To see the other types of publications on this topic, follow the link: Rolling Window Time Series Prediction.
Journal articles on the topic 'Rolling Window Time Series Prediction'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Rolling Window Time Series Prediction.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Li, Xue Mei, Jia Shu Chen, and Li Xing Ding. "Weighted LS-SVM Method for Building Cooling Load Prediction." Advanced Materials Research 121-122 (June 2010): 606–12. http://dx.doi.org/10.4028/www.scientific.net/amr.121-122.606.
Full textAbstract:
A number of different forecasting methods have been proposed for cooling load forecasting including historic method, real-time method, time series analysis, and artificial neural networks, but accuracy and time efficiency in prediction are a couple of contradictions to be hard to resolve for building cooling load prediction. In order to improve the prediction accuracy of cooling load time series, weighted least squares support vector machine regression (WLS-SVM) method for a chaotic cooling load prediction is proposed. In this method, a sliding time window is built and data in the sliding time window are employed to reconstruct the dynamic model. Different weights are assigned to different data in the sliding time window, and the model parameters are refreshed on-line with the rolling of the time window. The results show that the method has more superior performance than other methods like LS-SVM.
2
Wang, Zhihua, Yongbo Zhang, and Huimin Fu. "Autoregressive Prediction with Rolling Mechanism for Time Series Forecasting with Small Sample Size." Mathematical Problems in Engineering 2014 (2014): 1–9. http://dx.doi.org/10.1155/2014/572173.
Full textAbstract:
Reasonable prediction makes significant practical sense to stochastic and unstable time series analysis with small or limited sample size. Motivated by the rolling idea in grey theory and the practical relevance of very short-term forecasting or 1-step-ahead prediction, a novel autoregressive (AR) prediction approach with rolling mechanism is proposed. In the modeling procedure, a new developed AR equation, which can be used to model nonstationary time series, is constructed in each prediction step. Meanwhile, the data window, for the next step ahead forecasting, rolls on by adding the most recent derived prediction result while deleting the first value of the former used sample data set. This rolling mechanism is an efficient technique for its advantages of improved forecasting accuracy, applicability in the case of limited and unstable data situations, and requirement of little computational effort. The general performance, influence of sample size, nonlinearity dynamic mechanism, and significance of the observed trends, as well as innovation variance, are illustrated and verified with Monte Carlo simulations. The proposed methodology is then applied to several practical data sets, including multiple building settlement sequences and two economic series.
3
Shin, Yuna, Taekgeun Kim, Seoksu Hong, Seulbi Lee, EunJi Lee, SeungWoo Hong, ChangSik Lee, et al. "Prediction of Chlorophyll-a Concentrations in the Nakdong River Using Machine Learning Methods." Water 12, no. 6 (June 25, 2020): 1822. http://dx.doi.org/10.3390/w12061822.
Full textAbstract:
Many studies have attempted to predict chlorophyll-a concentrations using multiple regression models and validating them with a hold-out technique. In this study commonly used machine learning models, such as Support Vector Regression, Bagging, Random Forest, Extreme Gradient Boosting (XGBoost), Recurrent Neural Network (RNN), and Long–Short-Term Memory (LSTM), are used to build a new model to predict chlorophyll-a concentrations in the Nakdong River, Korea. We employed 1–step ahead recursive prediction to reflect the characteristics of the time series data. In order to increase the prediction accuracy, the model construction was based on forward variable selection. The fitted models were validated by means of cumulative learning and rolling window learning, as opposed to the hold–out technique. The best results were obtained when the chlorophyll-a concentration was predicted by combining the RNN model with the rolling window learning method. The results suggest that the selection of explanatory variables and 1–step ahead recursive prediction in the machine learning model are important processes for improving its prediction performance.
4
Wang, Yaping, Chaonan Yang, Di Xu, Jianghua Ge, and Wei Cui. "Evaluation and Prediction Method of Rolling Bearing Performance Degradation Based on Attention-LSTM." Shock and Vibration 2021 (May 20, 2021): 1–15. http://dx.doi.org/10.1155/2021/6615920.
Full textAbstract:
It is significant for the evaluation and prediction of the performance degradation of rolling bearings. However, the degradation stage division of the rolling bearing performance is not obvious in traditional methods, and the prediction accuracy is low. Therefore, an Attention-LSTM method is proposed to improve the evaluation and prediction of the performance degradation of rolling bearings. First, to reduce the uncertainty of the manual intervention, performance degradation characteristic indexes of rolling bearings are evaluated and screened by the correlation, the monotonicity, and the robustness. Second, the original characteristic indicator curve is divided into the Health Indicator (HI) curve and the residual curve by means of fixed-window averaging to quantitatively and intuitively reflect the deterioration degree of the rolling bearing performance. Finally, the Attention mechanism is combined with the LSTM model, and a scoring function is established to enhance the prediction accuracy. The scoring function is used to adjust the intermediate output state weight of the LSTM model and improve the prediction accuracy. The appropriate network structure and the parameter configuration are determined, and the prediction model of rolling bearing degradation performance is established. Compared with other models, the method proposed by this paper makes full use of the historical data and is more sensitive to the key information in the long time series, and the eRMSE index and the eMAE index of the two sets of experimental data are minimum, and the prediction accuracy of rolling bearing degradation performance is higher. The model has the strong robustness and the generalization ability, which has the important engineering practical value for the prediction of the equipment health state.
5
Gu, Wentao, Yongwei Yang, and Zhenshan Liu. "Forecasting Stock Returns Based on a Time-Varying Factor Weighted Density Model." Journal of Advanced Computational Intelligence and Intelligent Informatics 22, no. 6 (October 20, 2018): 831–37. http://dx.doi.org/10.20965/jaciii.2018.p0831.
Full textAbstract:
Stock returns play an important role in the empirical study of asset pricing, and are often applied in portfolio allocation and performance evaluation. The effect of macroeconomic and financial variables on stock returns is a hot topic and many studies have utilized these variables in time series models to improve the forecasts of stock returns. This study imposes macroeconomic and financial variables as weighting factors on kernel density and establishes a new prediction model – the time-varying factor weighted density model. We apply this model to monthly price data of the Chinese stock index and employ the rolling window strategy for out-of-sample forecasting. The result shows that this method improves both statistical and economic measures of out-of-sample forecasting performance.
6
Jeon, Jun-Woo, Okan Duru, Ziaul Haque Munim, and Naima Saeed. "System Dynamics in the Predictive Analytics of Container Freight Rates." Transportation Science 55, no. 4 (July 2021): 946–67. http://dx.doi.org/10.1287/trsc.2021.1046.
Full textAbstract:
This study proposes a two-tier cross-validation and backtesting procedure, including expanding and rolling-window test metrics in predictive analytics of container freight rates by utilizing the system dynamics approach. The study utilized system dynamics to represent the nonlinear complex structure of container freight rates for predictive analytics and performed univariate and multivariate time-series analysis as benchmarks of the conventional approach. In particular, the China containerized freight index (CCFI) has been investigated through various parametric methodologies (both conventional time-series and system dynamics approaches). This study follows a strict validation process consisting of expanding window and rolling-window test procedures for the out-of-sample forecasting accuracy of the proposed systemic model and benchmark models to ensure fair validation. In addition to the predictive features, major governing dynamics are presented in the analysis which may initiate further theoretical discussions on the economics and structure of the container shipping markets. Empirical results indicate that postsample accuracy can be affected by the sample size (training data size) in a given set of methodologies. Considering the economic challenges in the container shipping industry, the proposed methodology may help users to improve their cash-flow visibility and reduce the adverse effects of volatility in container shipping rates.
7
González-Enrique, Javier, Juan Jesús Ruiz-Aguilar, José Antonio Moscoso-López, Daniel Urda, Lipika Deka, and Ignacio J. Turias. "Artificial Neural Networks, Sequence-to-Sequence LSTMs, and Exogenous Variables as Analytical Tools for NO2 (Air Pollution) Forecasting: A Case Study in the Bay of Algeciras (Spain)." Sensors 21, no. 5 (March 4, 2021): 1770. http://dx.doi.org/10.3390/s21051770.
Full textAbstract:
This study aims to produce accurate predictions of the NO2 concentrations at a specific station of a monitoring network located in the Bay of Algeciras (Spain). Artificial neural networks (ANNs) and sequence-to-sequence long short-term memory networks (LSTMs) were used to create the forecasting models. Additionally, a new prediction method was proposed combining LSTMs using a rolling window scheme with a cross-validation procedure for time series (LSTM-CVT). Two different strategies were followed regarding the input variables: using NO2 from the station or employing NO2 and other pollutants data from any station of the network plus meteorological variables. The ANN and LSTM-CVT exogenous models used lagged datasets of different window sizes. Several feature ranking methods were used to select the top lagged variables and include them in the final exogenous datasets. Prediction horizons of t + 1, t + 4 and t + 8 were employed. The exogenous variables inclusion enhanced the model’s performance, especially for t + 4 (ρ ≈ 0.68 to ρ ≈ 0.74) and t + 8 (ρ ≈ 0.59 to ρ ≈ 0.66). The proposed LSTM-CVT method delivered promising results as the best performing models per prediction horizon employed this new methodology. Additionally, per each parameter combination, it obtained lower error values than ANNs in 85% of the cases.
8
Chen, Cathy W. S., and L. M. Chiu. "Ordinal Time Series Forecasting of the Air Quality Index." Entropy 23, no. 9 (September 4, 2021): 1167. http://dx.doi.org/10.3390/e23091167.
Full textAbstract:
This research models and forecasts daily AQI (air quality index) levels in 16 cities/counties of Taiwan, examines their AQI level forecast performance via a rolling window approach over a one-year validation period, including multi-level forecast classification, and measures the forecast accuracy rates. We employ statistical modeling and machine learning with three weather covariates of daily accumulated precipitation, temperature, and wind direction and also include seasonal dummy variables. The study utilizes four models to forecast air quality levels: (1) an autoregressive model with exogenous variables and GARCH (generalized autoregressive conditional heteroskedasticity) errors; (2) an autoregressive multinomial logistic regression; (3) multi-class classification by support vector machine (SVM); (4) neural network autoregression with exogenous variable (NNARX). These models relate to lag-1 AQI values and the previous day’s weather covariates (precipitation and temperature), while wind direction serves as an hour-lag effect based on the idea of nowcasting. The results demonstrate that autoregressive multinomial logistic regression and the SVM method are the best choices for AQI-level predictions regarding the high average and low variation accuracy rates.
9
Ge, Xiaohui, Lu Shen, Chaoming Zheng, Peng Li, and Xiaobo Dou. "A Decoupling Rolling Multi-Period Power and Voltage Optimization Strategy in Active Distribution Networks." Energies 13, no. 21 (November 5, 2020): 5789. http://dx.doi.org/10.3390/en13215789.
Full textAbstract:
With the increasing penetration of distributed photovoltaics (PVs) in active distribution networks (ADNs), the risk of voltage violations caused by PV uncertainties is significantly exacerbated. Since the conventional voltage regulation strategy is limited by its discrete devices and delay, ADN operators allow PVs to participate in voltage optimization by controlling their power outputs and cooperating with traditional regulation devices. This paper proposes a decoupling rolling multi-period reactive power and voltage optimization strategy considering the strong time coupling between different devices. The mixed-integer voltage optimization model is first decomposed into a long-period master problem for on-load tap changer (OLTC) and multiple short-period subproblems for PV power by Benders decomposition algorithm. Then, based on the high-precision PV and load forecasts, the model predictive control (MPC) method is utilized to modify the independent subproblems into a series of subproblems that roll with the time window, achieving a smooth transition from the current state to the ideal state. The estimated voltage variation in the prediction horizon of MPC is calculated by a simplified discrete equation for OLTC tap and a linearized sensitivity matrix between power and voltage for fast computation. The feasibility of the proposed optimization strategy is demonstrated by performing simulations on a distribution test system.
10
Csernai, Eszter, Gergely Horváth, Michele LeNoue-Newton, Kathleen Mittendorf, David Smith, Ben Ho Park, Jan Wolber, and Travis John Osterman. "Rolling window-based hepatitis toxicity prediction from routine bloodwork in patients undergoing immune checkpoint inhibitor therapy." Journal of Clinical Oncology 40, no. 16_suppl (June 1, 2022): e13565-e13565. http://dx.doi.org/10.1200/jco.2022.40.16_suppl.e13565.
Full textAbstract:
e13565 Background: Hepatitis toxicity is one of the most important adverse effects of immune checkpoint inhibitor (ICI) therapy, occurring in approximately 10% of patients. However, when identified early, it can be managed clinically, potentially allowing continuation of ICI treatment. The goal of the study was to evaluate the feasibility and clinical usefulness of an artificial intelligence (AI) model to predict the risk of developing hepatitis toxicity during the course of ICI treatment from routine bloodwork values. Methods: Our model uses a clinical dataset of 2438 patients who received ICI treatment at the Vanderbilt University Medical Center prior to the end of 2020. Hepatitis toxicity was defined as one or more of ALT, AST, ALKPHOS, BILIRUBIN values exceeding 2.5-times the upper limit of normal value. The available feature set was limited to the routinely available blood test values. All features were normalized to the upper limit of normal and transformed to a discretized symbolic representation, a modified version of Symbolic Aggregate ApproXimation. Motifs were extracted as n-grams from the symbol series, and the counts were used as input features for the predictive model. The study uses standard data science model training and evaluation concepts: train, validation, and test splits were created randomly on the patient level; the reported evaluation metrics are median AUC, TPR, TNR, PPV, NPV over 10 sampling runs. The final, best-performing model architecture is a boosted decision tree model (XGBoost) trained on the last four blood tests to predict hepatitis at the next blood sampling timepoint (i.e., at the time of the next ICI treatment appointment). Results: The best model uses the following eight blood values as features: ALT, AST, ALKPHOS, BILIRUBIN, ALBUMIN, CO2, CALCIUM, and BUN, and achieves an AUC of 0.82 (std. 0.01), with TPR = 0.32 (0.03), TNR = 0.97 (0.005), PPV = 0.18 (0.03), and NPV = 0.99 (0.002). It finds 32% of the timepoints where the patient is going to develop hepatitis toxicity prior to their next treatment, and about 1 in 5 positive predictions are correct. It is important to note that only about 1% of all ‘sequences’ of four consecutive blood tests are followed by hepatitis at the next test. That is, while a relatively large proportion of patients are going to develop hepatitis toxicity during their ICI treatment, the timepoint at which this happens is very uncertain. Conclusions: We demonstrate that an AI model built using only already available patient laboratory data could provide clinically useful input for clinicians to support their ICI treatment decisions to reduce the occurrence of hepatitis toxicity. The dynamic nature and below-patient-level granularity of the model would allow a clinician / clinical trial investigator to make adjustments to the therapy based on individual patient reaction over time.
11
Shcherbinina, A. V., and A. V. Alzheev. "Comparative analysis of the forecasting quality of the classical statistical model and the machine learning model on the data of the Russian stock market." Scientific notes of the Russian academy of entrepreneurship 20, no. 3 (October 5, 2021): 52–63. http://dx.doi.org/10.24182/2073-6258-2021-20-3-52-63.
Full textAbstract:
The main objective of this work is to compare the predictive ability of the classical machine learning model — ARIMA, as the most common and well-studied baseline model, and the ML model based on a sequential neural network — in this case, LSTM. The goal is to maximize accuracy and minimize error — selecting the most appropriate model for predicting time series with the highest accuracy. A description is given for these mathematical models. An algorithm is also proposed for forecasting time series using these models, based on the «Rolling window» approach. Practical implementation is implemented using the Python programming environment with the Pandas, Numpy, pmdarima, Keras, Statsmodels libraries. To train the models, we used stock data at the closing price per share of the leading Russian companies: Yandex, VTB, KamAZ, Kiwi, Gazprom, NLMK, Rosneft, Alrosa for the period. The studies carried out demonstrate the predictive superiority of the approach based on neural networks, while the RMSE is 71% less than the same indicator for the ARIMA model, which allows us to conclude that the use of the LSTM model is preferable for this class of problems.
12
Kombo, Omar Haji, Santhi Kumaran, Yahya H. Sheikh, Alastair Bovim, and Kayalvizhi Jayavel. "Long-Term Groundwater Level Prediction Model Based on Hybrid KNN-RF Technique." Hydrology 7, no. 3 (August 18, 2020): 59. http://dx.doi.org/10.3390/hydrology7030059.
Full textAbstract:
Reliable seasonal prediction of groundwater levels is not always possible when the quality and the amount of available on-site groundwater data are limited. In the present work, a hybrid K-Nearest Neighbor-Random Forest (KNN-RF) is used for the prediction of variations in groundwater levels (L) of an aquifer with the groundwater relatively close to the surface (<10 m) is proposed. First, the time-series smoothing methods are applied to improve the quality of groundwater data. Then, the ensemble K-Nearest Neighbor-Random Forest (KNN-RF) model is treated using hydro-climatic data for the prediction of variations in the levels of the groundwater tables up to three months ahead. Climatic and groundwater data collected from eastern Rwanda were used for validation of the model on a rolling window basis. Potential predictors were: the observed daily mean temperature (T), precipitation (P), and daily maximum solar radiation (S). Previous day’s precipitation P (t − 1), solar radiation S (t), temperature T (t), and groundwater level L (t) showed the highest variation in the fluctuations of the groundwater tables. The KNN-RF model presents its results in an intelligible manner. Experimental results have confirmed the high performance of the proposed model in terms of root mean square error (RMSE), mean absolute error (MAE), Nash–Sutcliffe (NSE), and coefficient of determination (R2).
13
Harris, Mallory J., Simon I. Hay, and John M. Drake. "Early warning signals of malaria resurgence in Kericho, Kenya." Biology Letters 16, no. 3 (March 2020): 20190713. http://dx.doi.org/10.1098/rsbl.2019.0713.
Full textAbstract:
Campaigns to eliminate infectious diseases could be greatly aided by methods for providing early warning signals of resurgence. Theory predicts that as a disease transmission system undergoes a transition from stability at the disease-free equilibrium to sustained transmission, it will exhibit characteristic behaviours known as critical slowing down, referring to the speed at which fluctuations in the number of cases are dampened, for instance the extinction of a local transmission chain after infection from an imported case. These phenomena include increases in several summary statistics, including lag-1 autocorrelation, variance and the first difference of variance. Here, we report the first empirical test of this prediction during the resurgence of malaria in Kericho, Kenya. For 10 summary statistics, we measured the approach to criticality in a rolling window to quantify the size of effect and directions. Nine of the statistics increased as predicted and variance, the first difference of variance, autocovariance, lag-1 autocorrelation and decay time returned early warning signals of critical slowing down based on permutation tests. These results show that time series of disease incidence collected through ordinary surveillance activities may exhibit characteristic signatures prior to an outbreak, a phenomenon that may be quite general among infectious disease systems.
14
Vo, Nguyen, and Robert Ślepaczuk. "Applying Hybrid ARIMA-SGARCH in Algorithmic Investment Strategies on S&P500 Index." Entropy 24, no. 2 (January 20, 2022): 158. http://dx.doi.org/10.3390/e24020158.
Full textAbstract:
This research aims to compare the performance of ARIMA as a linear model with that of the combination of ARIMA and GARCH family models to forecast S&P500 log returns in order to construct algorithmic investment strategies on this index. We used the data collected from Yahoo Finance with daily frequency for the period from 1 January 2000 to 31 December 2019. By using a rolling window approach, we compared ARIMA with the hybrid models to examine whether hybrid ARIMA-SGARCH and ARIMA-EGARCH can really reflect the specific time-series characteristics and have better predictive power than the simple ARIMA model. In order to assess the precision and quality of these models in forecasting, we compared their equity lines, their forecasting error metrics (MAE, MAPE, RMSE, MAPE), and their performance metrics (annualized return compounded, annualized standard deviation, maximum drawdown, information ratio, and adjusted information ratio). The main contribution of this research is to show that the hybrid models outperform ARIMA and the benchmark (Buy&Hold strategy on S&P500 index) over the long term. These results are not sensitive to varying window sizes, the type of distribution, and the type of the GARCH model.
15
Elgammal, Mohammed Mohammed, Fatma Ehab Ahmed, and David Gordon McMillan. "The predictive ability of stock market factors." Studies in Economics and Finance 39, no. 1 (October 21, 2021): 111–24. http://dx.doi.org/10.1108/sef-01-2021-0010.
Full textAbstract:
Purpose This paper aims to ask whether a range of stock market factors contain information that is useful to investors by generating a trading rule based on one-step-ahead forecasts from rolling and recursive regressions. Design/methodology/approach Using USA data across 3,256 firms, the authors estimate stock returns on a range of factors using both fixed-effects panel and individual regressions. The authors use rolling and recursive approaches to generate time-varying coefficients. Subsequently, the authors generate one-step-ahead forecasts for expected returns, simulate a trading strategy and compare its performance with realised returns. Findings Results from the panel and individual firm regressions show that an extended Fama-French five-factor model that includes momentum, reversal and quality factors outperform other models. Moreover, rolling based regressions outperform recursive ones in forecasting returns. Research limitations/implications The results support notable time-variation in the coefficients on each factor, whilst suggesting that more distant observations, inherent in recursive regressions, do not improve predictive power over more recent observations. Results support the ability of market factors to improve forecast performance over a buy-and-hold strategy. Practical implications The results presented here will be of interest to both academics in understanding the dynamics of expected stock returns and investors who seek to improve portfolio performance through highlighting which factors determine stock return movement. Originality/value The authors investigate the ability of risk factors to provide accurate forecasts and thus have economic value to investors. The authors conducted a series of moving and expanding window regressions to trace the dynamic movements of the stock returns average response to explanatory factors. The authors use the time-varying parameters to generate one-step-ahead forecasts of expected returns and simulate a trading strategy.
16
Shen, Li, Zijin Wei, and Yangzhu Wang. "Determining the Rolling Window Size of Deep Neural Network Based Models on Time Series Forecasting." Journal of Physics: Conference Series 2078, no. 1 (November 1, 2021): 012011. http://dx.doi.org/10.1088/1742-6596/2078/1/012011.
Full textAbstract:
Abstract Time series forecasting has always been a significant task in various domains. In this paper, we propose DeepARMA, a LSTM-based recurrent neural network to tackle this problem. DeepARMA is derived from an existing time series forecasting baseline, DeepAR, overcoming two of its weaknesses: (1) rolling window size determination: the way DeepAR determines rolling window size is casual and vulnerable, which may lead to the unnecessary computation and inefficiency of the model;(2) neglect of the noise: pure autoregressive model cannot deal with the condition where data are composed of various kinds of noise, neither do most of time series models including DeepAR. In order to solve these two problems, we first combine a classic information theoretic criterion, AIC, with the network to determine the proper rolling window size. Then, we propose a jointly-learned neural network fusing white Gaussian noise series given by ARIMA models to DeepAR’s input. That is exactly why we name the network ‘DeepARMA’. Our experiments on a real-world dataset demonstrate that our improvement settles those two problems put forward above.
17
Jiang, Gui Yan, and Cui Liu Kong. "Traffic Parameters Prediction Method Based on Rolling Time Series." Advanced Materials Research 671-674 (March 2013): 2946–50. http://dx.doi.org/10.4028/www.scientific.net/amr.671-674.2946.
Full textAbstract:
The technologies of traffic parameters prediction provide future traffic information so that management measures for traffic congestion can be made timely and accurately based on the retrieved information. According to the shortcomings of traditional methods for predicting traffic parameters, a rolling time series method is proposed through improving the traditional time series methods. To test the performance of our proposed approach, the rolling time series method is compared with the traditional time series methods using measured traffic flow based on a part road network of a large urban area in China. The results show that the prediction effects by the rolling time series method developed in this study are better than traditional approaches.
18
Yu, Yufeng, Yuelong Zhu, Shijin Li, and Dingsheng Wan. "Time Series Outlier Detection Based on Sliding Window Prediction." Mathematical Problems in Engineering 2014 (2014): 1–14. http://dx.doi.org/10.1155/2014/879736.
Full textAbstract:
In order to detect outliers in hydrological time series data for improving data quality and decision-making quality related to design, operation, and management of water resources, this research develops a time series outlier detection method for hydrologic data that can be used to identify data that deviate from historical patterns. The method first built a forecasting model on the history data and then used it to predict future values. Anomalies are assumed to take place if the observed values fall outside a given prediction confidence interval (PCI), which can be calculated by the predicted value and confidence coefficient. The use ofPCIas threshold is mainly on the fact that it considers the uncertainty in the data series parameters in the forecasting model to address the suitable threshold selection problem. The method performs fast, incremental evaluation of data as it becomes available, scales to large quantities of data, and requires no preclassification of anomalies. Experiments with different hydrologic real-world time series showed that the proposed methods are fast and correctly identify abnormal data and can be used for hydrologic time series analysis.
19
Yang, Xiyang, Shiqing Zhang, Xinjun Zhang, and Fusheng Yu. "Polynomial Fuzzy Information Granule-Based Time Series Prediction." Mathematics 10, no. 23 (November 28, 2022): 4495. http://dx.doi.org/10.3390/math10234495.
Full textAbstract:
Fuzzy information granulation transfers the time series analysis from the numerical platform to the granular platform, which enables us to study the time series at a different granularity. In previous studies, each fuzzy information granule in a granular time series can reflect the average, range, and linear trend characteristics of the data in the corresponding time window. In order to get a more general information granule, this paper proposes polynomial fuzzy information granules, each of which can reflect both the linear trend and the nonlinear trend of the data in a time window. The distance metric of the proposed information granules is given theoretically. After studying the distance measure of the polynomial fuzzy information granule and its geometric interpretation, we design a time series prediction method based on the polynomial fuzzy information granules and fuzzy inference system. The experimental results show that the proposed prediction method can achieve a good long-term prediction.
20
Dimoudis, Dimitris, Thanasis Vafeiadis, Alexandros Nizamis, Dimosthenis Ioannidis, and Dimitrios Tzovaras. "Utilizing an adaptive window rolling median methodology for time series anomaly detection." Procedia Computer Science 217 (2023): 584–93. http://dx.doi.org/10.1016/j.procs.2022.12.254.
Full text
21
NE, Gyamfi, Kyei KA, and Gill R. "African Stock Markets and Return Predictability." Journal of Economics and Behavioral Studies 8, no. 5(J) (October 30, 2016): 91–99. http://dx.doi.org/10.22610/jebs.v8i5(j).1434.
Full textAbstract:
This article re-examines the return predictability of eight African stock markets. When returns of stocks are predictable, arbitrageurs make abnormal gains from analyzing prices. The study uses a non-parametric Generalised Spectral (GS) test in a rolling window approach. The rolling window approach tracts the periods of efficiency over time. The GS test is robust to conditional heteroscedasticity and it detects the presence of linear and nonlinear dependencies in a stationary time series. Our results support the Adaptive Market Hypothesis (AMH). This is because, indices whose returns were observed to be predictable by analyzing them in absolute form and therefore weak - form inefficient showed trends of unpredictability in a rolling window.
22
Fan, Jin, Yipan Huang, Ke Zhang, Sen Wang, Jinhua Chen, and Baiping Chen. "DWNet: Dual-Window Deep Neural Network for Time Series Prediction." Complexity 2021 (October 13, 2021): 1–10. http://dx.doi.org/10.1155/2021/1125630.
Full textAbstract:
Multivariate time series prediction is a very important task, which plays a huge role in climate, economy, and other fields. We usually use an Attention-based Encoder-Decoder network to deal with multivariate time series prediction because the attention mechanism makes it easier for the model to focus on the really important attributes. However, the Encoder-Decoder network has the problem that the longer the length of the sequence is, the worse the prediction accuracy is, which means that the Encoder-Decoder network cannot process long series and therefore cannot obtain detailed historical information. In this paper, we propose a dual-window deep neural network (DWNet) to predict time series. The dual-window mechanism allows the model to mine multigranularity dependencies of time series, such as local information obtained from a short sequence and global information obtained from a long sequence. Our model outperforms nine baseline methods in four different datasets.
23
Isiaka, Abdulaleem, Abdulqudus Isiaka, and Abdulqadir Isiaka. "Forecasting with ARMA models." International Journal of Research in Business and Social Science (2147- 4478) 10, no. 1 (February 11, 2021): 205–34. http://dx.doi.org/10.20525/ijrbs.v10i1.1005.
Full textAbstract:
This paper employs the R software in identifying the most suitable ARMA model for forecasting the growth rate of the exchange rate between the US dollar and a unit of the British pound. The data is systematically split into two distinct periods identified as the in-sample period and the out of sample period. The best model selected for the in-sample period is used to make forecasts for the out of sample period. Both traditional and rolling window forecasting methods are employed. This research uses the MSE, MAE, MAPE and correct sign prediction criterion to compare the forecasting performance of the rolling window forecasting method and the traditional forecasting method. The results obtained suggest that the traditional forecasting method performs better judging by MSE, MAE and MAPE. In other words, the traditional forecasting method is more suitable for predicting the magnitude (i.e., size) by which the US /UK exchange rate changes over time. However, the results also suggest that the rolling window forecasting method performs better based on the correct sign prediction criterion. In other words, the rolling window forecasting method is more appropriate for predicting the changes in the sign of the US /UK exchange rate.
24
Wang, Yu Chao, Fan Ming Liu, and Hui Xuan Fu. "Ship Rolling Motion Prediction Based on Wavelet Neural Network." Applied Mechanics and Materials 190-191 (July 2012): 724–28. http://dx.doi.org/10.4028/www.scientific.net/amm.190-191.724.
Full textAbstract:
The traditional time series predictive models are not able to achieve a satisfying prediction effect in the problem of a non-linear system and nonstationary time series. To solve these problems, ship course time series prediction, which is based on back propagation wavelet neural network structure and algorithm, was proposed. It combined wavelet analysis and neural network characteristics, and employed the nonlinear Morlet wavelet radices as the activation function. This method was applied to ship rolling motion prediction, and simulation results showed the validity to improving the prediction accuracy.
25
Xia, Xin Tao, and Tao Mei Lv. "Chaos Prediction of Rolling Bearing Friction Torque." Applied Mechanics and Materials 26-28 (June 2010): 190–93. http://dx.doi.org/10.4028/www.scientific.net/amm.26-28.190.
Full textAbstract:
Based on the chaos theory, the adding-weight one-rank local-region method was applied to predict the time series of the rolling bearing friction torque. The experimental investigation on the rolling bearing for space applications shows that the method is able to predict effectively the rolling bearing friction torque, only with very small predicted error.
26
Pang, Yi-Hui, Hong-Bo Wang, Jian-Jian Zhao, and De-Yong Shang. "Analysis and Prediction of Hydraulic Support Load Based on Time Series Data Modeling." Geofluids 2020 (October 22, 2020): 1–15. http://dx.doi.org/10.1155/2020/8851475.
Full textAbstract:
Hydraulic support plays a key role in ground control of longwall mining. The smart prediction methods of support load are important for achieving intelligent mining. In this paper, the hydraulic support load data is decomposed into trend term, cycle term, and residual term, and it is found that the data has clear trend and period features, which can be called time series data. Based on the autoregression theory and weighted moving average method, the time series model is built to analyze the load data and predict its evolution trend, and the prediction accuracy of the sliding window model, ARIMA (Autoregressive Integrated Moving Average) model, and SARIMA (Seasonal Autoregressive Integrated Moving Average) model to the hydraulic support load under different parameters are evaluated, respectively. The results of single-point and multipoint prediction test with various sliding window values indicate that the sliding window method has no advantage in predicting the trend of the support load. The ARIMA model shows a better short-term trend prediction than the sliding window model. To some extent, increasing the length of the autoregressive term can improve the long-term prediction accuracy of the model, but it also increases the sensitivity of the model to support load fluctuation, and it is still difficult to predict the load trend in one support cycle. The SARIMA model has better prediction results than the sliding window model and the ARIMA model, which reveals the load evolution trend accurately during the whole support cycle. However, there are many external factors affecting the support load, such as overburden properties, hydraulic support moving speed, and worker’s operation. The smarter model of SARIMA considering these factors should be developed to be more suitable in predicting the hydraulic support load.
27
Raza, Syed Ali, Rashid Sbia, Muhammad Shahbaz, and Sahel Al Rousan. "Trade-growth nexus and the rolling window analysis in United Arab Emirates." Journal of Asia Business Studies 12, no. 4 (December 10, 2018): 469–88. http://dx.doi.org/10.1108/jabs-07-2016-0098.
Full textAbstract:
Purpose This paper aims to examine the relationship between trade and economic growth using data of UAE economy for the period of 1974-2011. Design/methodology/approach The bounds testing is applied for testing the cointegration relationship between the variables. The rolling window approach has been used to analyze the stability of long run coefficients. Findings The empirical analysis shows the presence of cointegration between trade and economic growth. Furthermore, exports have positive, but imports have negative effect on economic growth. The rolling window approach confirms the stability of long-run estimates. Practical implications This paper provides new insights for policymakers to use trade as economic tool for sustainable economic development. Originality/value This paper makes a unique contribution to the literature with reference to UAE, being a pioneering attempt to investigate the relationship between trade and economic growth by using long time series data and applying more rigorous techniques like time varying rolling window analysis.
28
Polanco-Martínez, Josué M. "RolWinMulCor: An R package for estimating rolling window multiple correlation in ecological time series." Ecological Informatics 60 (November 2020): 101163. http://dx.doi.org/10.1016/j.ecoinf.2020.101163.
Full text
29
Zheng, Hao, Jian Yan Tian, Fang Wang, and Jin Li. "Short-Term Wind Speed Combination Prediction Model of Neural Network and Time Series." Advanced Materials Research 608-609 (December 2012): 764–69. http://dx.doi.org/10.4028/www.scientific.net/amr.608-609.764.
Full textAbstract:
This paper uses neural network combined with time series to establish rolling neural network model to predict short-term wind speed in the wind farm. In order to improve wind speed prediction accuracy, this paper analyzes effects of wind direction on wind speed by gray correlation analysis and obtains the correlation coefficient between wind speed at next moment and current wind direction is the largest by calculating. Then wind direction at current moment, historical wind speed and residuals which determined by time series are used as input variables to establish wind prediction model with rolling BP neural network. The simulation results show that neural network combined with time series which considers wind direction could improve the prediction accuracy when wind speed fluctuation is large.
30
Taroni, Matteo, Giorgio Vocalelli, and Andrea De Polis. "Gutenberg–Richter B-Value Time Series Forecasting: A Weighted Likelihood Approach." Forecasting 3, no. 3 (August 6, 2021): 561–69. http://dx.doi.org/10.3390/forecast3030035.
Full textAbstract:
We introduce a novel approach to estimate the temporal variation of the b-value parameter of the Gutenberg–Richter law, based on the weighted likelihood approach. This methodology allows estimating the b-value based on the full history of the available data, within a data-driven setting. We test this methodology against the classical “rolling window” approach using a high-definition Italian seismic catalogue as well as a global catalogue of high magnitudes. The weighted likelihood approach outperforms competing methods, and measures the optimal amount of past information relevant to the estimation.
31
Li, Hongcheng, Yuan Gao, Bing Wang, Yuewei Ming, and Zhongwei Zhao. "Network Anomaly Sequence Prediction Method Based on LSTM and Two-layer Window Features." Journal of Physics: Conference Series 2216, no. 1 (March 1, 2022): 012063. http://dx.doi.org/10.1088/1742-6596/2216/1/012063.
Full textAbstract:
Abstract To solve the over-fitting problem in the prediction algorithm caused by the small number of features that arise during the network anomaly prediction process, an LSTM algorithm for network anomaly predictions based on two-layer time window features was proposed. Firstly, the network alarm data sequence was divided according to the observation time window and prediction time window. Secondly, considering that the time series of the anomaly alarm data can be somewhat periodic, a time window sequence dataset was created with the periodic features and statistical features in the two-layer windows. Finally, one-shot and feedback models of the LSTM algorithm were employed to predict network anomalies. The experiment showed that the best prediction accuracy for this method is over 80% with both one-shot and feedback models, when the prediction time window is 12h.
32
Anagiannis, Ioannis, Nikolaos Nikolakis, and Kosmas Alexopoulos. "Energy-Based Prognosis of the Remaining Useful Life of the Coating Segments in Hot Rolling Mill." Applied Sciences 10, no. 19 (September 29, 2020): 6827. http://dx.doi.org/10.3390/app10196827.
Full textAbstract:
The field of prognostic maintenance aims at predicting the remaining time for a system or component to continue being used under the desired performance. This time is usually named as Remaining Useful Life (RUL). The current study proposes a novel approach for the RUL estimation of coating segments placed on a hot rolling mill machine. A prediction method was developed, providing real-time updates of the RUL prediction during the rolling milling process. The proposed approach performs energy analysis on measurements of segment surface temperatures and hydraulic forces. It uses nonparametric statistical processes to update the predictions, within a prediction horizon/window, indicating the number of remaining products to be processed. To assess the probability of failure within the defined prediction window, Maximum Likelihood Estimation is used. The proposed methodology was implemented in a software prototype in the MATLAB environment and tested in an industrial use case coming from a steel parts manufacturer, facilitating testing and validation of the suggested approach. Real-world data were acquired from the operational machine, while the validation results support that the proposed methodology demonstrates reasonable performance and robustness against product type variations.
33
Han, Shuang, and Hongbin Dong. "A Temporal Window Attention-Based Window-Dependent Long Short-Term Memory Network for Multivariate Time Series Prediction." Entropy 25, no. 1 (December 21, 2022): 10. http://dx.doi.org/10.3390/e25010010.
Full textAbstract:
Multivariate time series prediction models perform the required operation on a specific window length of a given input. However, capturing complex and nonlinear interdependencies in each temporal window remains challenging. The typical attention mechanisms assign a weight for a variable at the same time or the features of each previous time step to capture spatio-temporal correlations. However, it fails to directly extract each time step’s relevant features that affect future values to learn the spatio-temporal pattern from a global perspective. To this end, a temporal window attention-based window-dependent long short-term memory network (TWA-WDLSTM) is proposed to enhance the temporal dependencies, which exploits the encoder–decoder framework. In the encoder, we design a temporal window attention mechanism to select relevant exogenous series in a temporal window. Furthermore, we introduce a window-dependent long short-term memory network (WDLSTM) to encode the input sequences in a temporal window into a feature representation and capture very long term dependencies. In the decoder, we use WDLSTM to generate the prediction values. We applied our model to four real-world datasets in comparison to a variety of state-of-the-art models. The experimental results suggest that TWA-WDLSTM can outperform comparison models. In addition, the temporal window attention mechanism has good interpretability. We can observe which variable contributes to the future value.
34
Xia, X., Z. Chang, Y. Li, L. Ye, and M. Qiu. "Analysis and Prediction for Time Series on Torque Friction of Rolling Bearings." Journal of Testing and Evaluation 46, no. 3 (December 1, 2017): 20160549. http://dx.doi.org/10.1520/jte20160549.
Full text
35
Xia, Xin Tao, and Tao Mei Lv. "Dynamic Prediction of Rolling Bearing Friction Torque Using Lyapunov Exponent Method." Applied Mechanics and Materials 44-47 (December 2010): 1120–24. http://dx.doi.org/10.4028/www.scientific.net/amm.44-47.1120.
Full textAbstract:
Based on the chaos theory, the Lyapunov exponent method is employed to predict dynamically the time series of the rolling bearing friction torque. First, the embedding dimension and the delay time for the phase space reconstruction are estimated with the Cao method and the mutual information method, respectively. Second, the maximum of the Lyapunov exponents is calculated by small data sets. Lastly, the nearest neighboring point is sought via the Euclidean distance. The experimental investigation shows that the method proposed in this paper is able to forecast effectively the rolling bearing friction torque as a time series, only with very small predicted error.
36
Shahriari, Siroos, Taha Hossein Rashidi, AKM Azad, and Fatemeh Vafaee. "COVIDSpread: real-time prediction of COVID-19 spread based on time-series modelling." F1000Research 10 (November 3, 2021): 1110. http://dx.doi.org/10.12688/f1000research.73969.1.
Full textAbstract:
A substantial amount of data about the COVID-19 pandemic is generated every day. Yet, data streaming, while considerably visualized, is not accompanied with modelling techniques to provide real-time insights. This study introduces a unified platform, COVIDSpread, which integrates visualization capabilities with advanced statistical methods for predicting the virus spread in the short run, using real-time data. The platform uses time series models to capture any possible non-linearity in the data. COVIDSpread enables lay users, and experts, to examine the data and develop several customized models with different restrictions such as models developed for a specific time window of the data. COVIDSpread is available here: http://vafaeelab.com/COVID19TS.html.
37
Pathak, Rajesh, Ranjan Das Gupta, Cleiton Guollo Taufemback, and Aviral Kumar Tiwari. "Testing the efficiency of metal's market: new evidence from a generalized spectral test." Studies in Economics and Finance 37, no. 2 (May 14, 2020): 311–21. http://dx.doi.org/10.1108/sef-07-2019-0253.
Full textAbstract:
Purpose This paper aims to examine the weak form of efficiency for price series of four precious metals, i.e. gold, silver, platinum and palladium, using a generalized spectral method. Design/methodology/approach The method has the advantage of detecting both linear and non-linear serial dependence in the conditional mean, and it is robust to various forms of conditional heteroscedasticity. The authors use three different rolling windows for the purpose of robustness. Findings The authors report weak form of efficiency across metals series for almost all rolling windows. The optimum efficiency for Gold and Palladium is achieved through 250 days rolling window estimates whereas it is 500 days rolling window for silver. Platinum has similar efficiency levels across rolling windows. The degree of efficiency for metal prices is observed to be varying over time with silver market possessing highest levels of efficiency. The efficiency synchronization also varies across rolling windows and metals. Research limitations/implications The results reveal that metal markets are efficient for most times implying the low predictability and the low likelihood of earning abnormal returns by speculating in these markets. Originality/value The study uses a relatively new statistical technique, the generalized spectral test, to capture linear and non-linear serial dependence. Therefore, the results possess adequate power against departure from market efficiency.
38
Xu, Bao Yu, Yi Lun Liu, Xu Dong Wang, and Fang Dong. "Stochastic Excitation Model of Strip Rolling Mill." Advanced Materials Research 216 (March 2011): 378–82. http://dx.doi.org/10.4028/www.scientific.net/amr.216.378.
Full textAbstract:
The stochastic excitation power spectral density (PSD) model and ARMA time series model are established based on the stochastic rolling force acquisition data, which is processed into stationary, normal and zero mean from a aluminum hot strip tandem mill. Characteristics of rolling force ARMA time series models are discussed by means of random process theory. The rolling forces PSD function of facilitating engineering application is obtained by utilizing Levenberg-Marquardt combined with generalized global planning algorithm, and the stochastic excitation model is established. It provides the basis for the prediction of rolling force.
39
Yuan, Can, Qi Cai, Gang Liu, and Feng Yan. "The Combinatorial Prediction about Chaotic Times Series of Natural Circulation Flow under Rolling Motion." Advanced Materials Research 989-994 (July 2014): 1348–51. http://dx.doi.org/10.4028/www.scientific.net/amr.989-994.1348.
Full textAbstract:
The paper has established a combinatorial prediction model of chaotic time series based on history data and coupling data. Through the study of the flow characteristic about natural circulation under rolling motion, the single variable reconstruction and coupling multivariate reconstruction are discussed for chaotic time series based on phase space reconstruction technique, and the combinatorial prediction model has been built which bases on developing trend of history data and coupling relationship of correlative data. The paper also studied an example of coolant volume flow prediction with a relative precision of 0.9804 with the established model. The result indicated that the model with high precision and robustness could apply for natural circulation coolant volume flow prediction under rolling motion.
40
Zhao Yong-Ping, Zhang Li-Yan, Li De-Cai, Wang Li-Feng, and Jiang Hong-Zhang. "Chaotic time series prediction using filtering window based least squares support vector regression." Acta Physica Sinica 62, no. 12 (2013): 120511. http://dx.doi.org/10.7498/aps.62.120511.
Full text
41
Feng, Fu Zhou, Dong Dong Zhu, Peng Cheng Jiang, and Hao Jiang. "GA-SVR Based Bearing Condition Degradation Prediction." Key Engineering Materials 413-414 (June 2009): 431–37. http://dx.doi.org/10.4028/www.scientific.net/kem.413-414.431.
Full textAbstract:
A genetic algorithm-support vector regression model (GA-SVR) is proposed for machine performance degradation prediction. The main idea of the method is firstly to select the condition-sensitive features extracted from rolling bearing vibration signals using Genetic Algorithm to form a condition vector. Then prediction model is established for each feature time series. And the third step is to establish support vector regression models to obtain prediction result in each series. Finally, the condition prognosis can be obtained through combing all components to form a condition vector. Vibration data from a rolling bearing bench test process are used to verify accuracy of the proposed method. The results show that the model is an effective prediction method with a higher speed and a better accuracy.
42
Ma, Leilei, Hong Jiang, Tongwei Ma, Xiangfeng Zhang, Yong Shen, and Lei Xia. "Fault Prediction of Rolling Element Bearings Using the Optimized MCKD–LSTM Model." Machines 10, no. 5 (May 6, 2022): 342. http://dx.doi.org/10.3390/machines10050342.
Full textAbstract:
The reliability and safety of rotating equipment depend on the performance of bearings. For complex systems with high reliability and safety needs, effectively predicting the fault data in the use stage has important guiding significance for reasonably formulating reliability plans and carrying out reliability maintenance activities. Many methods have been used to solve the problem of reliability prediction. Due to its convenience and efficiency, the data-driven method is increasingly widely used in practical reliability prediction. In order to ensure the reliability of bearing operation, the main objective of the present study is to establish a novel model based on the optimized maximum correlation kurtosis deconvolution (MCKD) and long short-term memory (LSTM) recurrent neural network to realize early bearing fault warnings by predicting bearing fault time series. The proposed model is based on the lifecycle vibration signal of the bearing. In the first step, the cuckoo search (CS) is utilized to optimize the parameter filter length and deconvolution period of MCKD, considering the influence of periodic bearing time series, and to improve the fault impact component of the optimized MCKD deconvolution time series. Then the LSTM learning rate is selected according to the deconvolution time series. Finally, the dataset obtained through various preprocessing approaches is used to train and predict the LSTM model. The analyses performed using the XJTU-SY bearing dataset demonstrate that the prediction results are in good consistency with real fault data, and the average prediction accuracy of the optimized MCKD–LSTM model is 26% higher than that of the original time series.
43
Gao, Lv, Wu, Si, and Hu. "Method for Determining Starting Point of Rolling Bearing Life Prediction Based on Linear Regression." Electronics 8, no. 9 (August 22, 2019): 923. http://dx.doi.org/10.3390/electronics8090923.
Full textAbstract:
Aimed at addressing the problem that the subjective selection of start prediction time (SPT) in rolling bearing remaining useful life (RUL) prediction will lead to excessive noise in the prediction signal, a linear-regression-based SPT point determination was proposed. The sliding window linear regression method was used to establish sliding windows in the root mean square (RMS) range to obtain the RMS gradient domain. The threshold for the RMS gradient was set, and the continuous trigger threshold mechanism to determine the SPT point was used. The experimental results show that the linear-regression-based method can adaptively determine the SPT point and improve the accuracy of life prediction.
44
Yu, Lean, and Yueming Ma. "A Data-Trait-Driven Rolling Decomposition-Ensemble Model for Gasoline Consumption Forecasting." Energies 14, no. 15 (July 29, 2021): 4604. http://dx.doi.org/10.3390/en14154604.
Full textAbstract:
In order to predict the gasoline consumption in China, this paper propose a novel data-trait-driven rolling decomposition-ensemble model. This model consists of five steps: the data trait test, data decomposition, component trait analysis, component prediction and ensemble output. In the data trait test and component trait analysis, the original time series and each decomposed component are thoroughly analyzed to explore hidden data traits. According to these results, decomposition models and prediction models are selected to complete the original time series data decomposition and decomposed component prediction. In the ensemble output, the ensemble method corresponding to the decomposition method is used for final aggregation. In particular, this methodology introduces the rolling mechanism to solve the misuse of future information problem. In order to verify the effectiveness of the model, the quarterly gasoline consumption data from four provinces in China are used. The experimental results show that the proposed model is significantly better than the single prediction models and decomposition-ensemble models without the rolling mechanism. It can be seen that the decomposition-ensemble model with data-trait-driven modeling ideas and rolling decomposition and prediction mechanism possesses the superiority and robustness in terms of the evaluation criteria of horizontal and directional prediction.
45
Dong, Limei, Desheng Fang, Xi Wang, Wei Wei, Robertas Damaševičius, Rafał Scherer, and Marcin Woźniak. "Prediction of Streamflow Based on Dynamic Sliding Window LSTM." Water 12, no. 11 (October 29, 2020): 3032. http://dx.doi.org/10.3390/w12113032.
Full textAbstract:
The streamflow of the upper reaches of the Yangtze River exhibits different timing and periodicity characteristics in different quarters and months of the year, which makes it difficult to predict. Existing sliding window-based methods usually use a fixed-size window, for which the window size selection is random, resulting in large errors. This paper proposes a dynamic sliding window method that reflects the different timing and periodicity characteristics of the streamflow in different months of the year. Multiple datasets of different months are generated using a dynamic window at first, then the long-short term memory (LSTM) is used to select the optimal window, and finally, the dataset of the optimal window size is used for verification. The proposed method was tested using the hydrological data of Zhutuo Hydrological Station (China). A comparison between the flow prediction data and the measured data shows that the prediction method based on a dynamic sliding window LSTM is more accurate by 8.63% and 3.85% than the prediction method based on fixed window LSTM and the dynamic sliding window back-propagation neural network, respectively. This method can be generally used for the time series data prediction with different periodic characteristics.
46
Cai, Bowen, and Qianli Di. "Different Forecasting Model Comparison for Near Future Crash Prediction." Applied Sciences 13, no. 2 (January 5, 2023): 759. http://dx.doi.org/10.3390/app13020759.
Full textAbstract:
A traffic crash is becoming one of the major factors that leads to unexpected death in the world. Short window traffic crash prediction in the near future is becoming more pragmatic with the advancements in the fields of artificial intelligence and traffic sensor technology. Short window traffic prediction can monitor traffic in real time, identify unsafe traffic dynamics, and implement suitable interventions for traffic conflicts. Crash prediction being an important component of intelligent traffic systems, it plays a crucial role in the development of proactive road safety management systems. Some near future crash prediction models were put forward in recent years; further improvements need to be implemented for actual applications. This paper utilizes traffic accident data from the study Freeway in China to build a time series-based count data model for daily crash prediction. Lane traffic flow, weather information, vehicle speed, and truck to car ratio were extracted from the deployment of non-intrusive detection systems with support of the Bridge Management Administration study and were input into the model as independent variables. Different types of prediction models in machine learning and time series forecasting methods such as boosting, ARIMA, time-series count data model, etc. are compared within the paper. Results show that integrating time series with a count data model can capture traffic accident features and account for the temporal structure for variable serial correlation. A prediction error of 0.7 was achieved according to Root Mean Squared Deviation.
47
Liu, Jingzhong. "Adaptive forgetting factor OS-ELM and bootstrap for time series prediction." International Journal of Modeling, Simulation, and Scientific Computing 08, no. 03 (September 2017): 1750029. http://dx.doi.org/10.1142/s1793962317500295.
Full textAbstract:
Online sequential extreme learning machine (OS-ELM) for single-hidden layer feedforward networks (SLFNs) is an effective machine learning algorithm. But OS-ELM has some underlying weaknesses of neglecting time series timeliness and being incapable to provide quantitative uncertainty for prediction. To overcome these shortcomings, a time series prediction method is presented based on the combination of OS-ELM with adaptive forgetting factor (AFF-OS-ELM) and bootstrap (B-AFF-OS-ELM). Firstly, adaptive forgetting factor is added into OS-ELM for adjusting the effective window length of training data during OS-ELM sequential learning phase. Secondly, the current bootstrap is developed to fit time series prediction online. Then associated with improved bootstrap, the proposed method can compute prediction interval as uncertainty information, meanwhile the improved bootstrap enhances prediction accuracy and stability of AFF-OS-ELM. Performances of B-AFF-OS-ELM are benchmarked with other traditional and improved OS-ELM on simulation and practical time series data. Results indicate the significant performances achieved by B-AFF-OS-ELM.
48
Gürsakal, Necmi, Fırat Melih Yilmaz, and Erginbay Uğurlu:. "Finding opportunity windows in time series data using the sliding window technique: The case of stock exchanges." Econometrics 24, no. 3 (2020): 1–19. http://dx.doi.org/10.15611/eada.2020.3.01.
Full textAbstract:
Data have shapes, and human intelligence and perception have to classify the forms of data to understand and interpret them. This article uses a sliding window technique and the main aim is to answer two questions. Is there an opportunity window in time series of stock exchange index? The second question is how to find a way to use the opportunity window if there is one. The authors defined the term opportunity window as a window that is generated in the sliding window technique and can be used for forecasting. In analysis, the study determined the different frequencies and explained how to evaluate opportunity windows embedded using time series data for the S&P 500, the DJIA, and the Russell 2000 indices. As a result, for the S&P 500 the last days of the patterns 0111, 1100, 0011; for the DJIA the last days of the patterns 0101, 1001, 0011; and finally for the Russell 2000, the last days of the patterns 0100, 1001, 1100 are opportunity windows for prediction
49
Gupta, Mehak, Raphael Poulain, Thao-Ly T. Phan, H. Timothy Bunnell, and Rahmatollah Beheshti. "Flexible-Window Predictions on Electronic Health Records." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 11 (June 28, 2022): 12510–16. http://dx.doi.org/10.1609/aaai.v36i11.21520.
Full textAbstract:
Various types of machine learning techniques are available for analyzing electronic health records (EHRs). For predictive tasks, most existing methods either explicitly or implicitly divide these time-series datasets into predetermined observation and prediction windows. Patients have different lengths of medical history and the desired predictions (for purposes such as diagnosis or treatment) are required at different times in the future. In this paper, we propose a method that uses a sequence-to-sequence generator model to transfer an input sequence of EHR data to a sequence of user-defined target labels, providing the end-users with ``flexible'' observation and prediction windows to define. We use adversarial and semi-supervised approaches in our design, where the sequence-to-sequence model acts as a generator and a discriminator distinguishes between the actual (observed) and generated labels. We evaluate our models through an extensive series of experiments using two large EHR datasets from adult and pediatric populations. In an obesity predicting case study, we show that our model can achieve superior results in flexible-window prediction tasks, after being trained once and even with large missing rates on the input EHR data. Moreover, using a number of attention analysis experiments, we show that the proposed model can effectively learn more relevant features in different prediction tasks.
50
Bhanja, Samit, and Abhisek Das. "A hybrid deep learning model for air quality time series prediction." Indonesian Journal of Electrical Engineering and Computer Science 22, no. 3 (June 1, 2021): 1611. http://dx.doi.org/10.11591/ijeecs.v22.i3.pp1611-1618.
Full textAbstract:
Air quality (mainly PM2.5) forecasting plays an important role in the early detection and control of air pollution. In recent times, numerous deep learning-based models have been proposed to forecast air quality more accurately. The success of these deep learning models heavily depends on the two key factors viz. proper representation of the input data and preservation of temporal order of the input data during the feature’s extraction phase. Here we propose a hybrid deep neural network (HDNN) framework to forecast the PM2.5 by integrating two popular deep learning architectures, viz. Convolutional neural network (CNN) and bidirectional long short-term memory (BDLSTM) network. Here we build a 3D input tensor so that CNN can extract the trends and spatial features more accurately within the input window. Here we also introduce a linking layer between CNN and BDLSTM to maintain the temporal ordering of feature vectors. In the end, our proposed HDNN framework is compared with the state-of-the-art models, and we show that HDNN outruns other models in terms of prediction accuracy.