Search

This article deals with the problem of mobile robot path planning in an unknown environment that contains both static and dynamic obstacles, utilizing a reinforcement learning approach. We propose an improved Dyna-Q algorithm, which incorporates heuristic search strategies, simulated annealing mechanism, and reactive navigation principle into Q-learning based on the Dyna architecture. A novel action-selection strategy combining ϵ-greedy policy with the cooling schedule control is presented, which, together with the heuristic reward function and heuristic actions, can tackle the exploration-exploitation dilemma and enhance the performance of global searching, convergence property, and learning efficiency for path planning. The proposed method is superior to the classical Q-learning and Dyna-Q algorithms in an unknown static environment, and it is successfully applied to an uncertain environment with multiple dynamic obstacles in simulations. Further, practical experiments are conducted by integrating MATLAB and robot operating system (ROS) on a physical robot platform, and the mobile robot manages to find a collision-free path, thus fulfilling autonomous navigation tasks in the real world.

Feature selection is performed to eliminate irrelevant features to reduce computational overheads. Metaheuristic algorithms have become popular for the task of feature selection due to their effectiveness and flexibility. Hybridization of two or more such metaheuristics has become popular in solving optimization problems. In this paper, we propose a hybrid wrapper feature selection technique based on binary butterfly optimization algorithm (bBOA) and Simulated Annealing (SA). The SA is combined with the bBOA in a pipeline fashion such that the best solution obtained by the bBOA is passed on to the SA for further improvement. The SA solution improves the best solution obtained so far by searching in its neighborhood. Thus the SA tries to enhance the exploitation property of the bBOA. The proposed method is tested on twenty datasets from the UCI repository and the results are compared with five popular algorithms for feature selection. The results confirm the effectiveness of the hybrid approach in improving the classification accuracy and selecting the optimal feature subset.

In this paper, a novel method of ultra-lightweight convolution neural network (CNN) design based on neural architecture search (NAS) and knowledge distillation (KD) is proposed. It can realize the automatic construction of the space target inverse synthetic aperture radar (ISAR) image recognition model with ultra-lightweight and high accuracy. This method introduces the NAS method into the radar image recognition for the first time, which solves the time-consuming and labor-consuming problems in the artificial design of the space target ISAR image automatic recognition model (STIIARM). On this basis, the NAS model's knowledge is transferred to the student model with lower computational complexity by the flow of the solution procedure (FSP) distillation method. Thus, the decline of recognition accuracy caused by the direct compression of model structural parameters can be effectively avoided, and the ultra-lightweight STIIARM can be obtained. In the method, the Inverted Linear Bottleneck (ILB) and Inverted Residual Block (IRB) are firstly taken as each block's basic structure in CNN. And the expansion ratio, output filter size, number of IRBs, and convolution kernel size are set as the search parameters to construct a hierarchical decomposition search space. Then, the recognition accuracy and computational complexity are taken as the objective function and constraint conditions, respectively, and the global optimization model of the CNN architecture search is established. Next, the simulated annealing (SA) algorithm is used as the search strategy to search out the lightweight and high accuracy STIIARM directly. After that, based on the three principles of similar block structure, the same corresponding channel number, and the minimum computational complexity, the more lightweight student model is designed, and the FSP matrix pairing between the NAS model and student model is completed. Finally, by minimizing the loss between the FSP matrix pairs of the NAS model and student model, the student model's weight adjustment is completed. Thus the ultra-lightweight and high accuracy STIIARM is obtained. The proposed method's effectiveness is verified by the simulation experiments on the ISAR image dataset of five types of space targets.

Product design constitutes a critical process for a firm to stay competitive. Whilst the biologically inspired Clonal Selection Algorithms (CSA) have been applied to efficiently solve several combinatorial optimization problems, they have not yet been tested for optimal product lines. By adopting a previous comparative analysis with real and simulated conjoint data, we adapt and compare in this context 23 CSA variants. Our comparison demonstrates the efficiency of specific cloning, selection and somatic hypermutation operators against other optimization algorithms, such as Simulated Annealing and Genetic Algorithm. To further investigate the robustness of each method to combinatorial size, we extend the previous paradigm to larger product lines and different optimization objectives. The consequent performance variation elucidates how each operator shifts the search focus of CSAs. Collectively, our study demonstrates the importance of a fine balance between global and local search in such combinatorial problems, and the ability of CSAs to achieve it.

RNA structure prediction with pseudoknots is an NP-complete problem, in which an optimal RNA structure with minimum energy is to be computed. In past decades, several methods have been developed to predict RNA structure with pseudoknots. Among them, metaheuristic approaches have proven to be beneficial for predicting long RNA structure in a very short time. In this paper, we have used two metaheuristic algorithms; Genetic Algorithm (GA) and Simulated Annealing (SA) for predicting RNA secondary structure with pseudoknots. We have also applied a combination of these two algorithms as GA-SA where GA is used for a global search and SA is used for a local search, and conversely SA-GA, where SA is used for a global search and GA is used for a local search. Four different energy models have been applied to calculate the energy of RNA structure. Five datasets, constructed from the RNA STRAND and Pseudobase++ database, have been used in the algorithms. The performances of the algorithms have been compared with several existing metaheuristic algorithms. Here we have obtained that the combination of GA and SA (GA-SA) gives better results than GA, SA and SA-GA algorithms and all other four state-of-art algorithms on all datasets.

The design parameters of heat pumps are related to each other nonlinearly or in a complicated manner; therefore, it is difficult to determine the optimal combination of design parameters, such as superheat, subcooling, and refrigerant type, analytically. To address this limitation, three representative heuristic algorithms, namely the genetic algorithm (GA), particle swarm optimization (PSO), and simulated annealing (SA), are applied to optimize a heat pump under the given process conditions. Heuristic algorithms are driven based on randomness; thus, the consistency of the calculation results and computational time represent the decision criteria for the appropriate optimizer. The GA is unsuitable as a heat pump optimizer because it requires an excessive number of iterations. In contrast, PSO and SA have a similar capability of consistency and calculation time with a rational number of iterations. In conclusion, PSO exhibits a slightly better consistency and use of computational resources; therefore, PSO is selected as the heat pump design optimization algorithm in this study. The novelty of this work lies in that the related design parameters of the heat pump are simultaneously globally optimized with minimal physical background, and the heuristic algorithm that is most applicable to heat pump design optimization is determined.

Recently, the numerical optimization field has attracted the research community to propose and develop various metaheuristic optimization algorithms. This paper presents a new metaheuristic optimization algorithm called Honey Badger Algorithm (HBA). The proposed algorithm is inspired from the intelligent foraging behavior of honey badger, to mathematically develop an efficient search strategy for solving optimization problems. The dynamic search behavior of honey badger with digging and honey finding approaches are formulated into exploration and exploitation phases in HBA. Moreover, with controlled randomization techniques, HBA maintains ample population diversity even towards the end of the search process. To assess the efficiency of HBA, 24 standard benchmark functions, CEC’17 test-suite, and four engineering design problems are solved. The solutions obtained using the HBA have been compared with ten well-known metaheuristic algorithms including Simulated annealing (SA), Particle Swarm Optimization (PSO), Covariance Matrix Adaptation Evolution Strategy (CMA-ES), Success-History based Adaptive Differential Evolution variants with linear population size reduction (L-SHADE), Moth-flame Optimization (MFO), Elephant Herding Optimization (EHO), Whale Optimization Algorithm (WOA), Grasshopper Optimization Algorithm (GOA), Thermal Exchange Optimization (TEO) and Harris hawks optimization (HHO). The experimental results, along with statistical analysis, reveal the effectiveness of HBA for solving optimization problems with complex search-space, as well as, its superiority in terms of convergence speed and exploration–exploitation balance, as compared to other methods used in this study. The source code of HBA is currently available for public at https://www.mathworks.com/matlabcentral/fileexchange/98204-honey-badger-algorithm .

Joint registration of point clouds obtained from multiple views is a key step of reconstruction for blades. However, due to the structural and surface characteristics of blades, some views do not meet the overlap constraints of registration, which results in significant initial errors of pose estimation. Thus, we propose a novel approach to recover the accuracy of poses estimation. The proposed method is robust to overlap extent of views through a stochastic framework. The approach formulates a variable-parameters graph optimization problem. Then a simulated annealing algorithm is used to solve the global optimal parameters. The candidate parameters in the simulated annealing process are obtained through the improved unscented Kalman filter, which reduces the initial errors and enhances the information matrices. The acceptance of the candidate parameters is determined by the optimization problem constrained by joint point correspondences and closed-loop consistency. And the parameters that can improve the registration accuracy are selected. We test our algorithm with simulated synthetic data and real data obtained by the robot measurement system. We compare the proposed algorithm with several state-of-the-art algorithms. The experimental results show that in the presence of significant initial errors, our method can estimate the poses more accurately and obtain better blade reconstructions.

Fused Deposition Modelling is a fast emerging technology due to its capacity to generate usable components with multiple geometrical designs in a fair period of time without the usage of any tooling or human interaction. The features and reliability of FDM fabricated parts are highly dependent on a small number of processing variables and their settings. The current study examines the relationship between five significant processing constraints. i.e. raster angle, part orientation, air gap, layer thickness and raster width and what effect do they have on the dimensional accuracy of the fabricated part. Twenty-seven experiments were piloted and configured using Taguchi’s architecture and recently formulated MARCOS Method. Here, the Genetic Algorithm Optimization, Simulated Annealing Algorithm Optimization, Particle Swarm Optimization, Grey-Wolf Optimization Algorithm, Moth Flame Optimization Algorithm, Whale Optimization Algorithm, Jaya Algorithm Optimization, Sunflower Optimization Algorithm, Lichtenberg Algorithm Optimization and Forensic Based Investigation Optimization approaches as ten different optimizations have been utilized to predict the optimal setting of the experiment. A comparative inspection of these nature-inspired algorithms in FDM printed part was performed in this study which reported part orientation as the most significant element.

Evolutionary algorithms are commonly used for the purpose of modelling manufacturing processes as they provide results with a great amount of efficiency and accuracy. This article presents a comparison between the two of the most popular optimization techniques namely genetic algorithm and simulated annealing. These techniques have been compared step by step by applying to an abrasive water jet drilling process. The process is represented with the help of both the models and the methods/results are compared. Inputs considered for developing the model are water pressure, abrasive flow volume and standoff distance. The responses selected are overcut, circularity and drill rate. In both the optimization models four stages are reported. Each model is characterized by the change in weights of the factors and the results for the individual cases have been analyzed. The results show that the results obtained from both the techniques is very close but the time required for genetic algorithm is considerably less when compared to the simulated annealing procedure.

Background: Hepatocellular Carcinoma (HCC) is one of the most common malignant tumors. Due to the insidious onset and poor prognosis, most patients have reached the advanced stage at the time of diagnosis. Objective: Studies have shown that Dynamic Network Biomarkers (DNB) can effectively identify the critical state of complex diseases such as HCC from normal state to disease state. Therefore, it is very important to detect DNB efficiently and reliably. Methods: This paper selects a dataset containing eight HCC disease states. First, an individual-specific network is constructed for each sample and features are extracted. In the context of this network, a simulated annealing algorithm is used to search for potential dynamic network biomarker modules, and the evolution of HCC is determined. Results: In fact, in the period of Low-Grade Dysplasia (LGD) and High-Grade Dysplasia (HGD), DNB sends an indicative warning signal, which means that liver dysplasia is a very important critical state in the development of HCC disease. Compared with landscape dynamic network biomarkers method (LDNB), our method can not only describe the statistical characteristics of each disease state, but also yield better results including getting more DNBs enriched in HCC related pathways. Conclusion: The results of this study may be of great significance to the prevention and early diagnosis of HCC.

The head–discharge relationship of an overflow weir is a prerequisite for flow measurement. Conventionally, it is determined by regression methods. With machine learning techniques, data-driven modelling becomes an alternative. However, a standalone model may be inadequate to generate satisfactory results, particularly for a complex system. With the intention of improving the performance of standard gene expression programming (GEP), a hybrid evolutionary scheme is proposed, which is coupled with grey system theory and probabilistic technique. As a gene filter, grey relational analysis (GRA) eliminates noise and simulated annealing (SA) reduces overfitting by optimising the gene weights. The proposed GEP-based model was developed and validated using experimental data of a submerged pivot weir. Compared with standalone GEP, the GRA–GEP–SA model was found to generate more accurate results. Its coefficients of determination and correlation were improved by 3.6% and 1.7%, respectively. The root mean square error was lowered by 24.8%, which is significant. The number of datasets with an error of less than 10% and 20% was increased by 15% and 12%, respectively. The proposed approach outperforms classic genetic programming and shows a comparative error level with the empirical formula. The hybrid procedure also provides a reference for applications in other hydraulic issues.

In this paper, a new U-shaped assembly line balancing problem is studied. For the first time, the criteria such as equipment cost, number of stations and activity performing quality level are considered to be optimized simultaneously by activity to station and worker to station decisions. For this aim, a multi-objective nonlinear formulation is proposed and its linearized version is also presented. Since, according to the literature, the U-shaped assembly line balancing problem with equipment requirements is an NP-hard problem, the problem of this study is NP-hard too. Because of this complexity, the classical algorithms like simulated annealing, variable neighborhood search, and classical genetic algorithm with a novel encoding/decoding scheme are used as solution approaches. As an extension, two hybrid versions of the proposed classical algorithms are proposed according to the characteristics of the problem. In order to evaluate the proposed meta-heuristics, because the problem is new, some test problems are generated randomly. Computational study of the paper, including sensitivity analysis of the proposed meta-heuristics and final experiments on the test problems, proves the superiority of the hybrid versions of the classical algorithms.

Many important challenges in science and technology can be cast as optimization problems. When viewed in a statistical physics framework, these can be tackled by simulated annealing, where a gradual cooling procedure helps search for ground-state solutions of a target Hamiltonian. Although powerful, simulated annealing is known to have prohibitively slow sampling dynamics when the optimization landscape is rough or glassy. Here we show that, by generalizing the target distribution with a parameterized model, an analogous annealing framework based on the variational principle can be used to search for ground-state solutions. Modern autoregressive models such as recurrent neural networks provide ideal parameterizations because they can be sampled exactly without slow dynamics, even when the model encodes a rough landscape. We implement this procedure in the classical and quantum settings on several prototypical spin glass Hamiltonians and find that, on average, it substantially outperforms traditional simulated annealing in the asymptotic limit, illustrating the potential power of this yet unexplored route to optimization. Optimization problems can be described in terms of a statistical physics framework. This offers the possibility to make use of ‘simulated annealing’, which is a procedure to search for a target solution similar to the gradual cooling of a condensed matter system to its ground state. The approach can now be sped up significantly by implementing a model of recurrent neural networks, in a new strategy called variational neural annealing.

This paper proposes a method to design optimal composite sandwich panels subjected to multiple blending rules and external forces. The method uses a two-step algorithm. The first step seeks to obtain the optimal stacking sequence for a laminate, using a blind A* searching scheme over an incremental decision tree. This A* search provides the non-local minimum solution (looking for the best ply orientations and the best core thickness) using a minimum number of finite element method (FEM) evaluations. Once the stacking sequence for the lightest constant-thickness laminate is determined, the second step is to perform a peeling-off process using a simulated annealing algorithm. The final result is an even lighter laminate with a variable thickness distribution. This algorithm is intrinsically discrete and, unlike most gradient-based techniques, is not affected by local minima. It is important to note that the optimization process is enhanced by manufacturing constraints (blending rules), which are fulfilled whenever a feasible solution exists. The algorithm could therefore be a suitable choice for topology purposes whenever the laminate is subjected to a set of blending rules and no constraint violation is allowed.

Bayesian networks are a class of popular graphical models that encode causal and conditional independence relations among variables by directed acyclic graphs (DAGs). We propose a novel structure learning method, annealing on regularized Cholesky score (ARCS), to search over topological sorts, or permutations of nodes, for a high-scoring Bayesian network. Our scoring function is derived from regularizing Gaussian DAG likelihood, and its optimization gives an alternative formulation of the sparse Cholesky factorization problem from a statistical viewpoint, which is of independent interest. We combine global simulated annealing over permutations with a fast proximal gradient algorithm, operating on triangular matrices of edge coefficients, to compute the score of any permutation. Combined, the two approaches allow us to quickly and effectively search over the space of DAGs without the need to verify the acyclicity constraint or to enumerate possible parent sets given a candidate topological sort. The annealing aspect of the optimization is able to consistently improve the accuracy of DAGs learned by local search algorithms. In addition, we develop several techniques to facilitate the structure learning, including pre-annealing data-driven tuning parameter selection and post-annealing constraint-based structure refinement. Through extensive numerical comparisons, we show that ARCS achieves substantial improvements over existing methods, demonstrating its great potential to learn Bayesian networks from both observational and experimental data., Comment: 15 pages, 7 figures, 5 tables

In recent years, the number of electrical and electronic devices used in production and life has been increasing. It leads to serious interference and aliasing among electromagnetic signals. To address electromagnetic interference (EMI) issues, we propose a feasible blind source separation method based on wavelet transform and improved equivariant adaptive separation via independence (EASI) algorithm. First, we leverage the wavelet transform algorithm to denoise mixed electromagnetic signals. Second, we use the variable step-size EASI algorithm to separate each signal from the mixed signals. It is inspired by the simulated annealing strategy. We conduct a series of experiments to demonstrate the effectiveness of WE method. The experimental results show that WE method can provide support for solving EMI problems.

Purpose This paper aims to propose a fast and robust 3D point set registration method for pose estimation of assembly features with few distinctive local features in the manufacturing process. Design/methodology/approach The distance between the two 3D objects is analytically approximated by the implicit representation of the target model. Specifically, the implicit B-spline surface is adopted as an interface to derive the distance metric. With the distance metric, the point set registration problem is formulated into an unconstrained nonlinear least-squares optimization problem. Simulated annealing nested Gauss-Newton method is designed to solve the non-convex problem. This integration of gradient-based optimization and heuristic searching strategy guarantees both global robustness and sufficient efficiency. Findings The proposed method improves the registration efficiency while maintaining high accuracy compared with several commonly used approaches. Convergence can be guaranteed even with critical initial poses or in partial overlapping conditions. The multiple flanges pose estimation experiment validates the effectiveness of the proposed method in real-world applications. Originality/value The proposed registration method is much more efficient because no feature estimation or point-wise correspondences update are performed. At each iteration of the Gauss–Newton optimization, the poses are updated in a singularity-free format without taking the derivatives of a bunch of scalar trigonometric functions. The advantage of the simulated annealing searching strategy is combined to improve global robustness. The implementation is relatively straightforward, which can be easily integrated to realize automatic pose estimation to guide the assembly process.

Feature selection (FS) represents an important task in classification. Hadith represents an example in which we can apply FS on it. Hadiths are the second major source of Islam after the Quran. Thousands of Hadiths are available in Islam, and these Hadiths are grouped into a number of classes. In the literature, there are many studies conducted for Hadiths classification. Sine Cosine Algorithm (SCA) is a new metaheuristic optimization algorithm. SCA algorithm is mainly based on exploring the search space using sine and cosine mathematical formulas to find the optimal solution. However, SCA, like other Optimization Algorithm (OA), suffers from the problem of local optima and solution diversity. In this paper, to overcome SCA problems and use it for the FS problem, two major improvements were introduced to the standard SCA algorithm. The first improvement includes the use of singer chaotic map within SCA to improve solutions diversity. The second improvement includes the use of the Simulated Annealing (SA) algorithm as a local search operator within SCA to improve its exploitation. In addition, the Gini Index (GI) is used to filter the resulted selected features to reduce the number of features to be explored by SCA. Furthermore, three new Hadith datasets were created. To evaluate the proposed Improved SCA (ISCA), the new three Hadiths datasets were used in our experiments. Furthermore, to confirm the generality of ISCA, we also applied it on 14 benchmark datasets from the UCI repository. The ISCA results were compared with the original SCA and the state-of-the-art algorithms such as Particle Swarm Optimization (PSO), Genetic Algorithm (GA), Grasshopper Optimization Algorithm (GOA), and the most recent optimization algorithm, Harris Hawks Optimizer (HHO). The obtained results confirm the clear outperformance of ISCA in comparison with other optimization algorithms and Hadith classification baseline works. From the obtained results, it is inferred that ISCA can simultaneously improve the classification accuracy while it selects the most informative features.

External pipe routing for aero-engine in limited three-dimensional space is a typical nondeterministic polynomial hard problem, where the parallel layout of pipes plays an important role in improving the utilization of layout space, facilitating pipe assembly, and maintenance. This paper presents an automatic multiple pipe routing method for aero-engine that focuses on parallel layout. The compressed visibility graph construction algorithm is proposed first to determine rapidly the rough path and interference relationship of the pipes to be routed. Based on these rough paths, the information of pipe grouping and sequencing are obtained according to the difference degree and interference degree, respectively. Subsequently, a coevolutionary improved differential evolution algorithm, which adopts the coevolutionary strategy, is used to solve multiple pipe layout optimization problem. By using this algorithm, pipes in the same group share the layout space information with one another, and the optimal layout solution of pipes in this group can be obtained in the same evolutionary progress. Furthermore, to eliminate the minor angle deviation of parallel pipes that would cause assembly stress in actual assembly, an accurate parallelization processing method based on the simulated annealing algorithm is proposed. Finally, the simulation results on an aero-engine demonstrate the feasibility and effectiveness of the proposed method.

The problem of assignment and sequencing of tasks is a very complex problem, which is related to whether the computer system can effectively exert the overall efficiency. Solving this problem can make the lowest cost and obtain the greatest benefit. However, the current algorithms for coordinating job assignment and sorting are not completely suitable for heterogeneous computing systems. In order to rationally arrange the problem of computer assignment and sorting, this paper proposes a mathematical programming algorithm to effectively solve the inadaptability of assignment and sorting to heterogeneous computing systems. This paper adopts the control variable method and the comparative analysis method, selects the mathematical programming algorithm and the genetic algorithm, the simulated annealing algorithm these two algorithms, selects the relevant performance indicators, designs the experiments to perform calculations and collects the data. Through the comparison of different algorithms in heterogeneous computing systems, it can be seen that in terms of performance, the average response time and node utilization of the three algorithms are not much different, but the availability of the mathematical programming algorithm is significantly higher than that of the other two. When the rate is 1.0, it still has an availability of 0.59. With the increase in the number of tasks and CPU utilization, the advantages of the mathematical programming algorithm are gradually becoming obvious. Although the receiving capabilities of the three algorithms are decreasing with the increase of these two indicators, when the number of tasks reaches 140, the mathematical programming algorithm can receive tasks remains at 78%, indicating that the algorithm is stable. By applying heterogeneous computing systems on different platforms, GPU and FPGA each have their own advantages. The purpose of coordinating assignments and sequencing is to better allocate resources in the future and maximize benefits. Through the study of mathematical programming algorithms, the time required to execute programs in heterogeneous computing systems can be better reduced, thereby improving the overall system effectiveness.

Given an undirected connected graph G = ( V , E ) with vertex set V and edge set E, the minimum conductance graph partitioning problem is to partition V into two disjoint subsets such that the conductance, i.e., the ratio of the number of cut edges to the smallest volume of two partition subsets is minimized. This problem has a number of practical applications in various areas such as community detection, bioinformatics , and computer vision . However, the problem is computationally challenging, especially for large problem instances. This work presents the first iterated multilevel simulated annealing algorithm for large-scale graph conductance minimization. The algorithm features a novel solution-guided coarsening method and an effective solution refinement procedure based on simulated annealing. Computational experiments demonstrate the high performance of the algorithm on 66 very large real-world sparse graphs with up to 23 million vertices. Additional experiments are presented to get insights into the influences of its algorithmic components . The source code of the proposed algorithm is publicly available, which can be used to solve various real world problems .

The paper considers the problem of designing an aerofoil with a Fowler flap. The proposed approach is based on the use of artificial neural networks for rapid evaluation of aerodynamic characteristics. The linear method of principal component analysis (PCA) is used to reduce the dimensionality of design parameter space and to generate ‘‘random’’ airfiols. The simulated annealing method is used to find the optimal shape of the airfoil and flap.