Artificial Neural Network for analyzing the chaotic time series motion: The case of the Lebanese GDP

Phase Space ◽

Regression Models ◽

Chaotic Dynamic ◽

Linear Regression Models ◽

Large Fluctuations ◽

Artificial Neural ◽

Abstract In this paper, we propose to analyze the motion of the Lebanese GDP over the period 1950-2019. This macroeconomic aggregate reveals large fluctuations notably during the civil war period (1975-1990). By estimating the Lyapunov exponents with the Artificial Neural Network (ANN) procedure, we show that this series exhibits a strange attractor generated by a chaotic dynamic and we use the embedding procedure to shed in light the bizarre structure of such a series. Thus, the ANN method gives better results regarding prediction than other linear regression models and allows to fit with accuracy the chaotic motion followed by the Lebanese GDP in the phase space.

Univariate Artificial Neural Network in Forecasting Demand of Low Cost House in Petaling Jaya

Jurnal Teknologi ◽

10.11113/jt.v40.406 ◽

2012 ◽

pp. 1-16 ◽

Cited By ~ 1

Author(s):

Norhisham Bakhary ◽

Khairulzan Yahya ◽

Chin Nam Ng

Keyword(s):

Neural Network ◽

Time Series ◽

Low Cost ◽

Housing Demand ◽

Percentage Error ◽

Potential Applications ◽

Low Cost Housing ◽

Artificial Neural ◽

Kebelakangan ini ramai penyelidik mendapati ‘Artificial Neural Network’ (ANN) untuk digunakan dalam berbagai bidang kejuruteraan awam. Banyak aplikasi ANN dalam proses peramalan menghasilkan kejayaan. Kajian ini memfokuskan kepada penggunaan siri masa ‘Univariate Neural Network’ untuk meramalkan permintaan rumah kos rendah di daerah Petaling Jaya, Selangor. Dalam kajian ini, beberapa kes bagi sesi latihan dan ramalan telah dibuat untuk mendapatkan model terbaik bagi meramalkan permintaan rumah. Nilai RMSE yang paling rendah yang diperolehi bagi tahap validasi adalah 0.560 dan nilai MAPE yang diperolehi adalah 8.880%. Hasil kajian ini menunjukkan kaedah ini memberikan keputusan yang boleh diterima dalam peramalan permintaan rumah berdasarkan data masa lalu. Kata kunci: Univariate Neural Network, permintaan rumah kos rendah, RMSE, MAPE Recently researchers have found the potential applications of Artificial Neural Network (ANN) in various fields in civil engineering. Many attempts to apply ANN as a forecasting tool has been successful. This paper highlighted the application of Time Series Univariate Neural Network in forecasting the demand of low cost house in Petaling Jaya district, Selangor, using historical data ranging from February 1996 to Appril 2000. Several cases of training and testing were conducted to obtain the best neural network model. The lowest Root Mean Square Error (RMSE) obtained for validation step is 0.560 and Mean Absolute Percentage Error (MAPE) is 8.880%. These results show that ANN is able to provide reliable result in term of forecasting the housing demand based on previous housing demand record. Key words: Time Series Univariate Neural Network, low cost housing demand, RMSE, MAPE

Multiple regression models and Artificial Neural Network (ANN) as prediction tools of changes in overall quality during the storage of spreadable processed Gouda cheese

European Food Research and Technology ◽

10.1007/s00217-019-03369-y ◽

2019 ◽

Vol 245 (11) ◽

pp. 2539-2547 ◽

Cited By ~ 2

Author(s):

J. Stangierski ◽

D. Weiss ◽

A. Kaczmarek

Keyword(s):

Neural Network ◽

Multiple Regression ◽

Regression Models ◽

Principal Component ◽

Multiple Regression Models ◽

Gouda Cheese ◽

Artificial Neural ◽

Validation Set ◽

Abstract The aim of the study was to compare the ability of multiple linear regression (MLR) and Artificial Neural Network (ANN) to predict the overall quality of spreadable Gouda cheese during storage at 8 °C, 20 °C and 30 °C. The ANN used five factors selected by Principal Component Analysis, which was used as input data for the ANN calculation. The datasets were divided into three subsets: a training set, a validation set, and a test set. The multiple regression models were highly significant with high determination coefficients: R2 = 0.99, 0.87 and 0.87 for 8, 20 and 30 °C, respectively, which made them a useful tool to predict quality deterioration. Simultaneously, the artificial neural networks models with determination coefficient of R2 = 0.99, 0.96 and 0.96 for 8, 20 and 30 °C, respectively were built. The models based on ANNs with higher values of determination coefficients and lower RMSE values proved to be more accurate. The best fit of the model to the experimental data was found for processed cheese stored at 8 °C.

Comparison of artificial neural network (ANN) and partial least squares (PLS) regression models for predicting respiratory ventilation: an exploratory study

European Journal of Applied Physiology ◽

10.1007/s00421-011-2118-6 ◽

2011 ◽

Vol 112 (5) ◽

pp. 1603-1611 ◽

Cited By ~ 15

Author(s):

Ming-I Brandon Lin ◽

William A. Groves ◽

Andris Freivalds ◽

Eun Gyung Lee ◽

Martin Harper

Keyword(s):

Neural Network ◽

Least Squares ◽

Partial Least Squares ◽

Exploratory Study ◽

Regression Models ◽

Pls Regression ◽

Artificial Neural ◽

Spatiotemporal monthly rainfall reconstruction via artificial neural network – case study: south of Brazil

Advances in Geosciences ◽

10.5194/adgeo-10-67-2007 ◽

2007 ◽

Vol 10 ◽

pp. 67-76 ◽

Cited By ~ 11

Author(s):

P. S. Lucio ◽

F. C. Conde ◽

I. F. A. Cavalcanti ◽

A. I. Serrano ◽

A. M. Ramos ◽

...

Keyword(s):

Neural Network ◽

Time Series ◽

Low Frequency ◽

Reconstruction Method ◽

Ann Model ◽

Monthly Total ◽

Artificial Neural ◽

Artificial Neural Network Ann ◽

South Of Brazil

Abstract. Climatological records users, frequently, request time series for geographical locations where there is no observed meteorological attributes. Climatological conditions of the areas or points of interest have to be calculated interpolating observations in the time of neighboring stations and climate proxy. The aim of the present work is the application of reliable and robust procedures for monthly reconstruction of precipitation time series. Time series is a special case of symbolic regression and we can use Artificial Neural Network (ANN) to explore the spatiotemporal dependence of meteorological attributes. The ANN seems to be an important tool for the propagation of the related weather information to provide practical solution of uncertainties associated with interpolation, capturing the spatiotemporal structure of the data. In practice, one determines the embedding dimension of the time series attractor (delay time that determine how data are processed) and uses these numbers to define the network's architecture. Meteorological attributes can be accurately predicted by the ANN model architecture: designing, training, validation and testing; the best generalization of new data is obtained when the mapping represents the systematic aspects of the data, rather capturing the specific details of the particular training set. As illustration one takes monthly total rainfall series recorded in the period 1961–2005 in the Rio Grande do Sul – Brazil. This reliable and robust reconstruction method has good performance and in particular, they were able to capture the intrinsic dynamic of atmospheric activities. The regional rainfall has been related to high-frequency atmospheric phenomena, such as El Niño and La Niña events, and low frequency phenomena, such as the Pacific Decadal Oscillation.

Comparison of artificial neural network and linear regression models for prediction of ring spun yarn properties. I. Prediction of yarn tensile properties

Fibers and Polymers ◽

10.1007/s12221-008-0014-4 ◽

2008 ◽

Vol 9 (1) ◽

pp. 87-91 ◽

Cited By ~ 32

Author(s):

Mustafa E. Üreyen ◽

Pelin Gürkan

Keyword(s):

Neural Network ◽

Linear Regression ◽

Tensile Properties ◽

Regression Models ◽

Linear Regression Models ◽

Spun Yarn ◽

Yarn Properties ◽

Ring Spun Yarn ◽

Artificial Neural

Development of artificial neural network and multiple linear regression models in the prediction process of the hot mix asphalt properties

Canadian Journal of Civil Engineering ◽

10.1139/cjce-2017-0300 ◽

2017 ◽

Vol 44 (12) ◽

pp. 994-1004 ◽

Cited By ~ 6

Author(s):

Ivica Androjić ◽

Ivan Marović

Keyword(s):

Neural Network ◽

Linear Regression ◽

Multiple Linear Regression ◽

Regression Models ◽

Prediction Models ◽

Hot Mix Asphalt ◽

Linear Regression Models ◽

Artificial Neural ◽

Multiple Linear Regression Models

The oscillation of asphalt mix composition on a daily basis significantly affects the achieved properties of the asphalt during production, thus resulting in conducting expensive laboratory tests to determine existing properties and predicting the future results. To decrease the amount of such tests, a development of artificial neural network and multiple linear regression models in the prediction process of predetermined dependent variables air void and soluble binder content is presented. The input data were obtained from a single laboratory and consists of testing 386 mixes of hot mix asphalt (HMA). It was found that it is possible and desirable to apply such models in the prediction process of the HMA properties. The final aim of the research was to compare results of the prediction models on an independent dataset and analyze them through the boundary conditions of technical regulations and the standard EN 13108-21.

Aplikasi Artificial Neural Network (ANN) dalamPeramalan Time Series Data: StudiKasus Lama SinarMatahari

IJECA (International Journal of Education and Curriculum Application) ◽

10.31764/ijeca.v0i0.2004 ◽

2018 ◽

pp. 207

Author(s):

Sulistyarini Sulistyarini

Keyword(s):

Neural Network ◽

Time Series ◽

Time Series Data ◽

Series Data ◽

Marriage Ceremony ◽

Library Research ◽

Wedding Ceremony ◽

Artificial Neural ◽

This paper discusses wedding ceremony in Central Lombok village of Plambik, which is potential to be a cultural attraction that supports the development of tourism. Marriage ceremony in Plambik has a number of stages, which are not necessarily similar to those customly practiced by other groups of Sasak people. in order to hold a wedding ceremony. This paper aimed to explore merariq tradition which is uniquely held by Sasak community in Plambik. Data of this research were collected through library research and interviews with Plambik natives. The data were then analyzed by comparing the documentary notes with the actual practices of merariq by Plambik villagers. The finding indicated unique features of merariq stages in Plambik.

Trajectory of COVID-19 Data in India: Investigation and Project Using Artificial Neural Network, Fuzzy Time Series and ARIMA Models

Annual Research & Review in Biology ◽

10.9734/arrb/2020/v35i930270 ◽

2020 ◽

pp. 46-54

Author(s):

Pradeep Mishra ◽

Chellai Fatih ◽

Deepa Rawat ◽

Saswati Sahu ◽

Sagar Anand Pandey ◽

...

Keyword(s):

Neural Network ◽

Time Series ◽

Arima Model ◽

Fuzzy Time Series ◽

Short Term ◽

Indian Health ◽

Artificial Neural ◽

Artificial Neural Network Ann ◽

The Impact

Due to the impact of Corona virus (COVID-19) pandemic that exists today, all countries, national and international organizations are in a continuous effort to find efficient and accurate statistical models for forecasting the future pattern of COVID infection. Accurate forecasting should help governments to take decisive decisions to master the pandemic spread. In this article, we explored the COVID-19 database of India between 17th March to 1st July 2020, then we estimated two nonlinear time series models: Artificial Neural Network (ANN) and Fuzzy Time Series (FTS) by comparing them with ARIMA model. In terms of model adequacy, the FTS model out performs the ANN for the new cases and new deaths time series in India. We observed a short-term virus spread trend according to three forecasting models.Such findings help in more efficient preparation for the Indian health system.