The prediction of wind power interval based on k-means clustering algorithm and hoeffding tree classification algorithm

2021 ◽  
Author(s):  
H. Shi ◽  
T. Gao ◽  
M. Ding ◽  
Z. Li ◽  
J. yan ◽  
...  
Keyword(s):  
Wind Power ◽  
Clustering Algorithm ◽  
Classification Algorithm ◽  
Hoeffding Tree

scholarly journals A novel clustering algorithm based on mathematical morphology for wind power generation prediction

2019 ◽  
Vol 136 ◽  
pp. 572-585 ◽  
Author(s):  
Ying Hao ◽  
Lei Dong ◽  
Xiaozhong Liao ◽  
Jun Liang ◽  
Lijie Wang ◽  
...  
Keyword(s):  
Power Generation ◽  
Wind Power ◽  
Mathematical Morphology ◽  
Clustering Algorithm ◽  
Wind Power Generation

scholarly journals Application of Multiacoustic Data in Feature Extraction of Anemometer

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Dawei Chen ◽  
Xu Guo
Keyword(s):  
Feature Extraction ◽  
Wind Power ◽  
Evaluation Method ◽  
Training Model ◽  
Classification Algorithm ◽  
Deep Belief Network ◽  
Evaluation Function ◽  
Trust Network ◽  
Belief Network ◽  
Acoustic Data

The acoustic characteristics of wind instruments are a major feature in the field of vocal music. This paper studies the application effect of wind power instrument feature extraction based on multiacoustic data. Combined with the acoustic data training model, the classification algorithm based on deep trust network is used to process multiple acoustic data. Using multiple acoustic data for feature extraction, the recognition and matching between multiple acoustic data and wind measuring instrument are realized. The experiment not only evaluates the error of the network classification algorithm but also describes the evaluation function of the deep belief network classification algorithm in the system. The traditional SNR evaluation method is used to improve the deficiency of evaluation function. Through the deep belief network classification algorithm for self-learning, the instrument recognition method with strong applicability is established. Finally, the effectiveness of multiacoustic data in wind power instrument feature extraction is verified.

scholarly journals Nonuniform Granularity-Based Classification in Social Interest Detection

2017 ◽  
Vol 2017 ◽  
pp. 1-10
Author(s):  
Wenjuan Shao ◽  
Qingguo Shen ◽  
Xianli Jin ◽  
Liaoruo Huang ◽  
Jingjing Chen
Keyword(s):  
Large Scale ◽  
Clustering Algorithm ◽  
Nearest Neighbor ◽  
Social Interest ◽  
Classification Performance ◽  
Classification Algorithm ◽  
Computing Paradigm ◽  
The Social ◽  
Interest Detection

Social interest detection is a new computing paradigm which processes a great variety of large scale resources. Effective classification of these resources is necessary for the social interest detection. In this paper, we describe some concepts and principles about classification and present a novel classification algorithm based on nonuniform granularity. Clustering algorithm is used to generate a clustering pedigree chart. By using suitable classification cutting values to cut the chart, we can get different branches which are used as categories. The size of cutting value is vital to the performance and can be dynamically adapted in the proposed algorithm. Experiments results carried on the blog posts illustrate the effectiveness of the proposed algorithm. Furthermore, the results for comparing with Naive Bayes, k-nearest neighbor, and so forth validate the better classification performance of the proposed algorithm for large scale resources.

scholarly journals A classification algorithm for selective dynamical downscaling of precipitation extremes

2018 ◽  
Vol 22 (8) ◽  
pp. 4183-4200 ◽  
Author(s):  
Edmund P. Meredith ◽  
Henning W. Rust ◽  
Uwe Ulbrich
Keyword(s):  
High Resolution ◽  
Extreme Precipitation ◽  
Clustering Algorithm ◽  
Dynamical Downscaling ◽  
Classification Algorithm ◽  
Climate Data ◽  
Catchment Scale ◽  
Computational Expense ◽  
Circulation Patterns ◽  
Climate Simulations

Abstract. High-resolution climate data O(1 km) at the catchment scale can be of great value to both hydrological modellers and end users, in particular for the study of extreme precipitation. While dynamical downscaling with convection-permitting models is a valuable approach for producing quality high-resolution O(1 km) data, its added value can often not be realized due to the prohibitive computational expense. Here we present a novel and flexible classification algorithm for discriminating between days with an elevated potential for extreme precipitation over a catchment and days without, so that dynamical downscaling to convection-permitting resolution can be selectively performed on high-risk days only, drastically reducing total computational expense compared to continuous simulations; the classification method can be applied to climate model data or reanalyses. Using observed precipitation and the corresponding synoptic-scale circulation patterns from reanalysis, characteristic extremal circulation patterns are identified for the catchment via a clustering algorithm. These extremal patterns serve as references against which days can be classified as potentially extreme, subject to additional tests of relevant meteorological predictors in the vicinity of the catchment. Applying the classification algorithm to reanalysis, the set of potential extreme days (PEDs) contains well below 10 % of all days, though it includes essentially all extreme days; applying the algorithm to reanalysis-driven regional climate simulations over Europe (12 km resolution) shows similar performance, and the subsequently dynamically downscaled simulations (2 km resolution) well reproduce the observed precipitation statistics of the PEDs from the training period. Additional tests on continuous 12 km resolution historical and future (RCP8.5) climate simulations, downscaled in 2 km resolution time slices, show the algorithm again reducing the number of days to simulate by over 90 % and performing consistently across climate regimes. The downscaling framework we propose represents a computationally inexpensive means of producing high-resolution climate data, focused on extreme precipitation, at the catchment scale, while still retaining the advantages of convection-permitting dynamical downscaling.

scholarly journals A classification algorithm for selective dynamical downscaling of precipitation extremes

2017 ◽  
Author(s):  
Edmund P. Meredith ◽  
Henning W. Rust ◽  
Uwe Ulbrich
Keyword(s):  
High Resolution ◽  
Extreme Precipitation ◽  
Clustering Algorithm ◽  
Dynamical Downscaling ◽  
Classification Algorithm ◽  
Climate Data ◽  
Catchment Scale ◽  
Computational Expense ◽  
Circulation Patterns ◽  
Climate Simulations

Abstract. High-resolution climate data [O(1 km)] at the catchment scale can be of great value to both hydrological modellers and end users, in particular for the study of extreme precipitation. Despite the well-known advantages of dynamical downscaling for producing quality high-resolution data, the added value of dynamically downscaling to O(1 km) resolutions can often not be realised due to the prohibitive computational expense. Here we present a novel and flexible classification algorithm for discriminating between days with an elevated potential for extreme precipitation over a catchment and days without, so that dynamical downscaling to convection-permitting resolution can be selectively performed on high-risk days only, drastically reducing total computational expense compared to continuous simulations; the classification method can be applied to climate model data or reanalyses. Using observed precipitation and the corresponding synoptic-scale circulation patterns from reanalysis, characteristic extremal circulation patterns are identified for the catchment via a clustering algorithm. These extremal patterns serve as references against which days can be classified as potentially extreme, subject to additional tests of relevant meteorological variables in the vicinity of the catchment. Applying the classification algorithm to reanalysis, the set of potential extreme days (PEDs) contains well below 10 % of all days, though includes essentially all extreme days; applying the algorithm to reanalysis-driven regional climate simulations over Europe (12 km resolution) shows similar performance and the subsequently dynamically downscaled simulations (2 km resolution) well reproduce the observed precipitation statistics of the PEDs from the training period. Additional tests on continuous 12- and 2 km resolution historical and future (RCP8.5) climate simulations show the algorithm again reducing the number of days to simulate by over 90 % and performing consistently across climate regimes. The downscaling framework we propose represents a computationally inexpensive means of producing high-resolution climate data, focused on extreme precipitation, at the catchment scale, while still retaining the advantages of the physically-based dynamical downscaling approach.

scholarly journals Improved Diabetes Prediction Model for Predicting Type-II Diabetes

2019 ◽  
Vol 8 (12) ◽  
pp. 230-235
Keyword(s):  
Logistic Regression ◽  
Hierarchical Clustering ◽  
Type Ii Diabetes ◽  
Clustering Algorithm ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Classification Algorithm ◽  
Type Ii ◽  
Diabetes Prediction ◽  
Hierarchical Clustering Algorithm

The state or disorder where the body cannot effectively use the insulin is called Diabetes. If the insulin levels are not maintained properly, the diabetes is one such disorder where it damages all other body parts. It is estimated that the diabetes is the 7th leading cause of deaths as per World Health Organisation report. Early recognition of diabetes, decreases the risk of serious ailments, which includes, heart diseases, brain stroke, eye related diseases, kidney diseases, nerve related diseases etc. In the present work, pima indians diabetes data set is considered as the best dataset and different models viz., hierarchical clustering with decision tree, hierarchical clustering with support vector machines, hierarchical clustering with logistic regression and k means with logistic regression are developed and implemented for identifying and predicting the diabetes. The accuracies of these prediction models range between 0.90 and 0.946. An Improved Diabetes Prediction Algorithm (IDPA) combining the hierarchical clustering algorithm and Naïve Bayes classification algorithm is developed to identify and predict the Type-II diabetes and has shown an accuracy of 0.96. In this IDPA, firstly, the grouping of data into two groups i.e. diabetes and non-diabetes is done by applying the hierarchical clustering algorithm. Then, the filtering is done by comparing the group value to the class value followed by applying Naïve Bayes classification algorithm for predicting diabetes. The results show that the proposed novel method i.e. IDPA can predict the diabetes with higher accuracy levels (0.96) than the traditional/existing methods and other methods which were implemented. This model can be used to predict diabetes early, thereby reducing the serious complications of diabetes.

Sign in / Sign up

Export Citation Format

Share Document