An Optimization Method for the Initial Parameters Selection of Fuzzy Cerebellar Model Neural Networks in Parametric Fault Diagnosis

2020 ◽  
Vol 22 (7) ◽  
pp. 2071-2082
Author(s):  
Qiongbin Lin ◽  
Shican Chen ◽  
Chih-Min Lin
Keyword(s):  
Neural Networks ◽  
Fault Diagnosis ◽  
Optimization Method ◽  
Parameters Selection ◽  
Parametric Fault ◽  
Selection Of

scholarly journals A New Hyper-Parameter Optimization Method for Power Load Forecast Based on Recurrent Neural Networks

Algorithms ◽  
2021 ◽  
Vol 14 (6) ◽  
pp. 163
Author(s):  
Yaru Li ◽  
Yulai Zhang ◽  
Yongping Cai
Keyword(s):  
Neural Networks ◽  
Parameter Optimization ◽  
Recurrent Neural Networks ◽  
Critical Role ◽  
Optimization Method ◽  
Bayesian Optimization ◽  
Power Load ◽  
Gradient Calculation ◽  
Truncated Newton ◽  
Selection Of

The selection of the hyper-parameters plays a critical role in the task of prediction based on the recurrent neural networks (RNN). Traditionally, the hyper-parameters of the machine learning models are selected by simulations as well as human experiences. In recent years, multiple algorithms based on Bayesian optimization (BO) are developed to determine the optimal values of the hyper-parameters. In most of these methods, gradients are required to be calculated. In this work, the particle swarm optimization (PSO) is used under the BO framework to develop a new method for hyper-parameter optimization. The proposed algorithm (BO-PSO) is free of gradient calculation and the particles can be optimized in parallel naturally. So the computational complexity can be effectively reduced which means better hyper-parameters can be obtained under the same amount of calculation. Experiments are done on real world power load data,where the proposed method outperforms the existing state-of-the-art algorithms,BO with limit-BFGS-bound (BO-L-BFGS-B) and BO with truncated-newton (BO-TNC),in terms of the prediction accuracy. The errors of the prediction result in different models show that BO-PSO is an effective hyper-parameter optimization method.

SVM Parameter Optimization based on Immune Memory Clone Strategy and Application in Bus Passenger Flow Counting

2012 ◽  
Vol 4 (4) ◽  
pp. 74-80
Author(s):  
Zhu Fang ◽  
Wei Junfang
Keyword(s):  
Optimization Method ◽  
Parameters Optimization ◽  
Immune Memory ◽  
Support Vector ◽  
Model Parameters ◽  
Passenger Flow ◽  
Parameters Selection ◽  
Svm Model ◽  
Peak Model ◽  
Selection Of

The performance of support vector mchine (SVM) depends on the selection of model parameters, however, the selection of SVM model parameters more depends on the empirical value. According to the above deficiency, this paper proposed a parameters optimization method of support vector machine based on immune memory clone strategy (IMC). This method can solve the multi-peak model parameters selection problem better which is introduced by n-folded cross-verification. Tests on standard datasets show that this method has higher precision and faster optimization speed compared with other four methods. Then the proposed method was applied to bus passenger flow counting. The experimental results show that the method reposed in this paper obtains higher classification accuracy.

Parametric Fault Diagnosis Based on Fuzzy Cerebellar Model Neural Networks

2019 ◽  
Vol 66 (10) ◽  
pp. 8104-8115 ◽  
Author(s):  
Qiongbin Lin ◽  
Shican Chen ◽  
Chih-Min Lin
Keyword(s):  
Neural Networks ◽  
Fault Diagnosis ◽  
Parametric Fault

A Shape Function-Based Updating Parameters Selection Method for Long-Span Bridges

2009 ◽  
Author(s):  
Gang Liu ◽  
Zongming Huang ◽  
Yimin Shao ◽  
Shangbin Weng
Keyword(s):  
Shape Function ◽  
Model Updating ◽  
Optimization Method ◽  
Selection Method ◽  
Shape Functions ◽  
Long Span Bridges ◽  
Long Span ◽  
Parameters Selection ◽  
Modal Updating ◽  
Selection Of

We present a new updating parameters (UPs) selection method to tackle the bottleneck created by having too many UPs and limited measured data in model updating processing. While the model updating is performed by parameter optimization, an ill-conditioned numerical problem may be encountered or the reliability of the result may be unacceptable if too many parameters are used. The selection of UPs thus becomes a key issue, especially for long-span bridges with finite element models that should be divided into at least hundreds of element numbers. A new method is introduced to reduce the number of UPs and retain their physical significance. In this method, original UPs are described by a few macro-parameters based on shape functions. The model subsequently is updated by a normal optimization algorithm, such as the first-order optimization method. Based on a bridge with a three-span continuous beam and a long-span tie-arch, the optimal effects are investigated, with or without a shape function and using different types of shape functions. The results indicate that the effect of the modal updating based on a shape function is more robust than without shape function and the effect of a linear shape function is better than that of a constant value shape function.

Research on Parameters Optimization Algorithm in Support Vector Machine Based on Immune Memory Clone Strategy

2012 ◽  
Vol 241-244 ◽  
pp. 1618-1621
Author(s):  
Fang Zhu ◽  
Jun Fang Wei
Keyword(s):  
Support Vector Machine ◽  
Optimization Method ◽  
Parameters Optimization ◽  
Immune Memory ◽  
Support Vector ◽  
Model Parameters ◽  
Standard Data ◽  
Parameters Selection ◽  
Optimum Model ◽  
Selection Of

The performance of support vector machine (SVM) depends on the selection of model parameters, however, the selection of SVM model parameters more depends on the empirical value. According to the above deficiency, this paper proposed a parameters optimization method of support vector machine based on immune memory clone strategy (IMC). This method can solve the multi-peak model parameters selection problem better which is introduced by n-folded cross-verification and automatic acquire the optimum model parameters. Proved by the simulation results on standard data, this method has higher precision and faster optimization speed. In a word, it can be used as an effective and feasible SVM parameters optimization method.

A HYBRID PSO-SA OPTIMIZING APPROACH FOR SVM MODELS IN CLASSIFICATION

2013 ◽  
Vol 06 (05) ◽  
pp. 1350036 ◽  
Author(s):  
HUIYAN JIANG ◽  
LINGBO ZOU
Keyword(s):  
Operating Characteristic ◽  
Fitness Function ◽  
Pso Algorithm ◽  
Optimization Method ◽  
Identification Accuracy ◽  
Support Vector ◽  
Swarm Optimization ◽  
Receiver Operating Characteristic Curves ◽  
Parameters Selection ◽  
Selection Of

Support vector machine (SVM) is a widely used tool in the field of image processing and pattern recognition. However, the parameters selection of SVMs is a dilemma in disease identification and clinical diagnosis. This paper proposed an improved parameter optimization method based on traditional particle swarm optimization (PSO) algorithm by changing the fitness function in the traditional evolution process of SVMs. Then, this PSO method was combined with simulated annealing global searching algorithm to avoid local convergence that traditional PSO algorithms usually run into. And this method has achieved better results which reflected in the receiver-operating characteristic curves in medical images classification and has gained considerable identification accuracy in clinical disease detection.

A Novel Parameter Optimization Algorithm Based on Immune Memory Clone Strategy

2012 ◽  
Vol 4 (3) ◽  
pp. 102-108
Author(s):  
Zhu Fang ◽  
Wei Junfang
Keyword(s):  
Support Vector Machine ◽  
Optimization Method ◽  
Parameters Optimization ◽  
Immune Memory ◽  
Support Vector ◽  
Model Parameters ◽  
Parameters Selection ◽  
Svm Model ◽  
Peak Model ◽  
Selection Of

The performance of support vector machine (SVM) depends on the selection of model parameters, however, the selection of SVM model parameters more depends on the empirical value. According to the deficiency, this paper proposes a parameters optimization method of support vector machine based on immune memory clone strategy (IMC). This method can solve the multi-peak model parameters selection problem better which is introduced by n-folded cross-verification. Tests on standard datasets show that this method has higher precision and faster optimization speed compared with other four methods. The proposed method was applied to bus passenger flow counting. The experimental results show that the method reposed in this paper obtains higher classification accuracy.

scholarly journals SVM Parameter Optimization Based on Immune Memory Clone Strategy and Application in Bus Passenger Flow Counting

2012 ◽  
Vol 6-7 ◽  
pp. 694-699
Author(s):  
Fang Zhu ◽  
Jun Fang Wei
Keyword(s):  
Support Vector Machine ◽  
Optimization Method ◽  
Parameters Optimization ◽  
Immune Memory ◽  
Support Vector ◽  
Model Parameters ◽  
Passenger Flow ◽  
Parameters Selection ◽  
Svm Model ◽  
Selection Of

The performance of support vector machine (SVM) depends on the selection of model parameters, however, the selection of SVM model parameters more depends on the empirical value. According to the above deficiency, this paper proposed a parameters optimization method of support vector machine based on immune memory clone strategy (IMC). This method can solve the multi-peak model parameters selection problem better which is introduced by n-folded cross-verification. Tests on standard datasets show that this method has higher precision and faster optimization speed compared with other four methods. Then the proposed method was applied to bus passenger flow counting. The experimental results show that the method reposed in this paper obtains higher classification accuracy.

Sign in / Sign up

Export Citation Format

Share Document