Short-Term Prediction of Ship Motion Based on EMD-SVM

Ship sailing at sea is affected by many factors, such as winds, waves and so on, which makes six degrees of freedom motions and thus influences the shipboard arms control, aircraft landing and other operations. In view of the non-linear and non-stationary features of ship motion in waves, a new method based on EMD (Empirical Model Decomposition) and SVM (Support Vector Machine) is presented to predict the ship motion. The EMD is used to decompose the ship motion time series data into several IMFs (intrinsic mode functions) and a residual trend term, which decreases the difficulty of prediction. As the IMF is relatively stationary, but also non-linear, these features are fit to be processed by using SVM. Then the decompositions are used as inputs into SVM to forecast ship motion. The simulation and comparison analysis show that the EMD-SVM prediction model can effectively forecast the ship motion in waves.

Download Full-text

Implementation of IoT Framework with Data Analysis Using Deep Learning Methods for Occupancy Prediction in a Building

Future Internet ◽

10.3390/fi13030067 ◽

2021 ◽

Vol 13 (3) ◽

pp. 67

Author(s):

Eric Hitimana ◽

Gaurav Bajpai ◽

Richard Musabe ◽

Louis Sibomana ◽

Jayavel Kayalvizhi

Keyword(s):

Machine Learning ◽

Time Series ◽

Deep Learning ◽

Time Series Data ◽

Multivariate Time Series ◽

Machine Learning Algorithms ◽

Series Data ◽

Support Vector ◽

Human Beings ◽

Feed Forward Network

Many countries worldwide face challenges in controlling building incidence prevention measures for fire disasters. The most critical issues are the localization, identification, detection of the room occupant. Internet of Things (IoT) along with machine learning proved the increase of the smartness of the building by providing real-time data acquisition using sensors and actuators for prediction mechanisms. This paper proposes the implementation of an IoT framework to capture indoor environmental parameters for occupancy multivariate time-series data. The application of the Long Short Term Memory (LSTM) Deep Learning algorithm is used to infer the knowledge of the presence of human beings. An experiment is conducted in an office room using multivariate time-series as predictors in the regression forecasting problem. The results obtained demonstrate that with the developed system it is possible to obtain, process, and store environmental information. The information collected was applied to the LSTM algorithm and compared with other machine learning algorithms. The compared algorithms are Support Vector Machine, Naïve Bayes Network, and Multilayer Perceptron Feed-Forward Network. The outcomes based on the parametric calibrations demonstrate that LSTM performs better in the context of the proposed application.

Download Full-text

Prediction and Analysis of Gold Prices using Ensemble Machine Learning Algorithms

International Journal for Research in Applied Science and Engineering Technology ◽

10.22214/ijraset.2021.36028 ◽

2021 ◽

Vol 9 (VI) ◽

pp. 4367-4374

Author(s):

Gudipally Chandrashakar

Keyword(s):

Machine Learning ◽

Time Series ◽

Time Series Data ◽

Gold Price ◽

Machine Learning Algorithms ◽

Series Data ◽

Gradient Boosting ◽

Support Vector ◽

Average Value ◽

Ensemble Machine Learning

In this article, we used historical time series data up to the current day gold price. In this study of predicting gold price, we consider few correlating factors like silver price, copper price, standard, and poor’s 500 value, dollar-rupee exchange rate, Dow Jones Industrial Average Value. Considering the prices of every correlating factor and gold price data where dates ranging from 2008 January to 2021 February. Few algorithms of machine learning are used to analyze the time-series data are Random Forest Regression, Support Vector Regressor, Linear Regressor, ExtraTrees Regressor and Gradient boosting Regression. While seeing the results the Extra Tree Regressor algorithm gives the predicted value of gold prices more accurately.

Download Full-text

Ensemble Empirical Mode Decomposition Based Deep Learning Model for Short-Term Wind Power Forecasting

10.21741/9781644901731-8 ◽

2022 ◽

Author(s):

J.M. González-Sopeña

Keyword(s):

Deep Learning ◽

Wind Power ◽

Empirical Mode Decomposition ◽

Time Series Data ◽

Ensemble Empirical Mode Decomposition ◽

Series Data ◽

Intrinsic Mode Functions ◽

Wind Power Forecasting ◽

Mode Decomposition ◽

Power Forecasting

Abstract. In the last few years, wind power forecasting has established itself as an essential tool in the energy industry due to the increase of wind power penetration in the electric grid. This paper presents a wind power forecasting method based on ensemble empirical mode decomposition (EEMD) and deep learning. EEMD is employed to decompose wind power time series data into several intrinsic mode functions and a residual component. Afterwards, every intrinsic mode function is trained by means of a CNN-LSTM architecture. Finally, wind power forecast is obtained by adding the prediction of every component. Compared to the benchmark model, the proposed approach provides more accurate predictions for several time horizons. Furthermore, prediction intervals are modelled using quantile regression.

Download Full-text

PREDICTION OF OZONE (O3) VALUES USING SUPPORT VECTOR REGRESSION METHOD

Jurnal Informatika Polinema ◽

10.33795/jip.v7i4.777 ◽

2021 ◽

Vol 7 (4) ◽

pp. 81-88

Author(s):

Chasandra Puspitasari ◽

Nur Rokhman ◽

Wahyono

Keyword(s):

Air Quality ◽

Support Vector Regression ◽

Time Series Data ◽

Motor Vehicles ◽

Primary Data ◽

Series Data ◽

Polynomial Kernel ◽

Support Vector ◽

Linear Kernel ◽

Air Quality Prediction

A large number of motor vehicles that cause congestion is a major factor in the poor air quality in big cities. Ozone (O3) is one of the main indicators in measuring the level of air pollution in the city of Surabaya to find out how air quality. Prediction of Ozone (O3) value is important as a support for the community and government in efforts to improve the air quality. This study aims to predict the value of Ozone (O3) in the form of time series data using the Support Vector Regression (SVR) method with the Linear, Polynomial, RBF, and ANOVA kernels. The data used in this study are 549 primary data from the daily average of ozone (O3) value of Surabaya in the period 1 July 2017 - 31 December 2018. The data will be used in the training and testing process until prediction results are obtained. The results obtained from this study are the Linear kernel produces the best prediction model with a MAPE value of 21.78% with a parameter value 𝜆 = 0.3; 𝜀 = 0.00001; cLR = 0.005; and C = 0.5. The results of the Polynomial kernel are not much different from the Linear kernel which has a MAPE value of 21.83%. While the RBF and ANOVA kernels each produce a model with MAPE value of 24.49% and 22.0%. These results indicate that the SVR method with the kernels used can predict Ozone values quite well.

Download Full-text

Modeling Statistical Downscaling for Prediction Precipitation Dry Season in Bireuen District Province Aceh

Indonesian Journal of Artificial Intelligence and Data Mining ◽

10.24014/ijaidm.v2i2.7518 ◽

2019 ◽

Vol 2 (2) ◽

pp. 74

Author(s):

Juniana Husna ◽

Sanusi Sanusi

Keyword(s):

Statistical Downscaling ◽

Time Series Data ◽

Rainfall Variability ◽

Series Data ◽

Polynomial Kernel ◽

Support Vector ◽

Monsoon Circulation ◽

Rainfall Forecasting ◽

Local Climate ◽

Correlation Degree

The Asian-Australian monsoon circulation specifically causes the Indonesian region to go through climate changebility that impacts on rainfall variability in different Indonesia’s zone. Local climate conditions such as rainfall data are commonly simulated using GCM time series data. This study tries to model the statistical downscaling of GCM in the form of 7x7 matrix using Support Vector Regression (SVR) for rainfall forecasting during drought in Bireuen Regency, Aceh. The output yields optimal result using certain parameter i.e. C = 0.5, γ = 0.8, d = 1, and ↋= 0.01. The duration of computation during training and testing are ± 45 seconds for linear kernels and ± 2 minutes for polynomials. The correlation degree and RMSE values of GCM and the actually observed data at Gandapura wheather station are 0.672 and 21.106. The RSME value obtained in that region is the lowest compared to the Juli station which is equal to 31,428. However, the Juli station has the highest correlation value that is 0.677. On the other hand, the polynomial kernel has a correlation degree and RMSE value equal to 0.577 and 29,895 respectively. To summary, the best GCM using SVR kernel is the one at Gandapura weather station in consideration of having the lowest RMSE value with a high correlation degree.

Download Full-text

Comparative Performance of Machine Learning Algorithms for Cryptocurrency Forecasting

Indonesian Journal of Electrical Engineering and Computer Science ◽

10.11591/ijeecs.v11.i3.pp1121-1128 ◽

2018 ◽

Vol 11 (3) ◽

pp. 1121 ◽

Cited By ~ 4

Author(s):

Nor Azizah Hitam ◽

Amelia Ritahani Ismail

Keyword(s):

Machine Learning ◽

Time Series Data ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Series Data ◽

Support Vector ◽

Small Range ◽

Accuracy Rate ◽

Comparative Performance ◽

Vector Machines

Machine Learning is part of Artificial Intelligence that has the ability to make future forecastings based on the previous experience. Methods has been proposed to construct models including machine learning algorithms such as Neural Networks (NN), Support Vector Machines (SVM) and Deep Learning. This paper presents a comparative performance of Machine Learning algorithms for cryptocurrency forecasting. Specifically, this paper concentrates on forecasting of time series data. SVM has several advantages over the other models in forecasting, and previous research revealed that SVM provides a result that is almost or close to actual result yet also improve the accuracy of the result itself. However, recent research has showed that due to small range of samples and data manipulation by inadequate evidence and professional analyzers, overall status and accuracy rate of the forecasting needs to be improved in further studies. Thus, advanced research on the accuracy rate of the forecasted price has to be done.

Download Full-text

Prediction of water quality time series data based on least squares support vector machine

Procedia Engineering ◽

10.1016/j.proeng.2012.01.1162 ◽

2012 ◽

Vol 31 ◽

pp. 1194-1199 ◽

Cited By ~ 44

Author(s):

Guohua Tan ◽

Jianzhuo Yan ◽

Chen Gao ◽

Suhua Yang

Keyword(s):

Water Quality ◽

Time Series ◽

Support Vector Machine ◽

Least Squares ◽

Time Series Data ◽

Series Data ◽

Support Vector

Download Full-text

The Effects Of Asymmetric Transmission Of Exchange Rate On Inflation In Iran: Application Of Threshold Models

Studies in Business and Economics ◽

10.1515/sbe-2015-0023 ◽

2015 ◽

Vol 10 (2) ◽

pp. 99-113

Author(s):

Yazdan Naghdi ◽

Soheila Kaghazian

Keyword(s):

Exchange Rate ◽

Time Series Data ◽

Public Procurement ◽

Consumer Price Index ◽

Series Data ◽

Asymmetric Transmission ◽

Exchange Rate Fluctuation ◽

Rate Fluctuation ◽

Non Linear ◽

The One

Abstract Given the recent fluctuation in the exchange rate and the presence of several factors such as the various economy-political sanctions (mainly embargos on oil and banking), extreme volatility in different economic fields, and consequently the devaluation of national and public procurement -A landmark that is emanating from exchange rate fluctuation - two points should be noted: First, it is essential to review the effect of exchange rate fluctuation on macro economic variables such as inflation and to provide appropriate policies. Second, the existence of this condition provides the chance to study the relation between exchange rate and inflation in a non-linear and asymmetric method. Hence, the present study seeks to use TAR model and, on the basis of monthly time series data over the period March 2002 to March 2014, to analyze the cross-asymmetric and non-linear exchange rate on consumer price index (CPI) in Iran. The results also show the presence of an asymmetric long-term relationship between these variables (exchange rate and CPI). Also, in the Iranian economy, the effect of negative shocks of exchange rate on inflation is more sustainable than the one from positive shocks.

Download Full-text

Forecasting Rice Production in West Bengal State in India

International Journal of Agricultural and Environmental Information Systems ◽

10.4018/ijaeis.2013100104 ◽

2013 ◽

Vol 4 (4) ◽

pp. 68-91 ◽

Cited By ~ 3

Author(s):

Arindam Chaudhuri

Keyword(s):

Time Series ◽

Multiple Regression ◽

Computational Intelligence ◽

Time Series Data ◽

Rice Production ◽

Productivity Index ◽

Series Data ◽

Support Vector ◽

Production Time ◽

Inference System

Forecasting rice production is a challenging problem in agricultural statistics. The inherent difficulty lies in demand and supply affected by many uncertain factors viz. economic policies, agricultural factors, credit measures, foreign trade etc. which interact in a complex manner. Since last few decades, Statistical techniques are used for developing predictive models to estimate required parameters. Determination of nature of rice production time series data is difficult, expensive, time consuming and involves tedious tests. In this paper, we use Interval Type Fuzzy Auto Regressive Integrated Moving Average (ITnARIMA), Adaptive Neuro Fuzzy Inference System (ANFIS) and Modified Regularized Least Squares Fuzzy Support Vector Regression (MRLSFSVR) for prediction of Productivity Index percent (PI %) of rice production time series data and compare it with traditional Statistical tool of Multiple Regression. The accuracies of ITnARIMA and ANFIS techniques are evaluated as relatively similar. It is found that ANFIS exhibits high performance than ITnARIMA, MRLSFSVR and Multiple Regression for predicting PI %. The performance comparison shows that Computational Intelligence paradigm is a promising tool for minimizing uncertainties in rice production data. Further Computational Intelligence techniques also minimize potential inconsistency of correlations.

Download Full-text