Global Artificial Bee Colony Algorithm for Boolean Function Classification

Based on the coupled vertical-torsional free vibration records of the spring-suspended section model of bridge decks, an improved Artificial Bee Colony (ABC) algorithm is proposed to identify the flutter derivatives. The ABC algorithm is a novel biological-inspired optimization algorithm, comparing with other iteration methods, the ABC algorithm can facilitate the identification process with no need for initial value. The standard ABC algorithm is good at exploration but poor at exploitation. To enhance the exploitation of the ABC algorithm, Powell’s method is used as a local search tool and a nonlinear factor is introduced for convergence control. Search equations applied to generate candidate solutions in the onlookers and scout bees phase are modified to improve the search ability of this method. The objective function in the optimization is weighted residual sum of squares between measured records and predicted values, where the weighting factors are optimized by an iteration process. The modified ABC algorithm is tested on several benchmark functions compared with the standard ABC algorithm. Simulation results show that the proposed algorithm has a higher convergence speed, better solution quality and stronger robustness. In order to investigate the effectiveness of the modified ABC algorithm in the flutter derivatives identification, numerical simulations of an ideal thin-plate model are carried out. The identification results show that the modified ABC algorithm for flutter derivatives identification of bridge decks is robust and reliable.

Accelerating neural network training using weight extrapolations

Ant colony optimization (ACO) algorithm has the powerful ability of searching the global optimal solution, and backpropagation (BP) algorithm has the feature of rapid convergence on the local optima. The proper hybrid of the two algorithms (ACO-BP) may accelerate the evolving speed of neural networks and improve the forecasting precision of the well-trained networks. ACO-BP scheme adopts ACO to search the optimal combination of weights in the solution space, and then uses BP algorithm to obtain the accurate optimal solution quickly. The ACO-BP and BP algorithms were applied to the problems of function approaching and modeling quantitative structure-activity relationships of Herbicides. Experiment results show that the proposed ACO-BP scheme is more efficient and effective than BP algorithm. Furthermore, ACO-BP reliably performs well when the number of hidden nodes varies.KeywordsHide NodeEvolve Neural NetworkForecast PrecisionPheromone TablePheromone IntensityThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

In this study, an ABC-Local Search (ABC-Ls) method was proposed by including a new local search procedure into the standard artificial bee colony (ABC) algorithm to perform the parameter estimation of photovoltaic systems (PV). The aim of the proposed ABC-Ls method was to improve the exploration capability of the standard ABC with a new local search procedure in addition to the exploitation and exploration balance of the standard ABC algorithm. The proposed ABC-Ls method was first tested on 15 well-known benchmark functions in the literature. In the results of the Friedman Mean Rank test used for statistical analysis, ABC-Ls method successfully ranked first with a value of 1.300 in benchmark functions. After obtaining successful results on the benchmark tests, the proposed ABC-Ls method was applied to the single diode, double diode and Photowatt-PWP-201 PV modules of PV systems for parameter estimations. In addition, the proposed ABC-Ls method has been applied to the KC200GT PV module for parameter estimation under different temperature and irradiance conditions of the PV modules. The success of ABC-Ls method was compared with genetic algorithm (GA), particle swarm optimization (PSO) algorithm, ABC algorithm, tree seed algorithm (TSA), Jaya, Atom search optimization (ASO). The comparison results were presented in tables and graphics in detail. The RMSE values for the parameter estimation of single diode, double diode and Photowatt-PWP-201 PV module of the proposed ABC-LS method were found as 9.8602E−04, 9.8257E−04 and 2.4251E−03, respectively. In this context, the proposed ABC-LS method has been compared with the literature for parameter estimation of single diode, double diode and Photowatt-PWP-201 PV module and it has been found that it provides a parameter estimation similar or better than other studies. The proposed ABC-Ls method for parameter estimation of the KC200GT PV module under different conditions is shown in convergence graphs and box plots, where it achieves more successful, effective and stable results than GA, PSO, ABC, TSA, Jaya and ASO algorithms.

The search space for backpropagation (BP) is usually of high dimensionality which shows convergence. Also, the number of minima abound, and thus the danger to fall in a shallow one is great. In order to limit the search space of BP in a sensible way, we incorporate domain knowledge in the training process. A Two-phase Backpropagation algorithms is presented. In the first phase the direction of the weight vectors of the first (and possibly the only) hidden layer are constrained to remain in the same directions as, for example, the ones of linear discriminants or Principal Components. The directions are chosen based on the problem at hand. Then in the second phase, the constraints are removed and standard Backpropagation algorithm takes over to further minimize the error function. The first phase swiftly situates the weight vectors in a good position (relatively low error) which can serve as the initialization of the standard Backpropagation. Other speed-up techniques can be used in both phases. The generality of its application, its simplicity, and the shorter training time it requires, make this approach attractive.© (1992) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

In applying neural network to identification, back propagation (BP) algorithm is usually trapped to a local optimum and has a low speed of convergence, whereas particle swarm optimization (PSO) is advantageous in terms of global optimal searching. In this paper, a new algorithms which combines guaranteed convergence particle swarm optimizer (GCPSO) algorithm with BP (Back Propagation) algorithm is introduced in this paper and applied to BP neural networks to optimize the parameters of BP neural networks so as to improve the convergence speed and precision of BP neural networks. Compared with the BP algorithm and PSO-BP algorithm, the results of the simulation show that the algorithm of BP Neural Network Model Based on Guaranteed Convergence Particle Swarm Optimization speeds up the convergence process and enhances the accurate rate in pattern recognition.

In order to study the energy-saving operation of high-speed trains, the energy consumption of trains is taken as the goal, and the speed at the transition point of the operating conditions is the optimization variable, an artificial bee colony algorithm is used to optimize the speed curve across the entire line, the purpose is to obtain the first stage optimization speed curve. On this basis, the conditions of the actual running line are fully considered, and the predictive control algorithm is used to optimize the local prediction of the speed, the purpose is to obtain the second stage optimization speed curve. The simulation results show that compared with the energy consumption in the time-saving mode, the energy consumption after the second prediction optimization is reduced by 19.29%. It is verified that the secondary speed curve obtained by the combination of the global artificial bee colony algorithm and the predictive control algorithm has better performance in energy saving effect. This paper can provide good reference value and practical significance for the energy-saving operation of other vehicles.

Grain is an important economic and strategic material of the country. In grain transportation, it is necessary to consider the running time, vehicle number, path length and other factors at the same time, which is a typical multi-objective problem, but also a NP-Hard problem. In this paper, an Artificial Bee Colony algorithm is introduced to solve the routing problem of grain transportation vehicles with multi-objective and time windows. Combined with the practical problems of grain transportation, the standard Artificial Bee Colony algorithm is improved in four aspects: population initialization, domain search mode, bulletin board setting and scout bee search mode, and a Multi-objective Artificial Bee Colony algorithm is proposed by using the strategy of first classification and then sorting and final iteration. The proposed algorithm is compared with other algorithms by using the standard test set in Solomon database. The results show that the Multi-objective Discrete Artificial Bee Colony algorithm has great advantages in solving the routing problem of grain transportation vehicles with time windows.

Stability analysis of a three-term backpropagation algorithm

The back propagation (BP) algorithm is the most popular supervised learning method for multi-layered feed forward Neural Network. It has been successfully deployed in numerous practical problems and disciplines. Regardless of its popularity, BP is still known for some major drawbacks such as easily getting stuck in local minima and slow convergence; since, it uses Gradient Descent (GD) method to learn the network. Over the years, many improved modifications of the BP learning algorithm have been made by researchers but the local minima problem remains unresolved. Therefore, to resolve the inherent problems of BP algorithm, this paper proposed BPGD-A3T algorithm where the approach introduces three adaptive parameters which are gain, momentum and learning rate in BP. The performance of the proposed BPGD-A3T algorithm is then compared with BPGD two term parameters (BPGD-2T), BP with adaptive gain (BPGD-AG) and conventional BP algorithm (BPGD) by means of simulations on classification datasets. The simulation results show that the proposed BPGD-A3T shows better performance and performed highest accuracy for all dataset as compared to other.

The mean-squared error estimator was used by standard BP (backpropagation) algorithms. Therefore these algorithms might get trapped in some local minimum, have slow convergence and be sensitive to initial weight values etc. In this paper, a kind of new robust BP mathematical theory which is based on the Lagrangian multiplier method and several kinds of robust error estimators is investigated in detail. Robust BP algorithms are obtained. Experiments illustrate: our algorithms not only converge fast and are less sensitive to initial weight values, but also can overcome the influence of outliers. The algorithms are robust for little noise perturbation and gross error.

To address the insufficient expressive capabilities of traditional methods in assessing the development level of rural tourism, this study explores the fusion application of the Bidirectional Encoder Representations from Transformers (BERT) and the Back Propagation (BP) algorithm to enhance the accuracy and comprehensiveness of rural tourism development assessment. Firstly, this study introduces the BERT deep learning model and its applications in natural language processing, alongside the role of the BP algorithm in pattern recognition and predictive analysis. Subsequently, a framework for assessing rural tourism development levels, integrating BERT and the BP algorithm, is proposed. This framework collects multidimensional rural tourism-related data and utilizes the BERT model for sentiment analysis and topic extraction from textual data. Empirical analysis of rural tourism development in a specific region validates the effectiveness of the proposed approach. Experimental results demonstrate: (1) The model achieves an accuracy of 84.33% and an F1 score of 85.33% on the publicly available Laptop dataset, with a processing time of 20 s, significantly outperforming other methods. Compared to traditional approaches, the proposed method accurately captures correlations between textual information and numerical data, thereby enhancing the credibility and accuracy of assessment results. (2) From the ablation study results, it is evident that removing any component from the model leads to performance degradation. Specifically, removing the Bidirectional Gated Recurrent Unit (BiGRU) reduces accuracy and F1 scores to 78.21% and 76.33% on the Laptop dataset, and to 85.10% and 70.45% on the Tourist_F dataset. Removing Text Convolutional Neural Network (CNN) reduces accuracy and F1 scores to 79.34% and 77.56% on the Laptop dataset, and to 86.25% and 72.11% on the Tourist_F dataset. The most significant performance decline occurs upon removing BERT, with accuracy and F1 scores decreasing to 70.14% and 66.43% on the Laptop dataset, and to 78.45% and 60.33% on the Tourist_F dataset. These results indicate that BiGcRU, TextCNN, and BERT each contribute significantly to the model’s performance. This study provides substantial support for advancing sustainable development in rural tourism, offering significant practical and innovative value.

In this paper, Dynamic Back Propagation (DBP) is reinvestigated in the context of indirect inverse control of unknown nonlinear dynamic systems using Artificial Neural Networks (ANNs). The overall control scheme includes two networks. The first is used as an approximating model of the unknown nonlinear dynamic behavior of the plant while the second is the controller. The trajectory error is backpropagated through the neural model using DBP algorithm to obtain the control input error. The controller, which is a recurrent ANN, is then adapted also using DBP algorithm. Simulation results obtained with both Standard Back Propagation (SBP) and DBP algorithms for a fourth order nonlinear system clearly show some advantage of DBP.

Back Propagation (BP) algorithm is one of the oldest learning techniques used by artificial neural networks (ANN). It has successfully been implemented in various practical problems. However, the algorithm still faces some drawbacks such as getting easily stuck at local minima and needs longer time to converge on an acceptable solution. Recently, the introduction of Second Order Methods has shown a significant improvement on the learning in BP but it still has some drawbacks such as slow convergence and complexity. To overcome these limitations, this research proposed a modified approach for BP by introducing the Conjugate Gradient and Quasi-Newton which were Second Order methods together with ‘gain’ parameter. The performances of the proposed approach is evaluated in terms of lowest number of epochs, lowest CPU time and highest accuracy on five benchmark classification datasets such as Glass, Horse, 7Bit Parity, Indian Liver Patient and Lung Cancer. The results show that the proposed Second Order methods with ‘gain’ performed better than the BP algorithm.

The reliability growth prediction is the most important part of the reliability engineering. This paper considers the backpropagation (BP) algorithm application in reliability growth prediction. The Gompertz model is a good reliability growth model. The paper examines the BP algorithm and compares it with the Gompertz model. The results show that they were both basically consistent. It indicates that the BP approach is feasible, effective, simple and adaptive. This paper also discusses the prediction of the reliability storage in the weapon system using the BP algorithm.