Modeling River Stream Flow Using Support Vector Machine

2013 ◽  
Vol 315 ◽  
pp. 602-605 ◽  
Author(s):  
Ali Rafidah ◽  
Yacob Suhaila
Keyword(s):  
Artificial Intelligence ◽  
Support Vector Machine ◽  
Stream Flow ◽  
Moving Average ◽  
Support Vector ◽  
Arima Models ◽  
Autoregressive Integrated Moving Average ◽  
Svm Model ◽  
Record Data ◽  
Better Than

Support Vector Machine (SVM) is a new tool from Artificial Intelligence (AI) field has been successfully applied for a wide variety of problem especially in river stream flow forecasting. In this paper, SVM is proposed for river stream flow forecasting. To assess the effectiveness SVM, we used monthly mean river stream flow record data from Pahang River at Lubok Paku, Pahang. The performance of the SVM model is compared with the statistical Autoregressive Integrated Moving Average (ARIMA) and the result showed that the SVM model performs better than the ARIMA models to forecast river stream flow Pahang River.

Civil Aeroengine Fault Diagnosis Based on Fuzzy Least Square Support Vector Machine

2011 ◽  
Vol 130-134 ◽  
pp. 2047-2050 ◽  
Author(s):  
Hong Chun Qu ◽  
Xie Bin Ding
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Coefficient Matrix ◽  
Least Square ◽  
Support Vector ◽  
Influence Coefficient ◽  
Structural Risk ◽  
Better Than

SVM(Support Vector Machine) is a new artificial intelligence methodolgy, basing on structural risk mininization principle, which has better generalization than the traditional machine learning and SVM shows powerfulability in learning with limited samples. To solve the problem of lack of engine fault samples, FLS-SVM theory, an improved SVM, which is a method is applied. 10 common engine faults are trained and recognized in the paper.The simulated datas are generated from PW4000-94 engine influence coefficient matrix at cruise, and the results show that the diagnostic accuracy of FLS-SVM is better than LS-SVM.

scholarly journals Real-time flood forecast using the coupling support vector machine and data assimilation method

2013 ◽  
Vol 16 (5) ◽  
pp. 973-988 ◽  
Author(s):  
Xiao-Li Li ◽  
Haishen Lü ◽  
Robert Horton ◽  
Tianqing An ◽  
Zhongbo Yu
Keyword(s):  
Support Vector Machine ◽  
Real Time ◽  
Time Scale ◽  
Support Vector ◽  
Flood Forecast ◽  
Risk Minimization ◽  
Svm Model ◽  
The Impact ◽  
Assimilation Time ◽  
Better Than

An accurate and real-time flood forecast is a crucial nonstructural step to flood mitigation. A support vector machine (SVM) is based on the principle of structural risk minimization and has a good generalization capability. The ensemble Kalman filter (EnKF) is a proven method with the capability of handling nonlinearity in a computationally efficient manner. In this paper, a type of SVM model is established to simulate the rainfall–runoff (RR) process. Then, a coupling model of SVM and EnKF (SVM + EnKF) is used for RR simulation. The impact of the assimilation time scale on the SVM + EnKF model is also studied. A total of four different combinations of the SVM and EnKF models are studied in the paper. The Xinanjiang RR model is employed to evaluate the SVM and the SVM + EnKF models. The study area is located in the Luo River Basin, Guangdong Province, China, during a nine-year period from 1994 to 2002. Compared to SVM, the SVM + EnKF model substantially improves the accuracy of flood prediction, and the Xinanjiang RR model also performs better than the SVM model. The simulated result for the assimilation time scale of 5 days is better than the results for the other cases.

Forecasting: Does the Box-Jenkins Method Work Better than Regression?

1988 ◽  
Vol 13 (1) ◽  
pp. 53-62 ◽  
Author(s):  
S Nanda
Keyword(s):  
Time Series Data ◽  
Moving Average ◽  
Supply And Demand ◽  
Regression Method ◽  
Series Data ◽  
Effective Management ◽  
Arima Models ◽  
Autoregressive Integrated Moving Average ◽  
Using Data ◽  
Better Than

A difficult exercise, forecasting is key to effective management. Models using time series data are frequently used for forecasting likely values of important variables such as supply and demand. The regression method is the most common, although it involves many critical assumptions that are difficult to satisfy in practice. Efforts to reduce the severity of the assumptions and improve our ability to manipulate data have led to generalized regression and the Box-Jenkins Autoregressive Integrated Moving Average (ARIMA) models. Nanda tests the forecasts from two models in each method, using data on monthly milk procurement by Amul Dairy from January 1965 to December 1975. The regression method produced better forecasts than the Box-Jenkins method.

scholarly journals Statistical Analysis and Prediction of COVID-19 outbreak in India using Machine Learning

2020 ◽  
pp. 199-207
Author(s):  
Akshar Patel ◽  
Dweepna Garg
Keyword(s):  
Moving Average ◽  
Arima Model ◽  
Support Vector ◽  
Health Security ◽  
Autoregressive Integrated Moving Average ◽  
Global Pandemic ◽  
Svm Model ◽  
The Government ◽  
Communication Paths ◽  
Model Support

Coronavirus disease globally known as COVID-19 is triggered by SARS-COV2. It is the predominant cause of an extremely dangerous disease that has bothered global health security. It is proposed that COVID-19 might be zoonotically based on the high number of people exposed in Wuhan City, China, to the wet animal market[1]. COVID-19 is a severe acute respiratory disease, transmitted by respiratory secretions and communication paths, as of WHO reports. The disease is spreading throughout the world at a faster pace. The first instance of COVID-19 was firstly discovered and found in Wuhan, Hubei Province, China in December 2019[1]. This paper analyses the outbreak of this disease until June 22, 2020, for India and other top major affected nations and also predictions were made regarding the number of cases for India over the next 17 days i.e from 23 June 2020 to 9 July 2020. Linear Regression model, Support Vector Machine Regressor (SVM) model, Autoregressive Integrated Moving Average (ARIMA) model and Facebook's Prophet model were used for prediction based on the Kaggle downloaded dataset with data collected from January 22, 2020, to June 22, 2020. By 22 June 2020, the disease has spread across more than 200 countries, reporting 12,322 confirmed cases, 45,26,333 recovered cases and 4,72,171 COVID-19 deaths. Assessment of this epidemic allows the Government to take the appropriate steps to curb the threat of this global pandemic.

scholarly journals Applications of Support Vector Machine in Genomic Prediction in Pig and Maize Populations

2020 ◽  
Vol 11 ◽  
Author(s):  
Wei Zhao ◽  
Xueshuang Lai ◽  
Dengying Liu ◽  
Zhenyang Zhang ◽  
Peipei Ma ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Plant Breeding ◽  
Genomic Prediction ◽  
Prediction Models ◽  
Prediction Performance ◽  
Kernel Functions ◽  
Support Vector ◽  
Data Sets ◽  
Svm Model ◽  
Better Than

Genomic prediction (GP) has revolutionized animal and plant breeding. However, better statistical models that can improve the accuracy of GP are required. For this reason, in this study, we explored the genomic-based prediction performance of a popular machine learning method, the Support Vector Machine (SVM) model. We selected the most suitable kernel function and hyperparameters for the SVM model in eight published genomic data sets on pigs and maize. Next, we compared the SVM model with RBF and the linear kernel functions to the two most commonly used genome-enabled prediction models (GBLUP and BayesR) in terms of prediction accuracy, time, and the memory used. The results showed that the SVM model had the best prediction performance in two of the eight data sets, but in general, the predictions of both models were similar. In terms of time, the SVM model was better than BayesR but worse than GBLUP. In terms of memory, the SVM model was better than GBLUP and worse than BayesR in pig data but the same with BayesR in maize data. According to the results, SVM is a competitive method in animal and plant breeding, and there is no universal prediction model.

Sign in / Sign up

Export Citation Format

Share Document