Intelligent Genetic Algorithm Research Articles

Total oxidation of toluene at low temperatures in air using sono-impregnated Mn/Cu bimetal over activated clinoptilolite as a nanocatalyst: Designing the oxidation reaction rate with the optimization of the fixed bed reactor CFD model

A series of manganese-copper oxides on clinoptilolite with various impregnation sequences were synthesized using ultrasonic irradiation. Their properties were characterized by XRD, BET, FTIR, FESEM, and EDX techniques. The XRD patterns confirmed the formation of Mn2O3/MnO and CuO as the crystalline phase on clinoptilolite. FESEM images confirmed that manganese and copper dispersed on support in nano-range size. EDX results indicated uniform dispersion of the elements. FTIR patterns demonstrated that surface groups of nanocatalysts agree with the patterns of metals and support applied in nanocatalysts synthesis. Catalysts were investigated in the oxidation of toluene from the polluted air. Results showed that bimetallic nanocatalysts are more active than single metal oxide nanocatalysts) Mn2O3/MnO/CuO(causing the synergism effect of active phases. The highest catalytic activity was observed on the Mn/Cu/CLT nanocatalyst in which excess manganese oxide as active sites existed on the support and led to a decreased complete oxidation temperature of toluene. The result of toluene oxidation from the polluted air demonstrated that the prepared nanocatalyst was very active and stable. Also, the Mars–Van Krevelen kinetic model and the calculated kinetic parameters of this model were used to develop and express the toluene catalytic oxidation reaction rate on newly synthesized catalysts using the combination of CFD method with an intelligent genetic optimization algorithm. All results obtained using this method have an RMSE less than 0.1. Also, the activation energy based on the Arrhenius law for the toluene oxidation reaction using the Mn/Cu/CLT optimal nanocatalyst was calculated by this method equal to 98480 J/mol with RMSE 0.0248.

Virtualized intelligent genetic load balancer for federated hybrid cloud environment using deep belief network classifier

Load balancing is major issue in federated cloud environment. Various services can be offered by different cloud service providers. As per current working environment cloud computing is used in major applications such as education, online shopping, multimedia services, etc. Dynamic load balancing is required to handle the resources. Federated cloud has various services offering system with computing resources, resource pooling, internet access services and storage. Intelligent Genetic algorithm is proposed to provide efficient load balancing service in hybrid cloud environment. Virtualized Intelligent Genetic Load Balancer algorithm consists of load balancer and resource provisioning system to allocate the resources. Enhanced Load Balancer is used to preserve the load and minimize the span time based on resource provisioning method. In this work we analyse automated virtual machine services by using runtime resource provision. Here we use enhanced load balancer to measure the performance using virtual machine placements, resource utilization and automated quality requirements. We design a deep belief network based on requirements and measure the accuracy using TensorFlow. The simulation results test the accuracy and compare the results. Virtualized Intelligent Genetic Load Balancer system is achieving the accuracy of 95% based on overall capacity requirements. We compare Virtualized Intelligent Genetic Load Balancer system performance with existing simulations results and compared the results.

NeuroCrossover: An intelligent genetic locus selection scheme for genetic algorithm using reinforcement learning

Researchers have been studying genetic algorithms (GAs) extensively in recent decades and employing them to address extremely challenging combinatorial optimization problems (COPs). Although GAs achieve superior performance, they are less efficient because most GAs are designed manually without intelligent parameter configuration to support scalable problem-solving strategies and learnable evolutionary operators. To address this issue, machine learning (ML) techniques have been integrated with GAs for operator and parameter selection, however, few studies have focused on intelligent genetic locus selection for influential operators in GAs. To fill this gap, this paper proposes an intelligent genetic locus selection algorithm that serves as the foundation of parameter configuration for critical operators. With the established framework, the Cross Information Synergistic Attention (CISA) model and the n-step proximal policy optimization (PPO) have been utilized to intelligently select the appropriate genetic locus for the most influential phase, i.e., crossover, during the evolutionary process. The proposed NeuroCrossover algorithm is validated on extensive COPs, including the traveling salesman problem, capacitated vehicle routing problem, and bin packing problem. The results demonstrate the efficiency and effectiveness of our algorithm, which outperforms other methods in terms of solution quality, convergence speed, and generalization. For instance, with the CISA, the average percentage gaps of our algorithm are 3.64% and 6.38% for instances in TSPLIB and CVRPLIB, respectively, obtaining gains of about 0.47% and 1.20% compared to those of GA. The proposed algorithm provides a novel solution to lead GAs to an efficient search and improve their scalability and learnability.

Early warning and detection of geological disasters based on intelligent genetic algorithm

Abstract In recent years, the frequent occurrence of earthquakes, landslides, debris flow and other geological disasters worldwide is endangering people's production and life, which not only causes serious damage to infrastructure, but also creates a certain degree of fear for people. Geological disaster is an open nonlinear complex system, which has extraordinary complex geological process, formation conditions, and causes. Therefore, it makes difficulty in capturing the dynamic information and searching for the global optimal solution. Meanwhile, traditional geological disaster warning system has the deficiencies of single disaster warning and low accuracy. In order to improve the level of early warning and detection of geological disasters, this paper combined the genetic algorithm with superior performance and Support Vector Regression (SVR) algorithm to establish a feasible and credible early warning and monitoring model for geological disasters. The experimental results show that the early warning and monitoring model proposed in this paper can greatly improve the ability of geological disaster prevention and early warning, and greatly improve the level of disaster prevention and early warning, with good engineering application value.

A Robust Controller of a Reactor Electromicrobial System Based on a Structured Fractional Transformation for Renewable Energy

The focus on renewable energy is increasing globally to lessen reliance on conventional sources and fossil fuels. For renewable energy systems to work at their best and produce the desired results, precise feedback control is required. Microbial electrochemical cells (MEC) are a relatively new technology for renewable energy. In this study, we design and implement a model-based robust controller for a continuous MEC reactor. We compare its performance with those of traditional methods involving a proportional integral derivative (PID), H-infinity (H∞) controller and PID controller tuned by intelligent genetic algorithms. Recently, a dynamic model of a MEC continuous reactor was proposed, which describes the complex dynamics of MEC through a set of nonlinear differential equations. Until now, no model-based control approaches for MEC have been proposed. For optimal and robust output control of a continuous-reactor MEC system, we linearize the model to state a linear time-invariant (LTI) state-space representation at the nominal operating point. The LTI model is used to design four different types of controllers. The designed controllers and systems are simulated, and their performances are evaluated and compared for various operating conditions. Our findings show that a structured linear fractional transformation (LFT)-based H∞ control approach is much better than the other approaches against various performance parameters. The study provides numerous possibilities for control applications of continuous MEC reactor processes.

Automatic Generation of Real-Time Animation Game Learning Levels Based on Artificial Intelligence Assistant

With the development of computer animation games, now many animation games use the automatic generation of animation game levels method to generate animation game content. Using the automatic generation levels of the animation game method can quickly generate many different levels, saving labor costs in manual production. And with the combination of other fields, more accurate results can be obtained. In this paper, the goal is to automatically generate the level of the animation game. This research proposed animation game objects and victory conditions to derive the concept of the clearance path and uses artificial intelligence genetic algorithms to obtain the clearance path that best meets the needs of the developer to recombine new levels. In addition, since the generated levels are regenerated from the clearance path, there are still too many blank areas. In order to make full use of these blank areas, this research provides a level complete system. The system has formulated its placement rules for existing animation game objects. These rules fill in these blank areas and produce a more complete level. The contributions of this search proved that the genetic algorithm can converge quickly due to the correction effect in the mutation. In the complete system, it has successfully achieved a complete and playable level. In the system running time, this research adjusted the method of selecting elites and the use of permutations and combinations to mate, so that the system’s operation can be stabilized on an average value.

An Intelligent Genetic Scheme for Multi-Objective Collaboration Services Scheduling

The optimization of collaborative service scheduling is the main bottleneck restricting the efficiency and cost of collaborative service execution. It is helpful to reduce the cost and improve the efficiency to deal with the scheduling problem correctly and effectively. The traditional genetic algorithm can solve the multi-objective problem more comprehensively than the optimization algorithm, such as stochastic greedy algorithm. But in the actual situation, the traditional algorithm is still one-sided. The intelligent genetic scheme (IGS) proposed in this paper enhances the expansibility and diversity of the algorithm on the basis of traditional genetic algorithm. In the process of initial population selection, the initial population generation strategy is changed, a part of the population is randomly generated and the selection process is iteratively optimized, which is a selection method based on population asymmetric exchange to realize selection. Mutation factors enhance the diversity of the population in the adaptive selection based on individual innate quality. The proposed IGS can not only maintain individual diversity, increase the probability of excellent individuals, accelerate the convergence rate, but also will not lead to the ultimate result of the local optimal solution. It has certain advantages in solving the optimization problem, and provides a new idea and method for solving the collaborative service optimization scheduling problem, which can save manpower and significantly reduce costs on the premise of ensuring the quality. The experimental results show that Intelligent Genetic algorithm (IGS) not only has better scalability and diversity, but also can increase the probability of excellent individuals and accelerate the convergence speed.

A hybrid intelligent genetic algorithm for truss optimization based on deep neutral network

The truss optimization problem has been extensively investigated, and the optimized trusses have been widely used in various fields. Truss optimization is a challenging optimization involving many difficulties, such as discrete variables and non-convex problems. In order to solve these problems, various metaheuristic optimization methods have been proposed. Due to the stochastic feature of these methods, it is always computationally intensive, and the optimization results may vary greatly in different optimization runs. In this paper, a hybrid intelligent genetic algorithm (HIGA) is proposed to improve the effectiveness and efficiency of truss optimization problems. This method systematically integrates deep neural network (DNN) and genetic algorithm (GA) in the optimization process. A two-step training procedure is proposed where the data generated during the optimization process is exploited to update DNN. Next, based on the generated DNN model, an optimization prediction procedure is proposed to seek more optimized trusses in an efficient manner. Through the investigation of three classical truss problems (size optimization, shape optimization and size-shape integrated optimization), the effectiveness of the proposed method is validated. In addition, the influence of different settings on the optimization performance and efficiency is investigated to demonstrate the applicability and robustness of the proposed method.

MULTI-VESSELS COLLISION AVOIDANCE STRATEGY FOR AUTONOMOUS SURFACE VEHICLES BASED ON GENETIC ALGORITHM IN CONGESTED PORT ENVIRONMENT

An improved genetic collision avoidance algorithm is proposed in this study to address the problem that Autonomous Surface Vehicles (ASV) need to comply with the collision avoidance rules at sea in congested sea areas. Firstly, a collision risk index model for ASV safe encounters is established taking into account the international rules for collision avoidance. The ASV collision risk index and the distance of safe encounters are taken as boundary values of the correlation membership function of the collision risk index model to calculate the optimal heading of ASV in real-time. Secondly, the genetic coding, fitness function, and basic parameters of the genetic algorithm are designed to construct the collision avoidance decision system. Finally, the simulation of collision avoidance between ASV and several obstacle vessels is performed, including the simulation of three collision avoidance states head-on situation, crossing situation, and overtaking situation. The results show that the proposed intelligent genetic algorithm considering the rules of collision avoidance at sea can effectively avoid multiple other vessels in different situations.

Artificial intelligence‐based tri‐objective optimization of different demand load patterns on the optimal sizing of a smart educational buildings

In this research, an integrated energy system for providing triple loads of an educational building has been modeled, analyzed, and optimized using artificial intelligence The use of different load supply patterns for the integrated system was optimized and evaluated from the point of view of exergy, economics, and environment. SketchUp, OpenStudio, and EnergyPlus are used to obtain the building loads, and the integrated system is dynamically modeled by the MATLAB software. The integrated system has been optimized based on different patterns, including monthly, seasonal, and two-state constant loads compared with hourly dynamic loads using an artificial intelligence genetic algorithm. The results show that the dynamic load pattern gives the highest exergy efficiency and the lowest total cost rate. The exergy efficiency and total cost rate in this scenario are 58.78% and 5.022 $/h, respectively. Also, the CO2 emission index has reached 363.1 g/kWh. Due to the subsidized price of grid electricity, there is a tendency to use low-capacity gas turbines and buy electricity from the grid for the dynamic model. The gas turbine capacity is 35.56 kW, and the system has purchased 242.4 MWh from the grid. Due to high heating loads, the capacity of the gas turbine significantly increases, and no electricity is purchased from the grid in the fixed-load pattern. The highest capacity of the gas turbine is 161.6 kW, which is obtained by a seasonal fixed-load pattern. Also, 994.9 MWh of electricity is sold to the grid in this mode.

Cyclic Anaerobic Exercise Performance and Neuromuscular Activity Based on Artificial Intelligence Genetic Algorithm

Anaerobic exercise capacity and neuromuscular activity research is an important content and an emerging research field in sports training research. At present, the understanding of anaerobic exercise ability in academia is still at the general and overall cognitive level, and the understanding and application of anaerobic exercise ability cannot fully meet the needs of competitive sports practice. In order to solve these problems, this paper proposes a cyclic anaerobic exercise performance and neuromuscular activity based on artificial intelligence genetic algorithm, aimed at studying the theory and application mechanism of anaerobic exercise capacity and neuromuscular activity and its application characteristics in competitive sports practice. The approach in this paper is to design genetic operators, compare artificial intelligence genetic algorithms, and test neuromuscular movements. The purpose of these methods is to provide exercisers with a feasible and more effective new method of daily training and to investigate whether this new training method can optimize anaerobic exercise in humans. In this paper, by studying the kinematic basis of anaerobic exercise capacity and the mechanism of neuromuscular regulation, a model of muscle neuron population in anaerobic exercise is established. The results showed that the CMC of the beta band was significantly higher than that of the alpha band at the same strength level, with a difference of 0.03.

A pulse‐and‐glide ‐driven adaptive cruise control system for electric vehicle

As the adaptive cruise control system (ACCS) on vehicles is well-developed today, vehicle manufacturers have increasingly employed this technology in new-generation intelligent vehicles. Pulse-and-glide (PnG) strategy is an efficacious driving strategy to diminish fuel consumption in traditional oil-fueled vehicles. However, current studies rarely focus on the verification of the energy-saving effect of PnG on an electric vehicle (EV) and embedding PnG in ACCS. This paper proposes a pulse-and-glide-driven adaptive cruise control system (PGACCS) model which leverages PnG strategy as a parallel function with cruise control (CC) and verifies that PnG is an efficacious energy-saving strategy on EV by optimizing the energy cost of the PnG operation using Intelligent Genetic Algorithm and Particle Swarm Optimization (IGPSO). This paper builds up a simulation model of an EV with regenerative braking and ACCS based on which the performance of PGACCS and regenerative braking is evaluated; the PnG energy performance is optimized and the effect of regenerative braking on PnG energy performance is evaluated. As a result of PnG optimization, the PnG operation in the PGACCS could cut down 28.3% energy cost of the EV compared to the CC operation in the traditional ACCS which verifies that PnG is an effective energy-saving strategy for EV and PGACCS is a promising option for EV.

An adapted multi-objective genetic algorithm for solving the cash in transit vehicle routing problem with vulnerability estimation for risk quantification

This study aimed to develop a model for vehicle routing problem with two objective functions of risk and distance minimization to optimize safety of cash/valuable commodities transportation. It is necessary to properly anticipate and prevent the occurrence of robbery to reduce the vulnerability to robbery attempts. The proposed approach for the vulnerability estimation of an armed robbery has been based on game theory and multi-criteria decision making (MCDM), which can accurately measure the amount of risk. A new multi-objective intelligent genetic algorithm (MOIGA) comprised of various heuristics is also designed to identify and intelligently select the most efficacious heuristic. The following experiments are used to test the proposed MOIGA: (1) Examining the influence of each proposed operator on the performance of the algorithm; (2) Evaluating the quality and diversity of MOIGA solutions compared to other popular algorithms. The obtained results demonstrate the effectiveness and efficiency of the proposed algorithm.

GeFeS: A generalized wrapper feature selection approach for optimizing classification performance

In this paper, we propose a generalized wrapper-based feature selection, called GeFeS, which is based on a parallel new intelligent genetic algorithm (GA). The proposed GeFeS works properly under different numerical dataset dimensions and sizes, carefully tries to avoid overfitting and significantly enhances classification accuracy. To make the GA more accurate, robust and intelligent, we have proposed a new operator for features weighting, improved the mutation and crossover operators, and integrated nested cross-validation into the GA process to properly validate the learning model. The k-nearest neighbor (kNN) classifier is utilized to evaluate the goodness of selected features. We have evaluated the efficiency of GeFeS on various datasets selected from the UCI machine learning repository. The performance is compared with state-of-the-art classification and feature selection methods. The results demonstrate that GeFeS can significantly generalize the proposed multi-population intelligent genetic algorithm under different sizes of two-class and multi-class datasets. We have achieved the average classification accuracy of 95.83%, 97.62%, 99.02%, 98.51%, and 94.28% while reducing the number of features from 56 to 28, 34 to 18, 279 to 135, 30 to 16, and 19 to 9 under lung cancer, dermatology, arrhythmia, WDBC, and hepatitis, respectively.

Root cause analysis improved with machine learning for failure analysis in power transformers

The root cause analysis, diagnosis and classification of faults in power transformers with high accuracy and efficiency is the fundamental key to ensure reliability and power quality with least interruptions. In this research, a new proposal was developed for an intelligent Genetic Algorithm tuned artificial neural network (ANN) classifier for transformer faults for to improve the root cause analysis, in this case, this new proposal is able to segregate all fault types using Dissolved Gas Analysis (DGA) samples from power transformers of a large range of providers and from other research papers, these input data have been pre-processed using the Fast Decision tree learner (FDTL), tree learner advanced, and M5 Rule (M5R) algorithm and NN. We replace the conventional action selection procedure of Reinforcement Learning (RL) by a machine learning based optimizer. In this research, a new proposal for computationally least expensive in comparison to other approaches is presented. Our proposed classifier could serve as an important tool in ensuring healthy operation of power transformers, the correlation is higher than 0.98 with tree learner classifier, with a validation of the over-fitting perspective.

GREMA: modelling of emulated gene regulatory networks with confidence levels based on evolutionary intelligence to cope with the underdetermined problem.

Non-linear ordinary differential equation (ODE) models that contain numerous parameters are suitable for inferring an emulated gene regulatory network (eGRN). However, the number of experimental measurements is usually far smaller than the number of parameters of the eGRN model that leads to an underdetermined problem. There is no unique solution to the inference problem for an eGRN using insufficient measurements. This work proposes an evolutionary modelling algorithm (EMA) that is based on evolutionary intelligence to cope with the underdetermined problem. EMA uses an intelligent genetic algorithm to solve the large-scale parameter optimization problem. An EMA-based method, GREMA, infers a novel type of gene regulatory network with confidence levels for every inferred regulation. The higher the confidence level is, the more accurate the inferred regulation is. GREMA gradually determines the regulations of an eGRN with confidence levels in descending order using either an S-system or a Hill function-based ODE model. The experimental results showed that the regulations with high-confidence levels are more accurate and robust than regulations with low-confidence levels. Evolutionary intelligence enhanced the mean accuracy of GREMA by 19.2% when using the S-system model with benchmark datasets. An increase in the number of experimental measurements may increase the mean confidence level of the inferred regulations. GREMA performed well compared with existing methods that have been previously applied to the same S-system, DREAM4 challenge and SOS DNA repair benchmark datasets. All of the datasets that were used and the GREMA-based tool are freely available at https://nctuiclab.github.io/GREMA. Supplementary data are available at Bioinformatics online.

An Intelligent Genetic Fuzzy Classifier for Transformer Faults

ABSTRACT Classification of faults in transformers with high accuracy is fundamental to ensuring good power quality with least interruptions. Our current work develops an intelligent genetic algorithm (GA)-tuned fuzzy classifier for transformer fault identification. The proposed classifier is able to segregate all fault types using dissolved gas analysis (DGA) samples from real power transformers of HPSEB (India) and other sources. DGA samples have been pre-processed using the J48 algorithm. We propose to replace the conventional action selection procedure of reinforcement learning by a GA-based optimizer. The classifier is able to garner very high classification accuracy which is higher than the one obtained with benchmark fuzzy Q learning (FQL) and other conventional classifiers. With our approach, the average fault classification rate achieved is 91.85% (FQL) and 97.51% genetic algorithm fuzzy Q-learning (GAFQL) though with a slightly higher computational complexity over the FQL. Our proposed classifier could serve as an important tool in ensuring the healthy operation of power transformers.

MULTI-OBJECTIVE ENERGY EFFICIENT MIXED MODEL ASSEMBLY LINE SEQUENCING FOR SUSTAINABLE MANUFACTURING

The sustainability of manufacturing systems is not thoroughly investigated in the existing literature despite that fact that it affects service-oriented organisations. This paper addresses this gap by incorporating the criterion of energy consumption in mixed model assembly line sequencing (MMALS) to explore the potential for energy saving. Energy consumption was integrated with makespan and sequence dependent setup time of mixed models to achieve the sustainability in sequencing. A mathematical model was developed for the optimisation of energy efficient MMAL (EEMMAL). The multi-objective intelligent genetic algorithm (MOIGA) was proposed for minimisation of three conflicting objectives. A case study was conducted using centrifugal pump assembly line to test the performance of proposed MOIGA and the results were compared with those obtained from multi-objective genetic algorithm (MOGA). Finally, a trade-off analysis was conducted between total setup time, makespan (a service level measure on shop floor) and energy consumption (a factor of environmental sustainability). This analysis indicated the effectiveness of MOIGA (compared to MOGA) for EEMMALS problems.

A comparison between Artificial Neural Network and Hybrid Intelligent Genetic Algorithm in predicting the severity of fixed object crashes among elderly drivers

Run-off-road (ROR) crashes have always been a major concern as this type of crash is usually associated with a considerable number of serious injury and fatal crashes. A substantial portion of ROR fatalities occur in collisions with fixed objects at the roadside. Thus, this study seeks to investigate the severity of ROR crashes where elderly drivers, aged 65 years or more, hit a fixed object. The reason why the present study investigates this issue among older drivers is that, comparing to younger drivers, this age group of drivers have different psychological and physical features. Because of these differences, they are more likely to get injured in ROR types of crashes. This paper applies two types of Artificial Intelligence (AI) techniques, including hybrid Intelligent Genetic Algorithm and Artificial Neural Network (ANN) using the crashe information of California in 2012 obtained from Highway Safety Information System (HSIS) database. Although the results showed that the developed ANN outperformed the hybrid Intelligent Genetic Algorithm, the hybrid approach was more capable of predicting high-severity crashes. This is rooted in the way the hybrid model was trained by taking advantage of the Genetic Algorithm (GA). The results also indicated that the light condition has been the most significant parameter in evaluating the level of severity associated with fixed object crashes among elderly drivers, which is followed by the existence of the right and left shoulders. Following these three contributing factors, cause of collision, Average Annual Daily Traffic (AADT), number of involved vehicles, age, road surface condition, and gender have been identified as the most important variables in the developed ANN, respectively. This helps to identify gaps and improve public safety towards improving the overall highway safety situation of older drivers.

A fingerprinting Algorithm Based on Artificial Intelligence Genetic Algorithm

Oil spill identification is an important means of investigation of oil spill through analysis and comparison of suspicious oil spill source. This paper proposed a GC/MS fingerprint fitting method based on genetic algorithm (GA) to identify the source of oil spill. In this method, dominant characteristic peaks were selected from the 3d fingerprint of the standard and stored in the prevailing characteristic fingerprint database (dominant database). Recessive characteristic peaks were screened out from the periphery of the dominant characteristic peaks of the sample and stored in the recessive characteristic fingerprint database (recessive database). Then a set of characteristic peaks was selected from the dominant library by GA to correct the characteristic peaks in the samples and automatically identify the similarity between the standard and the samples. Simulation calculation compared with experimental analysis results showed that the method to build a detailed identification of oil spill fingerprint was accurate and reliable. The method to identify the fingerprint peak can be clearly and accurately reflect the properties of the sample, which can be used for rapid automatic calculation of chromatographic fingerprint similarity, so as to strengthen sea spill accident discriminant scientific theory in identification, traceability and the application of legal liability.