Search

In the imprecise investment environment, there are many indeterminate factors impacting security returns. This paper introduces a portfolio optimization problem where cross-entropy is utilized to control portfolio risk within the framework of uncertainty theory and presents an uncertain bi-objective mean-entropy portfolio selection model. To be more realistic, some realistic factors such as minimum transaction lots, dividend factors and tax factors are also considered. By introducing a risk preference coefficient, the bi-objective model is converted into a single-objective model and some equivalents are discussed. Additionally, a hybrid intelligent algorithm integrating a genetic algorithm with uncertain estimation is designed to solve the proposed model. Finally, a case study is executed to confirm the practicability of the model and the performance of the algorithm, and an empirical analysis based on the proposed model and the uncertain mean–variance model is developed to illustrate the advantage of the uncertain mean-entropy model in practical investment. [ABSTRACT FROM AUTHOR]

Approximating a curve with a B-spline is a well-known problem with many challenges. Computing parametric values and knot vector that leads to the best approximation of a point sequence is an open problem. Existing methods are usually based on heuristics, genetic algorithms, or meta-heuristics. Nowadays, Deep Neural Networks have demonstrated their usefulness as shown in the use of a Multi-Layer Perceptron in the existing literature. Since its inception, the Transformer architecture has achieved state-of-the-art in multiple domains, like Natural Language Processing and Computer Vision. In this paper, we propose a method for knot placement that focuses on using a Transformer neural network architecture for B-spline approximation. We present and compare the results of our ongoing experimentations with Transformers for B-spline curve approximation. We conclude with possible improvements and modifications to our method for future experiments. [ABSTRACT FROM AUTHOR]

Purpose: This paper aims to describe the use of optimization approaches to increase the range of near-future howitzer ammunition. Design/methodology/approach: The performance of a gliding projectile concept is assessed using an aeroballistic workflow, comprising aerodynamic characterization and flight trajectory computation. First, a single-objective optimization is run with genetic algorithms to find the maximal attainable range for this type of projectile. Then, a multi-objective formulation of the problem is proposed to consider the compromise between range and time of flight. Finally, the aerodynamic model used for the gliding ammunition is evaluated, in comparison with direct computational fluid dynamics (CFD) computations. Findings: Applying single-objective range maximization results in a great improvement of the reachable distance of the projectile, at the expense of the flight duration. Therefore, a multi-objective optimization is implemented in a second time, to search sets of parameters resulting in an optimal compromise between fire range and flight time. The resulting Pareto front can be directly interpreted and has the advantage of being useful for tactical decisions. Research limitations/implications: The main limitation of the work concerns the aerodynamic model of the gliding ammunition, which was initially proposed as an alternative to reduce significantly the computational cost of aerodynamic characterization and enable optimizations. When compared with direct CFD computations, this method appears to induce an overestimation of the range. This suggests future evolution to improve the accuracy of this approach. Originality/value: To the best of the authors' knowledge, this paper presents an original ammunition concept for howitzers, aiming at extending the range of fire by using lifting surfaces and guidance. In addition, optimization techniques are used to improve the range of such projectile configuration. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of the study is to design the compensation network of a dynamic wireless power transfer system, considering the movement of the receiving coil along an electrified track with a large number of inductors buried on the road. Design/methodology/approach: A finite element model has been developed to calculate the self-inductances of transmitting and receiving coils as well as the mutual inductances between the receiving coil and the transmitting ones in the nearby and for various relative positions. The calculated lumped parameters, self-inductances and mutual inductances depending on the relative positions between the coils, have been considered to design the compensation network of the active coils, which is composed of three capacitive or inductive reactances connected in the T form. The optimal values of the six reactances, three for the transmitting coils and three for the receiving one, have been calculated by resorting to the Genetic Algorithm NSGA-II. Findings: In this paper, the results obtained by means of the optimizations have broadly discussed. The optimal values of the reactances of the compensation networks show a clear trend in the receiving part of the circuit. On the other hand, the problem seems very sensitive to the values of the reactances in the transmitting circuit. Originality/value: Dynamic wireless power transfer system is one of the newest ways of recharging electric vehicles. Hence, the design of compensation networks for this kind of systems is a new topic, and there is the need to investigate possible solutions to obtain a good performance of the recharging system. [ABSTRACT FROM AUTHOR]

Purpose: This paper aims to develop an algorithm to study the impact of dynamic resource disruption on project makespan and provide a suitable resource disruption ratio for various complex industrial and emergency projects. Design/methodology/approach: This paper addresses the RCPSP in dynamic environments, which assumes resources will be disrupted randomly, that is, the information about resource disruption is not known in advance. To this end, a reactive scheduling model is proposed for the case of random dynamic disruptions of resources. To solve the reactive scheduling model, a hybrid genetic algorithm with a variable neighborhood search is proposed. Findings: The results obtained on the PSLIB instances prove the performance advantage of the algorithm; through sensitivity analysis, it can be obtained, the project makespan increases exponentially as the number of disruptions increase. Furthermore, if more than 50% of the project's resources are randomly disrupted, the project makespan will be significantly impacted. Originality/value: The paper focuses on the impact of dynamic resource disruptions on project makespan. Few studies have considered stochastic, dynamic resource uncertainty. In addition, this research proposes a reasonable scheduling algorithm for the research problem, and the conclusions drawn from the research provide decision support for project managers. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this study is to develop a magnetic resonance imaging (MRI)-safe iron-free electrical actuator for MR-guided surgical interventions. Design/methodology/approach: The paper deals with the design of an MRI compatible electrical actuator. Three-dimensional electromagnetic and thermal analytical models have been developed to design the actuator. These models have been validated through 3D finite element (FE) computations. The analytical models have been inserted in an optimization procedure that uses genetic algorithms to find the optimal parameters of the actuator. Findings: The analytical models are very fast and precise compared to the FE models. The computation time is 0.1 s for the electromagnetic analytical model and 3 min for the FE one. The optimized actuator does not perturb imaging sequence even if supplied with a current 10 times higher than its rated one. Indeed, the actuator's magnetic field generated in the imaging area does not exceed 1 ppm of the B0 field generated by the MRI scanner. The actuator can perform up to 25 biopsy cycles without any risk to the actuator or the patient since he maximum temperature rise of the actuator is about 20°C. The actuator is compact and lightweight compared to its pneumatic counterpart. Originality/value: The MRI compatible actuator uses the B0 field generated by scanner as inductor. The design procedure uses magneto-thermal coupled models that can be adapted to the design of a variety actuation systems working in MRI environment. [ABSTRACT FROM AUTHOR]

Purpose: This paper presents the determination of the maximum power point of a bifacial photovoltaic (PV) system using two different cell models. The optimal power point is determined by using genetic algorithm (GA), as an optimisation tool. The purpose of this paper is to find which of the two analysed models gives better results in the determination of the maximum power point of a bifacial PV system for different solar irradiations. The quality of the results gained from both models is analysed based on the value of the objective function. Design/methodology/approach: In this research work, the maximum power point of bifacial PV modules is determined by using two different PV cell models, such as the simplified and two-diode models of PV cells. Based on the input electrical data for the analysed bifacial PV module as well as the mathematical model of the two PV cell presentations, the values for the current and the voltage at the maximum power point for a given solar irradiation and working temperature are determined by the algorithm for each solution in the population and generation. Findings: From the presented results and the performed analysis, it can be concluded that GA is quite appropriate for this purpose and gives adequate results for both models and for all working conditions. The two-diode model was found to be more suitable compared with the simplified model due to its complexity. Therefore, although the power difference for each of the scenarios for the two compared models does not differ significantly among the two models, it is in favour of the two-diode model. Which implicates that the for fast and simple calculation the simplified model can also do the job. Practical implications: This approach can be very successfully applied in the design process of a PV plant to forecast the output characteristics of the PV system if there is enough information about the weather conditions for a given location. This procedure can be very helpful in the process of selection of right PV module and inverter for a given location. Originality/value: An optimisation technique using GA as an optimisation tool has been developed and successfully applied in the determination of the maximum power point for a bifacial PV module using to different models of solar cell. The results are compared with the analytically determined values as well as with the values given from the producer and they show good agreement. [ABSTRACT FROM AUTHOR]

The deployment of floating photovoltaics (FPVs) is growing substantially in maritime locations. Despite the advantages gained from FPVs, it can still suffer from radiation fluctuation, which severely harms the system's production. Avoiding such obstacles can help countries like Egypt to increase their clean electricity production from its huge natural Northern Lakes. The adoption of soft computing maximum power point tracking (MPPT) algorithms showed great potential for optimizing system performance, especially the genetic algorithm (GA) and particle swarm optimization (PSO) algorithm. Yet insufficient memory and rapid radiation fluctuations can compromise algorithms. Hence, the present work addresses a hybrid GA-PSO algorithm combining the advantageous features of both algorisms to extract the MPPT from a 5.3 kW FPV system with greater frequency and accuracy in varying weather conditions, including partial shading (PS); MATLAB simulations are conducted to evaluate the proposed system's potential under a range of weather conditions. The hybrid GA-PSO outperforms GA or PSO alone while being simple to implement, with an average electrical efficiency and performance ratio of (23.40%,0.87) and (18.90%,0.79) for FPV and partially shading PSFPV, respectively. Finally, by implementing the hybrid GA-PSO, the FPV array may prevent 17.52 tons of CO 2 / season from being emitted into the air. [ABSTRACT FROM AUTHOR]

Purpose: This paper aims to provide a complete analysis framework and prediction method for the construction of the patent securitization (PS) basic asset pool. Design/methodology/approach: This paper proposes an integrated classification method based on genetic algorithm and random forest algorithm. First, comprehensively consider the patent value evaluation model and SME credit evaluation model, determine 17 indicators to measure the patent value and SME credit; Secondly, establish the classification label of high-quality basic assets; Then, genetic algorithm and random forest model are used to predict and screen high-quality basic assets; Finally, the performance of the model is evaluated. Findings: The machine learning model proposed in this study is mainly used to solve the screening problem of high-quality patents that constitute the underlying asset pool of PS. The empirical research shows that the integrated classification method based on genetic algorithm and random forest has good performance and prediction accuracy, and is superior to the single method that constitutes it. Originality/value: The main contributions of the article are twofold: firstly, the machine learning model proposed in this article determines the standards for high-quality basic assets; Secondly, this article addresses the screening issue of basic assets in PS. [ABSTRACT FROM AUTHOR]

This paper proposes a cooperative target allocation method for efficiently utilizing air-sea heterogeneous unmanned vehicles to counter saturation attacks by low-cost UAVs. Specifically, a bilevel model that combines the advantages of heuristic algorithms and the coalition formation game (CFG) is constructed by integrating unmanned vehicles' motion and attack attributes. The upper layer model aims to utilize the advantages of the heuristic algorithm to generate a feasible target allocation scheme in a shorter time. A genetic algorithm constrained by inheritance conditions (GAC) is proposed to solve the problem of the low efficiency of traditional genetic algorithms in solving the upper model. The lower layer model is established based on a coalition formation game, which aims to continuously and stably optimize the target allocation scheme. A search method based on mobile players is designed to form a stable coalition structure faster when the number of unmanned vehicles is enormous. Simulation results show the feasibility and superiority of the algorithm proposed in this paper in dealing with allocation tasks of different complexity. [ABSTRACT FROM AUTHOR]

This paper studies the dynamic output feedback (OF) control problem for unmanned aerial vehicles (UAVs) with limited network bandwidth by a genetic-algorithm-assisted design approach. In order to make full use of the limited network bandwidth, only partial measurement information is transmitted to the controller via the sensor-to-controller network. Round-Robin protocol is introduced to administrate the transmission rule. Sufficient conditions are presented to make sure that the closed-loop UAV system is exponentially stable with the required L 2 -gain performance. However, due to the nonlinear coupling terms of the dynamic OF controller parameters and some redundant variables in the system modeling, the established conditions are non-convex and difficult to be solved. Fortunately, genetic algorithms (GA) show good performance in solving optimization problem with nonlinear and non-convex constraints. Therefore, this paper skillfully combines GA with linear matrix inequality techniques to solve the established conditions. Finally, all the dynamic OF controller parameters and the minimal L 2 -gain can be obtained simultaneously. At the end of this paper, an UAV networked control example and a numerical example are performed to verify the effectiveness and superiorities of our method. [ABSTRACT FROM AUTHOR]

Purpose: The paper formulates a bi-objective mixed-integer nonlinear programming model, aimed at minimizing the total labor hours and the workload unfairness for the multi-skilled worker assignment problem in Seru production system (SPS). Design/methodology/approach: Three approaches, namely epsilon-constraint method, non-dominated sorting genetic algorithm 2 (NSGA-II) and improved strength Pareto evolutionary algorithm (SPEA2), are designed for solving the problem. Findings: Numerous experiments are performed to assess the applicability of the proposed model and evaluate the performance of algorithms. The merged Pareto-fronts obtained from both NSGA-II and SPEA2 were proposed as final solutions to provide useful information for decision-makers. Practical implications: SPS has the flexibility to respond to the changing demand for small amount production of multiple varieties products. Assigning cross-trained workers to obtain flexibility has emerged as a major concern for the implementation of SPS. Most enterprises focus solely on measures of production efficiency, such as minimizing the total throughput time. Solutions based on optimizing efficiency measures alone can be unacceptable by workers who have high proficiency levels when they are achieved at the expense of the workers taking more workload. Therefore, study the tradeoff between production efficiency and fairness in the multi-skilled worker assignment problem is very important for SPS. Originality/value: The study investigates a new mixed-integer programming model to optimize worker-to-seru assignment, batch-to-seru assignment and task-to-worker assignment in SPS. In order to solve the proposed problem, three problem-specific solution approaches are proposed. [ABSTRACT FROM AUTHOR]

The article focuses on utilizing genetic algorithms (GAs) to optimize various stages of a machine learning pipeline, specifically emphasizing data preparation and model tuning. It also provides the guidance for implementing GAs to automate labor-intensive tasks such as handling missing data, feature engineering, and hyperparameter optimization, ultimately enhancing the efficiency and robustness of machine learning models.

Geological drilling is an important means for exploration of the earth. Due to the nonlinearity and coupling, geological drilling is accompanied by low efficiency and safety, and difficult to accurately predict the drilling states. Moreover, the vertical well trajectory needs to follow the plumb line. A novel optimization method is proposed to solve these problems. First, working conditions are identified by fuzzy C-means clustering method and corresponding adjustment ranges of operating variables are refined for optimization. Meanwhile, support vector regression and hybrid bat algorithm are employed to construct reliable models for mud pit volume (MPV) and rate of penetration (ROP). Then, how to improve safety and efficiency is converted to a two-objective problem, that is to suppress MPV fluctuations and improve ROP with vertical well constraints. Nondominated sorting genetic algorithm II is invoked to solve this problem, and the appropriate solution is selected by two references points. Moreover, a short-time scale and long-time scale optimization strategy is introduced to cope with different adjustment interval of operating variables. Finally, the simulation results based on actual drilling data, application results in a semi-physical experiment system and comparison results from a vertical well verify the effectiveness and practicability for the developed method. [ABSTRACT FROM AUTHOR]

• We consider the objective empathetic relationships among experts. • The preferences of experts is handled based on their empathetic relationships. • We propose a method to determine the weights of experts based on ENA. • We propose a method to aggregate expert spatial information. • A large-scale group decision making method is proposed. Large-scale group decision making (LSGDM) involving a large number of experts has attracted more and more scholars' attention. Many LSGDM methods assumed that experts were independent to make evaluations, but the development of social media promotes the communication among experts, which makes experts no longer independent. In addition, existing LSGDM methods mainly adopted aggregation strategies such as the weighted average operator and arithmetic average operator to integrate the opinion of experts in a cluster, which makes the aggregation results cannot reflect the real opinion of the expert group. To address these issues, considering the empathetic network of experts, this study proposes an LSGDM method based on a new aggregation method for expert space information. Firstly, we determine objective weights of experts according to the objective empathetic relationships among experts. Then, the Steiner-Weber point problem is used as a prototype to establish an aggregation method called the spatial optimal aggregation (SOA) method to fuse the spatial information of experts. The model is solved by the genetic algorithm. Finally, an illustrative example about the selection of the most urgent risk in the transportation of COVID-19 vaccines is presented to show the validity and practicability of the proposed model. [ABSTRACT FROM AUTHOR]

Wind speed forecasting plays a crucial role in reducing the risk of wind power uncertainty, which is vital for power system planning, scheduling, control, and operation. However, it is challenging to obtain accurate wind speed forecasting results since wind speed series contain complex fluctuations. In this paper, a novel wind speed forecasting model is proposed by using a genetic algorithm (GA) and long short-term memory neural network (LSTM), where GA is used for evolving the architectures and hyper-parameters of the LSTM, called EvLSTM, because there is no clear knowledge to determine these crucial parameters. In the proposed EvLSTM forecasting model, a flexible gene encoding strategy, crossover operation, and mutation operation are proposed to describe the different architectures and hyper-parameters of the LSTM during the evolutionary process. In addition, to overcome the weakness of the single method for wind speed forecasting, the ensemble EvLSTM (EnEvLSTM) is proposed by using the no negative constraint theory ensemble learning strategy, whose weight coefficients are determined by the differential evolution algorithm. The proposed EvLSTM and EnEvLSTM forecasting models are evaluated on two real-world wind farms located in Inner Mongolia, China and Sotavento Galicia, Spain. Experimental results on two forecasting horizons demonstrate the superiority of EvLSTM and EnEvLSTM in terms of three performance indices and three statistical tests. [ABSTRACT FROM AUTHOR]

[Display omitted] • A framework is proposed for population-based optimization algorithms' convergence. • DIRECT's partition and population evolutions are repeated in this framework. • The global convergence of the framework is proved. • Framework is applied successfully on three population-based optimization algorithms. Population-based optimization algorithms, such as genetic algorithm and particle swarm optimization, have become a class of important algorithms for solving global optimization problems. However, there is an issue that the global convergence is often absent for most of them. This paper proposes a partition-based convergence framework for population-based optimization algorithms to solve this troubling problem. In this framework, regular partitions and evolutions of populations are implemented alternatively. Specifically, the initial population is generated from a regular partition on the search space; after several generations of evolution of the population, the evolution result is returned to join in the regular partition again, and a new population is generated. Repeat such progress until some stop condition is satisfied. Global convergence is guaranteed for the framework. Then this convergence framework is applied to particle swarm optimization, differential evolution, and genetic algorithm. The modified algorithms are globally convergent and perform better than the original version. [ABSTRACT FROM AUTHOR]

• A multi-objective profit-aware recommender system based on swarm intelligence. • A smart mutation operator has been designed and implemented for this problem. • The proposal has been compared with the only previous multi-objective approach. • The proposal has been also compared with collaborative filtering (a standard). • The experiments have been carried out based on different MovieLens datasets. Movie recommender systems are increasingly present in our daily lives, offering content of interest from streaming providers. Objectives in addition to the liking probability can be proposed to provide movie recommendations. However, there is a lack of recommenders that are aware of the benefit and that address the multi-objective nature of the problem. A profit-aware recommender system based on swarm intelligence in a multi-objective environment (multi-objective artificial bee colony, MOABC) has been designed, implemented, and applied. The proposed approach incorporates new intelligent operators that try to improve both objectives (liking probability and profit) simultaneously in each iteration instead of exclusively using randomness. This increases the quality of the recommendations with respect to the state-of-the-art algorithms. This new proposal has been evaluated using MovieLens datasets, covering different sizes (large, medium, and small). The experiments show that the MOABC performs better than collaborative filtering (CF, a standard in recommender systems) and Non-dominated Sorting Genetic Algorithm II (NSGA-II, the only multi-objective proposal in scientific literature that is profit aware) in terms of accuracy and global profit. Furthermore, statistical analysis shows that the proposed approach generates better and more robust results, also showing that the multi-objective nature of the problem must be exploited. [ABSTRACT FROM AUTHOR]

As environmental awareness grow, many organizations seek to implement Electric Vehicle (EV) fleets. Nonetheless, EVs' low driving ranges and high recharging times, and the limited Charging Stations (CS) availability make their management more challenging than conventional vehicles. The Electric Vehicle Routing Problem (E-VRP) tackles these challenges. However, many E-VRP variants drop relevant operational constraints, use overly simple models, or do not address route update solutions during operation. This work introduces a strategy to compute EV routes and update them according to observed traffic scenarios. By using an event-based EV state-space model, the strategy tracks relevant variables to account for multiple realistic elements, including nonlinear recharging function, partial recharging, mass-dependent energy consumption, maximum CS capacities, and time-dependent travel times. First, an Offline E-VRP (Off-E-VRP) variant is solved to find initial route candidates. Then, routes are periodically updated during operation according to traffic and EV state measurements by solving an Online E-VRP (On-E-VRP) variant. Genetic Algorithms (GA) are implemented to solve the problems via novel encoding and genetic operators. Finally, simulation results show that the strategy enables the fleet to fulfil its delivery duties, the pre-operation stage provides adequate initial route candidates, and the online stage can improve performance and service quality. [ABSTRACT FROM AUTHOR]

Mining high utility itemsets is an emerging and very active research area in data mining. The goal is to mine all itemsets with a utility value, in terms of importance to the user, no less than a predefined threshold value. Setting an appropriate threshold value is not trivial, requiring not only multiple trials but also the know-how in the application field. The advantage of algorithms for mining top- k high utility itemsets is they do not require such a utility threshold, but they suffer from very long runtimes and large memory requirements when large input data is considered. We propose a new genetic algorithm for mining top- k high utility itemsets, named TKHUIM-GA (Top-K High Utility Itemset Mining through Genetic Algorithms). It guides the search process by considering the utility of each item to produce initial solutions and to combine solutions accordingly, reducing the runtime and memory consumption as a result. A highly efficient data representation is utilized to reduce memory usage and runtime. A key advantage of TKHUIM-GA is that it works on positive, negative, integer and real unit utility values unlike existing approaches. Experiments on popular benchmark datasets demonstrate the high performance of the proposal regarding the state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

United multi-operator evolutionary algorithms (UMOEAs) combine multi-operator differential evolution (DE), the multi-operator genetic algorithm (MOGA), and the covariance matrix adaption evolution strategy (CMA-ES). UMOEAs-II, an improved version of UMOEAs, uses three differential evolution variants as multi-operator differential evolution (MODE), and CMA-ES. In this study, we further reform UMOEAs-II using an improved SHADE-cnEpSin that employs a novel adaptive strategy of scaling factor F , a crossover rate cr i , j updating mechanism which can calculate crossover rate for the i th individual with a particular j th component, an improved rank-based selective pressure based mutation strategy, and nonlinear population size reduction along with sequential quadratic programming method. The effectiveness of the improved rank-based selective pressure based mutation strategy, nonlinear population size reduction, and sequential quadratic programming are evident from the individual validations. The novel framework, enhanced the exploration and exploitation abilities, is named UMOEAs-III and is evaluated using the CEC2017 benchmark functions. The experiments are tested on 10, 30, 50, and 100 dimensions. The experimental results demonstrate the outstanding performance of UMOEAs-III in both low and high-dimensional tests compared to the state-of-the-art DE-based variants and hybrid algorithms. [ABSTRACT FROM AUTHOR]

The construction of low-impact development (LID) facilities has become an effective means to control urban waterlogging, but there is still a lack of scientific methods to achieve its accurate and reasonable planning and design. In this work, a high-precision hydrodynamic model was used to evaluate the construction effect of each LID facility scheme, and the fitted functional relationship was used to describe the law between the LID facility construction area and the construction effect. Finally, a genetic algorithm was used to automatically optimize the best LID facility construction scheme. Applying this method to the actual urban LID facility planning and construction, the optimal solution law is that the construction effect of single and combined LID facilities increases with the increase of construction cost. In the same low-cost construction scheme, the construction effect of combined LID facilities will be lower than that of single LID facilities, but with the continuous increase of construction cost, the construction effect of combined LID facilities will eventually be better than that of single LID facilities. According to this method, the decision-maker can get the optimal LID facility construction scheme to meet the actual engineering needs [ABSTRACT FROM AUTHOR]

The purpose of this paper is to investigate optimal control the non-linear fractional-order chaotic system of cancer cells by use of particle swarm optimization and genetic algorithms. The chaotic behavior of cancer cell growth and the tumor growth model were expressed as a system of differential equations. Then, optimal control of cancer cells using drugs was presented. Particle swarm optimization method and genetic algorithms were used to solve the problem of optimal control of cancer cell growth. The results of the control applied to the model can control the cancer cell growth. The application of control results in decreasing the number of cancer cells to zero. When the controller is applied from the beginning, the Results of genetic algorithm method are excellent. All the results obtained for the particle swarm optimization method show that this method has also been very successful and have results very close to the genetic algorithm method. [ABSTRACT FROM AUTHOR]

Saudi Arabia can be called a country with a desert and hot climate. Buildings consume more than 80% of the total electricity in this country. About 66% of the electricity in residential houses is wasted for cooling, which consequently emitted a significant CO 2. In this study, using computational fluid dynamic methods, the thermal behavior of buildings equipped with insulation was compared with conventional buildings in Saudi Arabia to determine how much adding insulation increases the capital cost and how much diminishes CO 2 emissions. For eight important areas (average temperature of 19–31 °C), insulation with a thickness of 1 to 10 cm was added to the envelopes in different positions, and the best installation location was explored in different indoor temperature scenarios using machine learning. There is a trade-off between the capital cost and operational CO 2 emissions as any insulation thickness rises, increases the former, and reduces the latter parameters. Using artificial neural network and Genetic algorithm, it was found that if the least emission of CO 2 is required, it is recommended to install insulation with a thickness of 10 cm in the outer layers, provided that the inside temperature is regulated at 27 °C. For Abha, the inside temperature should be set at 22–23 °C. The economic results revealed that each dollar investment in envelopes thermal reinforcement could diminish CO 2 emissions by up to 29.9 kg. Regardless of the economic issue, adding insulation by 10 cm led to CO 2 reduction by 66 kg m 2. y e a r [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this paper is to propose an innovative integration method based on decision-theoretic rough set and the extended VlseKriterijuska Optimizacija I Komoromisno Resenje (VIKOR) methods to address the resilient-sustainable supplier selection and order allocation (SS/OA) problem. Design/methodology/approach: Specifically, a two-stage approach is designed in this paper. First, the decision-theoretic rough set is employed to calculate the rough number for coping with the subjective uncertainty of data and assigning the weights for a resilient-sustainable evaluation criterion. On this basis, the supplier resilient-sustainable performance is ranked in combination with the extended VIKOR method. Second, a novel multi-objective optimization model is proposed that applies an improved genetic algorithm to select the resilient-sustainable supplier and allocate the corresponding order quantity under a multi-tier supplier network. Findings: The results reveal that joint consideration of resilience and sustainability is essential in the SS/OA process. The method proposed in this study based on decision-theoretic rough sets and the extended VIKOR method can handle imprecise information flexibly, reduce information loss and obtain acceptable solutions for decision-makers. Numerical cases validate that this integrated approach can combine resilience and sustainability for effective and efficient SS/OA. Practical implications: This paper provides industry managers with a new perspective on SS/OA from a resilience and sustainability perspective as a basis for best practices for industry resilience and sustainability. The proposed method helps to evaluate the resilient-sustainable performance of potential suppliers, which is applicable to solving real-world SS/OA problems and has important practical implications for the resilient-sustainable development of supply chains. Originality/value: The two interrelated priorities of resilience and sustainability have emerged as key strategic challenges in SS/OA issues. This paper is the first study of this issue that uses the proposed integrated approach. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this paper is to improve the overall heat transfer performance and the temperature uniformity of the heat sink and to explore the effects of the jet Reynolds number and the nanoparticle volume fraction of the nanofluids on the flow and heat transfer performance. Design/methodology/approach: A heat sink with discontinuous arc protrusions in the wall jet region is proposed for confined slot jet impingement. A sloping upper cover plate is added to improve the heat transfer effect in this area. An Al2O3–water nanofluid is selected as the working fluid of the jet for better heat transfer. The Standard k-e turbulence model is used for numerical calculation. The key structural parameters of the heat sink are optimized by the response surface method and a genetic algorithm. The effects of the jet Reynolds number (Re) and the nanofluid concentration (ϕ) on the flow and heat transfer performance of the optimized heat sink are investigated. Findings: The average Nusselt number of the optimal heat sink is 8.2% higher and the friction resistance is 5.9% lower than that of the initial flat plate heat sink when ϕ = 0.02 and Re = 8,000. The discontinuous arc protrusions and the sloping upper cover plate substantially enhance the heat transfer in the later stage of jet development, improving the temperature uniformity of the heat sink. The maximum temperature difference of the optimal heat sink is 28.1% lower than that of the flat plate heat sink at the same nozzle height. As the jet Reynolds number and the nanofluid particle concentration increase, the Nusselt number of the optimized heat sink and the friction coefficients increase, resulting in a decrease in the evaluation coefficient. However, the overall temperature uniformity of the heat sink is improved under all conditions. Originality/value: The novel heat sink structure provides a new way to enhance the heat transfer and temperature uniformity of confined slot jet impingement. The flow and heat transfer performance of the heat sink impinged by confined slot jet of nanofluids are obtained. The combination of response surface method and genetic algorithm can be applied to the multi-objective optimization of heat resistance and flow resistance of heat sink. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this paper is to solve the common problems that traditional optimization methods cannot fully improve the performance of electromagnetic linear actuators (EMLAs). Design/methodology/approach: In this paper, a multidisciplinary optimization (MDO) method based on the non-dominated sorting genetic algorithm-II (NSGA-II) algorithm was proposed. An electromagnetic-mechanical coupled actuator analysis model of EMLAs was established, and the coupling relationship between static/dynamic performance of the actuator was analyzed. Suitable optimization variables were designed based on fuzzy grayscale theory to address the incompleteness of the actuator data and the uncertainty of the coupling relationship. A multiobjective genetic algorithm was used to obtain the optimal solution set of Pareto with the maximum electromagnetic force, electromagnetic force fluctuation rate, time constant and efficiency as the optimization objectives, the final optimization results were then obtained through a multicriteria decision-making method. Findings: The experimental results show that the maximum electromagnetic force, electromagnetic force fluctuation rate, time constants and efficiency are improved by 18.1%, 38.5%, 8.5% and 12%, respectively. Compared with single-discipline optimization, the effectiveness of the multidiscipline optimization method was verified. Originality/value: This paper proposes a MDO method for EMLAs that takes into account static/dynamic performance, the proposed method is also applicable to the design and analysis of various electromagnetic actuators. [ABSTRACT FROM AUTHOR]

With the development of the logistics economy, problems such as the timeliness of logistics distribution and the high cost of distribution have emerged. A new adaptive genetic algorithm is proposed to solve these problems. The p c and p m values of the algorithm are related to the number of iterations and the individual fitness values. To improve the local optimization ability of the algorithm, a large neighborhood search algorithm is proposed. In addition, this study establishes a soft time window town logistics distribution model with constraints. The model considers the optimal cost as the objective function and customer satisfaction as the influencing factor. In the experiment, the proposed adaptive genetic algorithm is compared with the traditional genetic algorithm, validating the effectiveness of the proposed algorithm. • A new mathematical model of customer satisfaction is proposed. • Accurate mathematical expression of the new customer satisfaction model is given. • Some improvements are made to the adaptive genetic algorithm. [ABSTRACT FROM AUTHOR]

Some data mining, AI and data processing tasks might have data loss whose estimation/imputation is an important problem to be solved. Genetic algorithms are efficient and flexible global optimization methods able to deal with both multiple missing observations and multiple features such as continuous/discrete/binary data which are often found in multivariate databases unlike classical missing data estimation methods which only deal with univariate–continuous data. This paper presents a genetic algorithm to impute multiple missing observations in multivariate data which minimizes a new multi–objective (fitness) function based on the Minkowski distance of the means, variances, covariances and skewness between available/completed data. To do so, two sets of examples were tested: a continuous/discrete dataset which is compared to both the EM algorithm and auxiliary regressions, and a comparison over seven benchmark datasets. [ABSTRACT FROM AUTHOR]

The controller techniques for the Multiple-Input/Multiple-Output process is complex because of the difference in process dynamics that arise as a variation in process operating condition and the performance of non-linear dynamic coupling. In this work evolves real coded Genetic Algorithm tuned Adaptive Mixed Fuzzy Controller (AMFC) for Two Cylindrical Tank Interacting Level System (TCTILS). First, Adaptive Traditional Fuzzy Controller (ATFC) is developed and its output response is control action for every individual tank. Secondly, to reduce the coupling dynamics, a suitable Adaptive Coupling Fuzzy Controller (ACFC) is included into ATFC to reduce the coupling dynamic effect between each DOF. The real coded Genetic Algorithm (RGA) is used to compute the optimal scale factors for ATFC and ACFC. The simulation performance shows that the RGA tuned AMFC control scheme understands the proper dynamic behaviour of the system, a complete output response with minimum interaction and good disturbance rejection of external load. [ABSTRACT FROM AUTHOR]

Purpose: One of the main advantages of the proposed model is that it is flexible to generate n-day pairings simultaneously. It means that, despite previous researches, one-day to n-day pairings can be generated in a single model. The flexibility in generating parings causes that the proposed model leads to better solutions compared to existing models. Another advantage of the model is minimizing the risk of COVID-19 by limitation of daily flights as well as elapsed time minimization. As airports are among high risk places in COVID-19 pandemic, minimization of infection risk is considered in this model for the first time. Genetic algorithm is used as the solution approach, and its efficiency is compared to GAMS in small and medium-size problems. Design/methodology/approach: One of the most complex issues in airlines is crew scheduling problem which is divided into two subproblems: crew pairing problem (CPP) and crew rostering problem (CRP). Generating crew pairings is a tremendous and exhausting task as millions of pairings may be generated for an airline. Moreover, crew cost has the largest share in total cost of airlines after fuel cost. As a result, crew scheduling with the aim of cost minimization is one of the most important issues in airlines. In this paper, a new bi-objective mixed integer programming model is proposed to generate pairings in such a way that deadhead cost, crew cost and the risk of COVID-19 are minimized. Findings: The proposed model is applied for domestic flights of Iran Air airline. The results of the study indicate that genetic algorithm solutions have only 0.414 and 0.380 gap on average to optimum values of the first and the second objective functions, respectively. Due to the flexibility of the proposed model, it improves solutions resulted from existing models with fixed-duty pairings. Crew cost is decreased by 12.82, 24.72, 4.05 and 14.86% compared to one-duty to four-duty models. In detail, crew salary is improved by 12.85, 24.64, 4.07 and 14.91% and deadhead cost is decreased by 11.87, 26.98, 3.27, and 13.35% compared to one-duty to four-duty models, respectively. Originality/value: The authors confirm that it is an original paper, has not been published elsewhere and is not currently under consideration of any other journal. [ABSTRACT FROM AUTHOR]

The purpose of our paper is to address the multi-objective portfolio model with complex real-world constraints under the assumption that the returns of risky assets are fuzzy variables. Firstly, a new possibilistic mean-semiabsolute deviation-Yager entropy portfolio model is proposed with transaction costs, cardinality and quantity constraints Secondly, to solve the proposed model efficiently, a non-dominated sorting genetic algorithm-II (NSGA-II) is presented, which can not only reduce the computational complexity but also enhance the solution accuracy. Then, a numerical example is provided to verify the feasibility and effectiveness of our proposed model and algorithm. Based on these results, we analyze the efficient frontiers with different quantity constraints and transaction costs, and illustrate the portfolio distributions with different transaction costs by using the boxplot figures. Finally, these solutions solved by NSGA-II and four traditional computation methods are compared. Our proposed algorithm outperforms the minimax method (Polakabb, 2010), two-stage method (Masson, 2016), extended two-stage method (Li, 2012) and compromise approach-based genetic algorithm (Li, 2013) in the efficient frontier, accuracy and number of solutions. [ABSTRACT FROM AUTHOR]

This paper investigates the sliding mode control (SMC) problem of a class of Lur'e nonlinear switched systems under multi-strategy network attacks. Unlike traditional attacks, multi-strategy attacks select different attack strategies at different attack moments. False data injection (FDI) attacks may randomly occur in the sensor-to-controller (S/C) channel, leading to compromised system states. How to construct suitable sliding surface and optimal sliding matrix to ensure the dynamic performance of nonlinear switched systems in the damaged state is a key challenge. Bernoulli random distribution is used to establish the relationship model between the state of the system and attacked state. Based on this model, a sliding mode controller is designed using available state signals to ensure input-to-state in probability (ISSiP) of the closed-loop switched system and reachability of the sliding surface. A binary genetic algorithm (GA) is employed to search for the ideal sliding matrix, optimizing the sliding mode domain to enhance the system's control performance. Finally, two numerical examples are given to demonstrate the effectiveness of the obtained results. [ABSTRACT FROM AUTHOR]

A recent study conducted at King Saud University in Riyadh, Saudi Arabia, focused on improving breast cancer diagnosis through mammography using Genetic Algorithms (GA) and pre-trained Convolutional Neural Network (CNN) models. The research aimed to enhance feature selection and classification accuracy to address challenges such as low contrast and image noise. By integrating MobileNet with GA, the study demonstrated a significant improvement in classification accuracy, highlighting the method's efficacy and potential scalability to other medical imaging domains. The research has been peer-reviewed and offers innovative solutions for breast cancer imaging analysis. [Extracted from the article]

Researchers from the Department of Mathematics in West Bengal, India, have conducted a study on infectious diseases using an SIR model to understand and control their impact. The study incorporates a fractional-order epidemic model with genetic algorithm-based optimization to enhance the model's robustness. Funded by various institutions in India, the research focuses on determining equilibrium points, basic reproduction numbers, and stability criteria to effectively manage infectious diseases. The findings have been published in the Journal of Applied Mathematics and Computing and are available for further exploration. [Extracted from the article]

The article discusses the development of the AGAE score as a predictive biomarker for immune checkpoint inhibitor (ICI) therapy response in cancer patients. The AGAE score, created through transcriptomic analysis, showed strong predictive power for treatment outcomes, outperforming other biomarkers. Lower AGAE scores were associated with improved treatment response, increased immune cell infiltration, and higher antitumor immune activity. The study identified CEP55 as a potential therapeutic target to enhance immunotherapy precision. [Extracted from the article]

A study conducted at Xi'an University of Architecture and Technology in Shaanxi, People's Republic of China, focused on optimizing the performance of lateral exhaust hoods (LEH) using a combination of backpropagation neural network (BPNN) and genetic algorithm (GA). The research aimed to enhance the design efficiency of industrial exhaust hoods to improve worker health protection. The study identified critical factors influencing LEH performance, such as buoyant jet velocity, temperature, geometry, position, and exhaust velocity, emphasizing the importance of specific design parameters for optimal capture efficiency. The findings were published in Sustainable Cities and Society and can be accessed online for further information. [Extracted from the article]

A recent study conducted at Obuda University in Budapest, Hungary, focused on improving chemotherapy treatments for cancer patients. The research aimed to identify critical supervision intervals during in silico chemotherapy treatments to optimize therapy for patients. By utilizing a genetic algorithm and mathematical models, the study found that treatment time in hospitals could potentially be reduced by almost a third based on in silico tumor simulations. This peer-reviewed research provides valuable insights into enhancing cancer treatment strategies. [Extracted from the article]

A research report from the Department of Chemistry in Maharashtra, India, discusses the use of Ga-xgboost, an Explainable AI technique, along with genetic algorithms to analyze the thrombin inhibitory activity of 2803 molecules. The study found that the genetic algorithm - extreme gradient boosting model was effective in identifying structural features for drug discovery. Financial support for the research came from the Deanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University in Riyadh, Saudi Arabia. The research was peer-reviewed and concluded that Explainable AI could be valuable for future drug discovery efforts. [Extracted from the article]

Researchers from Kyungpook National University in South Korea have developed a new approach to skin lesion segmentation using a Genetic Algorithm (GA) guided feature selection. The researchers replaced the ResNet block with a custom block in the Modified TMU-Net architecture to improve adaptability to variable input sizes. The dual-pipeline design combines transformers for global representations and convolutional neural networks for local contextual representations. The GA is used to optimize image channel selection, resulting in enhanced segmentation. The proposed model achieved successful outcomes when trained on the ISIC 2017 dataset. [Extracted from the article]

Researchers at Hangzhou Dianzi University have developed an improved genetic algorithm for image segmentation in digital pathology. The algorithm addresses the limitations of traditional genetic algorithms by enhancing the selection mechanism and crossover operation, resulting in improved segmentation accuracy and computational efficiency. Experimental results demonstrate that the algorithm achieves a balance between precision and recall and outperforms traditional methods in terms of segmentation performance. The algorithm is particularly advantageous for high-precision segmentation tasks in pathology images and exhibits robustness and stability. This research provides a valuable reference for practical applications in image segmentation. [Extracted from the article]

A recent study conducted by researchers at Northern University in Barranquilla, Colombia, focuses on the design of a reverse logistics network for medical waste management. Medical waste is categorized as hazardous due to its infectious, toxic, or radioactive properties, posing risks to human health and the environment. The study proposes a bi-objective model that considers both economic factors and biomedical safety in determining the optimal quantity, depot locations, and routes for transporting waste from hospitals to treatment and disposal sites. The researchers developed a genetic algorithm to solve the complex location routing problem, and their results demonstrate the efficacy of this approach in addressing small and large instances of the problem. This research contributes to the scientific literature and provides a decision-making tool for practitioners in the field of medical waste management. [Extracted from the article]

A new report from researchers at the College of Computer and Information Sciences in Sakaka, Saudi Arabia, discusses the use of an ensemble model and deep learning algorithms to detect and classify anterior cruciate ligament (ACL) tears using knee magnetic resonance imaging (MRI). The proposed ensemble model, which combines three deep learning models and a genetic algorithm, was trained on a dataset of labeled MRI images. The model achieved high accuracy, recall, precision, specificity, and F1 score, suggesting its potential for accurately identifying and classifying ACL tears. This research was supported by the Deanship of Graduate Studies and Scientific Research at Jouf University. [Extracted from the article]

A patent has been issued for a personal health data collection system. The system includes a signal acquisition device (SAD) and a processor. The SAD has a blood flow occlusion device, a pressure sensor, and an optical blood flow detecting device. The processor uses a non-linear parametric function to estimate the diastolic blood pressure (DBP) and systolic blood pressure (SBP) of the subject by comparing predicted optical signals to measured optical signals. The system also includes features for estimating and correcting errors due to a misplaced body part and generating a correction factor to increase the accuracy of blood pressure estimation. [Extracted from the article]

A recent study conducted by researchers at Fuzhou University in Fujian, China, focuses on solving the problem of transportation between metro stations and final destinations, known as the "first/last mile" problem. The study proposes a model for designing microcirculation bus routes and coordinating schedules, taking into account the impact of shared bicycles. The researchers developed an improved genetic algorithm to solve the model and evaluated it using a case study near a metro station in Shenzhen. The results showed that considering the impact of shared bicycles led to more accurate passenger demand and reduced operating costs for public transport enterprises. The study concludes that optimal results are achieved when weight factors are set at 0.6 and 0.4 for the travel time cost of passengers and the operating cost of public transport enterprises, respectively. [Extracted from the article]

Researchers at Khulna University in Bangladesh have conducted a study on proteins, specifically focusing on the prediction of essential proteins. Essential proteins are important for cell survival and have implications in antibiotic preparation, disease diagnosis, and understanding organism structure. The researchers propose a genetic algorithm-based feature selection technique to identify essential proteins with high performance. They use different techniques for data balancing and evaluate their method using datasets from Saccharomyces cerevisiae and Escherichia coli. The proposed method outperforms existing methods in terms of accuracy, recall, and F1-score. [Extracted from the article]