convergence speed
Recently Published Documents





2022 ◽  
Vol 9 (2) ◽  
pp. 259-269
Gianvito Difilippo ◽  
Maria Pia Fanti ◽  
Agostino Marcello Mangini

2022 ◽  
Vol 11 (1) ◽  
pp. 66
Shenghua Xu ◽  
Yang Gu ◽  
Xiaoyan Li ◽  
Cai Chen ◽  
Yingyi Hu ◽  

The internal structure of buildings is becoming increasingly complex. Providing a scientific and reasonable evacuation route for trapped persons in a complex indoor environment is important for reducing casualties and property losses. In emergency and disaster relief environments, indoor path planning has great uncertainty and higher safety requirements. Q-learning is a value-based reinforcement learning algorithm that can complete path planning tasks through autonomous learning without establishing mathematical models and environmental maps. Therefore, we propose an indoor emergency path planning method based on the Q-learning optimization algorithm. First, a grid environment model is established. The discount rate of the exploration factor is used to optimize the Q-learning algorithm, and the exploration factor in the ε-greedy strategy is dynamically adjusted before selecting random actions to accelerate the convergence of the Q-learning algorithm in a large-scale grid environment. An indoor emergency path planning experiment based on the Q-learning optimization algorithm was carried out using simulated data and real indoor environment data. The proposed Q-learning optimization algorithm basically converges after 500 iterative learning rounds, which is nearly 2000 rounds higher than the convergence rate of the Q-learning algorithm. The SASRA algorithm has no obvious convergence trend in 5000 iterations of learning. The results show that the proposed Q-learning optimization algorithm is superior to the SARSA algorithm and the classic Q-learning algorithm in terms of solving time and convergence speed when planning the shortest path in a grid environment. The convergence speed of the proposed Q- learning optimization algorithm is approximately five times faster than that of the classic Q- learning algorithm. The proposed Q-learning optimization algorithm in the grid environment can successfully plan the shortest path to avoid obstacle areas in a short time.

Symmetry ◽  
2022 ◽  
Vol 14 (1) ◽  
pp. 132
Jianfeng Zheng ◽  
Shuren Mao ◽  
Zhenyu Wu ◽  
Pengcheng Kong ◽  
Hao Qiang

To solve the problems of poor exploration ability and convergence speed of traditional deep reinforcement learning in the navigation task of the patrol robot under indoor specified routes, an improved deep reinforcement learning algorithm based on Pan/Tilt/Zoom(PTZ) image information was proposed in this paper. The obtained symmetric image information and target position information are taken as the input of the network, the speed of the robot is taken as the output of the next action, and the circular route with boundary is taken as the test. The improved reward and punishment function is designed to improve the convergence speed of the algorithm and optimize the path so that the robot can plan a safer path while avoiding obstacles first. Compared with Deep Q Network(DQN) algorithm, the convergence speed after improvement is shortened by about 40%, and the loss function is more stable.

Jiang Hua ◽  
Sun Tao

In order to solve the problem that the evaluation algorithm is easy to fall into local extremum, which leads to slow convergence speed, a skilled talent quality evaluation algorithm based on a deep belief network model was designed. Establish an evaluation set with 4 first level indicators and 14 second level indicators, and calculate the corresponding weights to complete the construction of the evaluation index system. A DBN structure composed of several RBMs and a BP network is constructed. Based on the DBN, a quality evaluation algorithm is designed. The algorithm training is used to evaluate the test data and output the evaluation level. The experimental results show that the convergence speed of DBN based evaluation algorithm is significantly better than that of BP neural network and SVM based evaluation algorithm under the same number of iterations, which is suitable for the accurate evaluation of talent quality.

2022 ◽  
Vol 7 (4) ◽  
pp. 5563-5593
Peng Wang ◽  
Weijia He ◽  
Fan Guo ◽  
Xuefang He ◽  

<abstract><p>The atom search optimization (ASO) algorithm has the characteristics of fewer parameters and better performance than the traditional intelligent optimization algorithms, but it is found that ASO may easily fall into local optimum and its accuracy is not higher. Therefore, based on the idea of speed update in particle swarm optimization (PSO), an improved atomic search optimization (IASO) algorithm is proposed in this paper. Compared with traditional ASO, IASO has a faster convergence speed and higher precision for 23 benchmark functions. IASO algorithm has been successfully applied to maximum likelihood (ML) estimator for the direction of arrival (DOA), under the conditions of the different number of signal sources, different signal-to-noise ratio (SNR) and different population size, the simulation results show that ML estimator with IASO algorithum has faster convergence speed, fewer iterations and lower root mean square error (RMSE) than ML estimator with ASO, sine cosine algorithm (SCA), genetic algorithm (GA) and particle swarm optimization (PSO). Therefore, the proposed algorithm holds great potential for not only guaranteeing the estimation accuracy but also greatly reducing the computational complexity of multidimensional nonlinear optimization of ML estimator.</p></abstract>

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Guiting Ren

The traditional BP neural network has the disadvantages of easy falling into local minimum and slow convergence speed. Aiming at the shortcomings of BP neural network (BP neural network), an artificial bee colony algorithm (ABC) is proposed to cross-optimize the weight and threshold of BP network parameters. This study is mainly about the application of BP neural network algorithm in English curriculum recommendation technology. It includes the application of BP neural network algorithm in English course recommendation technology, English course teaching design mode, the application of BP neural network algorithm in English course, and the optimal combination of bee colony algorithm and BP neural network. After 4690 iterations, the neural network reaches the target accuracy, and the training is completed. At the same time, the prediction error of the model is less than 10%, which further shows that the performance of the prediction model is good. Therefore, the combination model is recommended in this paper. The results show that the optimization algorithm improves the solution accuracy and speeds up the convergence speed of the network.

2021 ◽  
Vol 2021 ◽  
pp. 1-17
Yifan Qin ◽  
Yang Lu ◽  
Jinchao Ma ◽  
Huiyu Yue

Current control laws for active control of helicopter structural vibration are designed for steady-state flight conditions, while the vibration response of maneuvering flight has not been taken into consideration yet. In order to obtain full-time vibration suppression capability, the authors propose a filtered least mean square-mixed sensitivity robust control method based on reference signal reconstruction (LMS-MSRC), driving piezoelectric stack actuators to suppress helicopter structural vibration response in maneuvering flight. When feedback controller designed by H ∞ theory is implemented, active damping is added on the secondary path to weaken the adverse effects of its sudden changes in maneuvering flight state. Furthermore, a reference signal reconstruction scheme is given concerning equivalent secondary path. In addition, the reconstruction accuracy, the convergence speed, stability, and global validity of the hybrid controller are analysed. Compared with multichannel Fx-LMS, numerical simulations of LMS-MSRC for vibration suppression are undertaken with a helicopter simplified finite element model under several typical flight conditions. Further experiments of real-time free-free beam vibration control are performed, driven by a stacked piezoelectric actuator. The instantaneous overshoot of measured response is 42% less than the peak value and its attenuation reaches 85% within 2.5 s. Numerical and experimental results reveal that the proposed algorithm is practical for suppressing transient disturbance and multifrequency helicopter vibration response during maneuvering flight with faster convergence speed and better robustness.

2021 ◽  
Vol 2021 ◽  
pp. 1-23
Xiaodan Liang ◽  
Dong Wu ◽  
Yang Liu ◽  
Maowei He ◽  
Liling Sun

In the past few decades, metaheuristic algorithms (MA) have been developed tremendously and have been successfully applied in many fields. In recent years, a large number of new MA have been proposed. Slime mould algorithm (SMA) is a novel swarm-based intelligence optimization algorithm. SMA solves the optimization problem by imitating the foraging and movement behavior of slime mould. It can effectively obtain a promising global optimal solution. However, it still suffers some shortcomings such as the unstable convergence speed, the imprecise search accuracy, and incapability of identifying a local optimal solution when faced with complicated optimization problems. With the purpose of overcoming the shortcomings of SMA, this paper proposed a multistrategy enhanced version of SMA called ESMA. The three enhanced strategies are chaotic initialization strategy (CIS), orthogonal learning strategy (OLS), and boundary reset strategy (BRS). The CIS is used to generate an initial population with diversity in the early stage of ESMA, which can increase the convergence speed of the algorithm and the quality of the final solution. Then, the OLS is used to discover the useful information of the best solutions and offer a potential search direction, which enhances the local search ability and raises the convergence rate. Finally, the BRS is used to correct individual positions, which ensures the population diversity and enhances the overall search capabilities of ESMA. The performance of ESMA was validated on the 30 IEEE CEC2014 functions and three IIR model identification problems, compared with other nine well-regarded and state-of-the-art algorithms. Simulation results and analysis prove that the ESMA has a superior performance. The three strategies involved in ESMA have significantly improved the performance of the basic SMA.

2021 ◽  
pp. 1-17
Maodong Li ◽  
Guanghui Xu ◽  
Yuanwang Fu ◽  
Tingwei Zhang ◽  
Li Du

 In this paper, a whale optimization algorithm based on adaptive inertia weight and variable spiral position updating strategy is proposed. The improved algorithm is used to solve the problem that the whale optimization algorithm is more dependent on the randomness of the parameters, so that the algorithm’s convergence accuracy and convergence speed are insufficient. The adaptive inertia weight, which varies with the fitness of individual whales, is used to balance the algorithm’s global search ability and local exploitation ability. The variable spiral position update strategy based on the collaborative convergence mechanism is used to dynamically adjust the search range and search accuracy of the algorithm. The effective combination of the two can make the improved whale optimization algorithm converge to the optimal solution faster. It had been used 18 international standard test functions, including unimodal function, multimodal function, and fixed-dimensional function to test the improved whale optimization algorithm in this paper. The test results show that the improved algorithm has faster convergence speed and higher algorithm accuracy than the original algorithm and several classic algorithms. The algorithm can quickly converge to near the optimal value in the early stage, and then effectively jump out of the local optimal through adaptive adjustment, and has a certain ability to solve large-scale optimization problems.

Symmetry ◽  
2021 ◽  
Vol 13 (12) ◽  
pp. 2364
Shangbin Jiao ◽  
Chen Wang ◽  
Rui Gao ◽  
Yuxing Li ◽  
Qing Zhang

The probability of the basic HHO algorithm in choosing different search methods is symmetric: about 0.5 in the interval from 0 to 1. The optimal solution from the previous iteration of the algorithm affects the current solution, the search for prey in a linear way led to a single search result, and the overall number of updates of the optimal position was low. These factors limit Harris Hawks optimization algorithm. For example, an ease of falling into a local optimum and the efficiency of convergence is low. Inspired by the prey hunting behavior of Harris’s hawk, a multi-strategy search Harris Hawks optimization algorithm is proposed, and the least squares support vector machine (LSSVM) optimized by the proposed algorithm was used to model the reactive power output of the synchronous condenser. Firstly, we select the best Gauss chaotic mapping method from seven commonly used chaotic mapping population initialization methods to improve the accuracy. Secondly, the optimal neighborhood perturbation mechanism is introduced to avoid premature maturity of the algorithm. Simultaneously, the adaptive weight and variable spiral search strategy are designed to simulate the prey hunting behavior of Harris hawk to improve the convergence speed of the improved algorithm and enhance the global search ability of the improved algorithm. A numerical experiment is tested with the classical 23 test functions and the CEC2017 test function set. The results show that the proposed algorithm outperforms the Harris Hawks optimization algorithm and other intelligent optimization algorithms in terms of convergence speed, solution accuracy and robustness, and the model of synchronous condenser reactive power output established by the improved algorithm optimized LSSVM has good accuracy and generalization ability.

Sign in / Sign up

Export Citation Format

Share Document