Rainfall Forecasting of Landslides Using Support Vector Regression

Lee, Zne-Jung; Lee, Chou‐Yuan; Yuan, Xiaojian; Chu, Kuang‐Han

doi:10.1109/ickii50300.2020.9318930

Cited by 5 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, SVM was used to detect fasting blood glucose level 37 and diagnosis of gestational diabetes, 38 whose results showed that the classification accuracy of SVM was significantly better than those of other comparable models. SVR was also applied to the numerical prediction, such as monthly river flow forecasting 39 and rainfall forecasting problems, 40 which all confirmed that SVR models performed better than others, such as artificial neural network (ANN), classification and regression technology (CART) and back-propagation neural (BPN). In the current study, due to the variety in kernel function selection of SVM classification prediction and higher numerical prediction performance of SVR as well as their convenient interface with optimization algorithms, we propose a two-stage prediction filling method with support vector technologies optimized competitively in stages by GWO and PSO.…”

Section: Discussionmentioning

confidence: 74%

A two-stage prediction filling method with support vector technologies optimized competitively in stages by grey wolf optimizer and particle swarm optimization for missing fasting blood glucose

Gao,

Xie,

et al. 2023

Proc Inst Mech Eng H

View full text Add to dashboard Cite

Missing values often affect the data utilization in epidemiological survey. In this study, according to the cut-off point value of the medical diagnostic standard of fasting blood glucose for diabetes, we divide fasting blood glucose test data from the China Health and Nutrition Survey (CHNS) of Shandong province in 2009 into two classes: the normal and the abnormal. Accordingly, for missing fasting blood glucose values, we propose a two-stage prediction filling method with optimized support vector technologies competitively by particle swarm optimization (PSO) or grey wolf optimizer (GWO), which is to first predict the class of the missing data with support vector machine (SVM) in the first stage and then predict the missing value with support vector regression (SVR) within the predicted class in the second stage. In addition, we use the LIBSVM as a gold standard to train both SVM and SVR in different stages. For two kinds of competitive optimizers in stages, in the first stage GWO has the highest classification accuracy (91.1%), and in the second stage PSO has the smallest in-class mean absolute error (0.48). So, GWO-SVM-PSO-SVR is determined as the optimal model and a predicted value with it serves as a fill value. The comparison results of the models in empirical analysis also show that it outdoes any of the other filling models in terms of mean absolute error and mean absolute percentage error. In addition, the sensitivity analysis shows that it presents high tolerance as the sample size changes and has a good stability.

show abstract

Section: Discussionmentioning

confidence: 74%

A two-stage prediction filling method with support vector technologies optimized competitively in stages by grey wolf optimizer and particle swarm optimization for missing fasting blood glucose

Gao,

Xie,

et al. 2023

Proc Inst Mech Eng H

View full text Add to dashboard Cite

show abstract

“…In the proposed algorithm, it is based on Apache Spark with AFE, RFM, Wald method, k-means, FCM, and the improved fuzzy decision tree. Spark is an open and useful platform for large-scale data processing [30,31]. Moreover, it can run fast analytics against data of any size with in-memory execution.…”

Section: Methods and Datamentioning

confidence: 99%

Clustering and Classification Based on Distributed Automatic Feature Engineering for Customer Segmentation

Lee

Chang

et al. 2021

Symmetry

Self Cite

View full text Add to dashboard Cite

To beat competition and obtain valuable information, decision-makers must conduct in-depth machine learning or data mining for data analytics. Traditionally, clustering and classification are two common methods used in machine mining. For clustering, data are divided into various groups according to the similarity or common features. On the other hand, classification refers to building a model by given training data, where the target class or label is predicted for the test data. In recent years, many researchers focus on the hybrid of clustering and classification. These techniques have admirable achievements, but there is still room to ameliorate performances, such as distributed process. Therefore, we propose clustering and classification based on distributed automatic feature engineering (AFE) for customer segmentation in this paper. In the proposed algorithm, AFE uses artificial bee colony (ABC) to select valuable features of input data, and then RFM provides the basic data analytics. In AFE, it first initializes the number of cluster k. Moreover, the clustering methods of k-means, Wald method, and fuzzy c-means (FCM) are processed to cluster the examples in variant groups. Finally, the classification method of an improved fuzzy decision tree classifies the target data and generates decision rules for explaining the detail situations. AFE also determines the value of the split number in the improved fuzzy decision tree to increase classification accuracy. The proposed clustering and classification based on automatic feature engineering is distributed, performed in Apache Spark platform. The topic of this paper is about solving the problem of clustering and classification for machine learning. From the results, the corresponding classification accuracy outperforms other approaches. Moreover, we also provide useful strategies and decision rules from data analytics for decision-makers.

show abstract

“…The training data set is for model construction, and the testing data set is used to truly evaluate the performance of the model. The random forest method is a combination of tree predictors [15,16]. It is inspired by the decision tree algorithm and improves the decision tree algorithm to form a new type of algorithm.…”

Section: Introduction To Decision Tree and Random Forest Modelmentioning

confidence: 99%

Data Analysis on the Influencing Factors of the Real Estate Price

He¹,

Chen²,

Xiao³

et al. 2021

Artificial Intelligence Evolution

Self Cite

View full text Add to dashboard Cite

China has carried out a large number of real estate market reforms that change the real estate market demand considerably. At the same time, the real estate price has soared in some cities and has surpassed the spending power of many ordinary people. As the real estate price has received widespread attention from society, it is important to understand what factors affect the real estate price. Therefore, we propose a data analysis method for finding out the influencing factors of real estate prices. The method performs data cleaning and conversion on the used data first. To discretize the real estate price, we use the mean ± standard deviation (SD), mean ± 0.5 SD, and mean ± 2 SD of the price and divide it into three categories as the output variable. Then, we establish the decision tree and random forest model for six different situations for comparison. When the data set is divided into training data (70%) and testing data (30%), it has the highest testing accuracy. In addition, by observing the importance of each input variable, it is found that the main influencing factors of real estate price are cost, interior decoration, location, and status. The results suggest that both the real estate industry and buyers should pay attention to these factors to adjust or purchase real estate.

show abstract

Rainfall Forecasting of Landslides Using Support Vector Regression

Cited by 5 publications

References 15 publications

A two-stage prediction filling method with support vector technologies optimized competitively in stages by grey wolf optimizer and particle swarm optimization for missing fasting blood glucose

A two-stage prediction filling method with support vector technologies optimized competitively in stages by grey wolf optimizer and particle swarm optimization for missing fasting blood glucose

Clustering and Classification Based on Distributed Automatic Feature Engineering for Customer Segmentation

Data Analysis on the Influencing Factors of the Real Estate Price

Contact Info

Product

Resources

About