scholarly journals A New Hybrid Methodology for Nonlinear Time Series Forecasting

2011 ◽  
Vol 2011 ◽  
pp. 1-5 ◽  
Author(s):  
Mehdi Khashei ◽  
Mehdi Bijari
Keyword(s):  
Time Series ◽  
Linear Models ◽  
Nonlinear Models ◽  
Time Series Forecasting ◽  
Data Set ◽  
Wide Range ◽  
Alternative Methodology ◽  
Opposite Situation ◽  
High Degree ◽  
Universal Approximators

Artificial neural networks (ANNs) are flexible computing frameworks and universal approximators that can be applied to a wide range of forecasting problems with a high degree of accuracy. However, using ANNs to model linear problems have yielded mixed results, and hence; it is not wise to apply them blindly to any type of data. This is the reason that hybrid methodologies combining linear models such as ARIMA and nonlinear models such as ANNs have been proposed in the literature of time series forecasting. Despite of all advantages of the traditional methodologies for combining ARIMA and ANNs, they have some assumptions that will degenerate their performance if the opposite situation occurs. In this paper, a new methodology is proposed in order to combine the ANNs with ARIMA in order to overcome the limitations of traditional hybrid methodologies and yield more general and more accurate hybrid models. Empirical results with Canadian Lynx data set indicate that the proposed methodology can be a more effective way in order to combine linear and nonlinear models together than traditional hybrid methodologies. Therefore, it can be applied as an appropriate alternative methodology for hybridization in time series forecasting field, especially when higher forecasting accuracy is needed.

An Efficient Time Series Forecasting Method Exploiting Fuzziness and Turbulences in Data

2018 ◽  
pp. 1773-1791 ◽  
Author(s):  
Prateek Pandey ◽  
Shishir Kumar ◽  
Sandeep Shrivastava
Keyword(s):  
Time Series ◽  
Performance Comparison ◽  
Time Series Forecasting ◽  
Fuzzy Time Series ◽  
Data Set ◽  
Common Trend ◽  
Proposed Model ◽  
Forecasting Method ◽  
High Degree ◽  
Degree Of Instability

In recent years, there has been a growing interest in Time Series forecasting. A number of time series forecasting methods have been proposed by various researchers. However, a common trend found in these methods is that they all underperform on a data set that exhibit uneven ups and downs (turbulences). In this paper, a new method based on fuzzy time-series (henceforth FTS) to forecast on the fundament of turbulences in the data set is proposed. The results show that the turbulence based fuzzy time series forecasting is effective, especially, when the available data indicate a high degree of instability. A few benchmark FTS methods are identified from the literature, their limitations and gaps are discussed and it is observed that the proposed method successfully overcome their deficiencies to produce better results. In order to validate the proposed model, a performance comparison with various conventional time series models is also presented.

scholarly journals Data-driven recursive input–output multivariate statistical forecasting model: case of DO concentration prediction in Advancetown Lake, Australia

2015 ◽  
Vol 17 (5) ◽  
pp. 817-833 ◽  
Author(s):  
Edoardo Bertone ◽  
Rodney A. Stewart ◽  
Hong Zhang ◽  
Cameron Veal
Keyword(s):  
Time Series ◽  
Mean Squared Error ◽  
Time Series Forecasting ◽  
Data Driven ◽  
Input Output ◽  
Model Case ◽  
Validation Data ◽  
Data Set ◽  
Wide Range ◽  
Do Concentration

A regression model integrating data pre-processing and transformation, input selection techniques and a data-driven statistical model, facilitated accurate 7 day ahead time series forecasting of selected water quality parameters. A core feature of the modelling approach is a novel recursive input–output algorithm. The herein described model development procedure was applied to the case of a 7 day ahead dissolved oxygen (DO) concentration forecast for the upper hypolimnion of Advancetown Lake, Queensland, Australia. The DO was predicted with an R2 > 0.8 and a normalised root mean squared error of 14.9% on a validation data set by using 10 inputs related to water temperature or pH. A key feature of the model is that it can handle nonlinear correlations, which was essential for this environmental forecasting problem. The pre-processing of the data revealed some relevant inputs that had only 6 days' lag, and as a consequence, those predictors were in-turn forecasted 1 day ahead using the same procedure. In this way, the targeted prediction horizon (i.e. 7 days) was preserved. The implemented approach can be applied to a wide range of time-series forecasting problems in the complex hydro-environment research area. The reliable DO forecasting tool can be used by reservoir operators to achieve more proactive and reliable water treatment management.

An Efficient Time Series Forecasting Method Exploiting Fuzziness and Turbulences in Data

2017 ◽  
Vol 6 (4) ◽  
pp. 83-98 ◽  
Author(s):  
Prateek Pandey ◽  
Shishir Kumar ◽  
Sandeep Shrivastava
Keyword(s):  
Time Series ◽  
Performance Comparison ◽  
Time Series Forecasting ◽  
Fuzzy Time Series ◽  
Time Series Models ◽  
Data Set ◽  
Common Trend ◽  
Proposed Model ◽  
Forecasting Method ◽  
High Degree

In recent years, there has been a growing interest in Time Series forecasting. A number of time series forecasting methods have been proposed by various researchers. However, a common trend found in these methods is that they all underperform on a data set that exhibit uneven ups and downs (turbulences). In this paper, a new method based on fuzzy time-series (henceforth FTS) to forecast on the fundament of turbulences in the data set is proposed. The results show that the turbulence based fuzzy time series forecasting is effective, especially, when the available data indicate a high degree of instability. A few benchmark FTS methods are identified from the literature, their limitations and gaps are discussed and it is observed that the proposed method successfully overcome their deficiencies to produce better results. In order to validate the proposed model, a performance comparison with various conventional time series models is also presented.

scholarly journals Mountain permafrost degradation documented through a network of permanent electrical resistivity tomography sites

2018 ◽  
Author(s):  
Coline Mollaret ◽  
Christin Hilbich ◽  
Cécile Pellet ◽  
Adrian Flores-Orozco ◽  
Reynald Delaloye ◽  
...  
Keyword(s):  
Time Series ◽  
Electrical Resistivity ◽  
Electrical Resistivity Tomography ◽  
Permafrost Degradation ◽  
Data Set ◽  
Resistivity Tomography ◽  
Wide Range ◽  
Mountain Permafrost ◽  
Ice Water

Abstract. Mountain permafrost is sensitive to climate change and is expected to gradually degrade in response to the ongoing atmospheric warming trend. Long-term monitoring the permafrost thermal state is a key task, but it is problematic where temperatures are close to 0 °C. The energy exchange is indeed often dominantly related to latent heat effects associated with phase change (ice/water), rather than ground warming or cooling. Consequently, it is difficult to detect significant spatio-temporal variations of ground properties (e.g. ice-water ratio) that occur during the freezing/thawing process with point scale temperature monitoring alone. Hence, electrical methods have become popular in permafrost investigations as the resistivities of ice and water differ by several orders of magnitude, theoretically allowing a clear distinction between frozen and unfrozen ground. In this study we present an assessment of mountain permafrost evolution using long-term electrical resistivity tomography monitoring (ERTM) from a network of permanent sites in the Central Alps. The time series consist of more than 1000 data sets from six sites, where resistivities have been measured on a regular basis for up to twenty years. We identify systematic sources of error and apply automatic filtering procedures during data processing. In order to constrain the interpretation of the results, we analyse inversion results and long-term resistivity changes in comparison with existing borehole temperature time series. Our results show that the resistivity data set provides the most valuable insights at the melting point. A prominent permafrost degradation trend is evident for the longest time series (19 years), but also detectable for shorter time series (about a decade) at most sites. In spite of the wide range of morphological, climatological and geological differences between the sites, the observed inter-annual resistivity changes and long-term tendencies are similar for all sites of the network.

scholarly journals Analysing Sensitive Data from Dynamically-Generated Overlapping Contingency Tables

2020 ◽  
Vol 36 (2) ◽  
pp. 275-296
Author(s):  
Joshua J. Bon ◽  
Bernard Baffour ◽  
Melanie Spallek ◽  
Michele Haynes
Keyword(s):  
Linear Models ◽  
Contingency Tables ◽  
Sensitive Data ◽  
Data Set ◽  
Administrative Records ◽  
Cell Counts ◽  
Wide Range ◽  
Australian Census ◽  
Australian Bureau Of Statistics ◽  
Log Linear

AbstractContingency tables provide a convenient format to publish summary data from confidential survey and administrative records that capture a wide range of social and economic information. By their nature, contingency tables enable aggregation of potentially sensitive data, limiting disclosure of identifying information. Furthermore, censoring or perturbation can be used to desensitise low cell counts when they arise. However, access to detailed cross-classified tables for research is often restricted by data custodians when too many censored or perturbed cells are required to preserve privacy. In this article, we describe a framework for selecting and combining log-linear models when accessible data is restricted to overlapping marginal contingency tables. The approach is demonstrated through application to housing transition data from the Australian Census Longitudinal Data set provided by the Australian Bureau of Statistics.

scholarly journals Electrical Insulator Fault Forecasting Based on a Wavelet Neuro-Fuzzy System

Energies ◽  
2020 ◽  
Vol 13 (2) ◽  
pp. 484 ◽  
Author(s):  
Stéfano Frizzo Stefenon ◽  
Roberto Zanetti Freire ◽  
Leandro dos Santos Coelho ◽  
Luiz Henrique Meyer ◽  
Rafael Bartnik Grebogi ◽  
...  
Keyword(s):  
Time Series ◽  
Fuzzy System ◽  
Time Series Forecasting ◽  
Subtractive Clustering ◽  
Anfis Model ◽  
Data Set ◽  
Inference System ◽  
Electrical Insulator ◽  
Fuzzy C Means ◽  
Neuro Fuzzy

The surface contamination of electrical insulators can increase the electrical conductivity of these components, which may lead to faults in the electrical power system. During inspections, ultrasound equipment is employed to detect defective insulators or those that may cause failures within a certain period. Assuming that the signal collected by the ultrasound device can be processed and used for both the detection of defective insulators and prediction of failures, this study starts by presenting an experimental procedure considering a contaminated insulator removed from the distribution line for data acquisition. Based on the obtained data set, an offline time series forecasting approach with an Adaptive Neuro-Fuzzy Inference System (ANFIS) was conducted. To improve the time series forecasting performance and to reduce the noise, Wavelet Packets Transform (WPT) was associated to the ANFIS model. Once the ANFIS model associated with WPT has distinct parameters to be adjusted, a complete evaluation concerning different model configurations was conducted. In this case, three inference system structures were evaluated: grid partition, fuzzy c-means clustering, and subtractive clustering. A performance analysis focusing on computational effort and the coefficient of determination provided additional parameter configurations for the model. Taking into account both parametrical and statistical analysis, the Wavelet Neuro-Fuzzy System with fuzzy c-means showed that it is possible to achieve impressive accuracy, even when compared to classical approaches, in the prediction of electrical insulators conditions.

scholarly journals ITERATIONS OF DEPENDENT RANDOM MAPS AND EXOGENEITY IN NONLINEAR DYNAMICS

2021 ◽  
pp. 1-38
Author(s):  
Zinsou Max Debaly ◽  
Lionel Truquet
Keyword(s):  
Time Series ◽  
Nonlinear Models ◽  
Functional Dependence ◽  
National Academy Of Sciences ◽  
Random Maps ◽  
Dependence Measure ◽  
Binary Choice Models ◽  
Wide Range ◽  
Categorical Time Series ◽  
Academy Of Sciences

Abstract We discuss the existence and uniqueness of stationary and ergodic nonlinear autoregressive processes when exogenous regressors are incorporated into the dynamic. To this end, we consider the convergence of the backward iterations of dependent random maps. In particular, we give a new result when the classical condition of contraction on average is replaced with a contraction in conditional expectation. Under some conditions, we also discuss the dependence properties of these processes using the functional dependence measure of Wu (2005, Proceedings of the National Academy of Sciences 102, 14150–14154) that delivers a central limit theorem giving a wide range of applications. Our results are illustrated with conditional heteroscedastic autoregressive nonlinear models, Generalized AutoRegressive Conditional Heteroskedasticity (GARCH) processes, count time series, binary choice models, and categorical time series for which we provide many extensions of existing results.

scholarly journals An Empirical Study of Error Evaluation in Trend and Seasonal Time Series Forecasting Based on SSA

2018 ◽  
pp. 945-960
Author(s):  
Winita Sulandari ◽  
Subanar Subanar ◽  
Suhartono Suhartono ◽  
Herni Utami ◽  
Muhammad Hisyam Lee
Keyword(s):  
Time Series ◽  
Numerical Study ◽  
Singular Spectrum Analysis ◽  
Real Data ◽  
Time Series Forecasting ◽  
Percentage Error ◽  
Error Evaluation ◽  
Data Set ◽  
Seasonal Time Series ◽  
Deterministic Function

SSA (Singular Spectrum Analysis) starts to become a popular method in decomposing time series into some separable and interpretable series. This study provides an error evaluation in the SSA-based model for trend and multiple seasonal time series forecasting. This error evaluation is obtained by means of a numerical study on the mean square error of the estimators and mean absolute percentage error of the forecast values. Four distinct types of data generating processes (DGP) with varying sample sizes are considered in this experimental study. The parameters are estimated from the component series of SSA. Each DGP is decomposed into trend, periodic and irregular components. All these components except the irregular one are fitted by appropriate deterministic function separately. Based on the numerical simulation results, the estimated parameters are closer to the true values as the sample size increases. As the illustrative example of the real data set implementation, we used the monthly atmospheric concentrations of CO2 from Moana Loa observatory for period January 1959 to June 1972. The proposed method produces better forecast values than the results of SSA-LRF (Linear Recurrent Formula) and TLSAR (Two Level Seasonal Autoregressive). The results encourage the improvement in the time series modeling on the more complex pattern.

scholarly journals NDACC harmonized formaldehyde time-series from 21 FTIR stations covering a wide range of column abundances

2018 ◽  
Author(s):  
Corinne Vigouroux ◽  
Carlos Augusto Bauer Aquino ◽  
Maïté Bauwens ◽  
Cornelis Becker ◽  
Thomas Blumenstock ◽  
...  
Keyword(s):  
Time Series ◽  
Transport Model ◽  
Limit Of Detection ◽  
Atmospheric Composition ◽  
Data Set ◽  
Satellite Validation ◽  
Spatial Coverage ◽  
Combining Data ◽  
Wide Range

Abstract. Among the more than twenty ground-based FTIR (Fourier Transform infrared) stations currently operating around the globe, only a few have provided formaldehyde (HCHO) total columns time-series until now. Although several independent studies have shown that the FTIR measurements can provide accurate and precise formaldehyde total columns, the spatial coverage has not been optimal for providing good diagnostics for satellite or model validation. Furthermore, these past studies used different retrieval settings, and biases as large as 50 % can be observed in the HCHO total columns depending on these retrieval choices, which is also a weakness for validation studies combining data from different ground-based stations. For the present work, the HCHO retrieval settings have been optimized based on experience gained from the past studies and have been applied consistently at the 21 participating stations, most of them are either part of the Network for the Detection of Atmospheric Composition Change (NDACC), or under consideration for membership. We provide the harmonized settings and a characterization of the HCHO FTIR products. Depending on the station, the systematic and random uncertainties of an individual HCHO total column measurement lie between 11 and 31 %; and between 1 and 11 × 1014  molec/cm2, respectively, with median values among all stations of 14 % and 2.6 × 1014 molec/cm2. This unprecedented harmonized formaldehyde data set from 21 ground-based FTIR stations is presented and its comparison to a global chemistry transport model shows its consistency, in absolute values as well as in seasonal cycles. The network covers very different concentration levels of formaldehyde, from very clean levels at the limit of detection (few 1013 molec/cm2) to highly polluted levels (7 × 1016 molec/cm2). Because the measurements can be made at any time during daylight, the diurnal cycle can be observed and is found to be significant at many stations. These HCHO time-series, some of them starting in the 1990's, are crucial for past and present satellite validation, and will be extended in the coming years for the next generation of satellite missions.

scholarly journals Time series analysis of three centuries of childbearing and fertility process in Finland

1992 ◽  
pp. 44-67 ◽  
Author(s):  
Nabil M. El-Khorazaty
Keyword(s):  
Twentieth Century ◽  
Time Series ◽  
Eighteenth Century ◽  
Time Series Analysis ◽  
Time Series Data ◽  
Time Series Forecasting ◽  
Series Data ◽  
Fertility Rates ◽  
First Birth ◽  
Data Set

A new time series data set of childbearing and fertility-inhibiting indices for Finland since 1722 is constructed. Calculation of these macro-level indices is accomplished by the application of new demographic and statistical methodologies, which require only knowledge of age-specific fertility rates, available for Finland since 1776, and the Box-Jenkins time series forecasting technique. The results depict that Finland passed through various childbearing patterns. These patterns are characterized by increasing ages at first and last birth in the eighteenth century to stabilization in the following century at high levels. Since the beginning of the twentieth century, ages at last birth declined dramatically while ages at first birth first increased, then declined in the 1940s and stayed at that low level later on. Increases in both indices have been witnessed since the mid-1970s.

Sign in / Sign up

Export Citation Format

Share Document