This article focuses on the critical importance of demand estimates for effective planning and decision-making in the railway freight transportation industry. Various departments within transportation companies, including marketing, production, distribution, and finance departments, heavily rely on accurate demand forecasts to make informed decisions. Forecasting demand is a crucial aspect of managing business processes, and the methods for doing this can vary across different industries. The ultimate goal remains consistent - to obtain precise predictions of future demand by analyzing historical data and current environmental factors. In the context of transportation services, accurate demand forecasting is essential for successful operational planning and management of functional areas such as transportation operations, marketing, and finance. The current case study specifically examines the National Company Kazakhstan Temir Zholy (KTZ), a transport and logistics holding engaged in rail transportation in Kazakhstan. KTZ’s main sources of income are related to freight transportation. The volume of cargo transportation (in tons) and the freight turnover play a significant role in assessing demand and forecasting future revenues from freight traffic. Different techniques for demand forecasting are explored, including qualitative and quantitative methods. Qualitative methods rely on judgments and opinions, while quantitative methods utilize historical data or identify causal relationships between variables. Overall, the present study highlights the critical role of demand forecasting in the railway freight transportation industry and its impact on efficient planning and decision-making processes.
Recently, time series forecasting modelling in the Con‐ sumer Price Index (CPI) has attracted the attention of the scientific community. Several research projects have tackled the problem of CPI prediction for their countries using statistical learning, machine learning and deep neural networks. The most popular approach to CPI in several countries is the Autoregressive Integrated Mov‐ ing Average (ARIMA) due to the nature of the data. This paper addresses the Cuban CPI forecasting problem using Transformer with attention model over univariate dataset. The fine tuning of the lag parameter shows that Cuban CPI has better performance with small lag and that the best result was in 𝑝 = 1. Finally, the comparative results between ARIMA and our proposal show that the Transformer with attention has a very high performance despite having a small data set.
The presence of an outlier at the starting point of a univariate time series negatively influences the forecasting accuracy. The starting outlier is effectively removed only by making it equal to the second time point value. The forecasting accuracy is significantly improved after the removal. The favorable impact of the starting outlier removal on the time series forecasting accuracy is strong. It is the least favorable for time series with exponential rising. In the worst case of a time series, on average only 7 % to 11 % forecasts after the starting outlier removal are worse than they would be without the removal.
PL
Wartość odstająca w punkcie początkowym jednowymiarowego szeregu czasowego negatywnie wpływa na dokładność prognozowania. W ramach przeprowadzonych badań dokonano analizy wpływu usunięcia wartości odstającej poprzez zrównanie jej z wartością drugiego punktu cza-sowego. Uzyskane wyniki wskazują, że przyjęta metoda znacznie poprawia dokładność progno-zowania dla większości szeregów czasowych. Jednak w przypadku szeregów czasowych z wykładniczym wzrostem, metoda okazała się mniej skuteczna. Minimalny wzrost dokładności prognozowania wynosił w tym przypadku od 7 % do 11 %.
A fast-and-flexible method of ARIMA model optimal selection is suggested for univariate time series forecasting. The method allows obtaining as-highly-accurate-as-possible forecasts auto-matically. It is based on effectively finding lags by the autocorrelation function of a detrended time series, where the best-fitting polynomial trend is subtracted from the time series. The fore-casting quality criteria are the root-mean-square error (RMSE) and the maximum absolute error (MaxAE) allowing to register information about the average inaccuracy and worst outlier. Thus, the ARIMA model optimal selection is performed by simultaneously minimizing RMSE and Max-AE, whereupon the minimum defines the best model. Otherwise, if the minimum does not exist, a combination of minimal-RMSE and minimal-MaxAE ARIMA models is used.
PL
W pracy zaproponowano szybką i elastyczną metodę optymalnego doboru modelu ARIMA na potrzeby prognozowania szeregów czasowych z jedną zmienną. Metoda pozwala na uzyskanie możliwie najdokładniejszych prognoz, opierając się na skutecznym znajdowaniu opóźnień. Po-szukiwanie opóźnień realizowane jest za pomocą funkcji autokorelacji szeregu czasowego bez trendu, w którym najlepiej dopasowany trend wielomianowy jest odejmowany od szeregu cza-sowego. Za kryteria jakości prognozowania przyjęto średni błąd kwadratowy (RMSE) i maksy-malny błąd bezwzględny (MaxAE), które pozwoliły na rejestrację informacji o średniej i maksymalnej niedokładności. Optymalny dobór modelu ARIMA odbywa się poprzez jednoczesną minimalizację RMSE i MaxAE, dla której wartość minimalna określa najlepszy model. W przeciw-nym razie, jeśli minimum nie istnieje, używana jest kombinacja modeli ARIMA z minimalnym RMSE i minimalnym MaxAE.
Real-time prediction of Earth Orientation Parameters is necessary for many advanced geodetic and astronomical tasks including positioning and navigation on Earth and in space. Earth Rotation Parameters (ERP) are a subset of EOP, consisting of coordinates of the Earth’s pole (PMx, PMy) and UT1-UTC (or Length of Day - LOD). This paper presents the ultra-short-term (up to 15 days into the future) and short-term (up to 30 days into the future) ERP prediction using geostatistical method of ordinary kriging and autoregressive integrated moving average (ARIMA) model. This contribution uses rapid GNSS products EOP 14 12h from IGS, CODE and GFZ and also IERS final products - IERS EOP 14 C04 12h (IAU2000A). The results indicate that the accuracy of ARIMA prediction for each ERP is better for ultra-short prediction. The maximum differences between methods for first few days of 15-day predictions are around 0.32 mas (PMx), 0.23 mas (PMy) and 0.004 ms (LOD) in favour of ARIMA model. The maximum differences of Mean Absolute Prediction Errors (MAPEs) on the last few days of 30-day predictions are 1.91 mas (PMx), 0.30 mas (PMy) and 0.026 ms (LOD) with advantage to kriging method. For all ERPs the differences of MAPEs for time series from various analysis centres are not significant and vary up to maximum value of around 0.05 mas (PMx), 0.04 mas (PMy) and 0.005 ms (LOD).
6
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
Forecasting rainfall time series is of great significance for hydrologists and geoscientists. Thus, this study represents a contribution to understanding the impact of the fractal time series variety on forecasting model performance. Multiple fractal series were generated via p-model and used for modeling. Subsequently, the forecasting was delivered based on existing observed monthly rainfall data (three stations in the UK, from 1865 to 2002) through five forecasting models. Finally, the association between series fractality and models’ performance was examined. The results indicated that the forecasting based on the mono-fractal series resulted in the most reliable results (R2=1 and RMSE less than 0.02). In the case of multifractal series, modeling based on series with the right side of the asymmetric curve of the multifractal spectrum presented series with the lowest RMSE (0.96) and highest R2 (0.99) (desirable performance). In contrast, the forecasting based on series with the left side of the asymmetric curve of the multifractal spectrum suggested the most unreliable outcomes (R2 range [−0.0007 ~ 0.988] and RMSE range [0.8526 ~ 39.3]). The forecasting based on the symmetric curve of the multifractal spectrum series delivered regular performance. Accordingly, high and low errors are expected from forecasting based on the time series with a left-skewed multifractal spectrum and right-skewed multifractal spectrum (and mono-fractal time series), respectively. Hybrid models were the best options for forecasting mono-fractal and multifractal time series with right side asymmetric and symmetric multifractal spectrum curves. The ARIMA model was suitable to predict multifractal time series with left side asymmetric multifractal spectrum curves.
X-ray computed tomography (CT) can reveal internal, three-dimensional details of objects in a non-destructive way and provide high-resolution, quantitative data in the form of CT numbers. The sensitivity of the CT number to changes in material density means that it may be used to identify lithology changes within cores of sedimentary rocks. The present pilot study confirms the use of Representative Elementary Volume (REV) to quantify inhomogeneity of CT densities of rock constituents of the Boda Claystone Formation. Thirty-two layers, 2 m core length, of this formation were studied. Based on the dominant rock-forming constituent, two rock types could be defined, i.e., clayey siltstone (20 layers) and fine siltstone (12 layers). Eleven of these layers (clayey siltstone and fine siltstone) showed sedimentary features such as, convolute laminations, desiccation cracks, cross-laminations and cracks. The application of the Autoregressive Integrated Moving Averages, Statistical Process Control (ARIMA SPC) method to define Representative Elementary Volume (REV) of CT densities (Hounsfield unit values) affirmed the following results: i) the highest REV values corresponded to the presence of sedimentary structures or high ratios of siltstone constituents (> 60%). ii) the REV average of the clayey siltstone was (5.86 cm3) and (6.54 cm3) of the fine siltstone. iii) normalised REV percentages of the clayey siltstone and fine siltstone, on the scale of the core volume studied were 19.88% and 22.84%; respectively. iv) whenever the corresponding layer did not reveal any sedimentary structure, the normalised REV values would be below 10%. The internal void space in layers with sedimentary features might explain the marked textural heterogeneity and elevated REV values. The drying process of the core sample might also have played a significant role in increasing erroneous pore proportions by volume reducation of clay minerals, particularly within sedimentary structures, where authigenic clay and carbonate cement were presumed to be dominant.
8
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
The ARIMA method, time series analysis technique, was proposed to perform short-term ionospheric Total Electron Content (TEC) forecast and to detect TEC anomalies. The success of the method was tested in two major earthquakes that occurred in India (M 7.7 Bhuj EQ, on Jan 26, 2001) and Turkey (M 7.1 Van EQ, on Oct 23, 2011). For ARIMA analysis, we have taken 18 and 29 days of TEC data with a 2-h temporal resolution and train the model with an accuracy of 5.1 and 2.7–2.9 TECU for India and Turkey EQs, respectively. After training the model and optimizing hyper model parameters, we applied on 8 and 9 days’ time-window to observe anomalies. In Bhuj EQ, the negative anomalies are recorded on Jan 19 and 22, 2001. Similarly, positive anomalies are recorded on Jan 23, 24, and 25, 2001. In Van EQ, we recorded a strong positive anomaly on Oct 21, 2011, and in the consecutive days before the earthquake, some weak negative anomalies have also observed. The results showed that ARIMA has an adequate short-term performance of the ionospheric TEC prediction and anomaly detection of the TEC time series.
This paper summarizes the arguments and counterarguments within the scientific discussion on developing the free-carbon economy in Ukraine. The main purpose of the paper is elaborating the energy efficiency profile of Ukraine to assure the development of the free-carbon economy. To achieve this purpose, the authors carried out an investigation in the following logical sequence. Firstly, the bibliometric analysis of 4674 of the most cited articles indexed by the Scopus database was conducted. The obtained findings indicated that the green economy transformation depended on the main factors such as economic performance, corruption, macroeconomic stability, social welfare, shadow economy etc. As a result, the forecast of the final energy consumption to 2030 was performed. The methodological tool of this research is based on the Autoregressive Integrated Moving Average (ARIMA) model. This study involved data of the Visegrad countries (Poland, the Czech Republic, the Slovak Republic and Hungary) and Ukraine from 2000 to 2018. The base of data is Eurostat, the EU statistical service. Based on the obtained results of analyzing the green economic transformation in the Visegrad countries and Ukraine, the authors intimated the existence of the significant energy-efficient gap in Ukraine compared to the analyzed countries. In reliance on the experience of the Visegrad countries and the forecast results, the authors provided the main recommendations for providing the green transforming in Ukraine. The authors highlighted that the obtained results of this paper were considered to be the base for future investigations considering the influence of endogenous and exogenous factors on developing the free-carbon economy in Ukraine.
PL
W artykule podsumowano argumenty i kontrargumenty w ramach dyskusji naukowej na temat rozwoju gospodarki wolnej od węgla na Ukrainie. Głównym celem artykułu jest opracowanie profilu efektywności energetycznej Ukrainy w celu zapewnienia rozwoju gospodarki niskoemisyjnej. Aby osiągnąć ten cel, autorzy przeprowadzili badanie w następującej logicznej kolejności. Po pierwsze, przeprowadzono analizę bibliometryczną 4674 najczęściej cytowanych artykułów zindeksowanych w bazie Scopus. Uzyskane wyniki wskazywały, że transformacja w kierunku zielonej gospodarki zależy głównie od takich czynników jak wyniki gospodarcze, korupcja, stabilność makroekonomiczna, dobrobyt społeczny, szara strefa itp. Następnie wykonano prognozę zużycia energii końcowej do 2030 roku. Narzędziem metodologicznym tego badania jest model autoregresywnej zintegrowanej średniej ruchomej (ARIMA). W badaniu uwzględniono dane z krajów Grupy Wyszehradzkiej (Polska, Czechy, Słowacja i Węgry) oraz Ukrainy w latach 2000–2018, których źródłem była baza Eurostat. Na podstawie uzyskanych wyników analizy przemian gospodarczych w krajach wyszehradzkich i na Ukrainie autorzy stwierdzili, że na Ukrainie istnieje znaczna luka w efektywności energetycznej w porównaniu z analizowanymi krajami. Opierając się na doświadczeniach krajów wyszehradzkich i prognozowanych wynikach, autorzy przedstawili najważniejsze rekomendacje dotyczące zapewnienia zielonej transformacji na Ukrainie. Autorzy podkreślili, że uzyskane wyniki przedstawione w niniejszym artykule można uznać za podstawę do dalszych badań nad wpływem czynników endogenicznych i egzogenicznych na rozwój gospodarki wolnej od węgla na Ukrainie.
10
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
The objective of this paper is to determine the trend and to estimate the streamflow of the Gökırmak River. The possible trend of the streamflow was forecasted using an autoregressive integrated moving average (ARIMA) model. Time series and trend analyses were performed using monthly streamflow data for the period between 1999 and 2014. Pettitt's change point analysis was employed to detect the time of change for historical streamflow time series. Kendall's tau and Spearman's rho tests were also conducted. The results of the change point analysis determined the change point as 2008. The time series analysis showed that the streamflow of the river had a decreasing trend from the past to the present. Results of the trend analysis forecasted a decreasing trend for the streamflow in the future. The decreasing trend in the streamflow may be related to climate change. This paper provides preliminary knowledge of the streamflow trend for the Gökırmak River.
11
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
W artykule przedstawiono metodykę wielokryterialnej analizy stóp procentowych bezrobocia w wybranych gospodarkach światowych oraz próby przeprowadzenia prognozowania stopy bezrobocia w USA na trzy przyszłe okresy. Badania rozpoczęto od analizy wielowymiarowej zmienności stóp procentowych bezrobocia w wybranych gospodarkach światowych w ujęciu sześciomiesięcznym w latach 2011-2018. Następnie przeprowadzono jej ocenę. Dalszym etapem badania była analiza i ocena szeregu czasowego danych dotyczących stóp procentowych bezrobocia w USA w ujęciu dynamicznym. Następnie zbudowano model prognostyczny ARIMA i wykonano prognozowanie na trzy przyszłe okresy.
EN
The article presents the methodology of multi-criteria analysis of unemployment interest rates in selected world economies, and an attempt to forecast the unemployment rate in the USA for three future periods. The research began with an analysis of the multidimensional volatility of unemployment interest rates in selected world economies on a six-month basis in 2011-2018. It was then assessed. The next stage of the study was the analysis and evaluation of the time series of data on the US unemployment interest rates in dynamic terms. Then, the ARIMA forecast model was built and forecasting for three future periods was performed.
COVID-19 has stamped an indelible mark in the history of humanity as one of the recorded deadly virus that has wiped out millions of lives on planet earth many whose exact cause of death cannot be account for due to lack of knowledge. It has become a household name in every nook and cranny from developed to the underdeveloped nations of the world. Most of the prominent signs of COVID-19 like fever, cough, difficulty in breathing and accessional muscle pain can also resemble those of many other notable diseases thereby making it highly necessary to undergo a diagnostic test to be able to categorically identify COVID-19 patients. The use of medical diagnostic tests can also help determine patients who have recovered from COVID-19. Various studies abound with researchers trying to predict and even forecast the level of damage and disruption of economic activities this may have brought to almost every nation of the world. This research attempts to find out the nature of the spread of the virus using Autoregressive Integrated Moving Average (ARIMA) and Artificial Neural Networks (ANN). The essence is to ascertain the exact model to use in forecasting the future occurrence of the pandemic especially at this stage where the second wave of the pandemic is in view. The study found that both linear and nonlinear predictions models can fit the trend of the virus in Nigeria with ARIMA producing results of over 97% on a 120-day period while ANN produced results of about 98.01% in some states. We conclude that future waves of the virus in addition to other epidemics of this nature can be predicted with high degree of accuracy with ARIMA or ANN.
In recent decades, the airline industry has become very competitive. With the advent of large aircraft in service, unit load devices (ULD) have become an essential ele‐ ment for efficient air transport. They can load a large amount of baggage, cargo or mail using only one unit. Since this results in fewer units to load, saving time and efforts of ground crews and helping to avoid delayed flig‐ hts. However, a deficient loading of the units causes ope‐ rating irregularities, costing the company and contribu‐ ting to the dissatisfaction of the customers. In contrast, an excess load of containers is at the expense of cargo. In this paper we propose an approach to predict the de‐ mand for baggage in order to optimize the management of its ULD flow. Specifically, we build prediction models: ARIMA following the BOX‐JENKINS approach and expo‐ nential smoothing methods, in order to obtain more accu‐ rate forecasts. The approach is tested using the operatio‐ nal data of flight processing and the results are compared with four benchmark method (SES, DES, Holt‐Winters and Naive prediction) using different performance indicators: MAE, MSE, MAPE , WAPE, RMSE, SMPE. The results obtai‐ ned with the exponential smoothing methods surpass the benchmarks by providing more accurate forecasts.
Forecasting and lot-sizing problems are key for a variety of products manufactured in a plant of finite capacity. The plant manager needs to put special emphasis on the way of selecting the right forecasting methods with a higher level of accuracy and to conduct procurement planning based on specific lot-sizing methods and associated rolling horizon. The study is con-ducted using real case data form the Fibertex Personal Care, and has evalu-ated the joint influence of forecasting procedures such as ARIMA, exponen-tial smoothing methods; and deterministic lot-sizing methods such as the Wagner-Whitin method, modified Silver-Meal heuristic to draw insights on the effect of the appropriate method selection on minimization of operational cost. The objective is to explore their joint effect on the cost minimization goal. It is found that a proficient selection process has a considerable impact on performance. The proposed method can help a manager to save substantial operational costs.
The article is devoted to the assessment of the transfer of exchange rates to domestic prices for the products of machine-building enterprises in Ukraine. The study found that the main reason for transferring the dynamics of exchange rates on the prices for the products of machine-building enterprises of Ukraine is a change in production costs for raw materials, resources, and a change in exchange rates. As a model for assessing the degree of transfer of currency rates to the prices of engineering enterprises were chosen the autocorrelation method and the predictive ARIMA model. The ARIMA model allowed detected a time gap between the change in the exchange rate indices and the change in domestic prices for products of Ukrainian machine-building enterprises. It was proposed to take into account in the process of pricing a new factor of influence - "time factor", which takes place in the calculation of prices taking into account the effect of the transfer of exchange rate changes. It was proposed indicators of modified price elasticity coefficients for engineering products depending on the rate of change in exchange rates. The aim of the research is to develop a methodology for modelling and managing the effect of shifting the dynamics of the exchange rates on the prices of the enterprises of machine-building in Ukraine. The main factors that increase the dependence of domestic prices on products of machine-building enterprises from exchange rates are: liberalization of the economy and openness of the machine-building industry for foreign markets; dependence of the raw material and resource base on imported components; increase in the export of machine-building products; weak price differentiation of production of machine-building enterprises.
PL
Artykuł poświęcony jest ocenie transferu kursów walutowych na ceny krajowych produktów przedsiębiorstw budowy maszyn na Ukrainie. Badanie wykazało, że głównym powodem przeniesienia dynamiki kursów wymiany na ceny produktów przedsiębiorstw budowy maszyn na Ukrainie jest zmiana kosztów produkcji surowców, zasobów, zmiana kursów walut. Jako model do oceny stopnia transferu kursów walut do cen przedsiębiorstw inżynieryjnych wybrano metodę autokorelacji i predykcyjny model ARIMA. Model ARIMA pozwolił wykryć lukę czasową między zmianą wskaźników kursu walutowego a zmianą cen krajowych produktów ukraińskich przedsiębiorstw budowy maszyn. Zaproponowano uwzględnienie w procesie wyceny nowego czynnika wpływu - „czynnika czasu”, który ma miejsce przy obliczaniu cen z uwzględnieniem efektu przeniesienia zmian kursu walutowego. Zaproponowano wskaźniki zmodyfikowanych współczynników elastyczności cen dla produktów inżynieryjnych w zależności od tempa zmian kursów wymiany. Celem badań jest opracowanie metodologii modelowania i zarządzania efektem transferu dynamiki kursów walutowych na ceny przedsiębiorstw budowy maszyn na Ukrainie. Głównymi czynnikami zwiększającymi zależność cen krajowych od produktów przedsiębiorstw przemysłu maszynowego od kursów walutowych są: liberalizacja gospodarki i otwartość przemysłu budowy maszyn na rynki zagraniczne; zależność surowców i zasobów od importowanych komponentów; wzrost eksportu produktów do budowy maszyn; słabe zróżnicowanie cenowe produkcji przedsiębiorstw budowlanych.
The paper proposes a robust faults detection and forecasting approach for a centrifugal gas compressor system, the mechanism of this approach used the Kalman filter to estimate and filtering the unmeasured states of the studied system based on signals data of the inputs and the outputs that have been collected experimentally on site. The intelligent faults detection expert system is designed based on the interval type-2 fuzzy logic. The present work is achieved by an important task which is the prediction of the remaining time of the system under study to reach the danger and/or the failure stage based on the Auto-regressive Integrated Moving Average (ARIMA) model, where the objective within the industrial application is to set the maintenance schedules in precisely time. The obtained results prove the performance of the proposed faults diagnosis and detection approach which can be used in several heavy industrial systems.
The forecast of rainfall and temperature is a difficult task due to their variability in time and space and also the inability to access all the parameters influencing rainfall of a region or locality. Their forecast is of relevance to agriculture and watershed management, which significantly contribute to the economy. Rainfall prediction requires mathematical modelling and simulation because of its extremely irregular and complex nature. Autoregressive integrated moving average (ARIMA) model was used to analyse annual rainfall and maximum temperature over Tordzie watershed and the forecast. Autocorrelation function (ACF) and partial autocorrelation function (PACF) were used to identify the models by aid of visual inspection. Stationarity tests were conducted using the augmented Dickey–Fuller (ADF), Mann–Kendall (MK) and Kwiatkowski–Phillips–Schmidt–Shin (KPSS) tests respectively. The chosen models were evaluated and validated using the Akaike information criterion corrected (AICC) and also Schwartz Bayesian criteria (SBC). The diagnostic analysis of the models comprised of the independence, normality, homoscedascity, P–P and Q–Q plots of the residuals respectively. The best ARIMA model for rainfall for Kpetoe and Tordzinu were (3, 0, 3) and (3, 1, 3) with AICC values of 190.07 and 178.23. That of maximum temperature for Kpetoe and Tordzinu were (3, 1, 3) and (3, 1, 3) and the corresponding AICC values of 23.81 and 36.10. The models efficiency was checked using sum of square error (SSE), mean square error (MSE), mean absolute percent error (MAPE) and root mean square error (RMSE) respectively. The results of the various analysis indicated that the models were adequate and can aid future water planning projections.
PL
Prognozowanie opadu i temperatury jest trudnym zadaniem z powodu zmienności tych parametrów w czasie i przestrzeni, a także nieznajomości wszystkich czynników wpływających na opady w regionie czy w danej miejscowości. Prognozowanie opadów jest ważne dla rolnictwa i gospodarki zlewniowej, mających znaczący wkład w gospodarkę regionu. Przewidywanie opadu wymaga modelowania matematycznego i symulacji z powodu jego skrajnie nieregularnego i złożonego charakteru. Do analizy i prognozowania rocznych opadów i maksymalnej temperatury w zlewni Tordzie wykorzystano autoregresyjny zintegrowany model średniej ruchomej (ARIMA). Do zidentyfikowania modeli metodą oglądu wizualnego użyto funkcji autokorelacji (ACF) i cząstkowej autokorelacji (PACF). Testy stacjonarności przeprowadzono za pomocą testów Dickeya–Fullera (ADF), Manna–Kendalla (MK) i Kwiatkowskiego–Phillipsa–Schmidta–Shina (KPSS). Wybrane modele poddano ocenie i walidacji z użyciem skorygowanego kryterium Akaike (AICC) i Bayesowskiego kryterium Schwartza (SBC). Diagnostyczna analiza modeli obejmowała niezależność, normalność, homoscedastyczność, wykresy P–P i Q–Q dla reszt. Najlepsze modele ARIMA dla opadu w Kpetoe i Tordzinu miały postać (3, 0, 3) i (3, 1, 3), gdy wartości AICC równe odpowiednio 190,07 i 178,23. Modele dla maksymalnej temperatury w Kpetoe i Tordzinu miały postać (3, 1, 3) i (3, 1, 3), a ich odpowiednie wartości AICC wynosiły 23,81 i 36,10. Wydajność modelu sprawdzano, wykorzystując sumę błędu kwadratowego (SSE), średni błąd kwadratowy (MSE), średni bezwzględny błąd procentowy (MAPE) i pierwiastek ze średniego błędu kwadratowego (RMSE). Wyniki różnych analiz wykazały, że modele są odpowiednie i mogą stanowić pomoc w przyszłej gospodarce wodnej.
18
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
W artykule omówiono założenia modelu obliczeniowego do określania czynników wpływu na prognozowane parametry liniowych robót budowlanych. Przedstawiono wstępne wyniki badań uzyskane w warunkach rzeczywistych na placach budów. Dokonano analizy i syntezy danych, systematyzując je w grupy. Wstępnie określono ich wpływ na prognozowane parametry realizacji procesu budowlanego. Przedstawiono kierunki dalszych badań z zastosowaniem metod statystycznych, np.: regresji wielorakiej, sieci neuronowych i ARIMA.
EN
The article discusses the test of forecasting road construction works in terms of duration and cost of the individual packages of works and to show risk factors for the implementation of roadworks. Carried out identification and analysis of factors affect the forecast implementation of linear works allows to minimize error estimating life-cycle of the construction process.The issue analyzed based on their own materials from various projects construction, and that the concept of a computational model using statistical tools for example multiple regression, Multi Layer Perceptron and ARIMA.
Od kilku lat bezpieczeństwo na drogach w Polsce systematycznie się poprawia. Obniża się zarówno liczba wypadków jak i ich ofiar. Mimo tego Polska zajmuje ostatnie miejsca w rankingu bezpieczeństwa na drogach wśród państw Unii Europejskiej. Wstępując do UE Polska zobowiązała się do realizacji polityki unijnej również w zakresie poprawy bezpieczeństwa w ruchu drogowym. Podstawą polityki drogowej krajów UE jest tzw. Wizja Zero, która przyświeca państwom wysoko rozwiniętym i jest filozofią zakładająca, że w perspektywie długofalowej nikt nie powinien ponosić ciężkich obrażeń, ani ginąć w wypadkach drogowych. Na pytanie, na ile jest to możliwe w Polsce, można udzielić odpowiedzi przeprowadzając prognozę długookresową dla wskaźników bezpieczeństwa w ruchu drogowym. W artykule przedstawiono prognozę liczby wypadków drogowych w województwie podkarpackim w 2015 roku w ujęciu sezonowym miesięcznym. Do wyznaczenia prognozy wykorzystano trzy modele sezonowe szeregów czasowych: autoregresyjny z trendem liniowym, ARIMA oraz model sieci neuronowych. Dane statystyczne dotyczyły odstępów miesięcznych i obejmowały okres od stycznia 2010 roku do grudnia 2014 roku. Prognozę miesięczną wyznaczono na kolejny rok, w okresie od stycznia 2015do grudnia 2015. Dane pochodziły ze strony głównej Komendy Policji. Obliczenia wykonano z użyciem programu Statistica 10 oraz arkusza kalkulacyjnego Excel. Oszacowane w pracy modele umożliwiają także przeprowadzenie prognoz długookresowych.
EN
For several years safety on the roads in Poland has been steadily improving. Both the number of accidents and their victims decrease. Despite this, Poland occupies the last place in the ranking of road safety among the EU countries. Poland, when accessing the EU, has been committed to the implementation of EU policies in improving road safety. The basis of the EU road policy is so-called Vision Zero project, which underlies the highly developed countries, and it is a philosophy which assumes that in the long term no one should suffer serious injury or fatalities in road traffic. The answer to the question whether it is possible in Poland can be found by conducting long-term forecasts for indicators of road safety. In this article the monthly forecasts of the number of road accidents in the Subcarpathian region were presented. To determine the forecast there were applied three seasonal time series models: autoregressive with linear trend, ARIMA and neural network model. Statistical data were related to monthly intervals and covered the period from January 2010 to December 2014. The monthly forecast is scheduled for next year, in the period from January 2015 to December 2015. The data came from the homepage of the Police. Calculations were performed by using Statistica 10 and an Excel spreadsheet. The models estimated in the paper allow also to carry out long-term forecasts.
Prediction of Internet traffic time series data (TSD) is a challenging research problem, owing to the complicated nature of TSD. In literature, many hybrids of auto-regressive integrated moving average (ARIMA) and artificial neural networks (ANN) models are devised for the TSD prediction. These hybrid models consider such TSD as a combination of linear and non-linear components, apply combination of ARIMA and ANN in some manner, to obtain the predictions. Out of the many available hybrid ARIMA-ANN models, this paper investigates as to which of them suits better for Internet traffic data. This suitability of hybrid ARIMA-ANN models is studied for both one-step ahead and multistep ahead prediction cases. For the purpose of the study, Internet traffic data is sampled at every 30 and 60 minutes. Model performances are evaluated using the mean absolute error and mean square error measurement. For one-step ahead prediction, with a forecast horizon of 10 points and for three-step prediction, with a forecast horizon of 12 points, the moving average filter based hybrid ARIMA-ANN model gave better forecast accuracy than the other compared models.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.