Search

Multimodal perception represents a vital approach for observing non-cooperative targets in space. The accurate determination of the extrinsic parameters for monocular camera and LiDAR systems serves as the cornerstone for achieving effective space multimodal perception. However, due to factors like launch and operation, these extrinsic parameters can experience drift, thereby compromising the overall performance of the multimodal perception system. To tackle this challenge, this study introduces a novel approach: an edge feature-based external calibration method for monocular camera and LiDAR using in-orbit data. The proposed methodology involves several steps. Firstly, edges are extracted from the image, followed by distance transformation based on the edge image. The subsequent integration of the edge image and distance image yields the search scene image. Then, edge feature is extracted from the point cloud data. Finally, after constructing the objective function, genetic algorithms are used to determine precise external parameters. Simulation results underscore the effectiveness of the proposed algorithm, affirming its ability to achieve high-precision calibration results for external parameters even within intricate spatial environments. [ABSTRACT FROM AUTHOR]

• This algorithm attains attitude inversion with less data, confirming accuracy and noise resilience. The attitude of space debris holds significant implications for active debris removal and collision warnings. This study constructs a comprehensive photometry dataset for the target, utilizing angle transformation relationships and drawing upon the CZ-4C photometric data tested in the laboratory. The photometry in the dataset with noise and translation simulates the telescope observed one. We use the genetic algorithm to search for attitude parameters of the photometry that matches the simulated photometry in the dataset under the constraint of attitude angle rules. The derived and preset values of attitude parameters exhibit a strong alignment, applicable to light curves with an amplitude of about 2.5 magnitudes and noise levels up to 1.0 magnitudes. This suggests that the algorithm's accuracy is validated against the preset values, demonstrating its robust resistance to noise. Furthermore, the algorithm proposed in this study for deriving attitude from photometry requires a small amount of photometry data. This study provides a promising algorithm for future attitude analyses from telescope-observed photometry. [ABSTRACT FROM AUTHOR]

The arrangement of charging infrastructure has become an urgent issue as electric logistics vehicles (ELVs) transition from urban areas to intercity operations. In this study, we established a multi-stage layout model for intercity charging and swapping infrastructure (CSI) based on the travel characteristics of electric logistics vehicles, to minimize the investment cost of operators and the time cost of vehicle users in Hubei Province, China. Furthermore, the effect of "random", "conservative", and "radical" layout strategies for the infrastructure deployment was analyzed based on an improved genetic algorithm. It is found that the random layout strategy leads to a balance between infrastructure operators and users with the lowest total cost, which is 81.2% and 88.8% of the costs based on the radical strategy and the conservative strategy, respectively. The conservative strategy could reduce investment risks for operators with the lowest investment cost, while the radical strategy prioritizes the convenience of electric logistics vehicles, with the lowest user time cost. The case study suggests that choosing conservative strategies can bring benefits when the budget is limited, while radical strategies have more advantages when the budget is abundant. Random strategies bring the best overall social benefits. The configuration of CSI and travel characteristics of ELVs play important roles in determining layout strategies. • Travel characteristics of electric logistics vehicles is explored. • Multi-stage layout model for intercity charging and swapping infrastructure. • To minimize the investment cost of operators and the time cost of vehicle users. • The effect of random, conservative, and radical strategies is analyzed. • Results show that each strategy has its specific application scenarios. [ABSTRACT FROM AUTHOR]

• Interstellar exploration is defined as bi-objective multi-vehicle problem with profits. • Mission return increases approximately linearly with mission duration. • Lower probe numbers enable more efficient routing through shorter transfers. In the past decade, the discovery of exoplanets has sparked new interests in the idea of interstellar travel and exploration. Despite various proposals for probe concepts and relevant technologies, there is a lack of extensive literature on viable exploration strategies for journeys beyond a single star system. Such exploration strategies might not only have implications on technology development strategies for achieving interstellar exploration but could also enrich existing models for galactic exploration feeding into solutions of the Fermi Paradox. This article presents optimal strategies for the exploration of a large number of near-by stars, using a dedicated, novel methodology, which sets it apart from existing literature: For the first time, the mission design problem of interstellar exploration is redefined as a bi-objective multi-vehicle open routing problem with profits. It is tackled by an adapted hybrid multi-objective genetic algorithm, which is further improved and modified according to the problem characteristics (e. g. large search space). The overall mission model assumes probes traveling on straight trajectories, utilizing flybys, and maintaining an average velocity of 10% of the speed of light. Surpassing prior research that typically relies on statistical models or restricted star data, the star models are founded on the second Gaia data release (Gaia DR2), which represents the most extensive star catalogue to the date of this study and is employed for the first time in the context of interstellar exploration. The resulting star model contains a maximum of 10,000 stars within a spherical region around Sol, covering a distance of 110 light years. It is found, that the number of explored stars J 1 scales with mission duration J 2 and probe number m according to J 1 ∼ J 2 m 0.66 , which provides an initial guidance for future interstellar mission design. Furthermore, the routes and selection of stars vary depending on the number of probes used: When conducting missions with a large number of probes, stars in close proximity to the Solar System are given more focus. On the other hand, missions with a small number of probes include more distant stars to facilitate shorter transfers along the route. Based on these findings, the following recommendations for interstellar exploration strategies can be drawn: When energy resources such as fuel reserves are scarce and the exploration mission is not limited to nearby stars, low probe numbers are more efficient. In contrast, high probe numbers enable faster exploration of nearby stars but involve less resource-efficient transfers, making them a suitable option for small, remotely propelled probe concepts. To address crowding effects in high probe number missions, swarm-based probe concepts are recommended based on the scaling law characteristics derived. [ABSTRACT FROM AUTHOR]

Catalytic methane decomposition (CMD) stands out as a promising alternative for hydrogen production, distinguished by its ability to generate hydrogen with minimal byproducts. While some studies have explored the use of biochar as an alternative catalyst in the CMD process, the role of biochar surface functional groups and inherent properties have not been well understood. This study aimed to explore the influence of various woody biochar types, acidic sites, physicochemical properties, and operating temperatures on their catalytic activity in catalytic methane decomposition (CMD) process. Biochar derived from three biomass sources (pine, poplar, and bark) were examined at 600, 800, and 1000 °C reaction temperature. The findings revealed that heat-treated (HT) poplar biochar exhibited the lowest specific surface area (215.1 m2g⁻1) and the highest concentration of acidic sites. All samples exhibited improved performance at 1000 °C compared to other temperatures. The CH 4 conversion order was observed as HT poplar > HT red pine > HT bark, with the initial conversion of approximately 50%, 35%, and 25%, respectively. Additionally, employing genetic algorithms, kinetics models for the CMD reaction were developed. The study concluded a consistent second order reaction and an activation energy in the range of 300–330 kJ/mol for all three biochar samples. [Display omitted] • The role of acidic functional groups on biochar activity during CMD was revealed. • Poplar demonstrated the highest acidity and best catalytic performance at 1000 °C. • The O:C and H:C ratios suggested potential for carbon sequestration potential. • Biocarbon-catalyzed CMD exhibited an activation energy between 300 and 330 kJ/mol. [ABSTRACT FROM AUTHOR]

• A new constellation lifecycle cost optimization problem was introduced. • Useful insights to the satellite burn-in problem can guide satellite manufacturers. • Long testing durations are undesirable; testing can be traded off with number of satellites produced. • Combining burn-in, warranty and availability analysis opens new paths for constellation research. Constellation lifecycle costs are an important metric for constellation designers. Recurring costs of mega constellations in particular are large relative to the non-recurring costs, yet little attention has been given to the reduction of recurring costs. Moreover, few studies exist on the impacts of pre-launch activities such as satellite testing on subsequent operational reliability. We thus study the lifecycle cost impacts of environmental stress screening during acceptance testing to minimize constellation lifecycle costs. Parallels are drawn with the field of electronics testing, and costs arising from burn-in, replacement and availability are considered in our formulation. A single-objective cost minimization problem and a multi-objective cost and unavailability minimization problem are presented to capture different mission applications that require different objectives. The effects of system homogeneity and the use of sparing strategies are investigated. We propose genetic algorithms to solve the optimization problems and give some insight into how burn-in should be carried out for minimizing total costs. The optimization is also applied to a case study of a proposed mission scenario and the constellation lifecycle costs of an optimized burn-in plan are compared to those of a typical "reliability target" burn-in plan. The optimization resulted in lifecycle cost savings of around 19% while significantly reducing the burn-in duration, showing much promise in the burn-in cost optimization approach. [ABSTRACT FROM AUTHOR]

Hydraulic turbine control system is a complex system with strong nonlinearity and multiple variables. Therefore, in order to better control the turbine system, it is necessary to obtain the parameters of key components. Aiming at the limitation of the traditional particle swarm optimization algorithm in global search ability, mutation operator and dynamic inertia weight coefficient are introduced to enhance the search ability of the algorithm. In addition, in order to further improve the global search performance of the algorithm, this paper combines the optimized particle swarm optimization algorithm with genetic algorithm to form a hybrid parameter identification algorithm. The hybrid algorithm not only uses the fast convergence of particle swarm optimization (PSO), but also uses the global search advantage of genetic algorithm (GA) to realize efficient and accurate identification of turbine torque and load parameters. Through MATLAB2021a/Simulink simulation experiments, the application effect of the algorithm in the identification of turbine torque and generator load parameters is verified. The simulation results show that the optimized particle swarm optimization algorithm has significant advantages in the accuracy and robustness of parameter identification, and the identified parameters have a high degree of fitting with the actual measured torque and speed. This study not only provides a new optimization strategy for the parameter identification of turbine regulation system, but also provides an effective intelligent algorithm solution for the parameter identification of nonlinear system. [ABSTRACT FROM AUTHOR]

To improve the cell productivity of Corynebacterium glutamicum , its initial specific growth rate was improved by medium improvement using deep neural network (DNN)-assisted design with Bayesian optimization (BO) and a genetic algorithm (GA). To obtain training data for the DNN, experimental design with an orthogonal array was set up using a chemically defined basal medium (GC XII). Based on the cultivation results for the training data, specific growth rates were observed between 0.04 and 0.3/h. The resulting DNN model estimated the test data with high accuracy (R2 test ≥ 0.98). According to the validation cultivation, specific growth rates in the optimal media components estimated by DNN-BO and DNN-GA increased from 0.242 to 0.355/h. Using the optimal media (UCB_3), the specific growth rate, along with other parameters, was evaluated in batch culture. The specific growth rate reached 0.371/h from 3 to 12 h, and the dry cell weight was 28.0 g/L at 22.5 h. From the cultivation, the cell yields against glucose, ammonium ion, phosphate ion, sulfate ion, potassium ion, and magnesium ion were calculated. The cell yield calculation was used to estimate the required amounts of each component, and magnesium was found to limit the cell growth. However, in the follow-up fed-batch cultivation, glucose and magnesium addition was required to achieve the high initial specific growth rate, while appropriate feeding of glucose and magnesium during cultivation resulted in maintaining the high specific growth rate, and obtaining a cell yield of 80 g/L ini. • A novel growth medium for Corynebacterium glutamicum was developed using deep neural networks and optimization algorithms. • During the validation cultivation, high specific growth rates were observed in the proposed media. • The limiting factors for high biomass yield were identified in the proposed medium. • To optimize productivity and yield, a fed-batch culture was designed using the proposed medium. [ABSTRACT FROM AUTHOR]

In this article, we investigate the interaction of multiple steps in hybrid rocket fuel grains. Previous studies have shown the potential of single steps to increase the regression rate. In this study, we evaluate if the single step results can be translated to a multi-step approach. Of special interest are the interactions between the different step configurations. Four grain profiles are assembled by using fuel grain segments with different inner diameters, therefore forming a multi-step approximation of the profiles that can easily be manufactured and scaled up. The multi-step grains enhance the regression rate because of increased mixing and convective heat transfer induced by the recirculation zones of the steps. The experimentally obtained regression rate profiles are similar to the single step experimental data. This signifies that they are reproducible and therefore predictable. Most importantly, multiple steps do not interfere negatively with each other, which proves that steps can be used to approximate different fuel grain profiles. We show experimentally that the regression rate can be increased up to 81% by accumulating the regression rate enhancing potential of single steps. Moreover, we developed a genetic algorithm to estimate the spatially resolved Marxman parameters with only one single burn. • Results from single steps translate to multiple steps. • Regression rate profiles reproducible for multi-steps. • Multi-step grains increase regression rate by up to 81%. • Spatial resolution of Marxman law possible with genetic algorithm. • Complex fuel profiles can be approximated with steps. [ABSTRACT FROM AUTHOR]

• For the first time 100% accuracy for epileptic seizure detection using electroencephalogram signals is demonstrated. • Both balanced and unbalanced datasets are studied. • Wavelet extraction from the original EEG signal enhances the feature extraction and selection steps. • Automatic segmentation with algorithmic intelligence is used. • As opposed to Genetic algorithms fast GA is used to achieve fast analysis. The precise electroencephalogram (EEG) signal classification with the highest possible accuracy is a key goal in the brain-computer interface (BCI). Considering the complexity and nonstationary nature of the EEG signals, there is an urgent need for effective feature extraction and data mining techniques. Here, we introduce a novel pipeline based on Bat and genetic algorithms for feature construction and dimension reduction of EEG signals. After wavelet extraction and segmentation, the Bat algorithm identifies the most relevant features. We use these features and a genetic algorithm combined with a neural network method to automatically classify the segments of the epilepsy EEG signals. We also use available classification methods based on k-Nearest Neighbors or naïve Bayes for comparison purposes. The code distinguishes individual signals within various combinations of data obtained from healthy volunteers with open or closed eyes and patients suffering from epilepsy disorders during seizure-free periods or seizure activities. Compared to the previously introduced methods, our proposed framework demonstrates a superior balance of high accuracy and short runtime. The minimum achieved accuracies for balanced and unbalanced classes are 100% and 75.9%, respectively. This approach has the potential for direct applications in clinics, enabling accurate and rapid analysis of the epilepsy EEG signals obtained from patients. [ABSTRACT FROM AUTHOR]

The last-mile delivery challenges and complexity are increasing simultaneously with the e-commerce growth, the e-commerce growth constitutes a threat to urban transport, especially for big cities and developing countries. This paper examines the economic impact of crowd-shipping based on public transport collaborated with the automated parcel locker and the impact of traditional delivery, as two different methods of last-mile delivery under the same circumstances. This paper aims to assess crowd-shipping as an alternative solution for last-mile delivery compared to traditional delivery. Data has been simulated based on Cairo reality, one of the largest cities in the world. The mathematical models were formulated for the problem, where the first model objective function minimizes the costs of vehicle possession and vehicle kilometers traveled, while the second model objective function minimizes the costs of establishing lockers, vehicle possession, and vehicle kilometers traveled. A genetic algorithm has been used due to the complexity of the problem. The results show that the economic impact of the crowd-shipping delivery system is better than the traditional delivery system under the conditions of large-sized and medium-sized demand, while the economic impact of traditional delivery is better than the crowd-shipping delivery system under the conditions of small-sized demand. [ABSTRACT FROM AUTHOR]

The research on particle size classification in lunar microgravity has gradually attracted the attention of scholars. Based on the discrete element method (DEM), this work proposes a double-layer auxiliary screening vibrating screen in the form of intermediate feeding, and takes the screening efficiency and screening time as the evaluation indicators. Firstly, the Helmholtz-Maxwell coil is used to simulate the force of particles under lunar microgravity, which verifies the reliability of the numerical simulation of particles under lunar microgravity based on the discrete element method. Then, the influence of the parameters of each screen on the comprehensive performance of screening was analyzed by a single-factor experiment. Finally, based on the BP (Back Propagation) neural network optimized by genetic algorithm, the evaluation model of screen parameters and screen performance is established, and the multi-objective genetic algorithm is used to optimize the screen parameters combination scheme with excellent performance. An efficient comprehensive model of screening is provided to improve the screening performance and the design of the screen machine under lunar microgravity. [ABSTRACT FROM AUTHOR]

The increased internet usage after the pandemic led the UN Forum to improve cybersecurity measures, with zero-knowledge proofs (ZKP) being a viable solution for securing confidential information. ZKP protocols can be demonstrated through the binary puzzle, an NP-complete logic puzzle with four specific constraints. The key contribution of this paper is its successful implementation of the genetic algorithm as a new method to solve the binary puzzle. The optimized fitness function determined the solution at an average of 1.33-2.33 generations for populations ranging from 100 to 500. Its quadratic property calculated the solution faster than the ordinary linear fitness function. [ABSTRACT FROM AUTHOR]

In the literature, the reliability analysis of one-shot devices is found under accelerated life testing in the presence of various stress factors. The application of one-shot devices can be extended to the bio-medical field, where we often evidence that inflicted with a certain disease, survival time would be under different stress factors like environmental stress, co-morbidity, the severity of disease etc. This work is concerned with a one-shot device data analysis and applies it to SEER gallbladder cancer data. The two-parameter logistic-exponential distribution is applied as a lifetime distribution. For robust parameter estimation, weighted minimum density power divergence estimators (WMDPDE) is obtained along with the conventional maximum likelihood estimators (MLE). The asymptotic behaviour of the WMDPDE and the robust test statistic based on the density power divergence measure are also studied. The performances of estimators are evaluated through extensive simulation experiments. Later those developments are applied to SEER gallbladder cancer data. Citing the importance of knowing exactly when to inspect the one-shot devices put to the test, a search for optimum inspection times is performed. This optimization is designed to minimize a defined cost function which strikes a trade-off between the precision of the estimation and experimental cost. The search is accomplished through the population-based heuristic optimization method genetic algorithm. • A robust inference based on weighted density power divergence. • Elaborated study of the asymptotic property. • Testing of hypothesis based on a robust statistic. • Search for optimum inspection times using genetic algorithm. • Application to SEER gallbladder cancer data. [ABSTRACT FROM AUTHOR]

Hydrogen purification from steam methane reforming (SMR) by pressure swing adsorption (PSA) technology is a common method to obtain high-purity hydrogen. The breakthrough time can well reflect the adsorption dynamics and help PSA cycle design. In order to avoid time-consuming and labor-intensive breakthrough curve experiments, it is very necessary to develop a fast and accurate surrogate model. In this study, a genetic algorithm (GA) and artificial neural network (ANN) are combined to predict and optimize breakthrough times of adsorbates in activated carbon/zeolite layered beds. Using the Latin hypercube sampling strategy, training data sets of GA-optimized ANN (GA-ANN) obtains from the physical model of adsorption, heat and mass transfer model. The genetic algorithm (GA) optimizes the weights and biases of ANN for better performance. The ANN topology has 4 input variables (superficial velocity, activated carbon height, adsorption pressure and feed temperature) and 3 output variables (breakthrough times of CH 4 , CO and CO 2). The number of neurons in the hidden layer for the GA-ANN model was optimized as 7 to predict and optimize the maximum breakthrough time of SMR with a four-component (H 2 /CH 4 /CO/CO 2) system. The sensitivity analysis displays that relative importance to the breakthrough time is in the order of superficial velocity (40.88%) > adsorption pressure (24.55%) > activated carbon height (21.04%) > feed temperature (13.53%). To obtain high-purity hydrogen, the GA-ANN model combined with multi-objective GA optimization is used to maximize the breakthrough times of CH 4 and CO. The GA-ANN surrogate model proposed in this paper can not only accurately and quickly achieve the purpose of predicting the system breakthrough time with a high correlation coefficient (R = 0.9937) but also obtains the optimal operating conditions of PSA hydrogen purification. • A rigorous heat and mass transfer model of multi-component adsorption is established. • Artificial neural network (ANN) is well-trained by Latin hypercube sampling method. • Genetic algorithm (GA) optimizes the weights and biases of ANN for better performance. • Superficial velocity has the highest relative importance value on breakthrough time. • GA-optimized ANN model and GA combined for maximal breakthrough time of impurities. [ABSTRACT FROM AUTHOR]

Accurate isotherm models contribute to predicting the amount of adsorbate adsorbed in the adsorbent within a certain range of pressure and temperature. Experimental adsorption isotherms of five components (CO 2 , CO, N 2 , CH 4 and H 2) on pelletized zeolite 13X from publication data were correlated with common-used fundamental isotherm models, including Langmuir, Sips, dual-site Langmuir (DSL), and temperature-dependent (TD) isotherm models, including TD Langmuir, TD Sips and TD DSL. Overall, the average relative errors (AREs) of TD models are higher than those of common-used fundamental isotherm models, but TD models have better applicability. In addition, three surrogate artificial neural networks (ANNs) optimized by genetic algorithm (GA) of single- and multi-component gas adsorption isotherm models are proposed. Three GA-ANN models set the adsorption amount as the output and take one, two or three potential inputs, such as adsorption pressure, temperature and adsorbate components. Three GA-ANN models generally have lower AREs and better applicability than fundamental isotherm models and TD isotherm models. The proposed GA-ANN3 model, which has three inputs, makes a new attempt at adsorption isotherms and can fit the multi-component gas adsorption at different temperatures with the change of adsorption pressure. The adsorber dynamics for multi-component adsorption (CO 2 : CO: N 2 : H 2 = 19.9: 0.1: 44.6: 35.4 mol%) in zeolite 13X bed are compared by the extended TD Langmuir model and extended TD DSL model. Since the AREs of the TD DSL model are smaller than that of the TD Langmuir, the breakthrough curves of multi-component gas simulated by the TD DSL model are better than that of TD Langmuir. These results can contribute to relevant researchers choosing suitable adsorption isotherm models for numerical simulations of adsorption processes. • Fitted dual-site Langmuir model performs better in breakthrough curve simulation. • Artificial neural network (ANN) enables construction of adsorption isotherm models. • Genetic algorithm (GA) optimizes the weights and biases of ANN for better performance. • Three GA-ANN models have lower average relative errors and better applicability. • GA-ANN3 attempts to express adsorption isotherms for multi-component mixtures. [ABSTRACT FROM AUTHOR]

We propose a new method, called a deep-genetic algorithm (deep-GA), to accelerate the performance of the so-called deep-BSDE method, which is a deep learning algorithm to solve high dimensional partial differential equations through their corresponding backward stochastic differential equations (BSDEs). Recognizing the sensitivity of the solver to the initial guess selection, we embed a genetic algorithm (GA) into the solver to optimize the selection. We aim to achieve faster convergence for the nonlinear PDEs on a broader interval than deep-BSDE. Our proposed method is applied to two nonlinear parabolic PDEs, i.e., the Black-Scholes (BS) equation with default risk and the Hamilton-Jacobi-Bellman (HJB) equation. We compare the results of our method with those of the deep-BSDE and show that our method provides comparable accuracy with significantly improved computational efficiency. • We introduce a deep-GA method. • The method provides a better accuracy and efficiency than the deep-BSDE solver. • Efficiency and accuracy is obtained by embedding a genetic algorithm (GA). • We solve the Black-Scholes with default risk and Hamilton-Jacobi-Bellman equations. [ABSTRACT FROM AUTHOR]

The flow field dominates the process of mass transport and distribution inside the proton exchange membrane water electrolysis cell (PEMEC). Initially, a three-dimensional and non-isothermal PEMEC channel model was estimated to investigate the impact of channel height and width. Based on these results, a complete PEMEC model with a parallel flow-field pattern was developed, and the channel heights and widths of the model were optimized using a genetic algorithm (GA). Compared to the original model, the optimized model decreased the pressure drop by 34.97% at a lower voltage. In addition, because of the optimized flow-field pattern, the optimized model improves the current density on the proton exchange membrane as well as the gas holdup situation in a partial position in the cathode gas diffusion layer. • PEMEC channel height influences the gas fraction, voltage, and pressure drop. • The channel width has a stronger influence on voltage. • GA was used to optimize PEMEC channel structure with two objectives. • The optimized model was characterized by a decrease in pressure drop of 34.97%. [ABSTRACT FROM AUTHOR]

Cryogenic supercritical hydrogen storage technology is a high-density physical hydrogen storage method, which is a highly promising hydrogen storage approach. However, existing research has mainly focused on the development of storage devices for cryogenic supercritical hydrogen, with limited research on the cooling process of supercritical hydrogen. Therefore, a novel cooling process for cryogenic supercritical hydrogen production based on helium expansion cycle with liquid nitrogen (LN 2) pre-cooling is proposed in this paper. In this process, after being compressed and cooled in multiple stages, the feed hydrogen is pre-cooled by LN 2. Then, cryogenic supercritical hydrogen (10 MPa, −235.15 °C, 63.36 g/L) is obtained by helium multi-stage expansion refrigeration. The process is simulated by Aspen HYSYS and optimized by genetic algorithm (GA) to obtain lower specific energy consumption (SEC). Thermodynamic analyses are conducted to evaluate the process. And compared with the conventional hydrogen liquefaction process, the results show that the proposed process is reasonable and superior. The SEC 0 , figure of merit (FOM), and the total exergy loss of the system are 5.432 kWh/kg H2 , 43.88%, and 289.69 kW respectively. This study indicates that the proposed process has significant implications for the hydrogen industry and provides valuable information for cryogenic supercritical hydrogen storage systems. • A novel high-density cryogenic supercritical hydrogen storage system is proposed. • Twelve key variables in the process are optimized to reduce the energy consumption. • The process has higher exergy efficiency than conventional LH 2 plants. • The volume storage density of hydrogen can reach 63.36 kg/m3 in the system. [ABSTRACT FROM AUTHOR]

Sustainable management of water distribution networks (WDNs) is essential to ensure the continuous supply of water. However, the water pipes in WDNs often experience unprecedented failure, which causes disruption in services, flooding, increased maintenance costs, and reduced water quality. Although researchers have developed models to predict the failure of water pipes, the literature lacks fully optimized and robust models. Therefore, this study proposes a new methodology to develop optimized models for predicting the failure probability of water pipes by fusing logistic regression with genetic algorithms. The methodology was applied to the data of the Hong Kong WDN, and experiments were conducted to optimize the hyperparameters and features of logistic regression models. The performance of the proposed methodology is evaluated using five key metrics: accuracy, precision, recall, F1 score, and Area Under the Curve (AUC). The results show significant improvement over conventional approaches, with the best model achieving an F1 score of 0.868 and an AUC of 0.944. These results show that the model can effectively predict the failure probability of water pipes. The relative contribution of each feature to the model's outcome was investigated using the SHapley Additive exPlanations. Additionally, a web application based on the proposed methodology in this study was developed for Hong Kong that other water utility management can benefit from, which can facilitate reliable decision-making for the management of WDNs. [ABSTRACT FROM AUTHOR]

Bundle AI is a marketing tool project motivated to provide solutions for manual product bundling, a popular marketing strategy that boosts sales of low-selling products and encourages mass purchases with promising customer satisfaction. It is a cost-effective solution as it does not depend on large volumes of transactional data, which is suitable for small businesses. The bundling of products was defined as a Multiple Constraints Knapsack Problem where the best solution is determined using Genetic Algorithm. Bundle AI delivers the fit product bundle with the incorporation of the value and reward system. [ABSTRACT FROM AUTHOR]

Due to the rapid development of confidential digital communication over international networks, security is the most significant factor. Steganography is the science of concealed communication and is used to conceal the presence of secret information among the various methods of hiding data in communications. Steganography techniques are usually implemented either in spatial or frequency domains. Some spatial domain methods fundamentally utilize the absolute difference value between neighbor pixels to encode the secret message, categorized as Pixel-Value Differencing Steganography methods (PVDS). In PVDS, the hiding capacity of the adjacent pixels depends on their difference value. Consequently, the secret data will be embedded with a high visual quality of the stego-image. Indicator-based PVDS (IPVDS) technique is derived from the PVDS method. It depends on an Indicator pixel (IP) to extract the secret data correctly. The Genetic Algorithm (GA) approach to optimization depends on the concept of survival of the fittest. This paper introduces two proposals, GA-based steganography schemes (GA-IPVD) and (GA-IPVDM). These new techniques encoded secret data using the IPVDS method. Before embedding data in the cover image, the order of the pixels corresponding to the secret data is modified and rearranged. GA controls the operation of rearranging and modifying the order of pixels and all parameters. The current paper addresses steganography as an optimization problem and seeks to determine the optimal order of the pixels that enhance the matching between the cover image and stego-image to reduce distortion despite high embedded capacity. In the first proposed technique GA-IPVD, GA concentrates on the imperceptibility of embedded data and maximizes the quality of the stego-image according to the given secret data. In contrast, the GA maximizes the capacity of embedded data while maintaining an acceptable amount of stego-image quality in the second proposed technique GA-IPVDM. The proposed systems have embedding key that increase the security of proposed schemes. The experimental results demonstrate that the proposed methods can embed a large quantity of secret data while maintaining an acceptable visual quality of the stego-images. The proposed technique has also demonstrated excellent resistance to a variety of stego-attacks, including the pixel difference histogram (PDH) as well as regular and singular (RS) analyses. Additionally, the out-of-boundary pixel issue (BI), which endures in the majority of modern data hiding algorithms, has been successfully resolved. [ABSTRACT FROM AUTHOR]

• A Cascade 2-stage condensation ORC is integrated with LNG vaporizing at 6 bar. • Simultaneous optimization in 3 levels is implemented using Genetic algorithm. • Novel variable definition method accelerates accurate result achievements. • Structure, working fluids, and variables optimized considering vital constraints. • A structure is proposed based on the exergy analysis result. One of the most efficient methods of exergy recovery during the regasification process is integrating the LNG stream with an Organic Rankine Cycle (ORC) to generate electricity. This study employs a cascade structure of ORC consisting of two double-stage condensations operating at 6 bar regasification pressure. To obtain an optimal ORC system integrated with an LNG, three optimization levels for a specific heat source are addressed, including process variables, working fluids, and structure. Ten process variables and two working fluid variables for the top and bottom cycle among 13 candidates of refrigerants were optimized to provide the maximum power output. The results determined that refrigerants of R41 and R1150 have the best performance in the optimized process conditions for the top and bottom cycles, respectively. For the regasification of 36 tonnes per hour of an LNG stream, the produced net power and the exergy efficiency are achieved by 2116.76 kW and 0.29, respectively. The exergy analysis revealed that employing the double-stage condenser ORC is not a good choice. Accordingly, a cascade-parallel structure is proposed for further studies. [ABSTRACT FROM AUTHOR]

Recovering ammonia from anaerobic digestion (AD) effluent offers the opportunity to produce a renewable fertilizer and reduce environmental impact. A novel process developed for such an application was evaluated during this study. The feature of the process is integrating biogas stripping and gypsum (CaSO 4 ·2H 2 O) absorption. The result revealed that the lower CO 2 content and the absorption temperature contributed the higher efficiency of ammonia recovery. The gypsum solution recovered around 95% of the stripped ammonia when the stripping gas contained 10% CO 2 and it rose to 100% when the gas contained more than 30% CO 2. Furthermore, a statistical model and genetic algorithm were applied to estimate the total ammonia recovery and optimize the operating parameters. The experimental and modeling results indicated that integrating biogas stripping with gypsum absorption can effectively harvest ammonia nitrogen and reduce CO 2 emissions while producing (NH 4) 2 SO 4 fertilizer from AD effluent. [Display omitted] [ABSTRACT FROM AUTHOR]

[Display omitted] • An end-to-end inverse framework achieves fast identification of 3D microstructures from tailored strength, stiffness, and fatigue property. • A deep learning and genetic algorithm framework that is capable of both forward and inverse predictions. • We demonstrated the performance of this framework in the context of Ti-6Al-4V in both forward/inverse directions and achieved tailored mechanical properties with large variance. • The framework is highly transferrable to other materials and scientific fields. Materials-by-design has been historically challenging due to complex process-microstructure-property relations. Conventional analytical or simulation-based approaches suffer from low accuracy or long computational time and poor transferability, limiting their applications in solving the inverse material design problem. Here, we establish a deep learning and genetic algorithm framework that integrates forward prediction and inverse exploration. This framework provides an end-to-end solution to achieve application-specific mechanical properties by microstructure optimization. In this study, we select the widely used Ti-6Al-4V alloy to demonstrate the effectiveness and efficiency of this framework. We realize this by tailoring its 3D microstructures to achieve various yield strengths and elastic moduli across a large design space, while minimizing stress concentration factors. Compared with conventional methods, our framework is efficient, versatile, and readily transferrable to a wide range of materials and properties. Paired with emerging additive manufacturing techniques in controlling local microstructural features, our method offers far-reaching potentials for the accelerated development of application-specific, high-performing materials. [ABSTRACT FROM AUTHOR]

After the completion of the launch mission, the soft landing recovery and reuse of the carrier rocket's first-stage can effectively control the landing area to ensure safety and significantly reduce the cost of space launch transportation. The trajectory optimization of the whole process from the first section to the landing site is significant to fuel saving. In the entire process, the first-stage needs to go through three startup ignitions of course adjustment, power deceleration, and vertical landing. For this segmented fuel optimization problem, optimizing the thrust size and direction during three sections and the switching time between each section is necessary. Optimizing the vertical landing section is essential to ensure the accuracy of landing position and speed, which greatly complicates the whole process's optimization. Therefore, the optimization process of the vertical landing is substituted by a neural network predictor, which is used to obtain the mapping relationship between the initial state of the vertical landing section and the fuel consumption of the segment. Besides, the thrust profiles of the first two startup sections are reasonably handled based on physical cognition. The combination of convex optimization and neural network successfully converted the multi-stage optimal control problem into a parameter optimization problem and solved it by a genetic algorithm. Optimization results were compared with the conventional method, which indicated its superiority. [ABSTRACT FROM AUTHOR]

• An optimal path planning is proposed for spacecraft fleet to asteroids detumbling. • Optimal low-thrust trajectories for the spacecraft fleets in a 3D high perturbed asteroid environment is designed through a combined GA-Collocation method. • A deep neural network is used to rapidly approximate the gravitational acceleration of the asteroid. • The optimal problem utilized optimization method, as GA for guessing systematically the optimal initial costates, with high speed and accuracy be able to it yield consistent and reliable results. Following space discoveries, asteroids were found as rich sources of minerals and organic matter that can be exploited. In this paper, we present a precise, fast, and robust energy-optimal soft landing with a combined GA-Collocation method for a spacecraft fleet aimed at an irregular asteroid detumbling mission. It is assumed that the spacecraft fleet carried to the asteroid's equilibrium points introduced as the start locations of the mission. Here, the 433 Eros asteroid has been considered as the stony target known for its irregular elongated shape and nearly large dimension. We modeled the gravitational potential field by polyhedron as the most accurate one for such asymmetric objects. Hence, to decline the high burden computational of related equations in gravitational acceleration calculation, a Deep Neural Network with seven hidden layers and a relatively large dataset covering 6000 pairs has been developed. We utilized a Genetic Algorithm to guess systematically more optimal and reliable initial costates of some key parameters to raise the speed and accuracy of estimation. The acceptable efficiency and accuracy in optimal path prediction of the presented approach for a fleet of spacecraft approved throughout precise simulations. Eventually, the feasibility of the proposed approach is demonstrated through the corresponding results. [ABSTRACT FROM AUTHOR]

The ejector, as one of the core components of the CO 2 trans-critical ejection refrigeration system, plays an important role in improving refrigeration capacity and reducing compressor power consumption. Although the ejector can be optimized by experiment and Computational Fluid Dynamics (CFD) simulation to improve its performance, these methods are time-consuming and complicated. This study aims to propose a method to improve the performance of the CO 2 trans-critical two-phase ejector assisted by using CFD, artificial neural network (ANN), and genetic algorithm (GA). Firstly, the influence of geometric parameters on ejector efficiency was analyzed by using CFD technology, and the database was generated. Next, the complex and time-consuming CFD model was replaced by the ANN surrogate model established to predict the ejector performance. Finally, the GA method was used to optimize the ejector to maximize the ejector efficiency. The results show that the efficiency of the optimized ejector is 35.39%. The optimized ejector increases the secondary flow velocity and eliminates the vortex in ejector, and the efficiency of the optimized ejector is raised by more than 8% on average than that of initial ejector under different primary and secondary flow conditions. The research shows that the combination of CFD, ANN, and GA has higher reliability and better performance in the optimization design of CO 2 two-phase ejector. [ABSTRACT FROM AUTHOR]

An Inertial Navigation System (INS) is a standalone system that provides continuous navigation information on the position, velocity, and attitude in various conditions. Gyroscopes and accelerometers are essential components of INS. However, these sensors are prone to errors that accumulate over time and degrade the accuracy of the INS. Therefore, enhancing the performance of INS is a challenging problem. This paper aims to address this problem by proposing a method to reduce errors in real-time processing. The method uses Lifting Wavelet Transform (LWT), a popular denoising technique that belongs to the wavelet family and has an advantage over the classic wavelets in terms of time and computation complexity. Moreover, the method employs an optimization technique based on the Genetic algorithm as an intelligent averaging for combining different multi-level LWTs, which significantly improves the accuracy and efficiency of INSs. Finally, a new and implementable structure is introduced for denoising inertial sensors. The results show that the proposed method achieves an 83% and 59% improvement in gyroscope and accelerometer data for dynamic data, compared with raw data. Besides, for static data, there are 71% and 36% improvements in gyroscope and accelerometer data, respectively. [ABSTRACT FROM AUTHOR]

Demand Side Management (DSM) plays a significant role in the smart grid to minimize Electricity Cost (EC). Home Energy Management Systems (HEMSs) have recently been studied and proposed explicitly for HEM. In this paper, we propose a novel nature-inspired hybrid Genetic Flower Pollination Algorithm (GFPA) to minimize cost with an affordable delay in appliance scheduling. Our proposed GFPA algorithm combines elements of the Genetic Algorithm (GA) and Flower Pollination Algorithm (FPA) to create a hybrid approach. To assess the effectiveness of the proposed algorithm, we consider a scalable town consisting of 1, 10, 30, and 50 homes, respectively. The proposed solution finds an optimal scheduling pattern that simultaneously minimizes EC and Peak to Average Ratio (PAR) while maximizing User Comfort (UC). We assume that all homes are homogeneous in terms of appliances and power consumption patterns. Simulation results show that our proposed scheme GFPA performs better when applying Critical Peak Pricing (CPP) signal using different Operational Time Intervals (OTIs) and compared with unscheduled, GA, and FPA-based solutions in terms of reducing cost since they achieve on average 98%, 36%, 23%, and 22%, respectively. Similarly, PAR averages 98%, 36%, 59%, and 55%, respectively. While, UC comparing to GA and FPA, are around 88%, 48%, and 63%, respectively. Our proposed scheme achieves better results by applying Real Time Pricing (RTP) signals and different OTIs. As these schemes, i.e., unscheduled, GA, FPA, and GFPA, achieve cost on average 92%, 50%, 29%, and 28%, respectively. While PAR on average 94%, 39%, 62%, and 56%, and UC for GA, FPA, and GFPA on average 98%, 52%, and 49%, respectively. Overall, our proposed GFPA algorithm offers a more effective solution for minimizing EC with an affordable delay in appliance scheduling while considering PAR and UC. [ABSTRACT FROM AUTHOR]

In the present study, dynamic modeling, optimal operation and control of a reactive batch distillation process is illustrated based on experimental and simulation studies using methyl acetate production case study. An equilibrium stage model, incorporating non-ideal VLE and start-up region of heating, is developed based on data generated on an experimental unit by identifying five input parameters representing uncertainties. The optimal control problem is solved using genetic algorithm, considering the objective function identified on the basis of trend analysis using the developed dynamic model, to find the optimal reflux ratio, heat input to the reboiler, and mole ratio of methanol to acetic acid in the initial reaction mixture. Open-loop and closed-loop implementations clearly illustrate the improved performance with respect to the quantity of methyl acetate in the distillate product with a reasonably high conversion and product purity within reasonably short batch duration, illustrating the successful optimal control implementation experimentally. [Display omitted] • Dynamic model for methyl acetate production in RBD unit is developed from cold start. • 5 uncertainty parameters are identified based on open-loop and closed-loop operation. • Objective function is chosen by trend analysis with respect to independent variables. • Optimal input variables and set point profiles are determined by genetic algorithm. • Optimal policies are implemented through open-loop and closed-loop experimentation. [ABSTRACT FROM AUTHOR]

The growing demand for industrial water has motivated techniques for water reuse within the ambit of production scheduling. In batch processes, these seek to minimize freshwater usage together with an economic objective, such as makespan. It may, however, be possible to increase reuse potential by compromising on the makespan objective and intentionally delaying the start of stages so as to enable better time synchronization. This work seeks to develop a scheduling methodology for batch processes that reduce freshwater requirements by intentionally waiting between stages. A genetic algorithm-based formulation is proposed to develop such a production schedule where delays up to a maximum allowed waiting duration are introduced if it enables water reuse. The proposed scheduling strategy is demonstrated using a textile industry case study. Our results show that, on average, a 20% decrease in freshwater usage can be obtained for a single-batch campaign while for a multi-batch campaign, the savings in freshwater is nearly 59% for a 19% increase in makespan. • A strategy for minimizing freshwater in multistage, multiproduct batch processes is proposed. • Intentional waiting increases potential opportunities for discharge water from a stage to be re-used. • Production schedules with intentional waiting are generated using a genetic algorithm. • The genetic algorithm has the twin objectives to minimize freshwater use and makespan. • The strategy is demonstrated using an industrial case study from the textile industry. [ABSTRACT FROM AUTHOR]

• Dendrite morphological neuron learning is based on deterministic linkage trees. • Linkage trees overcome k -means' non-reproducibility in learning dendrites' locations. • A micro genetic algorithm speeds up the automatic hyperparameter tuning of models. • A balanced fitness function favors solutions with a low error rate and few dendrites. • The proposed approach beats its counterparts related to accuracy and model complexity. The current learning approach for smooth dendrite morphological neurons (DMNs) determines dendrite parameters using k -means clustering, which is non-reproducible due to its stochastic nature, risking falling into local minima. To overcome this issue, we introduce a DMN learning approach based on a deterministic hierarchical clustering method, which builds a linkage tree for each class of patterns. In addition, a micro genetic algorithm automatically tunes the cut-off points in the linkage trees hierarchy to create suitable clusters of dendrites. The classification experiments consider 40 real-world datasets. The proposed approach outperforms three DMN models in classification performance and is quite competitive with a hybrid morphological-linear perceptron, multilayer perceptron, random forest, and support vector machine. Therefore, the proposed method is a suitable alternative for pattern classification applications. [ABSTRACT FROM AUTHOR]

Effective project planning is crucial for the successful execution of complex industrial projects, as it can significantly reduce costs and enhance overall efficiency. However, applying precise methods for obtaining optimal project plans is often limited to small activity graphs, rendering them impractical for real-world scenarios. To address this issue, heuristic and metaheuristic algorithms have been the focus of extensive research over the past few decades. This study explores an extended problem formulation known as the Multiple Contractor-Resource Project Scheduling Problem (MC-MRCPSP). This formulation extends beyond the basic problem structure, incorporating various constraints typically encountered in industrial project scheduling. To tackle this challenging optimization problem, we propose a novel hybrid algorithm that combines a fine-tuned genetic algorithm with an advanced tabu search. This approach strikes an optimal balance between exploration and exploitation of the solution space, leading to enhanced project plan optimization. Through comprehensive experiments and evaluations, we demonstrate the effectiveness of our proposed approach. Compared to a purely genetic algorithm, our hybrid solution achieves a 38% improvement in project plan optimization. These results underscore our study's significant contribution to project planning and lay the groundwork for future advancements in MC-MRCPSP solutions. Ultimately, our research brings us closer to improved resource utilization, cost reduction, and enhanced efficiency in managing complex industrial projects. [ABSTRACT FROM AUTHOR]

Fast Flux Botnet (FFB) is an advance method developed by cyber criminals to perpetrate distributed malicious attacks. The major problems of existing FFB detection systems are the vulnerability to evasion mechanisms, long detection time, and high dimensionality of the feature set. In this study, an improved FFB detection architecture called Bot-FFX was developed to address some of these problems. The developed Bot-FFX consists of four modules: extractor, filter, resolver, and detector. The extractor module is responsible for Domain Name System (DNS) queries on domains. The filter module can classify the incoming domains as either blacklist or whitelist and sends the unclassified domains to the resolver. The resolver extracts all IP addresses associated with the domain at its Time-To-Live (TTL) within a time frame of 10 min. The detector module uses a rule-based Genetic Algorithm (GA) and K-Nearest Neighbor (KNN) for botnet detection. The detector computed the Standard Deviation of Round Trip Time (SDRTT), Average Google Hits (AGH) and Genetic Threshold Value (GTV) for all IP addresses associated with the domains. The detector, built on a decision tree rules and the K-Dimensional (KD) tree KNN algorithm, classified the domains using the set of IP addresses, SDRTT, AGH, and GTV. The Bot-FFX was implemented on a dataset of 2,000 benign domains and 1,630 botnet domains. The dataset was split into 50% training and 50% testing sets. The evaluation results on the same datasets showed that Bot-FFX is an effective FFB detection system with accuracy, false positive, and false negative of 99.178%, 0.8%, and 0.8% respectively. [ABSTRACT FROM AUTHOR]

Packaging design, as an important element in product appearance, can directly affect customers' sensory perception of the product. Many universities even offer packaging design majors, which mainly use natural science and aesthetic knowledge to promote product sales. However, many old brands remain complacent and their packaging design still adopts traditional thinking, which to some extent affects their sales. Therefore, this article decided to use genetic algorithms as a tool to parameterize the 3D fractal images in packaging design, aiming to create more creative and eye-catching packaging designs. At the end of this article, an experiment was conducted on two branches of a certain brand. Branch 1 tried out the new design provided in this article, while Branch 2 continued to use the original design. After Branch 1 fully adopted the design, sales skyrocketed, from the original daily sales of 50-60 units to 70-85 units. Branch 2 remained unchanged, with a sharp contrast. [ABSTRACT FROM AUTHOR]

With the widespread use of substation intelligent simulation systems, existing substation intelligent simulation systems have problems such as platform redundancy, system dispersion, and information sharing, which can lead to the insecurity of substation intelligent simulation systems. Therefore, this paper proposes a security operation analysis of substation intelligent simulation system based on improved genetic algorithms, aiming to improve the security of substation intelligent simulation system by using improved genetic algorithms. This paper experimentally tests that the number of vulnerabilities in a substation intelligent simulation system using improved genetic algorithms is between 0 and 20 within a month, while the number of vulnerabilities in a traditional substation intelligent simulation system is between 30 and 50, indicating that improved genetic algorithms do have the effect of improving the safety coefficient of the substation intelligent simulation system. [ABSTRACT FROM AUTHOR]

To achieve the goal of exploiting all the advantages and avoiding the disadvantages, this paper presents a genetic algorithm-based development to integrate the spider colony algorithm for teaching optimization of English data recommendation methods. This algorithm first takes advantage of the genetic algorithm to extract the pheromone required by the ant colony algorithm, and then obtains a good solution through the fast and comprehensive integration mechanism of the global optimization of the ant colony algorithm. Therefore, combining the two algorithms can increase the processing time and efficiency. According to the experimental results, compared to using the genetic algorithm or the ant colony algorithm, the violation of the soft parameters of the training data based on the genetic ant hybrid algorithm is reduced to a minimum, and the feasibility and quality of the training data are good. alone. The power of our algorithm is directly proportional to the number of assignments. The security of the algorithm seems to be stable when the number of scales reaches one. For the same scale, the power of the hybrid genetic colony algorithm is the highest, the ant colony algorithm is the second, and the genetic algorithm is the last. When the class setting is 500, when the motor reaches 300, the algorithm stops working and the test is repeated 10 times. The genetic ant colony hybrid algorithm needs the shortest time to reach the fitness value. Conclusion: this algorithm is much better than genetic algorithm or spider colony algorithm. [ABSTRACT FROM AUTHOR]

Hyper-heuristics can be applied to solve complex optimization problems. However, they need a substantial number of fitness function evaluations to discover a good approximation to the global optimum, especially for large-scale problems. Recently, surrogate-assisted algorithms have drawn increasing attention, and have shown their potential to deal with expensive complex optimization problems. This paper aims to use surrogates to approximate HHGA's (Ahmed Bacha et al., 2019) fitness functions, an efficient hyper-heuristic for solving the permutation flowshop problem, one of the most important scheduling types in modern industries. The objective is to approximate, in an online approach, the fitness function, reducing considerably the execution time of HHGA while maintaining its quality. The proposed online surrogate model is mainly designed to capture the details of the fitness function to enhance the accuracy estimation. The experimental results on Taillard's widely used benchmark problems show that the proposed fitness approximation-assisted HHGA is able to achieve competitive performance on a limited computational budget. [ABSTRACT FROM AUTHOR]

A mobile stroke unit (MSU) is an advanced ambulance equipped with specialized technology and trained healthcare personnel to provide on-site diagnosis and treatment for stroke patients. Providing efficient access to healthcare (in a viable way) requires optimizing the placement of MSUs. In this study, we propose a time-efficient method based on a genetic algorithm (GA) to find the most suitable ambulance sites for the placement of MSUs (given the number of MSUs and a set of potential sites). We designed an efficient encoding scheme for the input data (the number of MSUs and potential sites) and developed custom selection, crossover, and mutation operators that are tailored according to the characteristics of the MSU allocation problem. We present a case study on the Southern Healthcare Region in Sweden to demonstrate the generality and robustness of our proposed GA method. Particularly, we demonstrate our method's flexibility and adaptability through a series of experiments across multiple settings. For the considered scenario, our proposed method outperforms the exhaustive search method by finding the best locations within 0.16, 1.44, and 10.09 minutes in the deployment of three MSUs, four MSUs, and five MSUs, resulting in 8.75x, 16.36x, and 24.77x faster performance, respectively. Furthermore, we validate the method's robustness by iterating GA multiple times and reporting its average fitness score (performance convergence). In addition, we show the effectiveness of our method by evaluating key hyperparameters, that is, population size, mutation rate, and the number of generations. [ABSTRACT FROM AUTHOR]

The string site-removal problem (SSRP) originates from the field of computational biology and is known to be NP-hard. The problem is defined on the set of strings of equal length and an integer k, and its goal is to find the largest subset of the strings that become identical after removing at most k sites (columns). This paper proposes two new approaches to SSRP. The first is an exact algorithm that uses the quadratically constrained program (QCP). The second approach combines QCP and genetic algorithm (GA). In a series of experiments, we showed that our exact program performs faster on average than the state-of-the-art method (Integer Linear Programming, ILP). Regarding heuristic approaches, our new proposal gives the identical results as the state-of-the-art reference method (Large Neighborhood Search, LNS) with the same CPU time budget. All source codes and benchmark instances we made publicly available via GitHub. [ABSTRACT FROM AUTHOR]

Natural Language Processing (NLP) systems have, over the past decade, shifted from using rule-based techniques to using machine learning-based algorithms. This has led to the development of different architectures and models for different tasks. Some of these architectures include models like the transformers, the CNN and the RNN, which have now become ubiquitous in NLP. However, designing these neural network architectures usually requires in-depth analysis and knowledge of multiple domain areas involved with the problem at hand. In our work, we evaluate an alternative solution to this problem in the domain of text classification. Here, we suggest using the Genetic Algorithm with gradient descent (GAGD) and NeuroEvolution of Augmenting Topologies (NEAT) to search for an optimal neural architecture for the Reuters-21578 and 20 Newsgroups datasets. We evaluate and compare the results of the two algorithms against the current state-of-the-art architectures and provide insight into their performance. [ABSTRACT FROM AUTHOR]

The performance and power of Wavelet Neural Networks (WNNs) rely on the proper structure of the WNN. In this study, a hybrid approach is suggested to build a Wavelet Neural Network. We design a network based on the genetic algorithm (GA), the Gram-Schmidt Selection (GSS) method, and the multilibrary wavelet function (MLWF). The initialization of the WNN is performed by the GSS method, which aims to select the candidate library wavelet functions (MLWF) to develop the WNN. The GA is used to solve the structure and the learning of the WNN and the GSS algorithm is applied to select the important wavelets. The GA was used to calculate the suitable values of the Network parameters, to solve the structure and learning of the WNN. In this research, the GSS method is used to determine a set of best wavelets whose centres and dilation parameters are used as initial values for subsequent training. Experimental tests proved that the proposed approach is very efficient and accurate. [ABSTRACT FROM AUTHOR]

Air source heat pump is recognized as an effective environmental protection and energy-saving technology. The heating temperature lift is one of the key factors affecting the performance of heat pump systems. In this paper, an in-depth quantitative thermodynamic comparison of cascade heat pump, recuperative heat pump and CO 2 heat pump for direct-heating and space heating was conducted. Aspen HYSYS was used to invoke advanced genetic algorithm in MATLAB to optimize the system parameters. The temperature matching in heat exchangers was employed to reveal the essence of the performances of different heat pump systems. The recuperative heat pump is more suitable for direct-heating with the temperature lift 60 °C, and its COP is up to 4.81 at the ambient temperature of 20 °C. The cascade heat pump performs best in space heating with the maximum COP of 2.47. The exergoeconomic factor of the compressor is less than 7%, which illustrated that the investment in compressor should be increased to further improve the system efficiency. The annual CO 2 and SO 2 lowest emissions is 4431 kg and 130 kg of recuperative heat pump for direct-heating, and the cascade heat pump has the lowest annual 4234 kg CO 2 and 127 kg SO 2 emissions for space heating. [ABSTRACT FROM AUTHOR]

• Optimal location of interurban electric vehicle charging station infrastructure. • Multi-objective genetic algorithm to improve stalls utility and stations coverage. • Experimental results in the USA improve the current infrastructure. In recent years, there has been a strong desire to meet the challenge of electrification of vehicles in order to achieve the decarbonization objective. However, as sales of electric vehicles have increased, there is a significant lack of infrastructure to support the charging of this type of vehicle. The infrastructural deficiencies are even more evident in the interurban environment, where the autonomy in kilometers of the battery is a critical issue. To minimize the substantial economic costs involved in installing sufficient charging points to ensure any interurban journey, it is necessary to establish mechanisms that evaluate appropriate locations to deploy the necessary stations. Accordingly, this paper proposes using an evolutionary approach to calculate the most suitable locations in an interurban environment for electric charging stations. For this purpose, different input information is taken into account in the allocation process. The proposed algorithm has been tested using real data from the USA. The results assess the current infrastructure and show the advantages of the locations proposed by the algorithm. [ABSTRACT FROM AUTHOR]

The satellite motion on the reference orbit (RO) with less energy consumption has always persuaded researchers to design optimal control systems. The nonlinear nature and time-varying equations of motion make this quest more challenging. The present study proposes a novel control system for satellite motion on the RO by considering a comprehensive model of its dynamics in orbit and a Nonlinear Model Predictive Controller (NMPC). The NMPC calculates the sub-optimal control inputs of satellite motion reference on the elliptic orbit by minimizing a convex cost function at each stage. Moreover, all weighting parameters of the cost function are optimized by the Genetic Algorithm (GA) to produce less perturbation and guarantee the best NMPC performance. Finally, the implemented NMPC has been compared to a Linear MPC (LMPC). The results show that not only can the NMPC resist against larger errors and perturbations, but it can also compensate for those errors by returning the satellite to its main orbit and maintaining it. [ABSTRACT FROM AUTHOR]

Due to the explosive growth and dynamic change of user demand, an efficient power and bandwidth allocation algorithm is quite essential for multibeam satellites with flexible digital payloads. To suit the real-time use of the multibeam satellites communication, we build a novel deep reinforcement learning (DRL) architecture for dynamic power and bandwidth allocation. For minimizing unmet system capacity (USC), the proposed DRL architecture adopts proximal policy optimization algorithm to directly allocate the resource in continuous space. Under the proposed DRL architecture, the DRL strategy for joint power and bandwidth allocation (named as pbDRL) reaps the best USC performance in comparison with the separate power or bandwidth allocation method of pDRL and bDRL. Besides, by implementing the allocation decision determined by pbDRL into the initial population of the existing genetic algorithm (GA), we also develop another improved GA, namely drlGA. Numerical results verify that (i) pbDRL outperforms the existing GA and PSO; (ii) pbDRL achieves comparable USC performance within a significantly reduced computation time compared with the existing optimized GA method; (iii) in comparison with the other three related heuristic algorithms, drlGA derives improved USC performance within the same computation time. These results draw a conclusion that the developed pbDRL and drlGA approaches are capable to meet the requirements of high timeliness and desirable demand satisfaction, respectively. • Allocate power and bandwidth jointly and dynamically in multibeam satellites. • Use proximal policy optimization algorithm to directly allocate continuous resource. • Achieve comparable unmet system capacity with dramatically reduced computation time. • Also can be applied to separate only power or bandwidth allocation. • Also develop another genetic algorithm for further improved unmet system capacity. [ABSTRACT FROM AUTHOR]