Single-point Crossover Research Articles

Neural architecture search via similarity adaptive guidance

Evolutionary neural network architecture search (ENAS) has attracted the attention of many experts due to its global optimization capabilities to automatically search for convolutional neural network architectures based on the target task. The current search space for ENAS is not to design a fully structured network, but to search for smaller cell architectures to reduce search costs. However, blind search strategies do not effectively utilize the potential experience of the population. In order to utilize the potential experience learned by the current population to guide the evolutionary search of the population, we propose a similarity guided neural network architecture search algorithm based on cell architecture, which utilizes the similarity between pairwise architectures in the population as empirical knowledge learned by the population. Our proposed algorithm provides a novel method for calculating architecture similarity, which calculates architecture similarity separately from the cell and macro-structure. Then we decouple the connections and operations in the cell and calculate connection and operation similarity separately. In addition, we propose adaptive similarity selection and binary tournament selection strategies to enhance the algorithm’s global and local search capabilities and effectively explore the search space. Finally, we design an improved single-point crossover operator to enhance the local search ability of the evolutionary operator. The experimental results show that SAGNAS is a competitive algorithm that achieves 97.44% and 81.60% in CIFAR10 and CIFAR100 with only 1.9 GPU-days spent.

An Efficient Binary Hybrid Equilibrium Algorithm for Binary Optimization Problems: Analysis, Validation, and Case Studies

Binary optimization problems belong to the NP-hard class because their solutions are hard to find in a known time. The traditional techniques could not be applied to tackle those problems because the computational cost required by them increases exponentially with increasing the dimensions of the optimization problems. Therefore, over the last few years, researchers have paid attention to the metaheuristic algorithms for tackling those problems in an acceptable time. But unfortunately, those algorithms still suffer from not being able to avert local minima, a lack of population diversity, and low convergence speed. As a result, this paper presents a new binary optimization technique based on integrating the equilibrium optimizer (EO) with a new local search operator, which effectively integrates the single crossover, uniform crossover, mutation operator, flipping operator, and swapping operator to improve its exploration and exploitation operators. In a more general sense, this local search operator is based on two folds: the first fold borrows the single-point crossover and uniform crossover to accelerate the convergence speed, in addition to avoiding falling into local minima using the mutation strategy; the second fold is based on applying two different mutation operators on the best-so-far solution in the hope of finding a better solution: the first operator is the flip mutation operator to flip a bit selected randomly from the given solution, and the second operator is the swap mutation operator to swap two unique positions selected randomly from the given solution. This variant is called a binary hybrid equilibrium optimizer (BHEO) and is applied to three common binary optimization problems: 0–1 knapsack, feature selection, and the Merkle–Hellman knapsack cryptosystem (MHKC) to investigate its effectiveness. The experimental findings of BHEO are compared with those of the classical algorithm and six other well-established evolutionary and swarm-based optimization algorithms. From those findings, it is concluded that BHEO is a strong alternative to tackle binary optimization problems. Quantatively, BHEO could reach an average fitness of 0.090737884 for the feature section problem and an average difference from the optimal profits for some used Knapsack problems of 2.482.

Size Optimization of Truss Structures Based on Genetic Algorithm by Developing Single-point Crossover with Bit-wise Mutation Using FORTRAN Programming

A truss is a collection of axially loaded structural elements connected through pin joints. Optimization of truss structures indicates the determination of best possible conditions that are necessary for achieving the most economical design in terms of lowest possible weights of the truss elements. According to recent studies, Size, Topology and Shape based optimizations are the three possible independent optimization scopes for finding the optimum weight of a truss. The current study focuses on the size optimization of truss structure and aims to identify the most cost-effective sections of the truss using a powerful evolutionary optimization technique named as Genetic Algorithm (GA). Here single point cross over method and bit wise mutation operator are adopted for expanding the search space with the assigned displacement and stress constraints. Fortran based sub routines are developed for each individual steps of GA such as fitness evaluation, selection, cross-over and mutation. Finaly the complete program is run for validation of its outcome. While comparing with the solution of an existing literature regarding a minimization of objective function having two design variables the outcomes tend to show a good correlation. Further, the study is extended for the weight minimization of two widely used truss having 10 members and 17 members respectively with standard Finite Element Method of analysis. Minimum weight of each truss is obtained via convergence plot and compared with the existing literatures. With this simple but efficient global optimization technique optimum weight of truss structure can easily be achieved.

Parallel Particle Swarm Optimization Algorithm for Identifying Complex Communities in Biological Networks

Identification of complex communities in biological networks is a critical and ongoing challenge since lots of network-related problems correspond to the subgraph isomorphism problem known in the literature as NP-hard. Several optimization algorithms have been dedicated and applied to solve this problem. The main challenge regarding the application of optimization algorithms, specifically to handle large-scale complex networks, is their relatively long execution time. Thus, this paper proposes a parallel extension of the PSO algorithm to detect communities in complex biological networks. The main contribution of this study is summarized in three- fold; Firstly, a modified PSO algorithm with a local search operator is proposed to detect complex biological communities with high quality. Secondly, the variability in the capability of PSO to extract community structure in biological networks is studied when different types of crossover operators are used. Finally, to reduce the computational time needed to solve this problem, especially when detecting complex communities in large-scale biological networks, we have implemented parallel computing to execute the algorithm. The performance of the proposed algorithm was tested and evaluated on two real biological networks. The experimental results showed the effective performance of the proposed algorithm when using single-point crossover operator, and its superiority over other counterpart algorithms. Moreover, the use of parallel computing in the proposed algorithm representation has greatly reduced the computational time required for its execution.

Optimizing Production Schedules: Balancing Worker Cooperation and Learning Dynamics in Seru Systems

This paper aims to investigate the seru scheduling problem while considering the dual effects of worker cooperation and learning behavior to minimize the makespan and order processing time. Given the complexity of this research problem, an improved shuffled frog leaping algorithm based on a genetic algorithm is proposed. We design a double-layer encoding based on the problem, introduce a single point and uniform crossover operator, and select the crossover method in probability form to complete the evolution of the meme group. To avoid damaging grouping information, the individual encoding structure is transformed into unit form. Finally, numerical experiments were conducted using numerical examples of large and small sizes for verification. The experimental results demonstrate the feasibility of the proposed model and algorithm, as well as the necessity of considering worker dual behavior in the seru scheduling problem.

GA-LNS Optimization for Helicopter Rescue Dispatch

Aviation emergency rescue has become one of the most effective means for natural disaster relief due to its flexible and timely characteristics. A reasonable emergency dispatch plan can guarantee the effective implementation of all the rescue measures. Most of previous studies in this area focused on the scheduling and routing but ignored the impact of the specific rescue process, for example the fuel consumption of various helicopters. In this paper, a multi-helicopter-multi-trip Aviation Rescue Routing Problem (ARRP) is analysed which covers the whole rescue process. In addition, a time-domain procedural simulation model is built which can consider different helicopters, refueling or not, various resource locations, multiple disaster sites and other operation factors. Based on that, a Genetic Algorithm (GA) hybridized Large Neighborhood Search (LNS) algorithm (GA-LNS) is proposed for optimization. In ARRP, single search algorithm may lead to the local optimum due to complexity. In contrast, the distance greedy strategy and the load ratio strategy are combined in GA-LNS which can fix the local optimum problem. More specifically, based on the helicopter-tagged-task-sequenced chromosome, the single-point crossover operator is used in GA and then, the worst removal strategy and the first/last insertion strategy are adopted in LNS. Finally, the numerical experiments are exercised to verify the effectiveness of the proposed GA-LNS algorithm which is compared with three traditional basic heuristic algorithms and a stateof-the-art memetic algorithm.

A nondominated sorting genetic algorithm III with three crossover strategies for the combined heat and power dynamic economic emission dispatch with or without prohibited operating zones

This paper presents a nondominated sorting genetic algorithm III with three crossover strategies (NSGA-III-TCS) for the combined heat and power dynamic economic emission dispatch (CHPDEED) problems with or without prohibited operating zones. The first strategy updates the individuals of the first nondomination rank by a modified improvisation of the harmony search algorithm, which accelerates the information exchanges of the elite individuals. The second strategy regulates the individuals of the last nondomination rank according to a modified single-point crossover of the genetic algorithm, which strengthens the convergence of the population. The third strategy adjusts the remaining individuals in terms of a modified DE/rand-to-best/1 mutation of the differential evolution algorithm, and it guides these individuals to move towards the ones which have at least one minimum objective function value, which is beneficial for expanding the distribution range of the population. NSGA-III-TCS obtains the largest average hypervolumes and shows a desirable convergence for six CHPDEED problems. NSGA-III-TCS achieves relatively high coverage rates in most cases, indicating the dominance of the Pareto sets of NSGA-III-TCS over those of the other algorithms. Also, it has relatively low average spacings for all problems, suggesting the good evenness of the Pareto sets.

SENSITIVITY ANALYSIS AND OPTIMIZATION OF WAVY FIN CIRCULAR TUBE HEAT EXCHANGER

The present study shows the strong ability of a genetic algorithm (GA) in the thermal design and optimization of a herringbone wavy fin and circular tube compact heat exchanger (FTHE). The influences of various design parameters on friction factor, Colburn factor, and minimum total annual cost (TAC) are presented. Mainly, three design objectives are considered, such as minimum friction factor, maximum Colburn factor, and minimum TAC. For optimization, the Optimization toolbox of Matlab is used. In the GA routine, tournament selection, single point crossover, and constraint dependent mutation are adopted. The multiobjective optimization reveals a couple of sets of optimal solutions by optimizing the two objectives, i.e., minimum friction factor and maximum Colburn factor. By minimizing the TAC, a significant amount of cost is found to be reduced as compared to previous works in the literature with some optimum geometrical parameters.

A novel crossover operator for genetic algorithm: Stas crossover

The genetic algorithm (GA) is a natural selection-inspired optimization algorithm. It is a population-based search algorithm that utilizes the concept of survival of the fittest. This study creates a new crossover operator called “Stas Crossover” that is a combination of four crossover operators, including Single point crossover, Two points crossover, Arithmetic crossover, and Scattered crossover, and then presents the performance of this crossover operator. The area size and probability of Stas crossover can be adjusted.GA is used to find the optimal solution for this multi-product and multi-period aggregate production planning (APP) problem, which was used to test the algorithm, which provides optimal levels of inventory, backorders, overtime and regular production rates, and other controllable variables. According to the findings of this study, the benefit of stable crossover is that it allows for more variety in the way offspring are created and increases the opportunity for offspring to obtain good genetic information directly.

Intelligent Machine Evolutionary Algorithm Learning Based on Artificial Intelligence

Intelligent machines are an important carrier of artificial intelligence, which are widely used not only in the industrial field, but also in various fields of daily life and work. Path planning is an important research direction for studying machine intelligence. The main purpose is to search for a feasible path so that the robot can walk along the searched path in a complex environment. This paper aims to study the evolutionary algorithm of intelligent machines based on artificial intelligence. On the basis of introducing the characteristics of artificial potential field algorithm, the concept and characteristics of genetic algorithm, using genetic algorithm as the framework, the artificial potential field algorithm is combined with the crossover of genetic algorithm. In the operator, the optimization performance of the crossover operator is improved. The research results show that the length of the path obtained by the improved algorithm is shorter and better than that of the genetic algorithm of the single-point crossover operator.

Unit Commitment Problem with Emission Cost Constraints by Using Genetic Algorithm

A power system’s operating cost needs to be minimized by satisfying varying load demand while taking into account the prevailing constraints in a multiple unit electrical power system. In this study, by using genetic algorithms (GA), a short-term thermal unit commitment problem was solved and an economical generating unit schedule was made with the solution obtained. Taking into account the negative effects of emissions due to the use of fossil fuels, emission costs were added to the objective function together with fuel and start-up costs. The GA chromosome structure was formed by binary encoding, new generations were selected by roulette wheel selection mechanism and single point crossover was applied. The representation, formulation and the simulation results of the problem for a 5-unit test system during the scheduling hours of the period are presented. The number and the operating hours of the generating units to be committed were determined by satisfying the prevailing constraints. During the planning period, 13360 MW of power demand was met by 755 MW of spinning reserve. Total operating cost was calculated as $430330. Of the total operating cost, 32% consists of emission costs.

Single-Point Crossover and Jellyfish Optimization for Handling Imbalanced Data Classification Problem

The imbalanced datasets and their classification has pulled in as a hot research topic over the years. It is used in different fields, for example, security, finance, health, and many others. The imbalanced datasets are balanced by applying resampling and various solutions are designed to tackle such datasets that mainly focus on class distribution issues. The imbalanced data is rebalanced using these methods. This paper introduces a technique for balancing data through two stages: first, oversampling methods are utilized in the process of rebalancing such imbalanced dataset using the single-point crossover to generate the new data of minority classes, second, it searches for an optimal subset of the imbalanced and balanced datasets by Jellyfish Search (JS) which is an optimization method. Experiments are performed on 18 real imbalanced datasets, and results are compared with famous oversampling methods and the recently published ACOR (Ant Colony Optimization Resampling) method in terms of different appraisal measurements. Higher performance is recorded by the proposed method and comparability with well-known and recent techniques.

A scalable species-based genetic algorithm for reinforcement learning problems

Abstract Reinforcement Learning (RL) methods often rely on gradient estimates to learn an optimal policy for control problems. These expensive computations result in long training times, a poor rate of convergence, and sample inefficiency when applied to real-world problems with a large state and action space. Evolutionary Computation (EC)-based techniques offer a gradient-free apparatus to train a deep neural network for RL problems. In this work, we leverage the benefits of EC and propose a novel variant of genetic algorithm called SP-GA which utilizes a species-inspired weight initialization strategy and trains a population of deep neural networks, each estimating the Q-function for the RL problem. Efficient encoding of a neural network that utilizes less memory is also proposed which provides an intuitive mechanism to apply Gaussian mutations and single-point crossover. The results on Atari 2600 games outline comparable performance with gradient-based algorithms like Deep Q-Network (DQN), Asynchronous Advantage Actor Critic (A3C), and gradient-free algorithms like Evolution Strategy (ES) and simple Genetic Algorithm (GA) while requiring far fewer hyperparameters to train. The algorithm also improved certain Key Performance Indicators (KPIs) when applied to a Remote Electrical Tilt (RET) optimization task in the telecommunication domain.

Research on Social Talent Governance Based on Genetic Algorithm

The existing social talent governance algorithms have a number of issues such as slow convergence rate, relatively low data accuracy, recall rate, and low anti-interference. To address these problems, this paper proposes a research on social talent governance algorithm based on genetic algorithm. We discuss the difference between the traditional and the genetic algorithms and determine the implementation process of genetic algorithm. On this basis, the excellent individuals are determined by independent computing fitness, and the initialization population is designed according to the individual similarity threshold. After the population is defined, the roulette and deterministic sampling selection method are integrated to clarify the selection calculation process. Based on the calculation results, we design the crossover operator by segmented single-point crossover between individuals. The mutation operator is designed by segmented mutation of different gene segments according to the calculation results. The results are incorporated into the simulated annealing acceptance probability to conduct simulated annealing for the individuals after the cross-mutation operation and set relevant conditions after the end of the algorithm. We seek the optimal solution of the data within the number of iterations and finally realize the whole process of social talent governance algorithm. The experimental results show that the proposed algorithm has fast convergence rate, high data precision and recall, and has certain feasibility.

DMFO-CD: A Discrete Moth-Flame Optimization Algorithm for Community Detection

In this paper, a discrete moth–flame optimization algorithm for community detection (DMFO-CD) is proposed. The representation of solution vectors, initialization, and movement strategy of the continuous moth–flame optimization are purposely adapted in DMFO-CD such that it can solve the discrete community detection. In this adaptation, locus-based adjacency representation is used to represent the position of moths and flames, and the initialization process is performed by considering the community structure and the relation between nodes without the need of any knowledge about the number of communities. Solution vectors are updated by the adapted movement strategy using a single-point crossover to distance imitating, a two-point crossover to calculate the movement, and a single-point neighbor-based mutation that can enhance the exploration and balance exploration and exploitation. The fitness function is also defined based on modularity. The performance of DMFO-CD was evaluated on eleven real-world networks, and the obtained results were compared with five well-known algorithms in community detection, including GA-Net, DPSO-PDM, GACD, EGACD, and DECS in terms of modularity, NMI, and the number of detected communities. Additionally, the obtained results were statistically analyzed by the Wilcoxon signed-rank and Friedman tests. In the comparison with other comparative algorithms, the results show that the proposed DMFO-CD is competitive to detect the correct number of communities with high modularity.

Travelling salesman problem: Greedy single point crossover in ordinal representation

Genetic Algorithm (GA) is a metaheuristic algorithm which has stages; coding, selection, crossover, and mutation. The crossover operator plays an important role in producing offspring to find solutions. Single Point Crossover (SPC) and Two Point Crossover (TPC) are classic crossover operators that are easy to apply to ordinal representation coding rather than path representation coding. The greedy algorithm is applied to the SPC operator to solve the Traveling Salesman Problem (TSP) to improve the performance of the genetic algorithm in the ordinal representation coding scheme. The results show that the proposed Greedy Single Point Crossover (GSPC) has higher performance in finding the global optimal solution for all population sizes and cities used, but it costs computation time.

Comparison of Crossover in Genetic Algorithm for Discrete-Time System Identification

System identification is a process where a mathematical model is derived in order to explain dynamical behaviour of a system. One of its step is model structure selection and it is crucial that, in this step, an adequate model i.e. a model with a good balance between parsimony and accuracy of the model is selected in approximating the system. Genetic algorithm (GA), a method known for optimisation, is used for selecting a model structure. GA is known to be able to reduce much computational burden. This paper investigates the effect of different types of crossover, namely, single-point, double-point, multiple-point and uniform crossover, within GA in producing an optimum model structure for system identification. This was carried out using a computational software on a number of simulated data. As a conclusion, using Akaike Information Criterion as objective function, single point crossover produces the model with the best balance in most of the tests.

Hybrid Fuzzy-Genetic Model for Fitness-Based Performance Optimization in Wireless Networks

In recent times, the application of autonomic soft computing techniques for design and optimization of wireless access networks is progressively becoming prevalent. These computational learning techniques are capable of handling uncertain and imprecise networking information while driving toward the optimal solution set in the problem search space. The approach proposed by this paper presents the application of the fuzzy logic inference combined with the evolutionary genetic algorithm to optimize the performance parameters in wireless networks. In particular, we consider optimal bit rate allocation and transmission power consumption through the joint design of fuzzy-genetic modeling framework. The sample training data generated through simulations of IEEE 802.11 wireless access network are analyzed for optimization by supplying it to the expert hybrid model comprising of the conjunctive design of both the computational intelligent techniques. Specifically, we contemplate the binary encoding scheme, single-point crossover, reversing mutation, and two fitness functions for executing the binary genetic operations of crossover and mutation. It is generally observed that the proposed hybrid model with polynomial fitness function yields better performance with scalable network datasets than the logarithmic fitness function in terms of higher objective value. Moreover, the results obtained through simulation experiments exhibit significant throughput gains and power efficiency for the deployed fitness functions with the evolving size of training dataset. Compared with the existing methods, our hybrid learning model demonstrates performance enhancement with higher expected fitness measure, improved throughput and power efficiency.

Path Planning of Mobile Robot Based on Improved Multiobjective Genetic Algorithm

Path planning is the core technology of mobile robot decision‐making and control and is also a research hotspot in the field of artificial intelligence. Aiming at the problems of slow response speed, long planning path, unsafe factors, and a large number of turns in the conventional path planning algorithm, an improved multiobjective genetic algorithm (IMGA) is proposed to solve static global path planning in this paper. The algorithm uses a heuristic median insertion method to establish the initial population, which improves the feasibility of the initial path and generates a multiobjective fitness function based on three indicators: path length, path security, and path energy consumption, to ensure the quality of the planned path. Then, the selection, crossover, and mutation operators are designed by using the layered method, the single‐point crossover method, and the eight‐neighborhood‐domain single‐point mutation method, respectively. Finally, the delete operation is added, to further ensure the efficient operation of the mobile robot. Simulation experiments in the grid environment show that the algorithm can improve the defects of the traditional genetic algorithm (GA), such as slow convergence speed and easy to fall into local optimum. Compared with GA, the optimal path length obtained by planning is shortened by 17%.

Utilizing Automatic Query Reformulations as Genetic Operations to Improve Feature Location in Software Models

In the combination of Model-Driven Engineering (MDE) and Search-Based Software Engineering (SBSE), genetic operations are one of the key ingredients. Our work proposes a novel adaptation of automatic query reformulations as genetic operations that leverage the latent semantics of software models (the cornerstone artefact of MDE). We analyze the impact of these reformulation operations in a real-world industrial case study of feature location in models. As baselines, we use: 1) the widespread single-point crossover plus random mutation; and 2) mask crossover plus random mutation, which is the best performer for feature location in models. We also perform a statistical analysis to provide quantitative evidence of the impact of the results and to show that this impact is significant. Our reformulation operations improve the results of the best baseline by 37.73 percent in recall and 14.08 percent in precision. These results are relevant for the task of feature location in models (one of the main activities performed during software maintenance and evolution). Furthermore, given that the only requirement to apply our approach is term availability in models, our work opens a new research direction to improve more tasks in MDE such as bug location or requirements traceability.