Genetic Algorithm Search Research Articles

Optimizing vertical transmission control: A hybrid neural network approach with Wolbachia for Zika virus

In this study, we investigate cutting-edge control strategies designed to address the global health threat posed by the Zika virus. Our exploration utilizes an advanced numerical approach, the artificial neural network (ANN), complemented by the hybrid efficiency of global and local search schemes. The research delves into the distinctive properties of Wolbachia, a bacterium, assessing its potential to hinder virus transmission and regulate the population of Ades aegypti mosquitoes, the primary carriers of the Zika virus. The study employs a rigorous mathematical framework, categorizing individuals into distinct compartments such as newborns, adults, Wolbachia-uninfected mosquitoes, and Wolbachia-infected mosquitoes. We pinpoint the disease-free equilibrium (DFE) and compute the basic reproductive number [Formula: see text]. Through extensive simulations, we scrutinize the model’s stability by manipulating critical parameters, including biting rates [Formula: see text], mosquito death rates [Formula: see text], and pregnancy delays [Formula: see text]. Importantly, our model incorporates the dynamics of Zika transmission and its correlation with microcephaly, both with and without the presence of Wolbachia. To numerically handle the dynamic model, we introduce a computational procedure, visually illustrating how the presence of Wolbachia significantly impacts infected classes, leading to a reduction in new cases and an improvement in overall model stability. We propose the utilization of the global optimization genetic algorithm (GA) and local search interior point algorithm (IPA) to solve the model. We devised an error-based objective function for the differential model, which was then optimized using the hybrid computational efficiency of GA-IPA. The validation of our proposed computational method, ANNPs-GA-IPA, involved a comprehensive comparison of the results obtained against reference solutions, affirming the accuracy and reliability of our approach.

Vehicle-routing problem for low-carbon cold chain logistics based on the idea of cost–benefit

In the low-carbon economy, the fresh industry constitutes an “impossible triangle” in products, prices and services. Therefore, based on the idea of cost–benefit, a comprehensive vehicle routing problem optimization model with the objective function of minimizing the cost of unit satisfied customer is presented. Then, a hybrid algorithm called local search genetic algorithm (LSGA) is proposed, which amalgamates the destroy-repair operator with GA algorithm. Extensive numerical experiments verify the feasibility and effectiveness of the proposed model and algorithm. Furthermore, the sensitivity analysis of freshness-keeping cost, carbon price and customer satisfaction weights were conducted. The experimental results show that appropriate freshness-keeping effort can reduce total costs and improve customer satisfaction. Increasing carbon price within a certain range can effectively reduce carbon emissions, and there is a trade-off relationship between carbon emissions and customer satisfaction. The results of considering both time satisfaction and freshness satisfaction are better than considering time satisfaction alone.

Bio particle swarm optimization and reinforcement learning algorithm for path planning of automated guided vehicles in dynamic industrial environments

Automated guided vehicles play a crucial role in transportation and industrial environments. This paper presents a proposed Bio Particle Swarm Optimization (BPSO) algorithm for global path planning. The BPSO algorithm modifies the equation to update the particles’ velocity using the randomly generated angles, which enhances the algorithm’s searchability and avoids premature convergence. It is compared with Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and Transit Search (TS) algorithms by benchmark functions. It has great performance in unimodal optimization problems, and it gains the best fitness value with fewer iterations and average runtime than other algorithms. The Q-learning method is implemented for local path planning to avoid moving obstacles and combines with the proposed BPSO for the safe operations of automated guided vehicles. The presented BPSO-RL algorithm combines the advantages of the swarm intelligence algorithm and the Q-learning method, which can generate the globally optimal path with fast computational speed and support in dealing with dynamic scenarios. It is validated through computational experiments with moving obstacles and compared with the PSO algorithm for AGV path planning.

Enhanced Sensor Placement Optimization and Defect Detection in Structural Health Monitoring Using Hybrid PI-DEIM Approach.

This work introduces a novel methodology for identifying critical sensor locations and detecting defects in structural components. Initially, a hybrid method is proposed to determine optimal sensor placements by integrating results from both the discrete empirical interpolation method (DEIM) and the random permutation features importance technique (PI). Subsequently, the identified sensors are utilized in a novel defect detection approach, leveraging a semi-intrusive reduced order modeling and genetic search algorithm for fast and reliable defect detection. The proposed algorithm has successfully located defects with low error, especially when using hybrid sensors, which combine the most critical sensors identified through both PI and DEIM. This hybrid method identifies defects with the lowest errors compared to using either the PI or DEIM methods alone.

Redundancy Allocation Problem for a Continuous‐State Series‐Parallel System With Degrading Components: Electric Vehicle Application

ABSTRACTSystem reliability is a critical factor in designing complex engineering systems. Redundancy allocation problem (RAP) has attracted more interest owing to its wide scope of industrial applications for system reliability optimization. RAPs for binary‐state and multistate systems have been extensively studied. However, the redundancy allocation for continuous‐state systems composed of degrading components has not yet been fully explored. This study attempts to build the RAP for the continuous‐state parallel‐series system consisting of identical, independent, and nonrepairable components under active and cold‐standby redundancy strategies. The degradation of individual components in a system is continuous and modeled by the gamma process. The degradation at the system level is derived according to a deterministic structure function that relates the system degradation to the degradation of its components. Genetic algorithm and exhaustive search method are used to find the cost‐optimal redundancy design while satisfying a system reliability requirement. Series‐parallel lithium‐ion battery pack systems for electric vehicles (EVs) are used as an illustrative example to validate the proposed RAP and optimization model.

Optimization of laser powder bed fusion process parameter for the fabrication of AlSi12 using NSGA‐II and Pareto search algorithm

AbstractAdditive manufacturing, notably laser powder bed fusion (LPBF), excels in producing complex geometries and is widely used in the automotive, aerospace, and naval industries. Laser powder bed fusion enables the creation of components with the required stiffness and strength at a lighter weight than traditional manufacturing methods. Aluminium alloys are particularly promising for laser powder bed fusion in the automotive and aerospace sectors. To enhance the effectiveness of laser powder bed fusion‐produced components, optimized process parameters must be designed for specific materials. This study investigates the influence of processing parameters, scan speed, scan strategy, and hatch space, on the relative density, surface roughness, and microhardness of AlSi12 samples fabricated by laser powder bed fusion. A Taguchi L27 orthogonal array was used to systematically analyze the effects of these parameters. A regression model was developed and evaluated through analysis of variance using signal‐to‐noise (S/N) ratios to identify optimal parameter values. Results indicated that the scan pattern significantly affects relative density, while hatch space impacts surface roughness and microhardness. Optimal solutions were obtained through multi‐objective optimization using the non‐dominated sorting genetic algorithm (NSGA‐II) and Pareto search algorithms. Experimental validation showed average errors of 0.483 % and 0.461 % for NSGA‐II and Pareto search algorithms, respectively.

Combined and General Methodologies of Key Space Partition for the Cryptanalysis of Block Ciphers

This paper proposes two new methods of key space partitioning for the cryptanalysis of block ciphers. The first one is called combined methodology of key space partition (CoMeKSPar), which allows us to simultaneously set some of the first and last consecutive bits of the key. In this way, the search is performed using the remaining middle bits. CoMeKSPar is a combination of two methods already proposed in the scientific literature, the Borges, Borges, Monier (BBM) and the Tito, Borges, Borges (TBB). The second method is called the general algorithm of key space reduction (GAKSRed), which makes it possible to perform a genetic algorithm search in the space formed by the unknown bits of the key, regardless of their distribution in the binary block. Furthermore, a method of attacking block ciphers is presented for the case where some key bits are known; the basic idea is to deduce some of the remaining bits of the block. An advantage of these methods is that they allow parallel computing, which allows simultaneous searches in different sub-blocks of key bits, thereby increasing the probability of success. The experiments are performed with the KLEIN (Small) lightweight block cipher using the genetic algorithm.

Intelligent computing framework to analyze the transmission risk of COVID-19: Meyer wavelet artificial neural networks

The optimum control methods for the epidemiology of the COVID-19 model are acknowledged using a novel advanced intelligent computing infrastructure that joins artificial neural networks with unsupervised learning-based optimizers i.e., Genetic Algorithms (GA) and sequential quadratic programming (SQP). Unsupervised learning strategy is provided which depends on the wavelet basis's sequential deconstruction of stochastic data. The weights or selection values of neural networks are utilizing cumulative algorithms of Meyer wavelet artificial neural networks (MWANNs) optimized with global search Genetic Algorithms (GAs) and Sequential Quadratic Programming (SQP), referred to as MWANNs-GA-SQP and the design technique is utilized to determine the COVID-19 model for five different scenarios employing different step sizes and input intervals. The findings of this research article examined that in order to minimize the total disease transmission at the lowest cost and complexity, safety, focused medical care, and exterior sterilization methods applicability. The provided data is validated through various graphical simulations, which surely authenticate the effectiveness and robustness of the proposed solver. The suggested solver, MWANNs-GA-SQP, is tested in a variety of circumstances to examine that how reliable, safe, and tolerant. Using the proposed MWANNs hubristic intelligent approach, an objective optimization function is created in feed forward neural networking to minimize the mean square error. An investigation of the hybrid GA-SQP is used to confirm the accuracy and dependability of the MWANNs model results. Mean absolute graphs have been constructed to assess the integrity and efficiency of the proposed methodology. The accuracy and reliability of the suggested method are demonstrated by constantly achieving maximum variables of analytical assessment criteria computed for a large appropriate variety of distinct trials.

Research on the application technology of expert knowledge graph based on genetic search algorithm

Abstract The present study investigates the application of a genetic search algorithm on an expert knowledge graph. By employing binary coding for candidate experts in the expert database, the matching evaluation function is utilized to define the environmental fitness index, thereby optimizing the selection of expert groups. Experimental results demonstrate that the GES algorithm exhibits a superior matching degree and reduced time consumption when addressing science and technology item-matching requirements in review work. In comparison with the traditional BFS algorithm and GIS algorithm, the GES algorithm showcases enhanced potential for application and stability when confronted with large datasets. This paper further analyzes the impact of factors such as the total number of experts, number of fields, and number of scientific and technological projects on algorithm performance, confirming that adjustment of algorithm parameters can effectively enhance matching degree while reducing time consumption, thus providing technical support for practical implementation.

A hybrid artificial bee colony algorithm with high robustness for the multiple traveling salesman problem with multiple depots

A hybrid artificial bee colony algorithm (AC-ABC) with high robustness is proposed to solve the multiple traveling salesman problem (MTSP) with multiple depots. It initially conducts small-scale local searches to generate a high-quality population. Subsequently, a probabilistic model is established to balance global and local searches in the process of updating this population and exploring the optimal solution for the MTSP based on pheromone concentration and city visibility. In the process of population representation and updating, we introduce a novel tensor representation, which not only offers more opportunities for crossover between populations, but also adaptively provides more route choices to meet the personalized needs of salesmen. Besides artificial bee colony (ABC), AC-ABC takes at least 23% less execution time than other algorithms to solve the MTSP on multiple TSPLIB instances, especially takes about 32%–93% less execution time than the ant colony-partheno genetic algorithm (AC-PGA). The travel cost of the optimal route obtained by AC-ABC is significantly better than that of ABC, partheno genetic algorithm (PGA), improved PGA (IPGA), and two-part wolf pack search (TWPS). AC-ABC always obtains less travel cost than AC-PGA when the number of cities n≤150. AC-ABC only obtains about 0.5%–7.4% more travel cost than AC-PGA when the number of cities n>150.

Flood risk decomposed: Optimized machine learning hazard mapping and multi-criteria vulnerability analysis in the city of Zaio, Morocco

Urban flood risk mapping has become crucial for effective mitigation and urban planning. This study assesses and maps flood risk in the city of Zaio, Morocco, using machine learning and Multi-Criteria Decision Analysis (MCDA) techniques to overcome data scarcity challenges. We employed the Random Forest (RF) model with nine flood conditioning factors for flood hazard and the Analytical Hierarchy Process (AHP) for vulnerability assessment. To enhance RF model performance, we compared three hyperparameter tuning techniques: Bayesian Optimization (RF-BO), Genetic Algorithm (RF-GA), and Grid Search (RF-GS). RF-BO demonstrated superior accuracy in flood hazard modelling. Flood vulnerability was assessed using AHP, incorporating social and physical factors. The final flood risk map was produced by combining the RF-BO hazard model with the AHP vulnerability assessment. Results indicate that flood hazard in Zaio is significantly affected by factors such as topography and distance to rivers. Moreover, areas with high population density closer to rivers, especially in the south-western residential area, were found to be more exposed to flood risk. The findings highlight the utility of ML models, MCDA, and hyperparameter optimization in urban flood risk mapping, enabling the identification of high-risk urban areas that should be prioritized for flood protection efforts. This approach proves especially valuable in ungauged regions with limited hydrological data.

Optimizing graph neural network architectures for schizophrenia spectrum disorder prediction using evolutionary algorithms

Background and Objective:The accurate diagnosis of schizophrenia spectrum disorder plays an important role in improving patient outcomes, enabling timely interventions, and optimizing treatment plans. Functional connectivity analysis, utilizing functional magnetic resonance imaging data, has been demonstrated to offer invaluable biomarkers conducive to clinical diagnosis. However, previous studies mainly focus on traditional machine learning methods or hand-crafted neural networks, which may not fully capture the spatial topological relationship between brain regions. Methods:This paper proposes an evolutionary algorithm (EA) based graph neural architecture search (GNAS) method. EA-GNAS has the ability to search for high-performance graph neural networks for schizophrenia spectrum disorder prediction. Moreover, we adopt GNNExplainer to investigate the explainability of the acquired architectures, ensuring that the model’s predictions are both accurate and comprehensible. Results:The results suggest that the graph neural network model, derived using genetic algorithm search, outperforms under five-fold cross-validation, achieving a fitness of 0.1850. Relative to conventional machine learning and other deep learning approaches, the proposed method yields superior accuracy, F1 score, and AUC values of 0.8246, 0.8438, and 0.8258, respectively. Conclusion:Based on a multi-site dataset from schizophrenia spectrum disorder patients, the findings reveal an enhancement over prior methods, advancing our comprehension of brain function and potentially offering a biomarker for diagnosing schizophrenia spectrum disorder.

Influence of heating elements layout on temperature uniformity in a large size heat treatment furnace

Computational Fluid Dynamics simulations were used to optimize heating elements placement on the walls of a large size electrical heat treatment furnace in order to reduce temperature gradients within the furnace and uneven temperatures on different faces of the blocks which could result in variabilities in final mechanical properties. Initial evaluations of different layouts highlighted the effectiveness of equipping two side walls. Subsequently, an optimal percentage of side wall coverage was identified through simulations and multi-objective evolutionary optimization. Genetic and pareto search algorithms yielded 10 % and 14.2 % as optimum values, respectively. Implementing an optimal coverage demonstrated significant reductions in surface temperature non-uniformity, surface-to-center temperature differential, and temperature differences between loaded blocks. These improvements suggest a potential for enhanced uniformity in mechanical properties across a batch of products. This approach presents a promising strategy for obtaining consistent and efficient heat treatment cycles in industrial heat treatment furnaces resulting in energy saving and improved product quality.

HTSA: A novel hybrid task scheduling algorithm for heterogeneous cloud computing environment

Cloud computing provides users and programs with scalable resources and on-demand services virtually in real time, making it a fundamental paradigm in modern computing. The concept for using remote computing resources is novel. Cloud computing relies on task scheduling to boost system performance, reduce execution time, and optimize resource use. Due to exponential task increase and problem complexity, the search space is huge. Optimization tasks like this are NP-hard. This work aims to find a near-optimal solution for a multi-objective task scheduling problem in the cloud while lowering search time. Using the Genetic Algorithm (GA) and Gravitational Search Algorithms (GSA) benefits while avoiding their drawbacks, we offer a standard cloud computing task scheduling method to improve system performance and optimize the Quality of service (QoS) parameters like energy, makespan, resource utilization and throughput. We use CloudSim to test standard functions, real-time, and synthetic workloads. The obtained results are compared to other similar, metaheuristic-based techniques that were evaluated under the same conditions. The designed technique outperforms Gravitational Search Algorithms (GSA), Ant Colony Optimization(ACO), and Particle Swarm optimization(PSO) in Degree Of Imbalance (12%), resource utilization (9%), Mean Response Time (7%) and energy consumption (6%).

Real time patient scheduling orchestration for improving key performance indicators in a hospital emergency department

Healthcare systems worldwide are increasingly subject to in-depth analysis. Problems in healthcare systems are of concern to the general public. For example, overcrowding in emergency departments creates several issues including longer waiting times, more frequent medical errors, a longer length of stay and worsened performance indicators. Overcrowding situations reduce the availability of staff and material resources, and therefore deteriorate the quality of care. The main cause of the overcrowding in emergency departments is the permanent interferences between the scheduled patients, unscheduled patients and urgent and unscheduled patients arriving at the emergency department. The objective of the present study is to develop an innovative decision support system that minimizes these interferences, while taking into account the perturbations that can occur throughout the day. The research’s ultimate goal is to improve the performance indicators via two processes: the first is a memetic algorithm based on a four dimensional hypercube genetic algorithm and local search techniques, and the second is based on a multi-agent system which dynamically orchestrates the patient pathway (given by the scheduling algorithm). In order to test and validate our approach, experiments are designed with real data from the adult emergency department at Lille University Medical Center. Simulations showed that with our approach we were able to reduce the waiting time of patients by 28.12%.

Hybrid quantum search with genetic algorithm optimization.

Quantum genetic algorithms (QGA) integrate genetic programming and quantum computing to address search and optimization problems. The standard strategy of the hybrid QGA approach is to add quantum resources to classical genetic algorithms (GA), thus improving their efficacy (i.e., quantum optimization of a classical algorithm). However, the extent of such improvements is still unclear. Conversely, Reduced Quantum Genetic Algorithm (RQGA) is a fully quantum algorithm that reduces the GA search for the best fitness in a population of potential solutions to running Grover's algorithm. Unfortunately, RQGA finds the best fitness value and its corresponding chromosome (i.e., the solution or one of the solutions of the problem) in exponential runtime, O(2n/2), where n is the number of qubits in the individuals' quantum register. This article introduces a novel QGA optimization strategy, namely a classical optimization of a fully quantum algorithm, to address the RQGA complexity problem. Accordingly, we control the complexity of the RQGA algorithm by selecting a limited number of qubits in the individuals' register and fixing the remaining ones as classical values of '0' and '1' with a genetic algorithm. We also improve the performance of RQGA by discarding unfit solutions and bounding the search only in the area of valid individuals. As a result, our Hybrid Quantum Algorithm with Genetic Optimization (HQAGO) solves search problems in O(2(n-k)/2) oracle queries, where k is the number of fixed classical bits in the individuals' register.

Optimized k-nearest neighbours classifier based prediction of epileptic seizures

Epileptic seizure is an unstable condition of the brain that cause severe mental disorder and can be fatal if not properly diagnosed at an early stage. Electroencephalogram (EEG) plays a major role in early diagnosis of epileptic seizures. The volume of medical databases is enormous. Classification may become less accurate if the dataset contains redundant and irrelevant attributes. To reduce the mortality rate due to epilepsy, a decision support system that can assist medical professionals in taking immediate precautionary measures prior to reaching the critical condition is required. In this work, k-nearest neighbours (KNN) classifier algorithm is optimised using genetic algorithm for effective classification and faster prediction to meet this requirement. Genetic algorithms search for optimal solutions in complex and large environments. Results are compared with other machine learning models such as support vector machine (SVM), KNN, decision tree classifier, and random forest. With optimization using genetic algorithm KNN was able to achieve an enhancement in accuracy at lower training and testing times. It was observed that the accuracy offered by optimized KNN was 92%. Random forest classifiers showed minimum complexity and KNN algorithm provided faster performance with better accuracy.

A hybrid genetic tabu search algorithm for distributed job-shop scheduling problems

The distributed job-shop scheduling problem (DJSP) is an extension of the traditional job-shop scheduling problem, which are composed of two sub-problems, assigning jobs to suitable factories and deciding the operation sequence on machines. To evaluate the performance of algorithms for solving DJSP, several famous benchmark instances have been proposed, and most of these instances have not been solved so far. This paper proposes a hybrid genetic tabu search algorithm (HGTSA) for solving DJSP. The proposed HGTSA combines the global search ability of the genetic algorithm (GA) and the local search ability of the tabu search (TS) well. In GA part, a crossover operation and a mutation operation are devised based on the critical factory. The two operations can effectively improve the discreteness of the population. In TS part, a tabu search procedure is performed on the critical factory. The procedure can effectively enhance the local search ability of HGTSA. For evaluating the performance of HGTSA, it has been compared with five classical algorithms on 240 benchmark instances. The computational results show the efficiency and effectiveness of HGTSA for solving DJSP. In particular, the proposed HGTSA updates the upper bounds for 235 out of these difficult instances.

Optimal placement of uPMUs to improve the reliability of distribution systems through genetic algorithm and variable neighborhood search

Due to the dynamic nature of modern distribution systems, the deployment of micro-phasor measurement units (uPMU) is becoming increasingly common among utilities to improve system monitoring and reliability. However, given their high investment costs, deploying a large number of these devices becomes unfeasible. Hence, unlike other approaches found in the literature that focus on observability criteria, this work presents an algorithm for optimal placement of uPMUs aimed at improving distribution system reliability. The algorithm defines the optimal number and location of the uPMUs through an objective function based on the resolution of a fault location technique that works in conjunction with pseudo-measurements to successfully locate a contingency. The meta-heuristics Genetic Algorithm and Reduced Variable Neighborhood Search are employed to address this problem. The proposed method has been validated on a three-phase 39-bus distribution system and a real distribution feeder with 962 buses from an Ecuadorian electric distribution utility. The results obtained confirm the effectiveness of the method, as with the deployment of only two uPMUs, the energy not supplied decreases by 13.84 % and 24.96 % for the 39-bus and 962-bus systems, respectively. Moreover, in the 962-bus system, the System Average Interruption Duration Index (SAIDI) is reduced by 20.36 %.

Global Path Planning for Articulated Steering Tractor Based on Multi-Objective Hybrid Algorithm.

With the development of smart agriculture, autopilot technology is being used more and more widely in agriculture. Because most of the current global path planning only considers the shortest path, it is difficult to meet the articulated steering tractor operation needs in the orchard environment and address other issues, so this paper proposes a hybrid algorithm of an improved bidirectional search A* algorithm and improved differential evolution genetic algorithm(AGADE). First, the integrated priority function and search method of the traditional A* algorithm are improved by adding weight influence to the integrated priority, and the search method is changed to a bidirectional search. Second, the genetic algorithm fitness function and search strategy are improved; the fitness function is set as the path tree row center offset factor; the smoothing factor and safety coefficient are set; and the search strategy adopts differential evolution for cross mutation. Finally, the shortest path obtained by the improved bidirectional search A* algorithm is used as the initial population of an improved differential evolution genetic algorithm, optimized iteratively, and the optimal path is obtained by adding kinematic constraints through a cubic B-spline curve smoothing path. The convergence of the AGADE hybrid algorithm and GA algorithm on four different maps, path length, and trajectory curve are compared and analyzed through simulation tests. The convergence speed of the AGADE hybrid algorithm on four different complexity maps is improved by 92.8%, 64.5%, 50.0%, and 71.2% respectively. The path length is slightly increased compared with the GA algorithm, but the path trajectory curve is located in the center of the tree row, with fewer turns, and it meets the articulated steering tractor operation needs in the orchard environment, proving that the improved hybrid algorithm is effective.