Wind Power Prediction of Kernel Extreme Learning Machine Based on Differential Evolution Algorithm and Cross Validation Algorithm

Li, Ning; He, Fuxing; Ma, Wentao; Wang, Ruotong; Zhang, Xiaoping

doi:10.1109/access.2020.2985381

Cited by 36 publications

(13 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This validation method is also to ensure that the resulting model can produce unbiased [59], consistent [60], and reliable [61] recognition results, which will be followed up with their identifications. It is also used to check the resulting model's performance [2], [62].…”

Section: F K-fold Cross Validationmentioning

confidence: 99%

Intelligent Military Aircraft Recognition and Identification to Support Military Personnel on the Air Observation Operation

Sumari¹,

Adinandra²,

Syulistyo³

et al. 2022

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

A hostile or unfriendly aircraft will mostly fly at low-level altitude or hide behind natural obstacles to avoid Radar detection. One of the ways to detect and recognize while at the same time identifying such aircraft is to perform air observation from the ground. A technique called Visual Aircraft Recognition (VACR) has been practiced in training soldiers to recognize and find an incoming aircraft from a distance using binoculars. Remembering so many types of aircraft have their challenge. To ease the task, we have designed and developed an intelligent military aircraft recognition and identification system using the combination of Back Propagation Neural Networks (BPNN) and Information Fusion to speed up the recognition and identification. We use 13 aircraft features fused into five primary ones as the inputs to the BPNN for the recognition, while the identification uses Hamming Distance to the recognition results. With 155 data consisting of 85 military aircraft and helicopters and 70 civilian aircraft and helicopters and applying the 80:20 scheme for the training and test data, our system can obtain 95.33% and 87% accuracy at the training phase and the test phase. It also succeeds in recognizing and identifying a new military aircraft that is not in the dataset, while the Information Fusion can speed up the recognition and identification by up to 6 seconds. This impacts the acceleration of aircraft recognition and identification.

show abstract

Section: F K-fold Cross Validationmentioning

confidence: 99%

Intelligent Military Aircraft Recognition and Identification to Support Military Personnel on the Air Observation Operation

Sumari¹,

Adinandra²,

Syulistyo³

et al. 2022

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

show abstract

“…One subsample is utilized for testing, while the other k-1 subsample is used for training. Cross-validation is carried out k times, with each subsample checked once [25]. Based on the first test, the accuracy value can be found using (2).…”

Section: K-fold Cross-validationmentioning

confidence: 99%

“…10-fold cross-validation is a cross-validation method that is very commonly used [25]. Therefore, in this study, the k value used for cross-validation is 10.…”

Section: K-fold Cross-validationmentioning

confidence: 99%

COVID-19 Chest X-Ray Detection Performance Through Variations of Wavelets Basis Function

Indradewi

Saraswati²,

Wardani³

2021

matrik

View full text Add to dashboard Cite

Our previous work regarding the X-Ray detection of COVID-19 using Haar wavelet feature extraction and the Support Vector Machines (SVM) classification machine has shown that the combination of the two methods can detect COVID-19 well but then the question arises whether the Haar wavelet is the best wavelet method. So that in this study we conducted experiments on several wavelet methods such as biorthogonal, coiflet, Daubechies, haar, and symlets for chest X-Ray feature extraction with the same dataset. The results of the feature extraction are then classified using SVM and measure the quality of the classification model with parameters of accuracy, error rate, recall, specification, and precision. The results showed that the Daubechies wavelet gave the best performance for all classification quality parameters. The Daubechies wavelet transformation gave 95.47% accuracy, 4.53% error rate, 98.75% recall, 92.19% specificity, and 93.45% precision.

show abstract

“…Considering the limitations of the single convolution model when predicting wind power, Ju et al (2019) proposed an innovative integration of the LightGBM classification algorithm in the model to improve the prediction accuracy and robustness. Li et al (2020) proposed a kernel extreme learning machine using differential evolution (DE) and crossvalidation optimization methods to predict short-term wind power generation. The DE algorithm was applied to optimize the regularization coefficient and kernel width of the kernel extreme learning machine to improve the prediction accuracy.…”

Section: Introductionmentioning

confidence: 99%

A Wind Power Prediction Method Based on DE-BP Neural Network

Wang

et al. 2022

Front. Energy Res.

Self Cite

View full text Add to dashboard Cite

With the continuous increase of installed capacity of wind power, the influence of large-scale wind power integration on the power grid is becoming increasingly apparent. Ultra-short-term wind power prediction is conducive to the dispatching management of the power grid and improves the operating efficiency and economy of the power system. In order to overcome the intermittency and uncertainty of wind power generation, this article proposes the differential evolution–back propagation (DE-BP) algorithm to predict wind power and addresses such shortcomings of the BP neural network as its falling into local optimality and slow training speed when predicting. In this article, the DE algorithm is used to find the optimal value of the initial weight and threshold of the BP neural network, and the DE-BP neural network prediction model is obtained. According to the data of a wind farm in Northwest China, the short-term wind power is predicted. Compared with the application of the BP model in wind power prediction, the results show that the accuracy of the DE-BP algorithm is improved by about 5%; compared with the genetic algorithm–BP model, the prediction time is shortened by 23.1%.

show abstract

Wind Power Prediction of Kernel Extreme Learning Machine Based on Differential Evolution Algorithm and Cross Validation Algorithm

Cited by 36 publications

References 31 publications

Intelligent Military Aircraft Recognition and Identification to Support Military Personnel on the Air Observation Operation

Intelligent Military Aircraft Recognition and Identification to Support Military Personnel on the Air Observation Operation

COVID-19 Chest X-Ray Detection Performance Through Variations of Wavelets Basis Function

A Wind Power Prediction Method Based on DE-BP Neural Network

Contact Info

Product

Resources

About