Progressive Learning Machine: A New Approach for General Hybrid System Approximation

2015 ◽  
Vol 26 (9) ◽  
pp. 1855-1874 ◽  
Author(s):  
Yimin Yang ◽  
Yaonan Wang ◽  
Q. M. Jonathan Wu ◽  
Xiaofeng Lin ◽  
Min Liu
IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 59172-59184 ◽  
Author(s):  
Xiaowei Chen ◽  
Songtao Tang ◽  
Zhihui Lu ◽  
Jie Wu ◽  
Yucong Duan ◽  
...  

Societies ◽  
2020 ◽  
Vol 10 (2) ◽  
pp. 38 ◽  
Author(s):  
Marcel Pikhart ◽  
Blanka Klímová

The implementation of various eLearning platforms has seen an incredible and unprecedented rise in the past decade in our universities. The aim of this pilot research study is to explore the gap in second language acquisition research for technologically savvy Generation Z, whose members use modern technologies, especially mobile applications, in their learning process in a massive way. More specifically, the authors focus on students’ perceptions of the use of traditional and blended learning supported by an eLearning course in order to reveal students’ attitudes to and expectations from these learning modalities. Altogether, 40 university students participated in an experiment. The findings clearly show that the present eLearning platform is no longer an attractive option for students of Generation Z since these students want to participate in the creation of its content and collaborate and interact with each other in ways they are used to with other social media platforms such as Facebook. The implications of the research are important for educators and designers of various eLearning courses who need to take this into account. Further implications suggest a new approach to the exploitation of eLearning platform connected to Web 4.0. The basic principle of the new approach is to use these platforms and should harness all the possibilities of artificial intelligence, deep learning, machine learning, and computational linguistics. In conclusion, the study reflects the basic and pragmatic principles upon which eLearning 4.0 should be based in order to become a more efficient tool for modern education and sustainability.


Author(s):  
Chalandi Hanene ◽  
Ben Slimane Jihane ◽  
Ksouri Moufida

<p>We focused in this work on a fault tolerant control of a non linear hybrid system class based on diagnosis method (determine and locate the defects and their types) and on the faults reconfiguration method.In literature we can found many important research activities over the fault-tolerant control of non linear systems and linear Hybridsystems. But it dosen´t exist too many for the non linear hybridsystem.The main idea in this paper is to consider a new approach to improve the reconfiguration performance of the non linear hybrid system by using hammerstein method which is designed to works only for linear systems. This method compensated the effect of the faults and guarantees the closed-loop system stable. The proposed method is simulated with a hydraulic system of two tanks with 4 modes.</p>


Author(s):  
Chalandi Hanene ◽  
Ben Slimane Jihane ◽  
Ksouri Moufida

<p>We focused in this work on a fault tolerant control of a non linear hybrid system class based on diagnosis method (determine and locate the defects and their types) and on the faults reconfiguration method.In literature we can found many important research activities over the fault-tolerant control of non linear systems and linear Hybridsystems. But it dosen´t exist too many for the non linear hybridsystem.The main idea in this paper is to consider a new approach to improve the reconfiguration performance of the non linear hybrid system by using hammerstein method which is designed to works only for linear systems. This method compensated the effect of the faults and guarantees the closed-loop system stable. The proposed method is simulated with a hydraulic system of two tanks with 4 modes.</p>


1997 ◽  
Vol 119 (4) ◽  
pp. 691-699 ◽  
Author(s):  
Boo-Ho Yang ◽  
Haruhiko H. Asada

A novel approach to stable adaptive control of complex systems with high relative orders is presented. A series of reference inputs are designed so that the system can learn control parameters stably and progressively, starting with the ones associated with low frequencies and moving up to those having a full spectrum. This progressive excitation method, termed “progressive learning,” allows for stable adaptive control even when a system’s relative order is three or higher. An averaging method is used to obtain stability conditions in terms of the frequency contents of the reference inputs. Based on this analysis, we prove that the stable convergence of control parameters is guaranteed if the system is excited gradually in accordance with the progress of the adaptation by providing a series of reference inputs having appropriate frequency spectra. A numerical example is provided to verify the above analysis.


Author(s):  
Yuehua Gao ◽  
Tianyi Chen

In order to improve learning efficiency and generalization ability of extreme learning machine (ELM), an efficient extreme learning machine based on fuzzy information granulation (FIG) is put forward. The new approach not only improves the speed of basic ELM algorithm that contains many hidden nodes, but also overcomes the weakness of basic ELM of low learning efficiency and generalization ability by getting rid of redundant information in the observed values. The experimental results show that the proposed method is effective and can produce desirable generalization performance in most cases based on a few regression and classification problem.


Author(s):  
Francesco Ghigliazza ◽  
Alberto Traverso ◽  
Mario L. Ferrari ◽  
John Wingate

The Multi-Purpose Model represents a new methodology for developing model based tools for control system design and verification. The Multi-Purpose Model, as described in this paper, simulates a SOFC hybrid system — a challenging and innovative application of dynamic modelling and control. Real-time modelling is a recognised approach to monitor advanced systems and to improve control capabilities. Applications of Real-Time (RT) models are commonly used in the automotive and aerospace fields. Starting from existing TRANSEO components and models, a new approach to fit hybrid system application has been developed. Original C-based models have been translated into embedded Matlab functions for direct use within Matlab-Simulink. The resulting models have then been used to autogenerate c-code with the Real-Time Workshop. The C-code has then been compiled to produce application specific executables.


Sign in / Sign up

Export Citation Format

Share Document