scholarly journals Applying Wavelet Filters in Wind Forecasting Methods

Energies ◽  
2021 ◽  
Vol 14 (11) ◽  
pp. 3181
Author(s):  
José Domínguez-Navarro ◽  
Tania Lopez-Garcia ◽  
Sandra Valdivia-Bautista
Keyword(s):  
Neural Network ◽  
Time Series ◽  
High Frequency ◽  
Physical Phenomenon ◽  
Frequency Component ◽  
High Frequency Component ◽  
Optimal Filtering ◽  
Wavelet Filter ◽  
Wavelet Filters ◽  
Forecasting Methods

Wind is a physical phenomenon with uncertainties in several temporal scales, in addition, measured wind time series have noise superimposed on them. These time series are the basis for forecasting methods. This paper studied the application of the wavelet transform to three forecasting methods, namely, stochastic, neural network, and fuzzy, and six wavelet families. Wind speed time series were first filtered to eliminate the high-frequency component using wavelet filters and then the different forecasting methods were applied to the filtered time series. All methods showed important improvements when the wavelet filter was applied. It is important to note that the application of the wavelet technique requires a deep study of the time series in order to select the appropriate family and filter level. The best results were obtained with an optimal filtering level and improper selection may significantly affect the accuracy of the results.

scholarly journals Forecasting Soil Moisture In The Soil Under The Caragana Shrubland Using Wavelet Analysis And NARX Neural Network

2021 ◽  
Author(s):  
Dong-Mei Bai ◽  
Zhong-Sheng Guo ◽  
Man-Cai Guo
Keyword(s):  
Neural Network ◽  
Soil Moisture ◽  
Wavelet Analysis ◽  
Soil Water ◽  
High Frequency ◽  
Sustainable Use ◽  
Low Frequency ◽  
Frequency Component ◽  
High Frequency Component ◽  
Narx Neural Network

Abstract Purpose: It is important for sustainable use of soil water resources to forecast soil moisture in forestland of water-limited regions. There are some soil moisture models. However, there is not a better method to forecast soil moisture.Methods: The change of soil moisture with time were investigated and the data of soil moisture were divided into a low frequency and a high frequency component using wavelet analysis, and then NARX neural network was used to build model I and model II. For model I, low frequency component was the input variable, and for model II, low frequency component and high frequency component were predicted.Results: the average relative error for model I is 3.5% and for model II is 0.3%. The average relative error of predicted soil moisture in100cm layer using model II is 0.8%, then soil water content in 40 cm and 200 cm soil depth is selected and the forecast errors are 4.9 % and 0.4 %.Using model II to predict soil water is well．Conclusion: Predicting soil water will be important for sustainable use of soil water resource and controlling soil degradation, vegetation decline and crop failure in water limited regions.

STATISTICAL AND MACHINE LEARNING HIGH-FREQUENCY TIME SERIES FORECASTING METHODS IN AUTOMATIC MODE

2020 ◽  
pp. 3-11
Author(s):  
Sai Van Cuong ◽  
M. V. Shcherbakov
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Time Series ◽  
High Frequency ◽  
Network Models ◽  
Time Series Forecasting ◽  
Neural Network Models ◽  
Automatic Mode ◽  
Forecasting Methods ◽  
The Neural Network

The research of the problem of automatic high-frequency time series forecasting (without expert) is devoted. The efficiency of high-frequency time series forecasting using different statistical and machine learning modelsis investigated. Theclassical statistical forecasting methods are compared with neural network models based on 1000 synthetic sets of high-frequency data. The neural network models give better prediction results, however, it takes more time to compute compared to statistical approaches.

scholarly journals Preliminary Research on Radiance Fog Detection based on time series MTSAT data

2015 ◽  
Vol XL-7/W3 ◽  
pp. 243-246
Author(s):  
X. Wen ◽  
Z. Li ◽  
S. Zhang ◽  
S. Shen ◽  
D. Hu ◽  
...  
Keyword(s):  
Time Series ◽  
Frequency Domain ◽  
High Frequency ◽  
Optimization Method ◽  
Frequency Component ◽  
Interval Length ◽  
High Frequency Component ◽  
Weather Phenomenon ◽  
The Difference ◽  
Fog Detection

Fog is a kind of disastrous weather phenomenon. In this paper, the geostationary satellite MTSAT imagery is selected as the main data source to radiance fog detection. According to the unique feature of radiance fog from its generation to dissipation, especially considering the difference between clouds and fog during their lifecycle, the characteristics in frequency domain was constructed to discriminate fog from clouds, The time series MTSAT images were register with a modified Gauss Newton optimization method firstly, then, the Savitzky-Golay smoothing filter was applied to the time series remote sensing imageries to process the noises in the original signal, after that the non-orthogonal Haar wavelets was applied to convert the signal from time domain into frequency domain. The coefficient of high frequency component, including the properties: “max”, “min”, “the location of the min”, “the interval length between the max and min”, “the coefficient of linear fit for the high frequency”, these properties are selected as the characteristic parameters to distinguish fog from clouds. The experiment shows that using the algorithm proposed in this paper, the radiance fog could be monitored effectively, and it is found that although it is difficult to calculate the thickness of the fog directly, while the duration of fog could be obtained by using the frequency feature.

Laser-Generated Ultrasonic Technique for Inspecting Delamination in CFRP

2006 ◽  
Vol 321-323 ◽  
pp. 968-971
Author(s):  
Won Su Park ◽  
Sang Woo Choi ◽  
Joon Hyun Lee ◽  
Kyeong Cheol Seo ◽  
Joon Hyung Byun
Keyword(s):  
High Frequency ◽  
Ultrasonic Method ◽  
Piezoelectric Sensor ◽  
Frequency Component ◽  
Guided Wave ◽  
Center Frequency ◽  
High Frequency Component ◽  
Ultrasonic Technique ◽  
Non Destructive Evaluation ◽  
Non Destructive

For improving quality of a carbon fiber reinforced composite material (CFRP) by preventing defects such as delamination and void, it should be inspected in fabrication process. Novel non-contacting evaluation technique is required because the transducer should be contacted on the CFRP in conventional ultrasonic technique during the non-destructive evaluation and these conventional contact techniques can not be applied in a novel fiber placement system. For the non-destructive evaluation of delamination in CFRP, various methods for the generation and reception of laser-generated ultrasound are applied using piezoelectric transducer, air-coupled transducer, wavelet transform technique etc. The high frequency component of laser-generated guided wave received with piezoelectric sensor disappeared after propagating through delamination region. Air-coupled transducer was tried to be adopted in reception of laser-generated guided wave generated by using linear slit array in order to generate high frequency guided wave with a frequency of 1.1 MHz. Nevertheless, it was failed to receive high frequency guided wave in using air-coupled transducer and linear slit array. Transmitted laser-generated ultrasonic wave was received on back-wall and its frequency was analyzed to establish inspecting technique to detect delamination by non-contact ultrasonic method. In a frequency spectrum analysis, intensity ratio of low frequency and center frequency was approvable parameter to detect delamination.

Hierarchal Predefined Codebook for High-Frequency Component Augmentation Image Enlargement

2010 ◽  
Author(s):  
Hakaru Tamukoh ◽  
Hideaki Kawano ◽  
Noriaki Suetake ◽  
Masatoshi Sekine ◽  
Byungki Cha ◽  
...  
Keyword(s):  
High Frequency ◽  
Frequency Component ◽  
High Frequency Component ◽  
Image Enlargement

A Novel Intuitionistic Fuzzy Time Series Method Based on Bootstrapped Combined Pi-Sigma Artificial Neural Network

2021 ◽  
Vol 01 ◽  
Author(s):  
Eren Bas ◽  
Erol Egrioglu ◽  
Emine Kölemen
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Artificial Neural Network ◽  
Stock Exchange ◽  
Fuzzy Time Series ◽  
Time Series Models ◽  
Intuitionistic Fuzzy ◽  
Forecasting Methods ◽  
Time Series Method ◽  
Artificial Neural

Background: Intuitionistic fuzzy time series forecasting methods have been started to solve the forecasting problems in the literature. Intuitionistic fuzzy time series methods use both membership and non-membership values as auxiliary variables in their models. Because intuitionistic fuzzy sets take into consideration the hesitation margin and so the intuitionistic fuzzy time series models use more information than fuzzy time series models. The background of this study is about intuitionistic fuzzy time series forecasting methods. Objective: The study aims to propose a novel intuitionistic fuzzy time series method. It is expected that the proposed method will produce better forecasts than some selected benchmarks. Method: The proposed method uses bootstrapped combined Pi-Sigma artificial neural network and intuitionistic fuzzy c-means. The combined Pi-Sigma artificial neural network is proposed to model the intuitionistic fuzzy relations. Results and Conclusion: The proposed method is applied to different sets of SP&500 stock exchange time series. The proposed method can provide more accurate forecasts than established benchmarks for the SP&500 stock exchange time series. The most important contribution of the proposed method is that it creates statistical inference: probabilistic forecasting, confidence intervals and the empirical distribution of the forecasts. Moreover, the proposed method is better than the selected benchmarks for the SP&500 data set.

Sign in / Sign up

Export Citation Format

Share Document