A Novel Heuristic Approach for the Simultaneous Selection of the Optimal Clustering Method and Its Internal Parameters for Time Series Data

This study aims to create a mathematical model that can be used to predict the amount of oil palm that will be produced at PT. Socfindo in Aceh Tamiang Regency in the coming period. The data used is data on the amount of oil palm that is ready to be produced every month in 2012-2015. The method used is the ARIMA method. The selection of this method is based on the data used, namely time series data. Before carrying out further testing, first, ensure that the data used meets the stationary state. From the test results, it is found that the data used fulfills the stationary state, then it is found that the MA (1) model can be used to predict the time series data. Furthermore, we obtain a model that can be used to predict the volume of oil palm production at PT. Socfindo is: Z_t = a_t-0.4096a_ (t-1) +521.57 With a_t ~ N (0; 29192.72)

Download Full-text

Choosing the content of textual summaries of large time-series data sets

Natural Language Engineering ◽

10.1017/s1351324905004031 ◽

2006 ◽

Vol 13 (1) ◽

pp. 25-49 ◽

Cited By ~ 45

Author(s):

JIN YU ◽

EHUD REITER ◽

JIM HUNTER ◽

CHRIS MELLISH

Keyword(s):

Time Series ◽

Gas Turbines ◽

Time Series Data ◽

Sensor Data ◽

Series Data ◽

Prototype System ◽

Data Sets ◽

Significant Patterns ◽

Numeric Data ◽

Selection Of

Natural Language Generation (NLG) can be used to generate textual summaries of numeric data sets. In this paper we develop an architecture for generating short (a few sentences) summaries of large (100KB or more) time-series data sets. The architecture integrates pattern recognition, pattern abstraction, selection of the most significant patterns, microplanning (especially aggregation), and realisation. We also describe and evaluate SumTime-Turbine, a prototype system which uses this architecture to generate textualsummaries of sensor data from gas turbines.

Download Full-text

SELECTION OF INPUT VARIABLES OF NONLINEAR AUTOREGRESSIVE NEURAL NETWORK MODEL FOR TIME SERIES DATA FORECASTING

MEDIA STATISTIKA ◽

10.14710/medstat.13.2.116-124 ◽

2020 ◽

Vol 13 (2) ◽

pp. 116-124

Author(s):

Hermansah Hermansah ◽

Dedi Rosadi ◽

Abdurakhman Abdurakhman ◽

Herni Utami

Keyword(s):

Neural Network ◽

Time Series ◽

Network Model ◽

Neural Network Model ◽

Time Series Data ◽

Series Data ◽

Input Variables ◽

Nonlinear Autoregressive ◽

Selection Of ◽

Autoregressive Neural Network

NARNN is a type of ANN model consisting of a limited number of parameters and widely used for various applications. This study aims to determine the appropriate NARNN model, for the selection of input variables of nonlinear autoregressive neural network model for time series data forecasting, using the stepwise method. Furthermore, the study determines the optimal number of neurons in the hidden layer, using a trial and error method for some architecture. The NARNN model is combined in three parts, namely the learning method, the activation function, and the ensemble operator, to get the best single model. Its application in this study was conducted on real data, such as the interest rate of Bank Indonesia. The comparison results of MASE, RMSE, and MAPE values with ARIMA and Exponential Smoothing models shows that the NARNN is the best model used to effectively improve forecasting accuracy.

Download Full-text

Parameter Selection of SVR Based on Improved K-Fold Cross Validation

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.462-463.182 ◽

2013 ◽

Vol 462-463 ◽

pp. 182-186 ◽

Cited By ~ 2

Author(s):

Ju E Wang ◽

Jian Zhong Qiao

Keyword(s):

Time Series ◽

Cross Validation ◽

Time Series Data ◽

Parameter Selection ◽

Small Samples ◽

Series Data ◽

Support Vector ◽

Model Parameters ◽

Fold Cross Validation ◽

Selection Of

This article firstly uses svm to forecast cashmere price time series. The forecasting result mainly depends on parameter selection. The normal parameter selection is based on k-fold cross validation. The k-fold cross validation is suitable for classification. In this essay, k-fold cross validation is improved to ensure that only the older data can be used to forecast latter data to improve prediction accuracy. This essay trains the cashmere price time series data to build mathematical model based on SVM. The selection of the model parameters are based on improved cross validation. The price of Cashmere can be forecasted by the model. The simulation results show that support vector machine has higher fitting precision in the situation of small samples. It is feasible to forecast cashmere price based on SVM.

Download Full-text