scholarly journals Forecasting hydrologic parameters using linear and nonlinear stochastic models

2019 ◽  
Vol 11 (4) ◽  
pp. 1284-1301
Author(s):  
Hamed Nozari ◽  
Fateme Tavakoli
Keyword(s):  
Support Vector Machine ◽  
Moving Average ◽  
Sustainable Use ◽  
Rain Gauge ◽  
Support Vector ◽  
Autoregressive Moving Average ◽  
Monthly Precipitation ◽  
Precipitation Prediction ◽  
Armax Model ◽  
Monthly Discharge

Abstract One of the most important bases in the management of catchments and sustainable use of water resources is the prediction of hydrological parameters. In this study, support vector machine (SVM), support vector machine combined with wavelet transform (W-SVM), autoregressive moving average with exogenous variable (ARMAX) model, and autoregressive integrated moving average (ARIMA) models were used to predict monthly values of precipitation, discharge, and evaporation. For this purpose, the monthly time series of rain-gauge, hydrometric, and evaporation-gauge stations located in the catchment area of Hamedan during a 25-year period (1991–2015) were used. Out of this statistical period, 17 years (1991–2007), 4 years (2008–2011), and 4 years (2012–2015) were used for training, calibration, and validation of the models, respectively. The results showed that the ARIMA, SVM, ARMAX, and W-SVM ranked from first to fourth in the monthly precipitation prediction and SVM, ARIMA, ARMAX, and W-SVM were ranked from first to fourth in the monthly discharge and monthly evaporation prediction. It can be said that the SVM has fewer adjustable parameters than other models. Thus, the model is able to predict hydrological changes with greater ease and in less time, because of which it is preferred to other methods.

scholarly journals Research on Monthly Precipitation Prediction Based on the Least Square Support Vector Machine with Multi-Factor Integration

Atmosphere ◽  
2021 ◽  
Vol 12 (8) ◽  
pp. 1076
Author(s):  
Jingchun Lei ◽  
Quan Quan ◽  
Pingzhi Li ◽  
Denghua Yan
Keyword(s):  
Support Vector Machine ◽  
Prediction Model ◽  
Flood Control ◽  
Historical Data ◽  
Yellow River ◽  
Least Square ◽  
Disaster Mitigation ◽  
Support Vector ◽  
Monthly Precipitation ◽  
Precipitation Prediction

Accurate precipitation prediction is of great significance for regional flood control and disaster mitigation. This study introduced a prediction model based on the least square support vector machine (LSSVM) optimized by the genetic algorithm (GA). The model was used to estimate the precipitation of each meteorological station over the source region of the Yellow River (SRYE) in China for 12 months. The Ensemble empirical mode decomposition (EEMD) method was used to select meteorological factors and realize precipitation prediction, without dependence on historical data as a training set. The prediction results were compared with each other, according to the determination coefficient (R2), mean absolute errors (MAE), and root mean square error (RMSE). The results show that sea surface temperature (SST) in the Niño 1 + 2 region exerts the largest influence on accuracy of the prediction model for precipitation in the SRYE (RSST2= 0.856, RMSESST= 19.648, MAESST= 14.363). It is followed by the potential energy of gravity waves (Ep) and temperature (T) that have similar effects on precipitation prediction. The prediction accuracy is sensitive to altitude influences and accurate prediction results are easily obtained at high altitudes. This model provides a new and reliable research method for precipitation prediction in regions without historical data.

EEG Signals Classification Using Support Vector Machine

2020 ◽  
Vol 12 (2) ◽  
pp. 215-224
Author(s):  
Abdelhakim Ridouh ◽  
Daoud Boutana ◽  
Salah Bourennane
Keyword(s):  
Support Vector Machine ◽  
Wavelet Decomposition ◽  
Moving Average ◽  
Real Life ◽  
Support Vector ◽  
Discrete Wavelet ◽  
Eeg Signal ◽  
Eeg Signals ◽  
Decomposition Level ◽  
Sensitivity Specificity

We address with this paper some real-life healthy and epileptic EEG signals classification. Our proposed method is based on the use of the discrete wavelet transform (DWT) and Support Vector Machine (SVM). For each EEG signal, five wavelet decomposition level is applied which allow obtaining five spectral sub-bands correspond to five rhythms (Delta, Theta, Alpha, Beta and gamma). After the extraction of some features on each sub-band (energy, standard deviation, and entropy) a moving average (MA) is applied to the resulting features vectors and then used as inputs to SVM to train and test. We test the method on EEG signals during two datasets: normal and epileptics, without and with using MA to compare results. Three parameters are evaluated such as sensitivity, specificity, and accuracy to test the performances of the used methods.

scholarly journals AUTOMATIC IDENTIFICATION OF EPILEPTIC AND BACKGROUND EEG SIGNALS USING FREQUENCY DOMAIN PARAMETERS

2010 ◽  
Vol 20 (02) ◽  
pp. 159-176 ◽  
Author(s):  
OLIVER FAUST ◽  
U. RAJENDRA ACHARYA ◽  
LIM CHOO MIN ◽  
BERNHARD H. C. SPUTH
Keyword(s):  
Support Vector Machine ◽  
Moving Average ◽  
Gaussian Mixture ◽  
Power Density Spectrum ◽  
Estimation Methods ◽  
Support Vector ◽  
Automatic Identification ◽  
Spectrum Estimation ◽  
Classification Rate ◽  
Density Spectrum

The analysis of electroencephalograms continues to be a problem due to our limited understanding of the signal origin. This limited understanding leads to ill-defined models, which in turn make it hard to design effective evaluation methods. Despite these shortcomings, electroencephalogram analysis is a valuable tool in the evaluation of neurological disorders and the evaluation of overall cerebral activity. We compared different model based power spectral density estimation methods and different classification methods. Specifically, we used the autoregressive moving average as well as from Yule-Walker and Burg's methods, to extract the power density spectrum from representative signal samples. Local maxima and minima were detected from these spectra. In this paper, the locations of these extrema are used as input to different classifiers. The three classifiers we used were: Gaussian mixture model, artificial neural network, and support vector machine. The classification results are documented with confusion matrices and compared with receiver operating characteristic curves. We found that Burg's method for spectrum estimation together with a support vector machine classifier yields the best classification results. This combination reaches a classification rate of 93.33%, the sensitivity is 98.33% and the specificy is 96.67%.

Fault Diagnosis of a Wind Turbine Benchmark via Statistical and Support Vector Machine

2018 ◽  
Vol 37 ◽  
pp. 29-42 ◽  
Author(s):  
Abderrahmane Mokhtari ◽  
Mohammed Belkheiri
Keyword(s):  
Support Vector Machine ◽  
Fault Detection ◽  
Wind Turbine ◽  
Moving Average ◽  
Fault Detection And Isolation ◽  
Support Vector ◽  
Svm Classifier ◽  
Actuator Faults ◽  
Active System ◽  
Benchmark Model

This paper addresses the problem of fault detection and isolation (FDI) in wind turbine benchmark model using data driven and multi-class support vector machine (SVM) approach. Since, the fault detection is fundamental for any active system, isolation is similarly vital, and identification is decisive for fault reconfiguration as well as maintenance addition to monitoring purposes. The need for man-made dynamic system to work automatically when sensor, actuator, or system faults occur was constantly developed in order to increase reliability and decrease unavailability and maintenance costs. The key step of our approach based on extraction of mean features from sensors measurements by applying the statistical methods such as moving standard deviation and the exponential weighted moving average (EWMA). The fault detection step is invoked later based on the multi-class SVM classifier that decides the presence or not of the fault. Another important contribution of this paper is the simulation of combined sensor and actuator faults simultaneously for the first time in wind turbine benchmark model. The FDI performances are illustrated through simulation study for seven different scenario tests. The results demonstrate clearly the effectiveness of statistical and SVM approach to detect and isolate single, multiple sensor and actuator faults and outperforms many results reported in the literature for solving this problem.

Recursive Identification of the Dynamic Behavior in a Distillation Column by Means of Autoregressive Models

2014 ◽  
Vol 136 (4) ◽  
Author(s):  
Lakhdar Aggoune ◽  
Yahya Chetouani ◽  
Hammoud Radjeai
Keyword(s):  
Performance Measures ◽  
Distillation Column ◽  
Moving Average ◽  
Information Criterion ◽  
Recursive Identification ◽  
Autoregressive Moving Average ◽  
Model Parameters ◽  
Recursive Algorithms ◽  
Optimal Model ◽  
Armax Model

In this study, an Autoregressive with eXogenous input (ARX) model and an Autoregressive Moving Average with eXogenous input (ARMAX) model are developed to predict the overhead temperature of a distillation column. The model parameters are estimated using the recursive algorithms. In order to select an optimal model for the process, different performance measures, such as Aikeke's Information Criterion (AIC), Root Mean Square Error (RMSE), and Nash–Sutcliffe Efficiency (NSE), are calculated.

Fast Diagnosis of Volatile Organic Compounds with a Temperature-Modulated Chemoresistor

2011 ◽  
Vol 495 ◽  
pp. 310-313 ◽  
Author(s):  
Amir Amini ◽  
Seyed Mohsen Hosseini-Golgoo
Keyword(s):  
Cross Validation ◽  
Operating Temperature ◽  
Moving Average ◽  
Feature Space ◽  
Autoregressive Moving Average ◽  
Temperature Modulation ◽  
Voltage Waveform ◽  
Volatile Organic ◽  
Gas Identification ◽  
Armax Model

Virtual arrays formed by operating temperature modulation of a commercial non selective chemoresistor have been utilized for gas identification. Here, we are reporting the details of a refined system which distinctly classifies methanol, ethanol, 1-butanol, acetone and hydrogen contaminations in a wide concentration range. A staircase voltage waveform of 5 plateaus is applied to the sensor’s microheater and gas recognition is achieved in 25 s. Sensor’s output is modeled by an “autoregressive moving average with exogenous variables” (ARMAX) model. The modeling parameters obtained for an unknown analyte are utilized as the components of its feature vectors which afford its classification in a feature space. Cross-validation in the 5 to 100 ppm concentration range for H2, and 200 to 2000 ppm for the other analytes examined, resulted in an overall classification success rate of 100%.

Assessing the Effects of Terrorism on Tourism by Use of Time Series Methods

2003 ◽  
Vol 9 (2) ◽  
pp. 179-190 ◽  
Author(s):  
Brian W. Sloboda
Keyword(s):  
Time Series ◽  
Impact Analysis ◽  
Moving Average ◽  
Single Equation ◽  
Autoregressive Moving Average ◽  
Short Term ◽  
Explanatory Variables ◽  
Use Of Time ◽  
Dependent Variables ◽  
Armax Model

This paper presents an assessment of the effects of terrorism on tourism by using time series methods, namely the ARMAX (autoregressive moving average with explanatory variables) model. This is a single-equation approach, which has the ability to provide impact analysis easily. The use of the ARMAX model allows for the general shape of the lag distribution of the impacts of the explanatory variables based on the ratio of lag polynomials for the independent and dependent variables. The ARMAX models, like the ARIMA models, provide for a short-term assessment of terrorist incidents on tourism.

Sign in / Sign up

Export Citation Format

Share Document