that correlate the THR with a number of parameters related to the composition and type of flame retardant used, the heating rate, the amount of residue, the HRC, the peak heat release rate (PHRR), the temperature at the peak pyrolysis rate (TPHRR) and the time elapsed until the occurrence of the peak heat release rate (Time). The best results in the training, validation and testing stages were achieved with the neural model with 9 neurons in the input layer, 40 neurons in the hidden layer and one neuron in the output layer. This model was incorporated into an optimization procedure, based on a genetic algorithm, to establish the values of the input parameters used in the training of the neural networks, in order to generate a minimum THR value, which is the output parameter. Since the synthesis of polystyrene particles with different GO concentrations is costly, this research helps to reduce the number of experimental tests and allows to determine the best GO concentration by means of neural models and genetic algorithms. [ABSTRACT FROM AUTHOR]

This work suggests to optimize the geometry of a quadrupole magnet by means of a genetic algorithm adapted to solve multi-objective optimization problems. To that end, a non-domination sorting genetic algorithm known as NSGA-III is used. The optimization objectives are chosen such that a high magnetic field quality in the aperture of the magnet is guaranteed, while simultaneously the magnet design remains cost-efficient. The field quality is computed using a magnetostatic finite element model of the quadrupole, the results of which are post-processed and integrated into the optimization algorithm. An extensive analysis of the optimization results is performed, including Pareto front movements and identification of best designs. [ABSTRACT FROM AUTHOR]

To appropriately construct the proportional–integral control strategy for stability enhancement of the speed performance of induction motors and current waveform, this study describes a novel optimization approach for three-phase induction motor pumps speed drive. This work provides a novel chaotic-billiards optimizer (C-BO) method. These strategies were implemented in the same hardware with modifications in the control algorithm. Both simulation and experimental investigation are carried out, and a comparative analysis of the optimized parameters is presented. The system setup is prepared and simulated in the environment of MATLAB/Simulink. The same system has been presented experimentally. The laboratory experiment is carried out in the Smart Systems Co laboratory using simulators of induction motors designed and manufactured by the Lucas-Nuelle company. The asynchronous motor is controlled by 3 phase variable speed drive A1000 of Yaskawa Co. The "ActiveServo" software included ensures user-friendly operation and visualization of the measurement values. Experiment has validated the speed the effectiveness of C-BO. The speed control and flux control using C-BO have a fast response even under pump load and improvement in rising time by 41.65% as compared to GA. The novel optimization model C-BO has improvement in integral square error (ISE) of the three controllers by 38.91% as compared to genetic algorithm systems. Furthermore, the difficulty of developing both systems is the same. The C-BO algorithm stands out for its uncomplicated design, low requirement for design specifications, high rate of convergence, and minimal computational strain. [ABSTRACT FROM AUTHOR]

The advancements in Robot-Assisted Surgery (RAS) may be a huge advantage to the healthcare systems in the world of digital OTs (Operating Theatres). RAS is a technical breakthrough that makes use of robotic articulations in order to assist the surgeon in complex surgeries. In occurrence of uncertainties and external disturbances, the control and dynamics of a highly nonlinear 3DOF surgical robot manipulator are addressed in this paper. Conventional controllers can be effective when used to single incisions and linear trajectories, but they are ineffective when applied to time-varying and nonlinear trajectories that include uncertainty. An intelligent GA (genetic algorithm) optimised adaptive fuzzy fractional-order sliding mode controller (AFFOSMC) is designed to cope with disturbances and uncertainties inherent in the system by introducing the fractional-order dynamics. GA provides optimal controller parameters for time-varying and nonlinear trajectories that include uncertainty. Therefore, the three-link surgical robot is being utilised as a case study to show the efficacy of proposed controller. The prototype of model is designed in laboratory, where its performance is validated on real-time using the OP5600 digital simulator to demonstrate the effectiveness of proposed technique. When compared with conventional controllers, the comparative analysis of simulation and experimental results of proposed AFFOSMC shed light on the efficiency and supremacy of proposed controller's performance based on time response parameters and accuracy. The attained accuracy is less than 2 mm which is imperative for the proper functioning of a surgical manipulator. [ABSTRACT FROM AUTHOR]

Heart disease is a leading cause of mortality on a global scale. Accurately predicting cardiovascular disease poses a significant challenge within clinical data analysis. The present study introduces a prediction model that utilizes various combinations of information and employs multiple established classification approaches. The proposed technique combines the genetic algorithm (GA) and the recursive feature elimination method (RFEM) to select relevant features, thus enhancing the model's robustness. Techniques like the under sampling clustering oversampling method (USCOM) address the issue of data imbalance, thereby improving the model's predictive capabilities. The classification challenge employs a multilayer deep convolutional neural network (MLDCNN), trained using the adaptive elephant herd optimization method (AEHOM). The proposed machine learning-based heart disease prediction method (ML-HDPM) demonstrates outstanding performance across various crucial evaluation parameters, as indicated by its comprehensive assessment. During the training process, the ML-HDPM model exhibits a high level of performance, achieving an accuracy rate of 95.5% and a precision rate of 94.8%. The system's sensitivity (recall) performs with a high accuracy rate of 96.2%, while the F-score highlights its well-balanced performance, measuring 91.5%. It is worth noting that the specificity of ML-HDPM is recorded at a remarkable 89.7%. The findings underscore the potential of ML-HDPM to transform the prediction of heart disease and aid healthcare practitioners in providing precise diagnoses, exerting a substantial influence on patient care outcomes. [ABSTRACT FROM AUTHOR]

Rapid placement of electric vehicle charging stations (EVCSs) is essential for the transportation industry in response to the growing electric vehicle (EV) fleet. The widespread usage of EVs is an essential strategy for reducing greenhouse gas emissions from traditional vehicles. The focus of this study is the challenge of smoothly integrating Plug-in EV Charging Stations (PEVCS) into distribution networks, especially when distributed photovoltaic (PV) systems are involved. A hybrid Genetic Algorithm and Simulated Annealing method (GA-SAA) are used in the research to strategically find the optimal locations for PEVCS in order to overcome this integration difficulty. This paper investigates PV system situations, presenting the problem as a multicriteria task with two primary objectives: reducing power losses and maintaining acceptable voltage levels. By optimizing the placement of EVCS and balancing their integration with distributed generation, this approach enhances the sustainability and reliability of distribution networks. [ABSTRACT FROM AUTHOR]

Clients can access various on-demand services and resources through the cloud-fog computing environment. Due to interdependence between activities, business processes are controlled utilizing workflow technology via the cloud, which poses one of the difficulties in optimum use of the resources, which can highly improve the quality of service (QoS) for a better user experience. In addition, it is not easy to schedule workflow applications in a Fog-Cloud environment to find the best balance between makespan, energy consumption and cost. A hybrid GA-modified PSO method is proposed in this research to assign tasks to the resources efficiently. By balancing the burden of dependent activities, the Hybrid GA (Genetic Algorithm)-modified PSO approach attempts to be less makespan, less cost, and minimize the energy consumption across heterogeneous resources in cloud-fog computing settings. The experiment's findings demonstrate that, in contrast to other algorithms, the Hybrid GA-modified PSO method reduces the overall execution time of the workflow tasks. Moreover, it lowers the cost of execution. The acquired findings further show that, compared to previous algorithms, the proposed approach converges to optimum solutions more quickly and with outstanding quality. [ABSTRACT FROM AUTHOR]

Workflow scheduling problems have been widely studied in cloud computing and edge computing, which aim to exploit cloud-edge resources to execute workflow tasks considering several constraints and optimization goals. However, in the era of Internet of things, the load of each computing task and the amount of data transferred between computing tasks will fluctuate, which changes the original workflow and needs for a new scheduling plan correspondingly. Existing methods are difficult to quickly cope with these dynamic changes and there are few studies applying neural networks to solve problems in workflow scheduling. To bridge the gap, we propose an innovative supervised learning method which leverages function-fitting strategy of neural networks to link the workflow environment and its optimal scheduling plan. Specifically, our approach can be divided into two steps, the first one is to generate dataset and train a seq2seq-based prediction models. In this step, we develop an algorithm for generating a significant amount of workflow instances while ensuring dataset diversity based on complexity estimation. Then we apply GA, NSGA, NSGA-NN three different types GA-based optimization methods to search optimal solutions. Finally, we construct dataset which includes {workflow, environment configurations → obtained optimal solution} and train a seq2seq-based model. The other part is real-time generation of scheduling plans based on trained seq2seq-based model. Simulation experiments have confirmed that our method is both effective and efficient, demonstrating its ability to adapt to changes in the execution environment, workflow task load, and task data transmission, and effectively schedule tasks in real-time. The simulation results show that the seq2seq-based prediction method can approach 90% of the optimal scheme. [ABSTRACT FROM AUTHOR]

This study explores the application of machine learning algorithms for the prediction of pan evaporation (Ep), which is a critical factor in water resource management for the assessment of water demand and usage. Specifically, this research evaluates the effectiveness of two base models: Random Forest (RF) and Multi-Layer Perceptron (MLP) and their optimized counterparts using a Genetic Algorithm (GA), designated as GA-RF and GA-MLP, for modeling Ep at a target station using data from adjacent stations. The datasets were split into a training set (70%) and a testing set (30%). The models' performances were judged using three statistical measures: Correlation Coefficient (CC), Scattered Index (SI), and Willmott's Index of agreement (WI). The enhanced models, particularly GA-MLP-5, showed superior performance with a CC of 0.8704, SI of 0.2539, and WI of 0.9212, indicating the potent ability of GA to refine RF and MLP models for predictive accuracy. Additionally, sensitivity analysis via the GA-RF indicates the varying influence of Ep from neighboring stations on the target station, shedding light on key predictors for effective water management. Conclusively, this study demonstrates that the hybrid models have significant potential in accurate Ep estimation and can be expanded to predict other meteorological variables, offering valuable tools for water resource management strategies. [ABSTRACT FROM AUTHOR]

Substantial deterioration of surface water quality, mainly caused by human activities and climate change, makes the assessment of water quality a global priority. Thus, in this study, four metaheuristic algorithms, namely the particle swarm optimization (PSO), differential evolution (DE), ant colony optimization algorithm (ACOR), and genetic algorithm (GA), were employed to improve the performance of the adaptive neuro-fuzzy inference system (ANFIS) in the evaluation of surface water total dissolved solids (TDS). Monthly and annual TDS were considered as target variables in the analysis. In order to evaluate and compare the authenticity of the models, an economic factor (convergence time) and statistical indices of the coefficient of determination (R2), Kling Gupta efficiency (KGE), root mean squared error (RMSE), mean absolute error (MAE), and Nash-Sutcliff efficiency (NSE) were utilized. The results revealed that the hybrid methods used in this study could enhance the classical ANFIS performance in the analysis of the monthly and annual TDS of both stations. For more clarification, the models were ranked using the TOPSIS approach by simultaneously applying the effects of statistical parameters, temporal and spatial change factors, and convergence time. This approach significantly facilitated decision-making in ranking models. The ANFIS-ACOR annual model considering discharge had the best performance in the Vanyar Station; Furthermore, the ANFIS-ACOR monthly model ignoring discharge was outstanding in the Gotvand Station. In total, after utilizing two defined and proposed temporal and spatial change factors, the ANFIS-ACOR and ANFIS-DE hybrid models had the best and worst performance in TDS prediction, respectively. [ABSTRACT FROM AUTHOR]

In this study, the optimization of the location of oil production and injection wells, the number of production and injection wells, and the economic evaluation in the water injection process has been carried out using three algorithms: PSO, GA, and HGAPSO. Optimizing the oil extraction process by optimizing well locations, the optimal number of production and injection wells, and economic evaluation can improve the performance and efficiency of the process. In this study, the optimization of the water injection process into oil reservoirs using the PSO, GA, and HGAPSO algorithms has been addressed. Additionally, economic evaluation, considering costs and profits from oil production using the best-optimized parameters, has been conducted, and the best Net Present Value (NPV) has been calculated. Initially, the optimal well location problem is modeled, taking into account reservoir characteristics and geological conditions. Using the PSO and GA algorithms, the best well location and number of water injection wells have been obtained, leading to improved efficiency and cost reduction. Then, the GA algorithm is used to combine and modify viewpoints and optimize the number and location of wells. This algorithm explores optimal solutions in the well location space. Economic evaluation is performed using the best-optimized parameters by the algorithms. Costs of water injection, oil production costs, and profits from increased oil production are considered. By calculating the best Net Present Value (NPV), optimal decisions regarding the water injection process and enhancing the performance of oil reservoirs are made. Simulation results indicate that the GA algorithm outperforms other algorithms and can be used as a robust and effective method for optimizing well locations and the number of production and injection wells in the oil injection process. Ultimately, this study assists the oil industry in making better decisions about optimizing water injection and improving the efficiency and profitability of the process using the introduced optimization algorithms. [ABSTRACT FROM AUTHOR]

The aim of this study is to improve the simulation effect of visual basketball teaching system. In order to solve the problem of poor visualization effect in basketball teaching system, we put forward the near infrared spectral imaging method based on genetic algorithm. The study first collected a series of near-infrared spectral image data of basketball players with different movements and postures. These image data are then optimized using genetic algorithms to obtain the best visualization results. In the process of optimization, different spectral wavelengths and reflection coefficients are considered, and the image reconstruction is optimized by iterative evolution. Through comparative experiments, the advantages of near-infrared spectral imaging based on genetic algorithm in the simulation of visual basketball teaching system are verified. The experimental results show that the NIR spectral imaging optimized by genetic algorithm can show the movement and posture characteristics of basketball players more clearly, and provide more accurate teaching guidance. [ABSTRACT FROM AUTHOR]

No-shows and non-punctual appointments have always been uncertain factors faced by managers of service-oriented enterprises and institutions, which usually lead to a low utilization rate of resources and a rapid decline in service satisfaction. Taking clinics as an example, this paper proposes a novel and efficient real-time sequencing strategy to minimize the cost associated with patient waiting time, provider idle time and overtime considering no-shows and unpunctuality. Four types of patient waiting time are considered for the first time, based on which the developed real-time sequencing strategy is used for scheduling the waiting patients when the provider becomes idle. Then, a biased random-key genetic algorithm is adopted to determine the number of patients on appointment slots and the length of each appointment slot. Extensive computational experiments show that the derived real-time sequencing strategy achieves a significant cost reduction compared with the famous FCFS (first come first served) and the state-of-art LAR (the larger of appointment time and real arrival time) rules. [ABSTRACT FROM AUTHOR]

Non-orthogonal multiple access (NOMA) communication is a potential strategy for overcoming the limits of classic orthogonal multiple access schemes, and it can improve possible rates. In contrast, MIMO–NOMA improves them even more due to multiple antenna diversity advantages. On the other hand, future wireless communication will rely on heterogeneous networks (HetNets), which allow many wireless access networks to coexist hierarchically. However, channel reciprocity is invalid because of the shorter channel coherence time in 5G and 6G communications. As a result, channel estimation through an uplink (UL) pilot no longer holds for downlink (DL) transmission. To address this issue, a statistical beamforming approach is proposed that does not consider channel reciprocity for channel estimation. Consequently, the proposed method saves the pilot transmission overhead required for channel estimation resulting in increased spectral efficiency. To achieve this, we propose to employ the characterization of the ratio of the indefinite quadratic form (IQF) to obtain a closed-form formula for the outage probability in MIMO–NOMA HetNets. The analytical expression obtained is then utilized to design optimal beamforming weights using the genetic algorithm (GA) that solves a constrained multi-objective optimization task. In summary, advantages of our proposed method are (1) it provides spectral efficient method of beamforming, (2) it derives an exact characterization of outage probability in MIMO–NOMA HetNets in closed form, and (3) it develops a GA based optimization solution that solves a constrained multi-objective optimization task simulation results presented validate the theoretical analysis and show supremacy of the proposed method over classical statistical method. [ABSTRACT FROM AUTHOR]

To address the detection difficulty problem of unmanned aerial vehicles (UAVs) in complex electromagnetic environments, this paper proposes a genetic algorithm-based heterogeneous integrated k-nearest neighbor (KNN) model for UAV signal recognition. First, the original data is pre-processed by discrete Fourier transform (DFT). Next, the genetic algorithm is deployed to find feature points for each base classifier to be integrated into the high-density power spectrum. Following this, each base classifier to be integrated is set into a strong classifier, and finally, the data to be detected is transferred to the trained integrated classifier to get the UAV signal detection results. The experimental results show that the genetic algorithm bagging KNN (GA-Bagging-KNN) algorithm achieves 98% accuracy in detecting binary classification and 79% accuracy in quadruple classification. [ABSTRACT FROM AUTHOR]

Reservoir ecological dispatching is a complex system problem involving multiple objectives, multiple criteria and multiple phases. This study established a multiobjective ecological dispatching model of the Yinma River Basin in Changchun city based on the water demand, socioeconomic development, river ecology, and constraints on reservoir characteristic parameters. Taking advantage of particle swarm optimization (PSO) and genetic algorithm (GA), a PSO-GA hybrid algorithm is proposed and applied to solve the schemes of ecological dispatching models considering different ecological flow requirements. The annual mean scheduling results show that the three scheduling schemes basically achieve the objectives of river ecological base flow scheduling. For ecologically suitable flows, the guaranteed rates for the RGOS1, RGOS2, and RGOS3 schedules at the Dehui section were 78.35%, 86.36%, and 95.98%, respectively, whereas the rates were 81.77%, 90.13%, and 96.57%, respectively, at the Nong'an section. The scheduling results of typical years show that the water security situation in the study area is not optimal, but the river ecological environment can be considerably improved by reservoir ecological dispatching. Finally, the excellent performance of the hybrid PSO-GA proposed in this study is verified via comparison with other algorithms. The Pareto front optimized by the PSO-GA can dominate the Pareto front solutions of the other algorithms. The IGD (0.19) of the Pareto front optimized by the PSO-GA is the smallest, and the SP (0.83) and HV (0.93) are the largest, indicating better convergence and comprehensive performance. [ABSTRACT FROM AUTHOR]

The tolerance allocation is an extremely sensitive task due to the complex effects on quality, product, and cost. Thus, tolerance allocation optimization covers design and manufacturing aspects and can help to bridge the gap between tolerance design and manufacturing process. Consequently, the objective of this paper is to establish a tolerance optimization method based on manufacturing difficulty computation using the genetic algorithm method with optimum parameters. To do this, the objective function of the proposed GA algorithm is to minimize the total cost. The proposed GA constraints are the tolerance equations of functional requirements considering difficulty coefficients. The manufacturing difficulty computation is based on tools for the study and analysis of reliability of the design or the process, as the Failure Mode, Effects and Criticality Analysis (FMECA) and Ishikawa diagram. The proposed approach, based on combining the Difficulty Coefficient Computation (DCC) and the GA optimization method produces the GADCC tool. This model is applied on mechanical assemblies taken from the literature and compared to previous methods regarding tolerance values and computed total cost. This comparative study highlights the benefits of the accomplished GADCC optimization method. The results lead to obtain optimal tolerances that minimize the total cost and respect the functional, quality and manufacturing requirements. [ABSTRACT FROM AUTHOR]

Neural architecture search (NAS) is an extremely complex optimization task. Recently, population-based optimization algorithms, such as evolutionary algorithm, have been adopted as search strategies for designing neural networks automatically. Various population-based NAS methods are promising in searching for high-performance neural architectures. The explosion gravitation field algorithm (EGFA) inspired by the formation process of planets is a novel population-based optimization algorithm with excellent global optimization capability and remarkable efficiency, compared with the classical population-based algorithms, such as GA and PSO. Thus, this paper attempts to develop a more efficient NAS method, called EGFA-NAS, by utilizing the work mechanisms of EGFA, which relaxes the search discrete space to a continuous one and then utilizes EGFA and gradient descent to optimize the weights of the candidate architectures in conjunction. To reduce the computational cost, a training strategy by utilizing the population mechanism of EGFA-NAS is proposed. In addition, a weight inheritance strategy for the new generated dust individuals is proposed during the explosion operation to improve performance and efficiency. The performance of EGFA-NAS is investigated in two typical micro search spaces: NAS-Bench-201 and DARTS, and compared with various kinds of state-of-the-art NAS competitors. The experimental results demonstrate that EGFA-NAS is able to match or outperform the state-of-the-art NAS methods on image classification tasks with remarkable efficiency improvement. [ABSTRACT FROM AUTHOR]

Route finding is an everyday challenge for urban residents. While many route planner applications exist, they cannot find suitable routes based on user preferences. According to user preferences, routing in a multimode urban transportation network can be considered a multiobjective optimization problem. Different objectives and modes for transportation, along with many routes as decision elements, give rise to the complexity of the problem. This study uses an elitism multiobjective evolutionary algorithm and the Pareto front concept to solve the problem. The data of a simulated multimode network consisting of 150 vertexes and 2600 edges are used to test and evaluate the proposed method. Four transport modes are considered: the metro, bus, taxi, and walking. Also, three minimization objective functions are considered: expense, discomfort, and time. The results show the competence of the algorithm in solving such a complex problem in a short run time. The optimal setting for the algorithm parameters is found by considering the algorithm run time, diversity of solutions, and convergence trend by running sensitivity analyses. A repeatability test is applied using the optimal setting of the algorithm, which shows a high level of repeatability. While NSGA-II (Non-dominated Sorting Genetic Algorithm II) may be a well-established algorithm in the literature, its application in multiobjective route finding in multimode transport networks is unique and novel. The outcomes of the proposed method are compared with existing methods in the literature, proving the better performance of the NSGA-II algorithm. [ABSTRACT FROM AUTHOR]

Identifying the rank of species in a complex ecosystem is a difficult task, since the rank of each species invariably depends on the interactions stipulated with other species through the adjacency matrix of the network. A common ranking method in economic and ecological networks is to sort the nodes such that the layout of the reordered adjacency matrix looks maximally nested with all nonzero entries packed in the upper left corner, called Nestedness Maximization Problem (NMP). Here we solve this problem by defining a suitable cost-energy function for the NMP which reveals the equivalence between the NMP and the Quadratic Assignment Problem, one of the most important combinatorial optimization problems, and use statistical physics techniques to derive a set of self-consistent equations whose fixed point represents the optimal nodes' rankings in an arbitrary bipartite mutualistic network. Concurrently, we present an efficient algorithm to solve the NMP that outperforms state-of-the-art network-based metrics and genetic algorithms. Eventually, our theoretical framework may be easily generalized to study the relationship between ranking and network structure beyond pairwise interactions, e.g. in higher-order networks. Species forming complex ecological or economic ecosystems are organized in hierarchies and the ranks of such species are determined by the adjacency matrix of their interaction network. We introduce a framework to calculate the ranks of species by finding the optimal permutation of rows and columns that makes the adjacency matrix maximally nested. [ABSTRACT FROM AUTHOR]

The generation of a large human-labelled facial expression dataset is challenging due to ambiguity in labelling the facial expression class, and annotation cost. However, facial expression recognition (FER) systems demand discriminative feature representation, and require many training samples to establish stronger decision boundaries. Recently, FER approaches have used data augmentation techniques to increase the number of training samples for model generation. However, these augmented samples are derived from existing training data, and therefore have limitations for developing an accurate FER system. To achieve meaningful facial expression representations, we introduce an augmentation technique based on deep learning and genetic algorithms for FER. The proposed approach exploits the hypothesis that augmenting the feature-set is better than augmenting the visual data for FER. By evaluating this relationship, we discovered that the genetic evolution of discriminative features for facial expression is significant in developing a robust FER approach. In this approach, facial expression samples are generated from RGB visual data from videos considering human face frames as regions of interest. The face detected frames are further processed to extract key-frames within particular intervals. Later, these key-frames are convolved through a deep convolutional network for feature generation. A genetic algorithm's fitness function is gauged to select optimal genetically evolved deep facial expression receptive fields to represent virtual facial expressions. The extended facial expression information is evaluated through an extreme learning machine classifier. The proposed technique has been evaluated on five diverse datasets i.e. JAFFE, CK+, FER2013, AffectNet and our application-specific Instructor Facial Expression (IFEV) dataset. Experimentation results and analysis show the promising accuracy and significance of the proposed technique on all these datasets. [ABSTRACT FROM AUTHOR]

The chimp optimization algorithm (ChOA) is a nature-inspired algorithm that imitates chimpanzees' individual intelligence and hunting behaviors. In this algorithm, the hunting process consists of four steps: driving, blocking, chasing, and attacking. Because of the novelty of ChOA, the steps of the hunting process have been modeled in the simplest possible way, leading to slow and premature convergence similar to other iterative algorithms. This paper proposes six spiral functions and introduces two novel hybrid spiral functions (SEB-ChOA) to rectify the abovementioned deficiencies. The SEB-ChOAs' performance is evaluated on 23 standard benchmarks, 20 benchmarks of IEEE CEC-2005, 10 cases of IEEE CEC06-2019 test-suite, and 12 constrained real-world engineering problems of IEEE CEC-2020. The SEB-ChOAs are compared with three groups of optimization algorithms, including Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) as the most well-known optimization algorithms, Slime Mould Algorithm (SMA), Marine Predators Algorithm (MPA), Ant Lion Optimization (ALO), Henry Gas Solubility Optimization (HGSO), as almost novel optimization algorithms, and jDE100 and DISHchain1e+12, as winners of IEEE CEC06-2019 competition, and also EBOwithCMAR and CIPDE as superior secondary optimization algorithms. The SEB-ChOAs reached the first rank among almost all benchmarks and demonstrated very competitive results compared to jDE100 and DISHchain1e+12 as the best-performing optimizers. Statistical evidence shows that the SEB-ChOA outperforms the PSO, GA, SMA, MPA, ALO, and HGSO optimizers while producing results comparable to those of the jDE100 and DISHchain1e+12 algorithms. [ABSTRACT FROM AUTHOR]

The increasing frequency of technological events has resulted in significant damage to the environment, human health, social stability, and economy, driving ongoing scientific development and interest in emergency management (EM). Traditional EM approaches are often inadequate because of incomplete and imprecise information during crises, making fast and effective decision-making challenging. Computational Intelligence techniques (CI) offer decision-supporting capabilities that can effectively address these challenges. However, there is still a need for deeper integration of emerging computational intelligence techniques to support evidence-based decision-making while also addressing gaps in metrics, standards, and protocols for emergency response and scalability. This study presents a coordinated decision-making system for multiple types of emergency case scenarios for technological disaster management based on CI techniques, including an Improved Genetic Algorithm (IGA), and Multi-objective Particle Swarm Optimization (MOPSO). The IGA enhances emergency performance by optimizing the task assignment for multiple agents involved in emergency response with coordination mechanisms, resulting in an approximately 15% improvement compared to other state-of-the-art methods. Ultimately, this study offers a promising foundation for future research to develop effective strategies for mitigating the impact of technological disasters on society and the environment. [ABSTRACT FROM AUTHOR]

The building sector contributes significantly to carbon emissions, impeding China's progress toward its 2030 carbon emissions peak target due to the limited utilization of renewable energy sources. This study aims to forecast the peak and timing of carbon emissions in China's construction industry to chart a low-carbon roadmap for the sector's future. Initially, an extended logarithmic mean divisia index (LMDI) decomposition model, based on the Kaya identity, is proposed to gauge the contribution levels of driving factors affecting building carbon intensity. Subsequently, a hybrid prediction model (IGA-BP) is constructed, employing an optimized two-hidden-layer neural network via a genetic algorithm, to forecast building carbon emissions and intensity. Additionally, four scenarios are outlined, each defining pathways to simulate emissions peak, carbon peak timing, and intensity within the Chinese building sector from 2020 to 2050. The research findings reveal: (1) The final emission factor of buildings primarily drives the surge in building carbon intensity, while the industrial structure stands as the most significant limiting factor. (2) Compared to alternative models, the proposed hybrid prediction model more effectively captures the evolution pattern of carbon emissions. (3) The prediction results indicate that China's building carbon intensity has reached its peak. Pathway 12 closely aligns with the sector's carbon emissions peak, projecting a peak value of 5.609 billion tons in 2029. To attain this pathway, China needs to develop more precise and feasible emission reduction strategies for its buildings. Overall, the research outcomes furnish robust references for decision-making in future efforts aimed at reducing building emissions. [ABSTRACT FROM AUTHOR]