This paper presents a comparative study of ARIMA and Neural Network AutoRegressive (NNAR) models for time series forecasting. The study focuses on simulated data generated using ARIMA(1, 1, 0) and applies both models ...This paper presents a comparative study of ARIMA and Neural Network AutoRegressive (NNAR) models for time series forecasting. The study focuses on simulated data generated using ARIMA(1, 1, 0) and applies both models for training and forecasting. Model performance is evaluated using MSE, AIC, and BIC. The models are further applied to neonatal mortality data from Saudi Arabia to assess their predictive capabilities. The results indicate that the NNAR model outperforms ARIMA in both training and forecasting.展开更多
Singular spectrum analysis is widely used in geodetic time series analysis.However,when extracting time-varying periodic signals from a large number of Global Navigation Satellite System(GNSS)time series,the selection...Singular spectrum analysis is widely used in geodetic time series analysis.However,when extracting time-varying periodic signals from a large number of Global Navigation Satellite System(GNSS)time series,the selection of appropriate embedding window size and principal components makes this method cumbersome and inefficient.To improve the efficiency and accuracy of singular spectrum analysis,this paper proposes an adaptive singular spectrum analysis method by combining spectrum analysis with a new trace matrix.The running time and correlation analysis indicate that the proposed method can adaptively set the embedding window size to extract the time-varying periodic signals from GNSS time series,and the extraction efficiency of a single time series is six times that of singular spectrum analysis.The method is also accurate and more suitable for time-varying periodic signal analysis of global GNSS sites.展开更多
In order to attain good quality transfer function estimates from magnetotelluric field data(i.e.,smooth behavior and small uncertainties across all frequencies),we compare time series data processing with and without ...In order to attain good quality transfer function estimates from magnetotelluric field data(i.e.,smooth behavior and small uncertainties across all frequencies),we compare time series data processing with and without a multitaper approach for spectral estimation.There are several common ways to increase the reliability of the Fourier spectral estimation from experimental(noisy)data;for example to subdivide the experimental time series into segments,taper these segments(using single taper),perform the Fourier transform of the individual segments,and average the resulting spectra.展开更多
Multivariate time series forecasting iswidely used in traffic planning,weather forecasting,and energy consumption.Series decomposition algorithms can help models better understand the underlying patterns of the origin...Multivariate time series forecasting iswidely used in traffic planning,weather forecasting,and energy consumption.Series decomposition algorithms can help models better understand the underlying patterns of the original series to improve the forecasting accuracy of multivariate time series.However,the decomposition kernel of previous decomposition-based models is fixed,and these models have not considered the differences in frequency fluctuations between components.These problems make it difficult to analyze the intricate temporal variations of real-world time series.In this paper,we propose a series decomposition-based Mamba model,DecMamba,to obtain the intricate temporal dependencies and the dependencies among different variables of multivariate time series.A variable-level adaptive kernel combination search module is designed to interact with information on different trends and periods between variables.Two backbone structures are proposed to emphasize the differences in frequency fluctuations of seasonal and trend components.Mamba with superior performance is used instead of a Transformer in backbone structures to capture the dependencies among different variables.A new embedding block is designed to capture the temporal features better,especially for the high-frequency seasonal component whose semantic information is difficult to acquire.A gating mechanism is introduced to the decoder in the seasonal backbone to improve the prediction accuracy.A comparison with ten state-of-the-art models on seven real-world datasets demonstrates that DecMamba can better model the temporal dependencies and the dependencies among different variables,guaranteeing better prediction performance for multivariate time series.展开更多
Iced transmission line galloping poses a significant threat to the safety and reliability of power systems,leading directly to line tripping,disconnections,and power outages.Existing early warning methods of iced tran...Iced transmission line galloping poses a significant threat to the safety and reliability of power systems,leading directly to line tripping,disconnections,and power outages.Existing early warning methods of iced transmission line galloping suffer from issues such as reliance on a single data source,neglect of irregular time series,and lack of attention-based closed-loop feedback,resulting in high rates of missed and false alarms.To address these challenges,we propose an Internet of Things(IoT)empowered early warning method of transmission line galloping that integrates time series data from optical fiber sensing and weather forecast.Initially,the method applies a primary adaptive weighted fusion to the IoT empowered optical fiber real-time sensing data and weather forecast data,followed by a secondary fusion based on a Back Propagation(BP)neural network,and uses the K-medoids algorithm for clustering the fused data.Furthermore,an adaptive irregular time series perception adjustment module is introduced into the traditional Gated Recurrent Unit(GRU)network,and closed-loop feedback based on attentionmechanism is employed to update network parameters through gradient feedback of the loss function,enabling closed-loop training and time series data prediction of the GRU network model.Subsequently,considering various types of prediction data and the duration of icing,an iced transmission line galloping risk coefficient is established,and warnings are categorized based on this coefficient.Finally,using an IoT-driven realistic dataset of iced transmission line galloping,the effectiveness of the proposed method is validated through multi-dimensional simulation scenarios.展开更多
Aiming at the problem of on-line damage diagnosis in structural health monitoring （SHM）, an algorithm of feature extraction and damage alarming based on auto-regressive moving-average （ARMA） time series analysis i...Aiming at the problem of on-line damage diagnosis in structural health monitoring （SHM）, an algorithm of feature extraction and damage alarming based on auto-regressive moving-average （ARMA） time series analysis is presented. The monitoring data were first modeled as ARMA models, while a principalcomponent matrix derived from the AR coefficients of these models was utilized to establish the Mahalanobisdistance criterion functions. Then, a new damage-sensitive feature index DDSF is proposed. A hypothesis test involving the t-test method is further applied to obtain a decision of damage alarming as the mean value of DDSF had significantly changed after damage. The numerical results of a three-span-girder model shows that the defined index is sensitive to subtle structural damage, and the proposed algorithm can be applied to the on-line damage alarming in SHM.展开更多
Time series forecasting is essential for generating predictive insights across various domains, including healthcare, finance, and energy. This study focuses on forecasting patient health data by comparing the perform...Time series forecasting is essential for generating predictive insights across various domains, including healthcare, finance, and energy. This study focuses on forecasting patient health data by comparing the performance of traditional linear time series models, namely Autoregressive Integrated Moving Average (ARIMA), Seasonal ARIMA, and Moving Average (MA) against neural network architectures. The primary goal is to evaluate the effectiveness of these models in predicting healthcare outcomes using patient records, specifically the Cancerpatient.xlsx dataset, which tracks variables such as patient age, symptoms, genetic risk factors, and environmental exposures over time. The proposed strategy involves training each model on historical patient data to predict age progression and other related health indicators, with performance evaluated using Mean Squared Error (MSE) and Root Mean Squared Error (RMSE) metrics. Our findings reveal that neural networks consistently outperform ARIMA and SARIMA by capturing non-linear patterns and complex temporal dependencies within the dataset, resulting in lower forecasting errors. This research highlights the potential of neural networks to enhance predictive accuracy in healthcare applications, supporting better resource allocation, patient monitoring, and long-term health outcome predictions.展开更多
Time series forecasting is important in the fields of finance,energy,and meteorology,but traditional methods often fail to cope with the complex nonlinear and nonstationary processes of real data.In this paper,we prop...Time series forecasting is important in the fields of finance,energy,and meteorology,but traditional methods often fail to cope with the complex nonlinear and nonstationary processes of real data.In this paper,we propose the FractalNet-LSTM model,which combines fractal convolutional units with recurrent long short-term memory(LSTM)layers to model time series efficiently.To test the effectiveness of the model,data with complex structures and patterns,in particular,with seasonal and cyclical effects,were used.To better demonstrate the obtained results and the formed conclusions,the model performance was shown on the datasets of electricity consumption,sunspot activity,and Spotify stock price.The result showed that the proposed model outperforms traditional approaches at medium forecasting horizons and demonstrates high accuracy for data with long-term and cyclical dependencies.However,for financial data with high volatility,the model’s efficiency decreases at long forecasting horizons,indicating the need for further adaptation.The findings suggest further adaptation.The findings suggest that integrating fractal properties into neural network architecture improves the accuracy of time series forecasting and can be useful for developing more accurate and reliable forecasting systems in various industries.展开更多
Accurate forecasting of oil production is essential for optimizing resource management and minimizing operational risks in the energy sector. Traditional time-series forecasting techniques, despite their widespread ap...Accurate forecasting of oil production is essential for optimizing resource management and minimizing operational risks in the energy sector. Traditional time-series forecasting techniques, despite their widespread application, often encounter difficulties in handling the complexities of oil production data, which is characterized by non-linear patterns, skewed distributions, and the presence of outliers. To overcome these limitations, deep learning methods have emerged as more robust alternatives. However, while deep neural networks offer improved accuracy, they demand substantial amounts of data for effective training. Conversely, shallow networks with fewer layers lack the capacity to model complex data distributions adequately. To address these challenges, this study introduces a novel hybrid model called Transfer LSTM to GRU (TLTG), which combines the strengths of deep and shallow networks using transfer learning. The TLTG model integrates Long Short-Term Memory (LSTM) networks and Gated Recurrent Units (GRU) to enhance predictive accuracy while maintaining computational efficiency. Gaussian transformation is applied to the input data to reduce outliers and skewness, creating a more normal-like distribution. The proposed approach is validated on datasets from various wells in the Tahe oil field, China. Experimental results highlight the superior performance of the TLTG model, achieving 100% accuracy and faster prediction times (200 s) compared to eight other approaches, demonstrating its effectiveness and efficiency.展开更多
Site index(SI)is determined from the top height development and is a proxy for forest productivity,defined as the expected top height for a given species at a certain index age.In Norway,an index age of 40 years is us...Site index(SI)is determined from the top height development and is a proxy for forest productivity,defined as the expected top height for a given species at a certain index age.In Norway,an index age of 40 years is used.By using bi-temporal airborne laser scanning(ALS)data,SI can be determined using models estimated from SI observed on field plots(the direct approach)or from predicted top heights at two points in time(the height differential approach).Time series of ALS data may enhance SI determination compared to conventional methods used in operational forest inventory by providing more detailed information about the top height development.We used longitudinal data comprising spatially consistent field and ALS data collected from training plots in 1999,2010,and 2022 to determine SI using the direct and height differential approaches using all combinations of years and performed an external validation.We also evaluated the use of data assimilation.Values of root mean square error obtained from external validation were in the ranges of 16.3%–21.4%and 12.8%–20.6%of the mean fieldregistered SI for the direct approach and the height differential approach,respectively.There were no statistically significant effects of time series length or the number of points in time on the obtained accuracies.Data assimilation did not result in any substantial improvement in the obtained accuracies.Although a time series of ALS data did not yield greater accuracies compared to using only two points in time,a larger proportion of the study area could be used in ALS-based determination of SI when a time series was available.This was because areas that were unsuitable for SI determination between two points in time could be subject to SI determination based on data from another part of the time series.展开更多
Load time series analysis is critical for resource management and optimization decisions,especially automated analysis techniques.Existing research has insufficiently interpreted the overall characteristics of samples...Load time series analysis is critical for resource management and optimization decisions,especially automated analysis techniques.Existing research has insufficiently interpreted the overall characteristics of samples,leading to significant differences in load level detection conclusions for samples with different characteristics(trend,seasonality,cyclicality).Achieving automated,feature-adaptive,and quantifiable analysis methods remains a challenge.This paper proposes a Threshold Recognition-based Load Level Detection Algorithm(TRLLD),which effectively identifies different load level regions in samples of arbitrary size and distribution type based on sample characteristics.By utilizing distribution density uniformity,the algorithm classifies data points and ultimately obtains normalized load values.In the feature recognition step,the algorithm employs the Density Uniformity Index Based on Differences(DUID),High Load Level Concentration(HLLC),and Low Load Level Concentration(LLLC)to assess sample characteristics,which are independent of specific load values,providing a standardized perspective on features,ensuring high efficiency and strong interpretability.Compared to traditional methods,the proposed approach demonstrates better adaptive and real-time analysis capabilities.Experimental results indicate that it can effectively identify high load and low load regions in 16 groups of time series samples with different load characteristics,yielding highly interpretable results.The correlation between the DUID and sample density distribution uniformity reaches 98.08%.When introducing 10% MAD intensity noise,the maximum relative error is 4.72%,showcasing high robustness.Notably,it exhibits significant advantages in general and low sample scenarios.展开更多
The annual frequency of red tides from 1977 to 2012 and the monthly frequency of red tides from 2001 to 2012 in China seas were used to establish the time series of red tide annual frequency and monthly frequency, res...The annual frequency of red tides from 1977 to 2012 and the monthly frequency of red tides from 2001 to 2012 in China seas were used to establish the time series of red tide annual frequency and monthly frequency, respectively. The annual frequency fit well with time segments revealed by piecewise linear regression analysis. The seasonal maximum of monthly frequency was in May （-18.22）, and the stochastic volatility tended to increase gradually with time series, with peak values occurring from May to July. Holt exponential smoothing and Holt-winter exponential smoothing were used to predict red tide annual and monthly frequencies, which revealed that the annual frequency of red tides would rise slowly by one time from 2013 to 2020, and that red tides would mainly occur from May to July in 2013-2016 with a peak value of about 25 times in May.展开更多
In this paper, we propose a cross reference method for nonlinear time series analyzing in semi blind case, that is, the dynamic equations modeling the time series are known but the corresponding parameters are not. ...In this paper, we propose a cross reference method for nonlinear time series analyzing in semi blind case, that is, the dynamic equations modeling the time series are known but the corresponding parameters are not. The tasks of noise reduction and parameter estimation which were fulfilled separately before are combined iteratively. With the positive interaction between the two processing modules, the method is somewhat superior. Some prior work can be viewed as special cases of this general framework. The simulations for noise reduction and parameter estimation of contaminated chaotic time series show improved performance of our method compared with previous work.展开更多
This paper presents a novel approach to identify and correct the gross errors in the microelectromechanical system （MEMS） gyroscope used in ground vehicles by means of time series analysis. According to the characte...This paper presents a novel approach to identify and correct the gross errors in the microelectromechanical system （MEMS） gyroscope used in ground vehicles by means of time series analysis. According to the characteristics of autocorrelation function （ACF） and partial autocorrelation function （PACF）, an autoregressive integrated moving average （ARIMA） model is roughly constructed. The rough model is optimized by combining with Akaike＇s information criterion （A/C）, and the parameters are estimated based on the least squares algorithm. After validation testing, the model is utilized to forecast the next output on the basis of the previous measurement. When the difference between the measurement and its prediction exceeds the defined threshold, the measurement is identified as a gross error and remedied by its prediction. A case study on the yaw rate is performed to illustrate the developed algorithm. Experimental results demonstrate that the proposed approach can effectively distinguish gross errors and make some reasonable remedies.展开更多
Objective To recognize the spatial and temporal characteristics of iodine deficiency disorders(IDD),China national IDD surveillance data for the years of 1995–2018 were analyzed.Methods Time series analysis was used ...Objective To recognize the spatial and temporal characteristics of iodine deficiency disorders(IDD),China national IDD surveillance data for the years of 1995–2018 were analyzed.Methods Time series analysis was used to describe and predict the IDD related indicators,and spatial analysis was used to analyze the spatial distribution of salt iodine levels.Results In China,the median urinary iodine concentration increased in 1995–1997,then decreased to adequate levels,and are expected to remain appropriate in 2019–2022.The goiter rate continually decreased and is expected to be maintained at a low level.Since 2002,the coverage rates of iodized salt and the consumption rates of qualified iodized salt(the percentage of qualified iodized salt in all tested salt) increased and began to decline in 2012;they are expected to continue to decrease.Spatial epidemiological analysis indicated a positive spatial correlation in 2016–2018 and revealed feature regarding the spatial distribution of salt related indicators in coastal areas and areas near iodine-excess areas.Conclusions Iodine nutrition in China showed gradual improvements.However,a recent decline has been observed in some areas following changes in the iodized salt supply in China.In the future,more regulations regarding salt management should be issued to strengthen IDD control and prevention measures,and avoid the recurrence of IDD.展开更多
In order to study the hydrodynamic characteristics of the karst aquifers in northern China,time series analyses(correlation and spectral analysis in addition with hydrograph recession analysis)are applied on Baotu Spr...In order to study the hydrodynamic characteristics of the karst aquifers in northern China,time series analyses(correlation and spectral analysis in addition with hydrograph recession analysis)are applied on Baotu Spring and Heihu Spring in Jinan karst spring system,a typical karst spring system in northern China.Results show that the auto-correlation coefficient of spring water level reaches the value of 0.2 after 123 days and 117 days for Baotu Spring and Heihu Spring,respectively.The regulation time obtained from the simple spectral density function in the same period is 187 days and 175 days for Baotu Spring and Heihu Spring.The auto-correlation coefficient of spring water level reaches the value of 0.2 in 34-82 days,and regulation time ranges among 40-59 days for every single hydrological year.The delay time between precipitation and spring water level obtained from cross correlation function is around 56 days for the period of 2012-2019,and varies among 30-79 days for every single hydrological year.In addition,the spectral bands in cross amplitude functions and gain functions are small with 0.02,and the values in the coherence functions are small.All these behaviors illustrate that Jinan karst spring system has a strong memory effect,large storage capacity,noticeable regulation effect,and time series analysis is a useful tool for studying the hydrodynamic characteristics of karst spring system in northern China.展开更多
Objective To investigate the relation between air pollution exposure and preterm birth in Shanghai, China. Methods We examined the effect of ambient air pollution on preterm birth using time-series approach in Shangha...Objective To investigate the relation between air pollution exposure and preterm birth in Shanghai, China. Methods We examined the effect of ambient air pollution on preterm birth using time-series approach in Shanghai in 2004. This method can eliminate potential confounding by individual risk factors that do not change over a short period of time. Daily numbers of preterm births were obtained from the live birth database maintained by Shanghai Municipal Center of Disease Control and Prevention. We used the generalized additive model （GAM） with penalized splines to analyze the relation between preterm birth, air pollution, and covariates. Results We observed a significant effect of outdoor air pollution only with 8-week exposure before preterm births. An increase of 10 μg/m^3 of 8-week average PM10, SO2, NO2, and O3 corresponded to 4.42% （95%CI 1.60%, 7.25%）, 11.89% （95%CI 6.69%, 17.09%）, 5.43% （95%CI 1.78%, 9.08%）, and 4.63% （95%CI 0.35%, 8.91%） increase of preterm birth. We did not find any significant acute effect of outdoor air pollution on preterm birth in the week before birth. Conclusion Ambient air pollution may contribute to the risk of preterm birth in Shanghai. Our analyses also strengthen the rationale for further limiting air pollution level in the city.展开更多
BACKGROUND Hepatitis B(HB)and hepatitis C(HC)place the largest burden in China,and a goal of eliminating them as a major public health threat by 2030 has been set.Making more informed and accurate forecasts of their s...BACKGROUND Hepatitis B(HB)and hepatitis C(HC)place the largest burden in China,and a goal of eliminating them as a major public health threat by 2030 has been set.Making more informed and accurate forecasts of their spread is essential for developing effective strategies,heightening the requirement for early warning to deal with such a major public health threat.AIM To monitor HB and HC epidemics by the design of a paradigmatic seasonal autoregressive fractionally integrated moving average(SARFIMA)for projections into 2030,and to compare the effectiveness with the seasonal autoregressive integrated moving average(SARIMA).METHODS Monthly HB and HC incidence cases in China were obtained from January 2004 to June 2023.Descriptive analysis and the Hodrick-Prescott method were employed to identify trends and seasonality.Two periods(from January 2004 to June 2022 and from January 2004 to December 2015,respectively)were used as the training sets to develop both models,while the remaining periods served as the test sets to evaluate the forecasting accuracy.RESULTS There were incidents of 23400874 HB cases and 3590867 HC cases from January 2004 to June 2023.Overall,HB remained steady[average annual percentage change(AAPC)=0.44,95%confidence interval(95%CI):-0.94-1.84]while HC was increasing(AAPC=8.91,95%CI:6.98-10.88),and both had a peak in March and a trough in February.In the 12-step-ahead HB forecast,the mean absolute deviation(15211.94),root mean square error(18762.94),mean absolute percentage error(0.17),mean error rate(0.15),and root mean square percentage error(0.25)under the best SARFIMA(3,0,0)(0,0.449,2)12 were smaller than those under the best SARIMA(3,0,0)(0,1,2)12(16867.71,20775.12,0.19,0.17,and 0.27,respectively).Similar results were also observed for the 90-step-ahead HB,12-step-ahead HC,and 90-step-ahead HC forecasts.The predicted HB incidents totaled 9865400(95%CI:7508093-12222709)cases and HC totaled 1659485(95%CI:856681-2462290)cases during 2023-2030.CONCLUSION Under current interventions,China faces enormous challenges to eliminate HB and HC epidemics by 2030,and effective strategies must be reinforced.The integration of SARFIMA into public health for the management of HB and HC epidemics can potentially result in more informed and efficient interventions,surpassing the capabilities of SARIMA.展开更多
Time-series analysis is important to a wide range of disciplines transcending both the physical and social sciences for proactive policy decisions. Statistical models have sound theoretical basis and have been success...Time-series analysis is important to a wide range of disciplines transcending both the physical and social sciences for proactive policy decisions. Statistical models have sound theoretical basis and have been successfully used in a number of problem domains in time series forecasting. Due to power and flexibility, Box-Jenkins ARIMA model has gained enormous popularity in many areas and research practice for the last three decades. More recently, the neural networks have been shown to be a promising alternative tool for modeling and forecasting owing to their ability to capture the nonlinearity in the data. However, despite the popularity and the superiority of ARIMA and ANN models, the empirical forecasting performance has been rather mixed so that no single method is best in every situation. In this study, a hybrid ARIMA and neural networks model to time series forecasting is proposed. The basic idea behind the model combination is to use each model’s unique features to capture different patterns in the data. With three real data sets, empirical results evidently show that the hybrid model outperforms ARIMA and ANN model noticeably in terms of forecasting accuracy used in isolation.展开更多
文摘This paper presents a comparative study of ARIMA and Neural Network AutoRegressive (NNAR) models for time series forecasting. The study focuses on simulated data generated using ARIMA(1, 1, 0) and applies both models for training and forecasting. Model performance is evaluated using MSE, AIC, and BIC. The models are further applied to neonatal mortality data from Saudi Arabia to assess their predictive capabilities. The results indicate that the NNAR model outperforms ARIMA in both training and forecasting.
基金supported by the National Natural Science Foundation of China(Grants:42204006,42274053,42030105,and 41504031)the Open Research Fund Program of the Key Laboratory of Geospace Environment and Geodesy,Ministry of Education,China(Grants:20-01-03 and 21-01-04)。
文摘Singular spectrum analysis is widely used in geodetic time series analysis.However,when extracting time-varying periodic signals from a large number of Global Navigation Satellite System(GNSS)time series,the selection of appropriate embedding window size and principal components makes this method cumbersome and inefficient.To improve the efficiency and accuracy of singular spectrum analysis,this paper proposes an adaptive singular spectrum analysis method by combining spectrum analysis with a new trace matrix.The running time and correlation analysis indicate that the proposed method can adaptively set the embedding window size to extract the time-varying periodic signals from GNSS time series,and the extraction efficiency of a single time series is six times that of singular spectrum analysis.The method is also accurate and more suitable for time-varying periodic signal analysis of global GNSS sites.
文摘In order to attain good quality transfer function estimates from magnetotelluric field data(i.e.,smooth behavior and small uncertainties across all frequencies),we compare time series data processing with and without a multitaper approach for spectral estimation.There are several common ways to increase the reliability of the Fourier spectral estimation from experimental(noisy)data;for example to subdivide the experimental time series into segments,taper these segments(using single taper),perform the Fourier transform of the individual segments,and average the resulting spectra.
基金supported in part by the Interdisciplinary Project of Dalian University(DLUXK-2023-ZD-001).
文摘Multivariate time series forecasting iswidely used in traffic planning,weather forecasting,and energy consumption.Series decomposition algorithms can help models better understand the underlying patterns of the original series to improve the forecasting accuracy of multivariate time series.However,the decomposition kernel of previous decomposition-based models is fixed,and these models have not considered the differences in frequency fluctuations between components.These problems make it difficult to analyze the intricate temporal variations of real-world time series.In this paper,we propose a series decomposition-based Mamba model,DecMamba,to obtain the intricate temporal dependencies and the dependencies among different variables of multivariate time series.A variable-level adaptive kernel combination search module is designed to interact with information on different trends and periods between variables.Two backbone structures are proposed to emphasize the differences in frequency fluctuations of seasonal and trend components.Mamba with superior performance is used instead of a Transformer in backbone structures to capture the dependencies among different variables.A new embedding block is designed to capture the temporal features better,especially for the high-frequency seasonal component whose semantic information is difficult to acquire.A gating mechanism is introduced to the decoder in the seasonal backbone to improve the prediction accuracy.A comparison with ten state-of-the-art models on seven real-world datasets demonstrates that DecMamba can better model the temporal dependencies and the dependencies among different variables,guaranteeing better prediction performance for multivariate time series.
基金research was funded by Science and Technology Project of State Grid Corporation of China under grant number 5200-202319382A-2-3-XG.
文摘Iced transmission line galloping poses a significant threat to the safety and reliability of power systems,leading directly to line tripping,disconnections,and power outages.Existing early warning methods of iced transmission line galloping suffer from issues such as reliance on a single data source,neglect of irregular time series,and lack of attention-based closed-loop feedback,resulting in high rates of missed and false alarms.To address these challenges,we propose an Internet of Things(IoT)empowered early warning method of transmission line galloping that integrates time series data from optical fiber sensing and weather forecast.Initially,the method applies a primary adaptive weighted fusion to the IoT empowered optical fiber real-time sensing data and weather forecast data,followed by a secondary fusion based on a Back Propagation(BP)neural network,and uses the K-medoids algorithm for clustering the fused data.Furthermore,an adaptive irregular time series perception adjustment module is introduced into the traditional Gated Recurrent Unit(GRU)network,and closed-loop feedback based on attentionmechanism is employed to update network parameters through gradient feedback of the loss function,enabling closed-loop training and time series data prediction of the GRU network model.Subsequently,considering various types of prediction data and the duration of icing,an iced transmission line galloping risk coefficient is established,and warnings are categorized based on this coefficient.Finally,using an IoT-driven realistic dataset of iced transmission line galloping,the effectiveness of the proposed method is validated through multi-dimensional simulation scenarios.
基金The National High Technology Research and Devel-opment Program of China (863Program) (No2006AA04Z416)the National Natural Science Foundation of China (No50538020)
文摘Aiming at the problem of on-line damage diagnosis in structural health monitoring （SHM）, an algorithm of feature extraction and damage alarming based on auto-regressive moving-average （ARMA） time series analysis is presented. The monitoring data were first modeled as ARMA models, while a principalcomponent matrix derived from the AR coefficients of these models was utilized to establish the Mahalanobisdistance criterion functions. Then, a new damage-sensitive feature index DDSF is proposed. A hypothesis test involving the t-test method is further applied to obtain a decision of damage alarming as the mean value of DDSF had significantly changed after damage. The numerical results of a three-span-girder model shows that the defined index is sensitive to subtle structural damage, and the proposed algorithm can be applied to the on-line damage alarming in SHM.
文摘Time series forecasting is essential for generating predictive insights across various domains, including healthcare, finance, and energy. This study focuses on forecasting patient health data by comparing the performance of traditional linear time series models, namely Autoregressive Integrated Moving Average (ARIMA), Seasonal ARIMA, and Moving Average (MA) against neural network architectures. The primary goal is to evaluate the effectiveness of these models in predicting healthcare outcomes using patient records, specifically the Cancerpatient.xlsx dataset, which tracks variables such as patient age, symptoms, genetic risk factors, and environmental exposures over time. The proposed strategy involves training each model on historical patient data to predict age progression and other related health indicators, with performance evaluated using Mean Squared Error (MSE) and Root Mean Squared Error (RMSE) metrics. Our findings reveal that neural networks consistently outperform ARIMA and SARIMA by capturing non-linear patterns and complex temporal dependencies within the dataset, resulting in lower forecasting errors. This research highlights the potential of neural networks to enhance predictive accuracy in healthcare applications, supporting better resource allocation, patient monitoring, and long-term health outcome predictions.
文摘Time series forecasting is important in the fields of finance,energy,and meteorology,but traditional methods often fail to cope with the complex nonlinear and nonstationary processes of real data.In this paper,we propose the FractalNet-LSTM model,which combines fractal convolutional units with recurrent long short-term memory(LSTM)layers to model time series efficiently.To test the effectiveness of the model,data with complex structures and patterns,in particular,with seasonal and cyclical effects,were used.To better demonstrate the obtained results and the formed conclusions,the model performance was shown on the datasets of electricity consumption,sunspot activity,and Spotify stock price.The result showed that the proposed model outperforms traditional approaches at medium forecasting horizons and demonstrates high accuracy for data with long-term and cyclical dependencies.However,for financial data with high volatility,the model’s efficiency decreases at long forecasting horizons,indicating the need for further adaptation.The findings suggest further adaptation.The findings suggest that integrating fractal properties into neural network architecture improves the accuracy of time series forecasting and can be useful for developing more accurate and reliable forecasting systems in various industries.
文摘Accurate forecasting of oil production is essential for optimizing resource management and minimizing operational risks in the energy sector. Traditional time-series forecasting techniques, despite their widespread application, often encounter difficulties in handling the complexities of oil production data, which is characterized by non-linear patterns, skewed distributions, and the presence of outliers. To overcome these limitations, deep learning methods have emerged as more robust alternatives. However, while deep neural networks offer improved accuracy, they demand substantial amounts of data for effective training. Conversely, shallow networks with fewer layers lack the capacity to model complex data distributions adequately. To address these challenges, this study introduces a novel hybrid model called Transfer LSTM to GRU (TLTG), which combines the strengths of deep and shallow networks using transfer learning. The TLTG model integrates Long Short-Term Memory (LSTM) networks and Gated Recurrent Units (GRU) to enhance predictive accuracy while maintaining computational efficiency. Gaussian transformation is applied to the input data to reduce outliers and skewness, creating a more normal-like distribution. The proposed approach is validated on datasets from various wells in the Tahe oil field, China. Experimental results highlight the superior performance of the TLTG model, achieving 100% accuracy and faster prediction times (200 s) compared to eight other approaches, demonstrating its effectiveness and efficiency.
基金part of the Centre for Research-based Innovation SmartForest:Bringing Industry 4.0 to the Norwegian forest sector(NFR SFI project no.309671,smartforest.no)。
文摘Site index(SI)is determined from the top height development and is a proxy for forest productivity,defined as the expected top height for a given species at a certain index age.In Norway,an index age of 40 years is used.By using bi-temporal airborne laser scanning(ALS)data,SI can be determined using models estimated from SI observed on field plots(the direct approach)or from predicted top heights at two points in time(the height differential approach).Time series of ALS data may enhance SI determination compared to conventional methods used in operational forest inventory by providing more detailed information about the top height development.We used longitudinal data comprising spatially consistent field and ALS data collected from training plots in 1999,2010,and 2022 to determine SI using the direct and height differential approaches using all combinations of years and performed an external validation.We also evaluated the use of data assimilation.Values of root mean square error obtained from external validation were in the ranges of 16.3%–21.4%and 12.8%–20.6%of the mean fieldregistered SI for the direct approach and the height differential approach,respectively.There were no statistically significant effects of time series length or the number of points in time on the obtained accuracies.Data assimilation did not result in any substantial improvement in the obtained accuracies.Although a time series of ALS data did not yield greater accuracies compared to using only two points in time,a larger proportion of the study area could be used in ALS-based determination of SI when a time series was available.This was because areas that were unsuitable for SI determination between two points in time could be subject to SI determination based on data from another part of the time series.
文摘Load time series analysis is critical for resource management and optimization decisions,especially automated analysis techniques.Existing research has insufficiently interpreted the overall characteristics of samples,leading to significant differences in load level detection conclusions for samples with different characteristics(trend,seasonality,cyclicality).Achieving automated,feature-adaptive,and quantifiable analysis methods remains a challenge.This paper proposes a Threshold Recognition-based Load Level Detection Algorithm(TRLLD),which effectively identifies different load level regions in samples of arbitrary size and distribution type based on sample characteristics.By utilizing distribution density uniformity,the algorithm classifies data points and ultimately obtains normalized load values.In the feature recognition step,the algorithm employs the Density Uniformity Index Based on Differences(DUID),High Load Level Concentration(HLLC),and Low Load Level Concentration(LLLC)to assess sample characteristics,which are independent of specific load values,providing a standardized perspective on features,ensuring high efficiency and strong interpretability.Compared to traditional methods,the proposed approach demonstrates better adaptive and real-time analysis capabilities.Experimental results indicate that it can effectively identify high load and low load regions in 16 groups of time series samples with different load characteristics,yielding highly interpretable results.The correlation between the DUID and sample density distribution uniformity reaches 98.08%.When introducing 10% MAD intensity noise,the maximum relative error is 4.72%,showcasing high robustness.Notably,it exhibits significant advantages in general and low sample scenarios.
基金financially supported by the Tianjin Marine Science and Technology Project (KJXH2011-05)local colleges and universities in Shanghai liberal arts academic programme (B5201120003)
文摘The annual frequency of red tides from 1977 to 2012 and the monthly frequency of red tides from 2001 to 2012 in China seas were used to establish the time series of red tide annual frequency and monthly frequency, respectively. The annual frequency fit well with time segments revealed by piecewise linear regression analysis. The seasonal maximum of monthly frequency was in May （-18.22）, and the stochastic volatility tended to increase gradually with time series, with peak values occurring from May to July. Holt exponential smoothing and Holt-winter exponential smoothing were used to predict red tide annual and monthly frequencies, which revealed that the annual frequency of red tides would rise slowly by one time from 2013 to 2020, and that red tides would mainly occur from May to July in 2013-2016 with a peak value of about 25 times in May.
文摘In this paper, we propose a cross reference method for nonlinear time series analyzing in semi blind case, that is, the dynamic equations modeling the time series are known but the corresponding parameters are not. The tasks of noise reduction and parameter estimation which were fulfilled separately before are combined iteratively. With the positive interaction between the two processing modules, the method is somewhat superior. Some prior work can be viewed as special cases of this general framework. The simulations for noise reduction and parameter estimation of contaminated chaotic time series show improved performance of our method compared with previous work.
基金The National Natural Science Foundation of China(No.61273236)the Natural Science Foundation of Jiangsu Province(No.BK2010239)the Ph.D.Programs Foundation of Ministry of Education of China(No.200802861061)
文摘This paper presents a novel approach to identify and correct the gross errors in the microelectromechanical system （MEMS） gyroscope used in ground vehicles by means of time series analysis. According to the characteristics of autocorrelation function （ACF） and partial autocorrelation function （PACF）, an autoregressive integrated moving average （ARIMA） model is roughly constructed. The rough model is optimized by combining with Akaike＇s information criterion （A/C）, and the parameters are estimated based on the least squares algorithm. After validation testing, the model is utilized to forecast the next output on the basis of the previous measurement. When the difference between the measurement and its prediction exceeds the defined threshold, the measurement is identified as a gross error and remedied by its prediction. A case study on the yaw rate is performed to illustrate the developed algorithm. Experimental results demonstrate that the proposed approach can effectively distinguish gross errors and make some reasonable remedies.
基金partly supported by the National Natural Science Foundation of China [81773370 and 82173638]the Natural Science Foundation of Heilongjiang Province [TD2019H001]
文摘Objective To recognize the spatial and temporal characteristics of iodine deficiency disorders(IDD),China national IDD surveillance data for the years of 1995–2018 were analyzed.Methods Time series analysis was used to describe and predict the IDD related indicators,and spatial analysis was used to analyze the spatial distribution of salt iodine levels.Results In China,the median urinary iodine concentration increased in 1995–1997,then decreased to adequate levels,and are expected to remain appropriate in 2019–2022.The goiter rate continually decreased and is expected to be maintained at a low level.Since 2002,the coverage rates of iodized salt and the consumption rates of qualified iodized salt(the percentage of qualified iodized salt in all tested salt) increased and began to decline in 2012;they are expected to continue to decrease.Spatial epidemiological analysis indicated a positive spatial correlation in 2016–2018 and revealed feature regarding the spatial distribution of salt related indicators in coastal areas and areas near iodine-excess areas.Conclusions Iodine nutrition in China showed gradual improvements.However,a recent decline has been observed in some areas following changes in the iodized salt supply in China.In the future,more regulations regarding salt management should be issued to strengthen IDD control and prevention measures,and avoid the recurrence of IDD.
基金This study is supported by the geological survey project:National Glacier and Desertification Remote Sensing Geological Survey(DD20190515)Youth Innovation Fund of China Aero Geophysical Prospecting and Remote Sensing Center for Natural Resources(2020YFL18).
文摘In order to study the hydrodynamic characteristics of the karst aquifers in northern China,time series analyses(correlation and spectral analysis in addition with hydrograph recession analysis)are applied on Baotu Spring and Heihu Spring in Jinan karst spring system,a typical karst spring system in northern China.Results show that the auto-correlation coefficient of spring water level reaches the value of 0.2 after 123 days and 117 days for Baotu Spring and Heihu Spring,respectively.The regulation time obtained from the simple spectral density function in the same period is 187 days and 175 days for Baotu Spring and Heihu Spring.The auto-correlation coefficient of spring water level reaches the value of 0.2 in 34-82 days,and regulation time ranges among 40-59 days for every single hydrological year.The delay time between precipitation and spring water level obtained from cross correlation function is around 56 days for the period of 2012-2019,and varies among 30-79 days for every single hydrological year.In addition,the spectral bands in cross amplitude functions and gain functions are small with 0.02,and the values in the coherence functions are small.All these behaviors illustrate that Jinan karst spring system has a strong memory effect,large storage capacity,noticeable regulation effect,and time series analysis is a useful tool for studying the hydrodynamic characteristics of karst spring system in northern China.
基金The current work was co-funded by China National Science Foundation through grant 30500397 (PI: Y. Zhang)ShanghaiRising-Star Program for Young Investigators through grant 04QMX1402 (PI: H. Kan).
文摘Objective To investigate the relation between air pollution exposure and preterm birth in Shanghai, China. Methods We examined the effect of ambient air pollution on preterm birth using time-series approach in Shanghai in 2004. This method can eliminate potential confounding by individual risk factors that do not change over a short period of time. Daily numbers of preterm births were obtained from the live birth database maintained by Shanghai Municipal Center of Disease Control and Prevention. We used the generalized additive model （GAM） with penalized splines to analyze the relation between preterm birth, air pollution, and covariates. Results We observed a significant effect of outdoor air pollution only with 8-week exposure before preterm births. An increase of 10 μg/m^3 of 8-week average PM10, SO2, NO2, and O3 corresponded to 4.42% （95%CI 1.60%, 7.25%）, 11.89% （95%CI 6.69%, 17.09%）, 5.43% （95%CI 1.78%, 9.08%）, and 4.63% （95%CI 0.35%, 8.91%） increase of preterm birth. We did not find any significant acute effect of outdoor air pollution on preterm birth in the week before birth. Conclusion Ambient air pollution may contribute to the risk of preterm birth in Shanghai. Our analyses also strengthen the rationale for further limiting air pollution level in the city.
基金Supported by the Key Scientific Research Project of Universities in Henan Province,No.21A330004Natural Science Foundation in Henan Province,No.222300420265.
文摘BACKGROUND Hepatitis B(HB)and hepatitis C(HC)place the largest burden in China,and a goal of eliminating them as a major public health threat by 2030 has been set.Making more informed and accurate forecasts of their spread is essential for developing effective strategies,heightening the requirement for early warning to deal with such a major public health threat.AIM To monitor HB and HC epidemics by the design of a paradigmatic seasonal autoregressive fractionally integrated moving average(SARFIMA)for projections into 2030,and to compare the effectiveness with the seasonal autoregressive integrated moving average(SARIMA).METHODS Monthly HB and HC incidence cases in China were obtained from January 2004 to June 2023.Descriptive analysis and the Hodrick-Prescott method were employed to identify trends and seasonality.Two periods(from January 2004 to June 2022 and from January 2004 to December 2015,respectively)were used as the training sets to develop both models,while the remaining periods served as the test sets to evaluate the forecasting accuracy.RESULTS There were incidents of 23400874 HB cases and 3590867 HC cases from January 2004 to June 2023.Overall,HB remained steady[average annual percentage change(AAPC)=0.44,95%confidence interval(95%CI):-0.94-1.84]while HC was increasing(AAPC=8.91,95%CI:6.98-10.88),and both had a peak in March and a trough in February.In the 12-step-ahead HB forecast,the mean absolute deviation(15211.94),root mean square error(18762.94),mean absolute percentage error(0.17),mean error rate(0.15),and root mean square percentage error(0.25)under the best SARFIMA(3,0,0)(0,0.449,2)12 were smaller than those under the best SARIMA(3,0,0)(0,1,2)12(16867.71,20775.12,0.19,0.17,and 0.27,respectively).Similar results were also observed for the 90-step-ahead HB,12-step-ahead HC,and 90-step-ahead HC forecasts.The predicted HB incidents totaled 9865400(95%CI:7508093-12222709)cases and HC totaled 1659485(95%CI:856681-2462290)cases during 2023-2030.CONCLUSION Under current interventions,China faces enormous challenges to eliminate HB and HC epidemics by 2030,and effective strategies must be reinforced.The integration of SARFIMA into public health for the management of HB and HC epidemics can potentially result in more informed and efficient interventions,surpassing the capabilities of SARIMA.
文摘Time-series analysis is important to a wide range of disciplines transcending both the physical and social sciences for proactive policy decisions. Statistical models have sound theoretical basis and have been successfully used in a number of problem domains in time series forecasting. Due to power and flexibility, Box-Jenkins ARIMA model has gained enormous popularity in many areas and research practice for the last three decades. More recently, the neural networks have been shown to be a promising alternative tool for modeling and forecasting owing to their ability to capture the nonlinearity in the data. However, despite the popularity and the superiority of ARIMA and ANN models, the empirical forecasting performance has been rather mixed so that no single method is best in every situation. In this study, a hybrid ARIMA and neural networks model to time series forecasting is proposed. The basic idea behind the model combination is to use each model’s unique features to capture different patterns in the data. With three real data sets, empirical results evidently show that the hybrid model outperforms ARIMA and ANN model noticeably in terms of forecasting accuracy used in isolation.
