检索结果-内蒙古大学图书馆

13th International Conference on Intelligent Computing (ICIC)

作者： Zang, Di Ding, Jianping Cheng, Jiujun Zhang, Dongdong Tang, Keshuang Tongji Univ Dept Comp Sci & Technol Shanghai Peoples R China Tongji Univ Minist Educ Key Lab Embedded Syst & Serv Comp Shanghai Peoples R China Tongji Univ Dept Transportat Informat & Control Engn Shanghai Peoples R China

ISBN: (纸本)9783319633152;9783319633145

The stochastic gradient descend (SGD) is a prevalence algorithm used to optimize Convolutional Neural Network (CNN) by many researchers. However, it has several disadvantages such as occurring in local optimum and vanishing gradient problems that need to be overcome or optimized. In this paper, we propose a hybrid learning algorithm which aims to tackle the above mentioned drawbacks by integrating the methods of particle swarm optimization (PSO) and SGD. To take advantage of the excellent global search capability of PSO, we introduce the velocity update formula which is combined with the gradient descend to overcome the shortcomings. In addition, due to the cooperation of the particles, the proposed algorithm helps the convolutional neural network dampen overfitting and obtain better results. The German traffic sign recognition (GTSRB) benchmark is employed as dataset to evaluate the performance and experimental results demonstrate that proposed method outperforms the standard SGD and conjugate gradient (CG) based approaches.

关键词： Particle swarm optimization Convolutional neural network hybrid learning algorithm Stochastic gradient descent

来源：评论

学校读者我要写书评

暂无评论

Intelligent AVR and PSS with Adaptive hybrid learning algorithm

Intelligent AVR and PSS with Adaptive Hybrid Learning Algori...

引用

General Meeting of the IEEE-Power-and-Energy-Society

作者： Mitra, P. Chowdhury, S. P. Chowdhury, S. Pal, K. Crossley, P. A. IEEE Electrical Engineering Department Jadavpur University Kolkata India Electrical Engineering Women's Polytechnic Kolkata India Department of Electrical Engineering University of Manchester United Kingdom

ISBN: (纸本)9781424419050

The paper presents a step-by-step design methodology of an Adaptive Neuro-Fuzzy Inference System (ANFIS) based Automatic Voltage Regulator (AVR) and Power System Stabilizer (PSS) and also demonstrates its performance in a single-muchine-infinite-bus and a multi-machine power system through digital simulation. The design employs a zero and a first order Sugeno fuzzy model, whose parameters are tuned off-line through hybrid learning algorithm. This algorithm is a combination of Least Square Estimator and Error Backpropagation method. The performance of this ANFIS-based AVR and PSS in damping both local and inter-area oscillation is then compared with conventional fuzzy AVR and PSS performances. It is found that the damping characteristics of both ANFIS-based AVR and PSS are better than the conventional fuzzy AVR and PSS. The effectiveness of the proposed ANFIS-based AVR and PSS in small-signal stability is thus established.

关键词： AVR PSS Fuzzy Logic Adaptive Neuro-Fuzzy Inference System Sugeno-Fuzzy Model hybrid learning algorithm

来源：评论

学校读者我要写书评

暂无评论

A self-organizing fuzzy neural network with hybrid learning algorithm for nonlinear system modeling

引用

INFORMATION SCIENCES 2023年第1期642卷

作者： Meng, Xi Zhang, Yin Quan, Limin Qiao, Junfei Beijing Univ Technol Fac Informat Technol Beijing 100124 Peoples R China Beijing Lab Smart Environm Protect Beijing 100124 Peoples R China Minist Educ Engn Res Ctr Intelligence Percept & Autonomous Con Beijing 100124 Peoples R China Qingdao Univ Technol Sch Informat & Control Engn Qingdao 266520 Peoples R China Beijing Univ Technol Beijing 100124 Peoples R China

Fuzzy neural networks (FNNs) integrating the advantages of fuzzy systems and neural networks are useful techniques for nonlinear system modeling. However, how to determine the structure and parameters to guarantee satisfactory modeling performance still remains a challenge. In this study, a self-organizing FNN with hybrid learning algorithm (SOFNN-HLA) is developed for nonlinear system modeling. First, a growing-and-pruning constructive scheme is proposed based on the network learning accuracy and the rule firing strength. New fuzzy rules can be developed with appropriate initial parameters based on the idea of an error-correction algorithm to improve the learning performance. Meanwhile, some redundant rules with low firing strength would be pruned to ensure a compact structure. Second, a hybrid learning algorithm combining an improved second-order algorithm and the least square method is developed for parameter adjustment. In this hybrid learning algorithm, linear parameters and nonlinear parameters are tackled separately to enhance the learning efficiency. Finally, the effectiveness of SOFNN-HLA is validated by two benchmark simulations and one real problem from wastewater treatment pro-cesses. The results show that the proposed SOFNN-HLA can achieve desirable generalization performance with a compact structure for nonlinear system modeling.

关键词： Fuzzy neural network Growing -and -pruning scheme hybrid learning algorithm Nonlinear system modeling

来源：评论

学校读者我要写书评

暂无评论

Identification using ANFIS with intelligent hybrid stable learning algorithm approaches and stability analysis of training methods

引用

APPLIED SOFT COMPUTING 2009年第2期9卷 833-850页

作者： Shoorehdeli, Mahdi Aliyari Teshnehlab, Mohammad Sedigh, Ali Khaki Khanesar, M. Ahmadieh KN Toosi Univ Technol Tehran Iran

This paper proposes a novel hybrid learning algorithm with stable learning laws for Adaptive Network based Fuzzy Inference System (ANFIS) as a system identifier and studies the stability of this algorithm. The new hybrid learning algorithm is based on particle swarm optimization (PSO) for training the antecedent part and forgetting factor recursive least square (FFRLS) for training the conclusion part. Two famous training algorithms for ANFIS are the gradient descent (GD) to update antecedent part parameters and using GD or recursive least square (RLS) to update conclusion part parameters. Lyapunov stability theory is used to study the stability of the proposed algorithms. This paper, also studies the stability of PSO as an optimizer in training the identifier. Stable learning algorithms for the antecedent and consequent parts of fuzzy rules are proposed. Some constraints are obtained and simulation results are given to validate the results. It is shown that instability will not occur for the leaning rate and PSO factors in the presence of constraints. The learning rate can be calculated on-line and will provide an adaptive learning rate for the ANFIS structure. This new learning scheme employs adaptive learning rate that is determined by input-output data. Also, stable learning algorithms for two common methods are proposed based on Lyapunov stability theory and some constraints are obtained. (C) 2008 Elsevier B. V. All rights reserved.

关键词： learning rate hybrid learning algorithm Intelligent optimization Gradient based Recursive least square and particle swarm optimization Fuzzy systems Fuzzy neural networks ANFIS Lyapunov theory Identification Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Training ANFIS as an identifier with intelligent hybrid stable learning algorithm based on particle swarm optimization and extended Kalman filter

引用

FUZZY SETS AND SYSTEMS 2009年第7期160卷 922-948页

作者： Shoorehdeli, Mahdi Aliyari Teshnehlab, Mohammad Sedigh, Ali Khaki KN Toosi Univ Technol Fac Elect Engn ISLAB Tehran Iran

This paper proposes a novel hybrid learning algorithm with stable learning laws for Adaptive Network-based Fuzzy Inference System (ANFIS) as a system identifier. The proposed hybrid learning algorithm is based on the particle swarm optimization (PSO) for training the antecedent part and the extended Kalman filter (EKF) for training the conclusion part. Lyapunov stability theory is used to study the stability of the proposed algorithm. Comparison results of the proposed approach, PSO algorithm for training the antecedent part and recursive least squares (RLSs) or EKF algorithm for training the conclusion part, with the other classical approaches such as, gradient descent, resilient propagation, quick propagation, Levenberg-Marquardt for training the antecedent part and RLSs algorithm for training the conclusion part are provided. Moreover, it is shown that applying PSO, a powerful optimizer, to optimally train the parameters of the membership function on the antecedent part of the fuzzy rules in ANFIS system is a stable approach which results in an identifier with the best trained model. Stability constraints are obtained and different simulation results are given to validate the results. Also, the stability of Levenberg-Marquardt algorithms for ANFIS training is analyzed. (C) 2008 Elsevier B.V. All rights reserved.

关键词： Identification Stability analysis hybrid learning algorithm Particle swarm optimization Extended Kalman filter ANFIS

来源：评论

学校读者我要写书评

暂无评论

Identification using ANFIS with intelligent hybrid stable learning algorithm approaches

引用

NEURAL COMPUTING & APPLICATIONS 2009年第2期18卷 157-174页

作者： Shoorehdeli, Mahdi Aliyari Teshnehlab, Mohammad Sedigh, Ali Khaki KN Toosi Univ Technol Tehran Iran

This paper suggests novel hybrid learning algorithm with stable learning laws for adaptive network based fuzzy inference system (ANFIS) as a system identifier and studies the stability of this algorithm. The new hybrid learning algorithm is based on particle swarm optimization (PSO) for training the antecedent part and gradient descent (GD) for training the conclusion part. Lyapunov stability theory is used to study the stability of the proposed algorithm. This paper, studies the stability of PSO as an optimizer in training the identifier, for the first time. Stable learning algorithms for the antecedent and consequent parts of fuzzy rules are proposed. Some constraints are obtained and simulation results are given to validate the results. It is shown that instability will not occur for the leaning rate and PSO factors in the presence of constraints. The learning rate can be calculated on-line and will provide an adaptive learning rate for the ANFIS structure. This new learning scheme employs adaptive learning rate that is determined by input-output data.

关键词： learning rate hybrid learning algorithm Intelligent optimization Fuzzy systems TSK system ANFIS Lyapunov theory Identification Stability analysis Fuzzy neural networks Gradient based Recursive least square and particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

A Novel Parameter Identification Approach via hybrid learning for Aggregate Load Modeling

引用

IEEE TRANSACTIONS ON POWER SYSTEMS 2009年第3期24卷 1145-1154页

作者： Bai, Hua Zhang, Pei Ajjarapu, Venkataramana Iowa State Univ Dept Elect & Comp Engn Ames IA 50010 USA EPRI Palo Alto CA 94304 USA

Parameter identification is the key technology in measurement-based load modeling. A hybrid learning algorithm is proposed to identify parameters for the aggregate load model (ZIP augmented with induction motor). The hybrid learning algorithm combines the genetic algorithm (GA) and the nonlinear Levenberg-Marquardt (L-M) algorithm. It takes advantages of the global search ability of GA and the local search ability of L-M algorithm, which is a more powerful search technique. The proposed algorithm is tested for load parameter identifications using both simulation data and field measurement data. Numerical results illustrate that the hybrid learning algorithm can improve the accuracy and reduce the computation time for load model parameter identifications.

关键词： Genetic algorithm hybrid learning algorithm Levenberg-Marquardt algorithm load modeling parameter identification

来源：评论

学校读者我要写书评

暂无评论

hybrid fuzzy modeling of wastewater quality with artificial intelligence learning

引用

ENVIRONMENTAL ENGINEERING SCIENCE 2008年第6期25卷 941-950页

作者： Yoo, ChangKyoo Hwang, Sun-Jin Moon, Il Kyung Hee Univ Coll Environm & Appl Chem Green Energy Ctr Yongin 446701 Gyeonggi Do South Korea Yonsei Univ Dept Chem Engn Seoul 120479 South Korea

The wastewater treatment process (WWTP) is highly nonlinear and complex, and its dynamics are difficult to model. Process data obtained under multiple operating conditions that have a number of operating models and changes in operating conditions, such as biological WWTP, should be modeled carefully. In this paper, we propose a new hybrid technique for modeling wastewater quality that is based on the Takagi-Sugeno-Kang fuzzy model with artificial intelligence learning and employs real-coded genetic algorithms. The hybrid learning framework integrates the multiple fuzzy model, which can find the rule base and the membership functions of the fuzzy model simultaneously. We applied the proposed method to predict the effluent chemical oxygen demand in a full-scale coke wastewater treatment plant. The modeling results show that the hybrid model can accurately model the real nonlinear processes under diverse operating conditions, and that it is able to identify various operating regions in a full-scale WWTP.

关键词： COD prediction data-driven model genetic algorithm hybrid learning algorithm modeling Takagi-Sugeno-Kang fuzzy model wastewater quality modeling

来源：评论

学校读者我要写书评

暂无评论

Artificial Bee Colony Optimization of Interval Type-2 Fuzzy Extreme learning System for Chaotic Data 3

Artificial Bee Colony Optimization of Interval Type-2 Fuzzy ...

引用

3rd International Conference on Computer and Information Sciences (ICCOINS)

作者： Hassan, Saima Jaafar, Jafreezal Khanesar, Mojtaba A. Khosravi, Abbas Univ Teknol PETRONAS Dept Comp & Informat Sci Tronoh Perak Malaysia Kohat Univ Sci & Technol Inst Informat Technol Kohat Kpk Pakistan Semnan Univ Fac Elect & Comp Engn Semnan Iran Deakin Univ Ctr Intelligent Syst Res Bldg KCWaurn Ponds Campus Geelong Vic 3217 Australia

ISBN: (纸本)9781509025497

The major challenge in the design of Interval type-2 fuzzy logic system (IT2FLS) is to determine the optimal parameters for their antecedent and consequent parts. This paper propose a novel hybrid learning algorithm for the design of IT2FLS. The proposed hybrid learning algorithm utilizes the combination of extreme learning machine (ELM) and artificial bee colony optimization (ABC) to tune the parameters of the consequent and antecedent parts of the IT2FLS, respectively. The effective forecasting performance of the proposed hybrid learning algorithm is analyzed by modeling a chaotic data set. It is found that the forecasted errors gradually decrease with decrease in the level of noise in data and vise versa.

关键词： Interval type-2 fuzzy logic system artificial bee colony optimization extreme learning machine hybrid learning algorithm forecasting

来源：评论

学校读者我要写书评

暂无评论

Internal Model Control based on Extreme learning ANFIS for Nonlinear Application

Internal Model Control based on Extreme Learning ANFIS for N...

引用

IEEE International Conference on Signal Processing, Informatics, Communication and Energy Systems (SPICES)

作者： Shihabudheen, K., V Pillai, G. N. Indian Inst Technol Roorkee Dept Elect Engn Roorkee Uttar Pradesh India

ISBN: (纸本)9781479918232

Extreme learning Adaptive Neuro Fuzzy Inference System (ELANFIS) is a new learning machine which combines the learning capabilities of neural networks and the explicit knowledge of the fuzzy systems as in the case of conventional adaptive neuro-fuzzy inference system (ANFIS). ELANFIS reduces the computational complexity of ANFIS by eliminating the hybrid learning algorithm and avoids the randomness of the Extreme learning Machine (ELM). This paper proposes implementation of Non Linear Internal Model Controller (NIMC) using ELANFIS algorithm. NIMC model and its inverse controller is developed using ELANFIS architecture. The performance of proposed controller is tested in MATLAB environment using nonlinear conical tank system. Simulation results shows that proposed controller produces good generalization along with perfect trajectory tracking compared to conventional ANFIS algorithm.

关键词： Internal Model Control hybrid learning algorithm Conical tank system Membership function

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：