scholarly journals Analysis of time series by the example of registration of variations in the gravitational field

2021 ◽  
Vol 43 (4) ◽  
pp. 76-90
Author(s):  
R.Z. Burtiev ◽  
Yu.V. Semenova ◽  
V.T. Kiriyak ◽  
E.V. Sidorenko ◽  
S.V. Troyan ◽  
...  
Keyword(s):  
Time Series ◽  
Statistical Data ◽  
Time Series Model ◽  
Statistical Dependence ◽  
Data Series ◽  
Time Series Models ◽  
Geophysical Processes ◽  
Gravimetric Data ◽  
Predicted Values

In this work, a time series model is used to study the structure of gravimetric data series to identify patterns in the change in the levels of the series and build its model in order to predict and study the relationships between the levels of gravimetric data. Observations of the activity of geophysical processes showed that the periods of variations in geophysical processes are scattered chaotically on the time axis. According to their schedule, it is impossible to definitely speak about the regularity in the duration of the periods of variations, and in the alternation of periods of seismic calm with a period of high seismic activity. The impetus for this study was the desire to analyze the structure of a number of formal methods to search for statistical patterns in the variations of geophysical parameters over time. Time series models were used to study the dynamics of geophysical events. Forecasting was carried out using the SPSS 20 package and EXCEL 2016. The accuracy of the forecast is indicated by the comparison of the forecast series with the actual data. The predicted values of the gravimetric data are within the confidence intervals. If you start forecasting too early, the forecast may differ from the forecast based on all statistical data. If the data shows seasonal trends, it is recommended to start forecasting from the date before the last point of the statistical data. Spatial and time series models can be used to study the dynamics of geophysical events. A spatial model describes a set of geophysical parameters at a given point in time. A time series is a series of regular observations of a certain parameter at successive points in time or at intervals of time. In this work, the time series model is used: to identify the statistical relationship between the frequency and depth of occurrence of earthquakes, as well as to identify the statistical dependence of these data on gravimetric variations; determination of patterns in the change in the levels of the series and the construction of its model in order to predict and study the relationships between geophysical phenomena.

scholarly journals Characterization of Export Regimes in Concentration–Discharge Plots via an Advanced Time-Series Model and Event-Based Sampling Strategies

Water ◽  
2021 ◽  
Vol 13 (13) ◽  
pp. 1723
Author(s):  
Ana Gonzalez-Nicolas ◽  
Marc Schwientek ◽  
Michael Sinsbeck ◽  
Wolfgang Nowak
Keyword(s):  
Time Series ◽  
Linear Regression ◽  
Time Series Model ◽  
Data Series ◽  
Additional Parameter ◽  
Sampling Strategies ◽  
Discharge Rates ◽  
Regression Approach ◽  
Event Based ◽  
Stochastic Time Series

Currently, the export regime of a catchment is often characterized by the relationship between compound concentration and discharge in the catchment outlet or, more specifically, by the regression slope in log-concentrations versus log-discharge plots. However, the scattered points in these plots usually do not follow a plain linear regression representation because of different processes (e.g., hysteresis effects). This work proposes a simple stochastic time-series model for simulating compound concentrations in a river based on river discharge. Our model has an explicit transition parameter that can morph the model between chemostatic behavior and chemodynamic behavior. As opposed to the typically used linear regression approach, our model has an additional parameter to account for hysteresis by including correlation over time. We demonstrate the advantages of our model using a high-frequency data series of nitrate concentrations collected with in situ analyzers in a catchment in Germany. Furthermore, we identify event-based optimal scheduling rules for sampling strategies. Overall, our results show that (i) our model is much more robust for estimating the export regime than the usually used regression approach, and (ii) sampling strategies based on extreme events (including both high and low discharge rates) are key to reducing the prediction uncertainty of the catchment behavior. Thus, the results of this study can help characterize the export regime of a catchment and manage water pollution in rivers at lower monitoring costs.

Time Series Model Based Earning Forecasting

2013 ◽  
Vol 791-793 ◽  
pp. 2147-2150
Author(s):  
Xiang Rong Jiang ◽  
Ying Ying Cui
Keyword(s):  
Time Series ◽  
Empirical Study ◽  
Relative Stability ◽  
Listed Companies ◽  
Time Series Model ◽  
New Method ◽  
Time Series Models ◽  
Seasonal Patterns ◽  
Model Based ◽  
Over Time

We propose a procedure to forecast earning of listed companies. It is a modification of method developed for forecasting series with stable seasonal patterns. The new method is motivated by the observations that seasonal patterns, which may be evolving over time and remain relative stability, arise in finance market. The method can be applied to forecast individual observations as well as the end-of-season totals. Empirical study will be conducted with data from finance market to evaluate the performance of the proposed method. The new method is proved more effective than traditional time series models.

Criteria for Recognition of Wheel Skid of Trains Based on Time Series Analysis

2013 ◽  
Vol 440 ◽  
pp. 237-242
Author(s):  
Jun Bin Peng ◽  
Xiao Yi Hu ◽  
Yong Jun Liu
Keyword(s):  
Time Series ◽  
Time Series Analysis ◽  
Characteristic Equation ◽  
Critical Value ◽  
Time Series Model ◽  
Data Series ◽  
Velocity Difference ◽  
Series Analysis ◽  
Greens Function ◽  
Order Determination

Current criteria to judge wheel skid of trains such as velocity difference often cannot recognize wheel skid timely and have no uniform critical value for different trains or railway lines. Aiming at the disadvantages, new criteria based on time series analysis are proposed. With appropriate method of order determination and parameter estimation, AR time series model is established for the data series of velocity difference. Then, Greens function and characteristic equation are constructed with the parameters of the model to determine wheel skid by the convergence state of Greens function or the value of characteristic equations roots. Simulation result shows that the two criteria based on time series model can recognize wheel skid earlier than velocity difference. Moreover, the roots of characteristic equation can also be used as a criterion with a uniform critical value under different application conditions.

scholarly journals ANALYSIS OF THE PRINCIPAL CONSTITUENTS OF SOLID EARTH TIDES ESTIMATED WITH GRAVIMETRIC AND GNSS DATA IN MANAUS AND BRASÍLIA

2019 ◽  
Vol 37 (1) ◽  
pp. 11
Author(s):  
Mário A. de Abreu ◽  
Giuliano S. Marotta ◽  
Lavoisiane Ferreira ◽  
Denizar Blitzkow ◽  
Ana C. O. C. de Matos ◽  
...  
Keyword(s):  
Time Series ◽  
Solid Earth ◽  
Earth Tide ◽  
Earth Tides ◽  
Data Series ◽  
Long Period ◽  
Solid Earth Tides ◽  
Gravimetric Data ◽  
Time Required ◽  
Solid Earth Tide

ABSTRACT. Solid Earth tide is the periodic displacement due to the tidal force. This effect is present in all geodesic and geophysical observations and should be eliminated when high accuracy surveying is required. It is necessary to determine the amplitudes and phases of the harmonic constituents to estimate the terrestrial tide effect magnitude. This article presents a methodology for estimating and analyzing the amplitudes and phases of the solid Earth tide principal constituents from gravimetric/GNSS observations. The methodology was applied to data collected in the Manaus/AM and Brasília/DF stations, Brazil, to determine the amplitude and phase values for the long period, monthly, diurnal and semidiurnal constituents, besides determining the time required for the convergence of the estimated constituent values. The estimated amplitude and phase values, using gravimetric data, converged between the 2nd and 6th months of the time series. For the positioning observations, the constituents values converged between the 2nd and 17th month of the data series, except for the long period constituent, which requires a longer time series to obtain satisfactory values for both methods. The results show that the solid Earth tide constituents were better estimated by the gravimetric data compared to the positioning data considering the series analyzed.Keywords: gravimetry, GNSS, solid Earth tide, tidal constituents.RESUMO. Maré terrestre é o deslocamento periódico decorrente da força de maré. Este é um efeito que deve ser eliminado quando se deseja realizar levantamentos nos quais é necessária alta acurácia tanto em observações geodésicas quanto geofísicas. Para estimar o efeito de maré terrestre deve-se determinar as amplitudes e fases de suas componentes harmônicas. Este artigo apresenta uma metodologia para a estimativa das amplitudes e fases das principais componentes de maré terrestre, a partir de observações gravimétricas/GNSS. A metodologia foi aplicada a dados coletados em estações instaladas em Manaus/AM e Brasília/DF, Brasil, resultando na determinação dos valores de amplitude e fase para componentes de longo período, mensais, diurnas e semidiurnas, além da análise da convergência dos valores estimados para estas componentes. As amplitudes e fases calculadas, utilizando dados gravimétricos, convergiram entre o 2_ e o 6_ mês analisados, enquanto para os dados de posicionamento a convergência ocorreu entre o 2_ e o 17_ mês observado, com exceção da componente de longo período, que não pôde ser determinada em ambos os métodos. Para o período analisado, as componentes de maré terrestre foram melhor estimadas utilizando dados gravimétricos, se comparadas aos resultados obtidos com dados de posicionamento.Palavras-chave: gravimetria, GNSS, maré terrestre, componentes de maré.

IMPACT OF VACCINATION ON THE COVID-19 PANDEMIC: BIBLIOMETRIC ANALYSIS AND CROSS COUNTRY FORECASTING BY FOURIER SERIES

2021 ◽  
Vol 74 (10) ◽  
pp. 2359-2367
Author(s):  
Olha V. Kuzmenko ◽  
Vladyslav A. Smiianov ◽  
Lesia A. Rudenko ◽  
Mariia O. Kashcha ◽  
Tetyana A. Vasilyeva ◽  
...  
Keyword(s):  
Time Series ◽  
Incidence Rate ◽  
United States Of America ◽  
Statistical Data ◽  
Self Organization ◽  
Disease Course ◽  
Cross Country ◽  
Predicted Values ◽  
Cyclic Models ◽  
The Impact

The aim: Is to build a forecast of the COVID-19 disease course, considering the vaccination of the population from particular countries. Materials and methods: Based on the analysis of statistical data, the article deals with the topical issue of the impact made by vaccination on the prevention of the COVID-19 pandemic. The time series, showing the dynamics of changes in the number of infected in Chile, Latvia, Japan, Israel, Australia, Finland, India, United States of America, New Zealand, Czech Republic, Venezuela, Poland, Ukraine, Brazil, Georgia for the period 07.08. 2020–09.09.2021, are analyzed. Trend-cyclic models of time series are obtained using fast Fourier transform. The predicted values of the COVID-19 incidence rate for different countries in the period from September 10, 2021 to February 2, 2022 were calculated using the constructed models. Results and conclusions: The results of the study show that vaccination of the population is one of the most effective methods to prevent the COVID-19 pandemic. The proposed method of modeling the dynamics of the incidence rate based on statistical data can be used to build further predictions of the incidence rate dynamics. The study of behavioral aspects of trust in vaccination is proposed to be conducted within the theory regarding the self-organization of complex systems.

STATISTICAL ANALYSIS AND PREDICTIVE MODELING OF EXTERNAL AND INTERNAL REINSURANCE MARKET STRUCTURES

2020 ◽  
Vol 11 (3) ◽  
pp. 167-175
Author(s):  
Vladimir D. Bogatyrev ◽  
Elena P. Rostova
Keyword(s):  
Time Series ◽  
Statistical Analysis ◽  
Predictive Modeling ◽  
Statistical Data ◽  
Time Series Models ◽  
Retrospective Data ◽  
Market Structures ◽  
Advantageous Position ◽  
The Russian Federation ◽  
Reinsurance Market

In the article the authors examine the reinsurance market of the Russian Federation; consider reinsurance premiums for incoming and outgoing external and internal reinsurance; based on statistical data, the authors made a conclusion about the externally oriented ceding market in the period 2013–2019. The authors present the structure of the reinsurance market by major companies and identify the main players in the market of incoming and outgoing reinsurance; consider the ratio of external and internal premiums for incoming and outgoing reinsurance. The authors complied time series models of reinsurance premiums for incoming and outgoing external and internal reinsurance based on retrospective data for 2016–2019. All functions are increasing, which indicates the positive dynamics of the studied market and the possibilities for further expansion and development. Based on the models, forecast values are calculated that allow to draw conclusions about the development and structure of the Russian reinsurance market. The reasons for the dominance of external reinsurance over internal in relation to outgoing contracts, consisting in the retroceding of risks to large international reinsurance companies, are identified, that occupy the most advantageous position in this market in comparison with domestic reinsurers. 

TIME-SERIES MODEL WITH PERIODIC STOCHASTIC REGIME SWITCHING

2000 ◽  
Vol 4 (4) ◽  
pp. 467-486 ◽  
Author(s):  
Eric Ghysels
Keyword(s):  
Time Series ◽  
Regime Switching ◽  
Transition Probabilities ◽  
Time Series Model ◽  
Time Series Models ◽  
Seasonal Cycles ◽  
Arma Processes ◽  
Regime Switching Models ◽  
Switching Models ◽  
Stochastic Properties

We present a class of stochastic regime-switching models. The time-series models may have periodic transition probabilities and the drifts may be seasonal. In the latter case, the model exhibits seasonal dummy variation that may change with the regime. The processes entail nontrivial interactions between so-called business and seasonal cycles. We discuss the stochastic properties as well as their relationship with periodic ARMA processes. Estimation and testing are also discussed in detail.

scholarly journals Observation of Time Series Model

2018 ◽  
Vol 33 (01) ◽  
Author(s):  
Achal Lama ◽  
K. N. Singh ◽  
Vishal Gurung ◽  
Ravindra Singh Sekhawat ◽  
H. S. Roy
Keyword(s):  
Time Series ◽  
Linear Model ◽  
Linear Time ◽  
Time Series Model ◽  
Time Series Models ◽  
Arima Models ◽  
Non Linear ◽  
Basic Concepts

In this paper an attempt has been made to highlight the basic concepts of time series models. The linear time series models such as AR, MA and ARIMA models are dealt in brief. Non-linear model such as GARCH have also been introduced along with its some unique properties. Finally, the paper is concluded with emphasis on the use of these models.

Fuzzy Multiple-Periods Time-Series Model Based on GSP and AR for Forecasting Gold Price

2011 ◽  
Vol 211-212 ◽  
pp. 1124-1128 ◽  
Author(s):  
Jing Wei Liu ◽  
Ching Hsue Cheng ◽  
Chung Ho Su ◽  
Ming Chien Tsai
Keyword(s):  
Time Series ◽  
Fuzzy Rule ◽  
Time Series Model ◽  
Gold Price ◽  
Fuzzy Time Series ◽  
Time Series Models ◽  
Fuzzy Relations ◽  
Previous Time ◽  
Proposed Model ◽  
Comparison Results

In the recent years, traditional time series model has been widely researched. The previous time series methods can predict future problems based on historical data, but have a problem that determines subjectively the length of intervals. Song and Chissom[6-7]proposed the fuzzy time series to solve the problem of traditional time series methods. So far, many researchers have proposed different fuzzy time series models to deal with uncertain and vague data. Besides, the consideration of a forecasting stage only discusses the relations for previous period and next period. In addition, a shortcoming of previous time series models didn’t consider appropriately the weights of fuzzy relations. This study builds fuzzy rule based on association rules and compute the cardinality of each fuzzy relation. Then, calculating the weights of fuzzy relations solve above problems. Moreover, the proposed method is able to build the multiple periods fuzzy rules based on concept of large itemsets of Apriori. To verify the proposed model, the gold price datasets is employed as experimental datasets. This study compares the forecasting accuracy of proposed model with other methods, and the comparison results show that the proposed method has better performance than other methods.

scholarly journals Prediction of Indian Monsoon Rainfall by Interval based Simplified High Order Fuzzy Time Series Model

2020 ◽  
Vol 9 (4) ◽  
pp. 782-785
Keyword(s):  
Time Series ◽  
Monsoon Rainfall ◽  
Time Series Model ◽  
Fuzzy Time Series ◽  
Time Data ◽  
Rainfall Forecasting ◽  
Rainfall Prediction ◽  
Soft Computing Techniques ◽  
Predicted Values ◽  
High Degree

Rain is of uttermost importance for agriculture based economies. Most of the Asian countries, India in particular largely depend on a good rainfall. The prediction of rainfall will not only help government to make better future policies but also farmers and agro based companies can make better future management. Rainfall forecasting involves high degree of uncertainty and for such conditions fuzzy time series and other soft computing techniques are best to deal with. The utility of a forecasting method lies with the accuracy with the predicted values. In this paper rainfall prediction by fuzzy time series model is proposed in which two difference values of the interval corresponding to the fuzzified forecasted value is proposed. This model is tested on real time data of average monsoon rainfall in India. The predicted values are compared with Chen model. The results show that the proposed model have less error compared to Chen’s model.

Sign in / Sign up

Export Citation Format

Share Document