scholarly journals The Analysis of China’s Grain Output Fluctuation Based on EMD

2017 ◽  
Vol 9 (11) ◽  
pp. 64
Author(s):  
Qiting Chen ◽  
Meng Wang
Keyword(s):  
Neural Network ◽  
Empirical Mode Decomposition ◽  
Driving Forces ◽  
Unit Area ◽  
Rbf Neural Network ◽  
The Other ◽  
Cyclical Fluctuation ◽  
Output Fluctuations ◽  
Mode Decomposition ◽  
Emd Method

Food is one of the most important resources for staying alive. This paper analyzes grain output fluctuations and their driving forces in China from 1978 to 2014, based on Empirical Mode Decomposition (EMD) method. These results show that there are two type cycles of cyclical fluctuation, one is 3-yearterm, and another is 8-year term. These results show that the 8-year cyclical fluctuation is the major term. Grain production’s cyclical fluctuation in 3 years was mainly influenced by yield of grain per unit area from 1978-2004 and 2007-2014, and by the area sown from 2004 to 2007. On the other hand, the longer cyclical fluctuation of 8 years is mainly affected by the yield of grain per unit area. The grain output is predicted for the next three years through the RBF neural network optimized by PSO. These results show that China’s annul grain output in the next three years will be stabilized at about 600 million tons, which may grow slowly though.

scholarly journals P300 characterization using empirical mode decomposition

2019 ◽  
Vol 8 (3) ◽  
pp. 40
Author(s):  
Victor S. Braz ◽  
Ana Claudia Souza ◽  
Gustavo F. Rodrigues
Keyword(s):  
Neural Network ◽  
Empirical Mode Decomposition ◽  
Communication Systems ◽  
Feedforward Neural Network ◽  
Essential Step ◽  
Mode Decomposition ◽  
Electrophysiological Signals ◽  
Low Volume ◽  
Emd Method

As the communication between brain and computer becomes more accessible the extraction of important features of electrophysiological signals is an essential step in artificial communication systems. This paper proposes the usage of the Empirical Mode Decomposition to identify characteristics of the P300 signal and classify target and non-target signals using a feedforward neural network. The results show that through the usage of EMD method it is possible to identify the P300 signal using low volume of data.

Speech Recognition Algorithm Based on Empirical Mode Decomposition and RBF Neural Network

2013 ◽  
Vol 831 ◽  
pp. 465-469
Author(s):  
Wei Wei Shi ◽  
Wei Hua Xiong ◽  
Wei Chen
Keyword(s):  
Neural Network ◽  
Speech Recognition ◽  
Empirical Mode Decomposition ◽  
Rbf Neural Network ◽  
Recognition Rate ◽  
Good Method ◽  
Recognition Algorithm ◽  
Intrinsic Mode Functions ◽  
Mode Decomposition ◽  
Learning Speed

This paper presents a novel method of the speech recognition in combining the empirical mode decomposition with radical basis function neural network. Speech signals which pretreated are decomposed by empirical mode decomposition to get a set of intrinsic mode functions. It extracts mel frequency cepstrum coefficient from intrinsic mode function. Features parameters are made up of the coefficients. For BP Neural Network, RBF Neural Network has advantages on approximating ability and learning speed. So using RBF Neural Network as a recognition model is a good method. Experiments show that this new method has good robustness and adaptability. The speech recognition rate of this method reach ninety-one percents accurately under no noise environment. Speech signal recognition is feasible and effective in noisy environment.

Traffic Forecast Based on Empirical Mode Decomposition and RBF Neural Network

2013 ◽  
Vol 846-847 ◽  
pp. 1270-1273
Author(s):  
Shi Bao Jiang ◽  
Chuan Feng Bai ◽  
Cui Feng Du
Keyword(s):  
Neural Network ◽  
Empirical Mode Decomposition ◽  
Mobile Networks ◽  
Rbf Neural Network ◽  
Base Stations ◽  
Scale Analysis ◽  
Network Coverage ◽  
Traffic Jam ◽  
Multi Scale ◽  
Mode Decomposition

Traffic analysis and forecast are the classic topics of telecommunication research, as they provide strategic ground to address the issues such as mobile networks traffic jam, network coverage planning design, marketing management etc. On the basis of the empirical mode decomposition theory and methods, this article first implements multi-scale analysis of the time series of traffic, then it goes on to executes RBF neural network based on the different compositions, and finally reach the forecast expectation of voice traffics of selected base stations.

Multi-Step-Ahead Forecasting of Wind Speed Based on EMD-RBF Model

2011 ◽  
Vol 347-353 ◽  
pp. 2219-2222
Author(s):  
Dong Feng Wang ◽  
Fu Qiang Wang ◽  
Pu Han
Keyword(s):  
Neural Network ◽  
Wind Speed ◽  
Rbf Neural Network ◽  
Wind Speed Forecasting ◽  
Wind Energy Conversion Systems ◽  
Mode Decomposition ◽  
Energy Conversion Systems ◽  
Non Stationary Signal ◽  
Wind Resource ◽  
Emd Method

Wind speed forecasting is critical for wind energy conversion systems. Adaptive and reliable methods and techniques of wind speed forecasting are urgently needed in view of the stochastic nature of wind resource, which is varying from time to time and from site to site. Multi-step-ahead speed forecasting is built with empirical mode decomposition (EMD) method and RBF neural network, which makes use of non-linear and non-stationary signal characteristics. Time series of original wind speed data is decomposed by EMD method. And RBF neural network is used to predict the decomposition of the various components. Experimental results show that the method effectively improves the accuracy and the reliability of wind speed forecasting.

APPLICATION OF THE EMPIRICAL MODE DECOMPOSITION METHOD TO GROUND-ROLL NOISE ATTENUATION IN SEISMIC DATA

2013 ◽  
Vol 31 (4) ◽  
pp. 619 ◽  
Author(s):  
Luiz Eduardo Soares Ferreira ◽  
Milton José Porsani ◽  
Michelângelo G. Da Silva ◽  
Giovani Lopes Vasconcelos
Keyword(s):  
Empirical Mode Decomposition ◽  
Seismic Data ◽  
Low Frequency ◽  
High Amplitude ◽  
Seismic Line ◽  
Seismic Processing ◽  
Mode Decomposition ◽  
Ground Roll ◽  
Fortran 90 ◽  
Emd Method

ABSTRACT. Seismic processing aims to provide an adequate image of the subsurface geology. During seismic processing, the filtering of signals considered noise is of utmost importance. Among these signals is the surface rolling noise, better known as ground-roll. Ground-roll occurs mainly in land seismic data, masking reflections, and this roll has the following main features: high amplitude, low frequency and low speed. The attenuation of this noise is generally performed through so-called conventional methods using 1-D or 2-D frequency filters in the fk domain. This study uses the empirical mode decomposition (EMD) method for ground-roll attenuation. The EMD method was implemented in the programming language FORTRAN 90 and applied in the time and frequency domains. The application of this method to the processing of land seismic line 204-RL-247 in Tacutu Basin resulted in stacked seismic sections that were of similar or sometimes better quality compared with those obtained using the fk and high-pass filtering methods.Keywords: seismic processing, empirical mode decomposition, seismic data filtering, ground-roll. RESUMO. O processamento sísmico tem como principal objetivo fornecer uma imagem adequada da geologia da subsuperfície. Nas etapas do processamento sísmico a filtragem de sinais considerados como ruídos é de fundamental importância. Dentre esses ruídos encontramos o ruído de rolamento superficial, mais conhecido como ground-roll . O ground-roll ocorre principalmente em dados sísmicos terrestres, mascarando as reflexões e possui como principais características: alta amplitude, baixa frequência e baixa velocidade. A atenuação desse ruído é geralmente realizada através de métodos de filtragem ditos convencionais, que utilizam filtros de frequência 1D ou filtro 2D no domínio fk. Este trabalho utiliza o método de Decomposição em Modos Empíricos (DME) para a atenuação do ground-roll. O método DME foi implementado em linguagem de programação FORTRAN 90, e foi aplicado no domínio do tempo e da frequência. Sua aplicação no processamento da linha sísmica terrestre 204-RL-247 da Bacia do Tacutu gerou como resultados, seções sísmicas empilhadas de qualidade semelhante e por vezes melhor, quando comparadas as obtidas com os métodos de filtragem fk e passa-alta.Palavras-chave: processamento sísmico, decomposição em modos empíricos, filtragem dados sísmicos, atenuação do ground-roll.

scholarly journals Bearing Fault Classification Using Ensemble Empirical Mode Decomposition and Convolutional Neural Network

Electronics ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 1248
Author(s):  
Rafia Nishat Toma ◽  
Cheol-Hong Kim ◽  
Jong-Myon Kim
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Empirical Mode Decomposition ◽  
Vibration Signal ◽  
Ensemble Empirical Mode Decomposition ◽  
Fault Classification ◽  
Original Signal ◽  
Time Frequency ◽  
Mode Decomposition ◽  
Reconstructed Signal

Condition monitoring is used to track the unavoidable phases of rolling element bearings in an induction motor (IM) to ensure reliable operation in domestic and industrial machinery. The convolutional neural network (CNN) has been used as an effective tool to recognize and classify multiple rolling bearing faults in recent times. Due to the nonlinear and nonstationary nature of vibration signals, it is quite difficult to achieve high classification accuracy when directly using the original signal as the input of a convolution neural network. To evaluate the fault characteristics, ensemble empirical mode decomposition (EEMD) is implemented to decompose the signal into multiple intrinsic mode functions (IMFs) in this work. Then, based on the kurtosis value, insignificant IMFs are filtered out and the original signal is reconstructed with the rest of the IMFs so that the reconstructed signal contains the fault characteristics. After that, the 1-D reconstructed vibration signal is converted into a 2-D image using a continuous wavelet transform with information from the damage frequency band. This also transfers the signal into a time-frequency domain and reduces the nonstationary effects of the vibration signal. Finally, the generated images of various fault conditions, which possess a discriminative pattern relative to the types of faults, are used to train an appropriate CNN model. Additionally, with the reconstructed signal, two different methods are used to create an image to compare with our proposed image creation approach. The vibration signal is collected from a self-designed testbed containing multiple bearings of different fault conditions. Two other conventional CNN architectures are compared with our proposed model. Based on the results obtained, it can be concluded that the image generated with fault signatures not only accurately classifies multiple faults with CNN but can also be considered as a reliable and stable method for the diagnosis of fault bearings.

Sign in / Sign up

Export Citation Format

Share Document