Search results

The purpose of this study is to explore using real-observation quantum genetic algorithms (RQGAs) to evolve neural controllers that are capable of controlling a self-reconfigurable modular robot in an adaptive locomotion task.

Quantum-inspired genetic algorithms (QGAs) have shown their superiority against conventional genetic algorithms in numerous challenging applications in recent years. The authors have experimented with several QGAs variants and real-observation QGA achieved the best results in solving numerical optimization problems. The modular robot used in this study is a hybrid simulated robot; each module has two degrees of freedom and four connecting faces. The modular robot also possesses self-reconfiguration and self-mobile capabilities.

The authors have conducted several experiments using different robot configurations ranging from a single module configuration to test the self-mobile property to several disconnected modules configuration to examine self-reconfiguration, as well as snake, quadruped and rolling track configurations. The results demonstrate that the robot was able to perform self-reconfiguration and produce stable gaits in all test scenarios.

The artificial neural controllers evolved using the real-observation QGA were able to control the self-reconfigurable modular robot in the adaptive locomotion task efficiently.

Following earlier claims that quantum‐inspired evolutionary algorithm (QIEA) may offer advantages in high‐dimensional environments, the purpose of this paper is to test a real‐valued QIEA on a series of benchmark functions of varying dimensionality in order to examine its scalability within both static and dynamic environments.

This paper compares the performance of both the QIEA and the canonical genetic algorithm (GA) on a series of test benchmark functions.

The results show that the QIEA obtains highly competitive results when benchmarked against the GA within static environments, while substantially outperforming both binary and real‐valued representation of the GA in terms of running time. Within dynamic environments, the QIEA outperforms GA in terms of stability and run time.

This paper suggests that QIEA has utility for real‐world high‐dimensional problems, particularly within dynamic environments, such as that found in real‐time financial trading.

The purpose of the paper is to propose a new optimization algorithm to realize a synchronous optimization of sensor array and classifier, to improve the performance of E-nose in the detection of wound infection. When an electronic nose (E-nose) is used to detect the wound infection, sensor array’s optimization and parameters’ setting of classifier have a strong impact on the classification accuracy.

An enhanced quantum-behaved particle swarm optimization based on genetic algorithm, genetic quantum-behaved particle swarm optimization (G-QPSO), is proposed to realize a synchronous optimization of sensor array and classifier. The importance-factor (I-F) method is used to weight the sensors of E-nose by its degree of importance in classification. Both radical basis function network and support vector machine are used for classification.

The classification accuracy of E-nose is the highest when the weighting coefficients of the I-F method and classifier’s parameters are optimized by G-QPSO. All results make it clear that the proposed method is an ideal optimization method of E-nose in the detection of wound infection.

To make the proposed optimization method more effective, the key point of further research is to enhance the classifier of E-nose.

In this paper, E-nose is used to distinguish the class of wound infection; meanwhile, G-QPSO is used to realize a synchronous optimization of sensor array and classifier of E-nose. These are all important for E-nose to realize its clinical application in wound monitoring.

The innovative concept improves the performance of E-nose in wound monitoring and paves the way for the clinical detection of E-nose.

It is of a great significance for the health monitoring of a liquid rocket engine to build an accurate and reliable fault prediction model. The thrust of a liquid rocket engine is an important indicator for its health monitoring. By predicting the changing value of the thrust, it can be judged whether the engine will fail at a certain time. However, the thrust is affected by various factors, and it is difficult to establish an accurate mathematical model. Thus, this study uses a mixture non-parametric regression prediction model to establish the model of the thrust for the health monitoring of a liquid rocket engine.

This study analyzes the characteristics of the least squares support vector regression (LS-SVR) machine . LS-SVR is suitable to model on the small samples and high dimensional data, but the performance of LS-SVR is greatly affected by its key parameters. Thus, this study implements the advanced intelligent algorithm, the real double-chain coding target gradient quantum genetic algorithm (DCQGA), to optimize these parameters, and the regression prediction model LSSVRDCQGA is proposed. Then the proposed model is used to model the thrust of a liquid rocket engine.

The simulation results show that: the average relative error (ARE) on the test samples is 0.37% when using LS-SVR, but it is 0.3186% when using LSSVRDCQGA on the same samples.

The proposed model of LSSVRDCQGA in this study is effective to the fault prediction on the small sample and multidimensional data, and has a certain promotion.

The original contribution of this study is to establish a mixture non-parametric regression prediction model of LSSVRDCQGA and properly resolve the problem of the health monitoring of a liquid rocket engine along with modeling the thrust of the engine by using LSSVRDCQGA.

Due to unceasing declination in environment, sustainable agro-food supply chains have become a topic of concern to business, government organizations and customers. The purpose of this study is to examine a problem associated with sustainable network design in context of Indian agro-food grain supply chain.

A mixed integer nonlinear programming (MINLP) model is suggested to apprehend the major complications related with two-echelon food grain supply chain along with sustainability aspects (carbon emissions). Genetic algorithm (GA) and quantum-based genetic algorithm (Q-GA), two meta-heuristic algorithms and LINGO 18 (traditional approach) are employed to establish the vehicle allocation and selection of orders set.

The model minimizes the total transportation cost and carbon emission tax in gathering food grains from farmers to the hubs and later to the selected demand points (warehouses). The simulated data are adopted to test and validate the suggested model. The computational experiments concede that the performance of LINGO is superior than meta-heuristic algorithms (GA and Q-GA) in terms of solution obtained, but there is trade-off with respect to computational time.

In literature, inadequate study has been perceived on defining environmental sustainable issues connected with agro-food supply chain from farmer to final distribution centers. A MINLP model has been formulated as practical scenario for central part of India that captures all the major complexities to make the system more efficient. This study is regulated to agro-food Indian industries.

The suggested network design problem is an innovative approach to design distribution systems from farmers to the hubs and later to the selected warehouses. This study considerably assists the organizations to design their distribution network more efficiently.

Gross domestic product (GDP) is an important indicator to measure a country's economic development. If the future development trend of a country's GDP can be accurately predicted, it will have a positive effect on the formulation and implementation of the country's future economic development policies. In order to explore the future development trend of China's GDP, the purpose of this paper is to establish a new grey forecasting model with time power term to forecast GDP.

Firstly, the shortcomings of the traditional grey prediction model with time power term are found out through analysis, and then the generalized grey prediction model with time power term is established (abbreviated as PTGM (1,1, α) model). Secondly, the PTGM (1,1, α) model is improved by linear interpolation method, and the optimized PTGM (1,1, α) model is established (abbreviated as OPTGM (1,1, α) model), and the parameters of the OPTGM (1,1, α) model are solved by the quantum genetic algorithm. Thirdly, the advantage of the OPTGM (1,1, α) model over the traditional grey models is illustrated by two real cases. Finally the OPTGM (1,1, α) model is used to predict China's GDP from 2020 to 2029.

The OPTGM (1,1, α) model is more suitable for predicting China's GDP than other grey prediction models.

A new grey prediction model with time power term is proposed.

The purpose of this paper is to develop a new recognition system for identifying advanced radar emitter signals (RES).

Initially, the framework of the new recognition system is outlined. Then, feature extraction using resemblance coefficient and wavelet packet decomposition, and feature selection based on quantum‐inspired genetic algorithm, and a classifier combining K‐means clustering, support vector machines and Mahalanobis distance are applied to actualize the recognition system. Finally, experiments are carried out on RES.

A valid recognition system with its framework and implementation is presented to solve the difficult problem of advanced RES recognition.

Initial investigation is made on modern RES recognition. Further work may be done on decreasing the error rates and enhancing recognition efficiency. Real signals instead of simulated signals can be applied.

The system developed here can be applied to electronic reconnaissance systems such as electronic support measures, electronic intelligence and radar warning receiver.

The paper presents a novel recognition system and its implementation for modern RES. Extensive experiments conducted on 155 RES with eight intra‐pulse modulations show the feasibility and validity of the introduced system.

In this work, the authors show the performance of the proposed diploid scheme (a representation where each individual contains two genotypes) with respect to two dynamic optimization problems, while addressing drawbacks the authors have identified in previous works which compare diploid evolutionary algorithms (EAs) to standard EAs. The paper aims to discuss this issue.

In the proposed diploid representation of EA, each individual possesses two copies of the genotype. In order to convert this pair of genotypes to a single phenotype, each genotype is individually evaluated in relation to the fitness function and the best genotype is presented as the phenotype. In order to provide a fair and objective comparison, the authors make sure to compare populations which contain the same amount of genetic information, where the only difference is the arrangement and interpretation of the information. The two representations are compared using two shifting fitness functions which change at regular intervals to displace the global optimum to a new position.

For small fitness landscapes the haploid (standard) and diploid algorithms perform comparably and are able to find the global optimum very quickly. However, as the search space increases, rediscovering the global optimum becomes more difficult and the diploid algorithm outperforms the haploid algorithm with respect to how fast it relocates the new optimum. Since both algorithms use the same amount of genetic information, it is only fair to conclude it is the unique arrangement of the diploid algorithm that allows it to explore the search space better.

The diploid representation presented here is novel in that instead of adopting a dominance scheme for each allele (value) in the vector of values that is the genotype, dominance is adopted across the entire genotype in relation to its homologue. As a result, this representation can be extended across any alphabet, for any optimization function.

The purpose of this paper is to report the investigations on the potential of a new evolutionary algorithm based on probabilistic models – the quantum-inspired evolutionary algorithm (QEA) in solving inverse problems.

An improved QEA.

The proposed algorithm is an efficient and robust global optimizer for solving inverse problems.

To enhance the convergence speed without compromising the diversity performances of the populations, a new definition of global information sharing is introduced and implemented. To guarantee the balance between exploration and exploitation searches, a different migration strategy and formula, as well as a novel formulation for adaptively updating the rotation angle, are developed.

This paper aims to provide a complete analysis framework and prediction method for the construction of the patent securitization (PS) basic asset pool.

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.

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.

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.