This paper investigates human mobility patterns in an urban taxi transportation system. This work focuses on predicting human mobility from discovering patterns of in the number of passenger pick-ups quantity （PUQ） ...This paper investigates human mobility patterns in an urban taxi transportation system. This work focuses on predicting human mobility from discovering patterns of in the number of passenger pick-ups quantity （PUQ） from urban hotspots. This paper proposes an improved ARIMA based prediction method to forecast the spatial-temporal variation of passengers in a hotspot. Evaluation with a large-scale real- world data set of 4 000 taxis＇ GPS traces over one year shows a prediction error of only 5.8%. We also explore the applica- tion of the pl^di^fioti approach to help drivers find their next passetlgerS, The sinatllation results using historical real-world data demonstrate that, with our guidance, drivers can reduce the time taken and distance travelled, to find their next pas- senger＋ by 37.1% and 6.4% respectively,展开更多
In this paper, a data-driven linear clustering(DLC) method is proposed to solve the long-term system load forecasting problem caused by load fluctuation in some developed cities. A large substation load dataset with a...In this paper, a data-driven linear clustering(DLC) method is proposed to solve the long-term system load forecasting problem caused by load fluctuation in some developed cities. A large substation load dataset with annual interval is utilized and firstly preprocessed by the proposed linear clustering method to prepare for modelling.Then optimal autoregressive integrated moving average(ARIMA) models are constructed for the sum series of each obtained cluster to forecast their respective future load. Finally, the system load forecasting result is obtained by summing up all the ARIMA forecasts. From error analysis and application results, it is both theoretically and practically proved that the proposed DLC method can reduce random forecasting errors while guaranteeing modelling accuracy, so that a more stable and precise system load forecasting result can be obtained.展开更多
Outbreaks of hand-foot-mouth disease（HFMD） have occurred many times and caused serious health burden in China since 2008. Application of modern information technology to prediction and early response can be helpful ...Outbreaks of hand-foot-mouth disease（HFMD） have occurred many times and caused serious health burden in China since 2008. Application of modern information technology to prediction and early response can be helpful for efficient HFMD prevention and control. A seasonal auto-regressive integrated moving average（ARIMA） model for time series analysis was designed in this study. Eighty-four-month（from January 2009 to December 2015） retrospective data obtained from the Chinese Information System for Disease Prevention and Control were subjected to ARIMA modeling. The coefficient of determination（R^2）, normalized Bayesian Information Criterion（BIC） and Q-test P value were used to evaluate the goodness-of-fit of constructed models. Subsequently, the best-fitted ARIMA model was applied to predict the expected incidence of HFMD from January 2016 to December 2016. The best-fitted seasonal ARIMA model was identified as（1,0,1）（0,1,1）12, with the largest coefficient of determination（R^2=0.743） and lowest normalized BIC（BIC=3.645） value. The residuals of the model also showed non-significant autocorrelations（P_（Box-Ljung（Q））=0.299）. The predictions by the optimum ARIMA model adequately captured the pattern in the data and exhibited two peaks of activity over the forecast interval, including a major peak during April to June, and again a light peak for September to November. The ARIMA model proposed in this study can forecast HFMD incidence trend effectively, which could provide useful support for future HFMD prevention and control in the study area. Besides, further observations should be added continually into the modeling data set, and parameters of the models should be adjusted accordingly.展开更多
In the mobile edge computing environments,Quality of Service(QoS)prediction plays a crucial role in web service recommendation.Because of distinct features of mobile edge computing,i.e.,the mobility of users and incom...In the mobile edge computing environments,Quality of Service(QoS)prediction plays a crucial role in web service recommendation.Because of distinct features of mobile edge computing,i.e.,the mobility of users and incomplete historical QoS data,traditional QoS prediction approaches may obtain less accurate results in the mobile edge computing environments.In this paper,we treat the historical QoS values at different time slots as a temporal sequence of QoS matrices.By incorporating the compressed matrices extracted from QoS matrices through truncated Singular Value Decomposition(SVD)with the classical ARIMA model,we extend the ARIMA model to predict multiple QoS values simultaneously and efficiently.Experimental results show that our proposed approach outperforms the other state-of-the-art approaches in accuracy and efficiency.展开更多
Objective:To model the monthly number of dengue fever cases in northeastern Thailand using time series analysis.Methods:Autoregressive Integrated Moving Average(ARIMA) models have been developed on the monthly data co...Objective:To model the monthly number of dengue fever cases in northeastern Thailand using time series analysis.Methods:Autoregressive Integrated Moving Average(ARIMA) models have been developed on the monthly data collected from January 1981 to December 2006 and validated using the data from January 2007 to April 2010.Results:The ARIMA(3,1,4) model has been found as the most suitalile model with the least Akaike Information Criterion(AIC) of 14.060 and Mean Absolute Percent Error(MAPE) of 7.000.The model was fiuther validated by the Portmanteau test with no significant autocorrelation between residuals at different lag times.Conclusions: Early warning based on the data in the previous months could assist in improving vector control, community intervention,and personal protection.展开更多
Air pollution is a severe environmental problem in urban areas.Accurate air quality prediction can help governments and individuals make proper decisions to cope with potential air pollution.As a classic time series f...Air pollution is a severe environmental problem in urban areas.Accurate air quality prediction can help governments and individuals make proper decisions to cope with potential air pollution.As a classic time series forecasting model,the AutoRegressive Integrated Moving Average(ARIMA)has been widely adopted in air quality prediction.However,because of the volatility of air quality and the lack of additional context information,i.e.,the spatial relationships among monitor stations,traditional ARIMA models suffer from unstable prediction performance.Though some deep networks can achieve higher accuracy,a mass of training data,heavy computing,and time cost are required.In this paper,we propose a hybrid model to simultaneously predict seven air pollution indicators from multiple monitoring stations.The proposed model consists of three components:(1)an extended ARIMA to predict matrix series of multiple air quality indicators from several adjacent monitoring stations;(2)the Empirical Mode Decomposition(EMD)to decompose the air quality time series data into multiple smooth sub-series;and(3)the truncated Singular Value Decomposition(SvD)to compress and denoise the expanded matrix.Experimental results on the public dataset show that our proposed model outperforms the state-of-art air quality forecasting models in both accuracy and time cost.展开更多
Extreme precipitation events bring considerable risks to the natural ecosystem and human life.Investigating the spatial-temporal characteristics of extreme precipitation and predicting it quantitatively are critical f...Extreme precipitation events bring considerable risks to the natural ecosystem and human life.Investigating the spatial-temporal characteristics of extreme precipitation and predicting it quantitatively are critical for the flood prevention and water resources planning and management.In this study,daily precipitation data(1957–2019)were collected from 24 meteorological stations in the Weihe River Basin(WRB),Northwest China and its surrounding areas.We first analyzed the spatial-temporal change of precipitation extremes in the WRB based on space-time cube(STC),and then predicted precipitation extremes using long short-term memory(LSTM)network,auto-regressive integrated moving average(ARIMA),and hybrid ensemble empirical mode decomposition(EEMD)-LSTM-ARIMA models.The precipitation extremes increased as the spatial variation from northwest to southeast of the WRB.There were two clusters for each extreme precipitation index,which were distributed in the northwestern and southeastern or northern and southern of the WRB.The precipitation extremes in the WRB present a strong clustering pattern.Spatially,the pattern of only high-high cluster and only low-low cluster were primarily located in lower reaches and upper reaches of the WRB,respectively.Hot spots(25.00%–50.00%)were more than cold spots(4.17%–25.00%)in the WRB.Cold spots were mainly concentrated in the northwestern part,while hot spots were mostly located in the eastern and southern parts.For different extreme precipitation indices,the performances of the different models were different.The accuracy ranking was EEMD-LSTM-ARIMA>LSTM>ARIMA in predicting simple daily intensity index(SDII)and consecutive wet days(CWD),while the accuracy ranking was LSTM>EEMD-LSTM-ARIMA>ARIMA in predicting very wet days(R95 P).The hybrid EEMD-LSTM-ARIMA model proposed was generally superior to single models in the prediction of precipitation extremes.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
The primary objective of the paper is to forecast the beta values of companies listed on Sensex,Bombay Stock Exchange(BSE).The BSE Sensex constitutes 30 top most companies listed which are popularly known as blue-chip...The primary objective of the paper is to forecast the beta values of companies listed on Sensex,Bombay Stock Exchange(BSE).The BSE Sensex constitutes 30 top most companies listed which are popularly known as blue-chip companies.To reach out the predefined objectives of the research,Auto Regressive Integrated Moving Average method is used to forecast the future risk and returns for 10 years of historical data from April 2007 to March 2017.Validation accomplished by comparison of forecasted and actual beta values for the hold back period of 2 years.Root-Mean-Square-Error and Mean-Absolute-Error both are used for accuracy measurement.The results revealed that out of 30 listed companies in the BSE Sensex,10 companies’exhibits high beta values,12 companies are with moderate and 8 companies are with low beta values.Further,it is to note that Housing Development Finance Corporation(HDFC)exhibits more inconsistency in terms of beta values though the average beta value is lowest among the companies under the study.A mixed trend is found in forecasted beta values of the BSE Sensex.In this analysis,all the p-values are less than the F-stat values except the case of Tata Steel and Wipro.Therefore,the null hypotheses were rejected leaving Tata Steel and Wipro.The values of actual and forecasted values are showing the almost same results with low error percentage.Therefore,it is concluded from the study that the estimation ARIMA could be acceptable,and forecasted beta values are accurate.So far,there are many studies on ARIMA model to forecast the returns of the stocks based on their historical data.But,hardly there are very few studies which attempt to forecast the returns on the basis of their beta values.Certainly,the attempt so made is a novel approach which has linked risk directly with return.On the basis of the present study,authors try to through light on investment decisions by linking it with beta values of respective stocks.Further,the outcomes of the present study undoubtedly useful to academicians,researchers,an展开更多
The mode of telecommunication network management is changing from“network oriented”to“subscriber oriented”.Aimed at enhancing subscribers’feeling,proactive performance monitoring(PPM)can enable a fast fault corre...The mode of telecommunication network management is changing from“network oriented”to“subscriber oriented”.Aimed at enhancing subscribers’feeling,proactive performance monitoring(PPM)can enable a fast fault correction by detecting anomalies designating performance degradation.In this paper,a novel anomaly detection approach is the proposed taking advantage of time series prediction and the associated confidence interval based on multiplicative autoregressive integrated moving average(ARIMA).Furthermore,under the assumption that the training residual is a white noise process following a normal distribution,the associated confidence interval of prediction can be figured out under any given confidence degree 1–αby constructing random variables satisfying t distribution.Experimental results verify the method’s effectiveness.展开更多
文摘This paper investigates human mobility patterns in an urban taxi transportation system. This work focuses on predicting human mobility from discovering patterns of in the number of passenger pick-ups quantity （PUQ） from urban hotspots. This paper proposes an improved ARIMA based prediction method to forecast the spatial-temporal variation of passengers in a hotspot. Evaluation with a large-scale real- world data set of 4 000 taxis＇ GPS traces over one year shows a prediction error of only 5.8%. We also explore the applica- tion of the pl^di^fioti approach to help drivers find their next passetlgerS, The sinatllation results using historical real-world data demonstrate that, with our guidance, drivers can reduce the time taken and distance travelled, to find their next pas- senger＋ by 37.1% and 6.4% respectively,
基金supported by the National Energy(Shanghai)Smart Grid Research Centerthe National Natural Science Foundation of China(No.51377103)
文摘In this paper, a data-driven linear clustering(DLC) method is proposed to solve the long-term system load forecasting problem caused by load fluctuation in some developed cities. A large substation load dataset with annual interval is utilized and firstly preprocessed by the proposed linear clustering method to prepare for modelling.Then optimal autoregressive integrated moving average(ARIMA) models are constructed for the sum series of each obtained cluster to forecast their respective future load. Finally, the system load forecasting result is obtained by summing up all the ARIMA forecasts. From error analysis and application results, it is both theoretically and practically proved that the proposed DLC method can reduce random forecasting errors while guaranteeing modelling accuracy, so that a more stable and precise system load forecasting result can be obtained.
基金financially supported by the Health and Family Planning Commission of Hubei Province(No.WJ2017F047)the Health and Family Planning Commission of Wuhan(No.WG17D05)
文摘Outbreaks of hand-foot-mouth disease（HFMD） have occurred many times and caused serious health burden in China since 2008. Application of modern information technology to prediction and early response can be helpful for efficient HFMD prevention and control. A seasonal auto-regressive integrated moving average（ARIMA） model for time series analysis was designed in this study. Eighty-four-month（from January 2009 to December 2015） retrospective data obtained from the Chinese Information System for Disease Prevention and Control were subjected to ARIMA modeling. The coefficient of determination（R^2）, normalized Bayesian Information Criterion（BIC） and Q-test P value were used to evaluate the goodness-of-fit of constructed models. Subsequently, the best-fitted ARIMA model was applied to predict the expected incidence of HFMD from January 2016 to December 2016. The best-fitted seasonal ARIMA model was identified as（1,0,1）（0,1,1）12, with the largest coefficient of determination（R^2=0.743） and lowest normalized BIC（BIC=3.645） value. The residuals of the model also showed non-significant autocorrelations（P_（Box-Ljung（Q））=0.299）. The predictions by the optimum ARIMA model adequately captured the pattern in the data and exhibited two peaks of activity over the forecast interval, including a major peak during April to June, and again a light peak for September to November. The ARIMA model proposed in this study can forecast HFMD incidence trend effectively, which could provide useful support for future HFMD prevention and control in the study area. Besides, further observations should be added continually into the modeling data set, and parameters of the models should be adjusted accordingly.
文摘In the mobile edge computing environments,Quality of Service(QoS)prediction plays a crucial role in web service recommendation.Because of distinct features of mobile edge computing,i.e.,the mobility of users and incomplete historical QoS data,traditional QoS prediction approaches may obtain less accurate results in the mobile edge computing environments.In this paper,we treat the historical QoS values at different time slots as a temporal sequence of QoS matrices.By incorporating the compressed matrices extracted from QoS matrices through truncated Singular Value Decomposition(SVD)with the classical ARIMA model,we extend the ARIMA model to predict multiple QoS values simultaneously and efficiently.Experimental results show that our proposed approach outperforms the other state-of-the-art approaches in accuracy and efficiency.
基金Financial support from the Thailand Research Fund thiough the Royal Golden Jubilee Ph.D.Program (Grant No.PHD/0201/2548) to Siriwan Wongkoon and Mullica Jaroensutasinee,Walailak University Fund 06/2552 and Center of Excellence for Ecoinformatics,NECTEC/ Walailak University
文摘Objective:To model the monthly number of dengue fever cases in northeastern Thailand using time series analysis.Methods:Autoregressive Integrated Moving Average(ARIMA) models have been developed on the monthly data collected from January 1981 to December 2006 and validated using the data from January 2007 to April 2010.Results:The ARIMA(3,1,4) model has been found as the most suitalile model with the least Akaike Information Criterion(AIC) of 14.060 and Mean Absolute Percent Error(MAPE) of 7.000.The model was fiuther validated by the Portmanteau test with no significant autocorrelation between residuals at different lag times.Conclusions: Early warning based on the data in the previous months could assist in improving vector control, community intervention,and personal protection.
文摘Air pollution is a severe environmental problem in urban areas.Accurate air quality prediction can help governments and individuals make proper decisions to cope with potential air pollution.As a classic time series forecasting model,the AutoRegressive Integrated Moving Average(ARIMA)has been widely adopted in air quality prediction.However,because of the volatility of air quality and the lack of additional context information,i.e.,the spatial relationships among monitor stations,traditional ARIMA models suffer from unstable prediction performance.Though some deep networks can achieve higher accuracy,a mass of training data,heavy computing,and time cost are required.In this paper,we propose a hybrid model to simultaneously predict seven air pollution indicators from multiple monitoring stations.The proposed model consists of three components:(1)an extended ARIMA to predict matrix series of multiple air quality indicators from several adjacent monitoring stations;(2)the Empirical Mode Decomposition(EMD)to decompose the air quality time series data into multiple smooth sub-series;and(3)the truncated Singular Value Decomposition(SvD)to compress and denoise the expanded matrix.Experimental results on the public dataset show that our proposed model outperforms the state-of-art air quality forecasting models in both accuracy and time cost.
基金Under the auspices of National Key Research and Development Program of China(No.2017YFE0118100-1)。
文摘Extreme precipitation events bring considerable risks to the natural ecosystem and human life.Investigating the spatial-temporal characteristics of extreme precipitation and predicting it quantitatively are critical for the flood prevention and water resources planning and management.In this study,daily precipitation data(1957–2019)were collected from 24 meteorological stations in the Weihe River Basin(WRB),Northwest China and its surrounding areas.We first analyzed the spatial-temporal change of precipitation extremes in the WRB based on space-time cube(STC),and then predicted precipitation extremes using long short-term memory(LSTM)network,auto-regressive integrated moving average(ARIMA),and hybrid ensemble empirical mode decomposition(EEMD)-LSTM-ARIMA models.The precipitation extremes increased as the spatial variation from northwest to southeast of the WRB.There were two clusters for each extreme precipitation index,which were distributed in the northwestern and southeastern or northern and southern of the WRB.The precipitation extremes in the WRB present a strong clustering pattern.Spatially,the pattern of only high-high cluster and only low-low cluster were primarily located in lower reaches and upper reaches of the WRB,respectively.Hot spots(25.00%–50.00%)were more than cold spots(4.17%–25.00%)in the WRB.Cold spots were mainly concentrated in the northwestern part,while hot spots were mostly located in the eastern and southern parts.For different extreme precipitation indices,the performances of the different models were different.The accuracy ranking was EEMD-LSTM-ARIMA>LSTM>ARIMA in predicting simple daily intensity index(SDII)and consecutive wet days(CWD),while the accuracy ranking was LSTM>EEMD-LSTM-ARIMA>ARIMA in predicting very wet days(R95 P).The hybrid EEMD-LSTM-ARIMA model proposed was generally superior to single models in the prediction of precipitation extremes.
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.
文摘The primary objective of the paper is to forecast the beta values of companies listed on Sensex,Bombay Stock Exchange(BSE).The BSE Sensex constitutes 30 top most companies listed which are popularly known as blue-chip companies.To reach out the predefined objectives of the research,Auto Regressive Integrated Moving Average method is used to forecast the future risk and returns for 10 years of historical data from April 2007 to March 2017.Validation accomplished by comparison of forecasted and actual beta values for the hold back period of 2 years.Root-Mean-Square-Error and Mean-Absolute-Error both are used for accuracy measurement.The results revealed that out of 30 listed companies in the BSE Sensex,10 companies’exhibits high beta values,12 companies are with moderate and 8 companies are with low beta values.Further,it is to note that Housing Development Finance Corporation(HDFC)exhibits more inconsistency in terms of beta values though the average beta value is lowest among the companies under the study.A mixed trend is found in forecasted beta values of the BSE Sensex.In this analysis,all the p-values are less than the F-stat values except the case of Tata Steel and Wipro.Therefore,the null hypotheses were rejected leaving Tata Steel and Wipro.The values of actual and forecasted values are showing the almost same results with low error percentage.Therefore,it is concluded from the study that the estimation ARIMA could be acceptable,and forecasted beta values are accurate.So far,there are many studies on ARIMA model to forecast the returns of the stocks based on their historical data.But,hardly there are very few studies which attempt to forecast the returns on the basis of their beta values.Certainly,the attempt so made is a novel approach which has linked risk directly with return.On the basis of the present study,authors try to through light on investment decisions by linking it with beta values of respective stocks.Further,the outcomes of the present study undoubtedly useful to academicians,researchers,an
基金supported by the National Key Technologies R&D program of China during the 11th Five-Year Plan Period (No.2006BAH02A03).
文摘The mode of telecommunication network management is changing from“network oriented”to“subscriber oriented”.Aimed at enhancing subscribers’feeling,proactive performance monitoring(PPM)can enable a fast fault correction by detecting anomalies designating performance degradation.In this paper,a novel anomaly detection approach is the proposed taking advantage of time series prediction and the associated confidence interval based on multiplicative autoregressive integrated moving average(ARIMA).Furthermore,under the assumption that the training residual is a white noise process following a normal distribution,the associated confidence interval of prediction can be figured out under any given confidence degree 1–αby constructing random variables satisfying t distribution.Experimental results verify the method’s effectiveness.
文摘通过网络提供服务的Web Service的服务质量会随着网络环境、服务器负载等因素的变化而变化,如何更好地帮助用户选择在未来一段时间内符合服务质量需求的Web Service,是目前服务计算领域中需要解决的关键问题之一。针对上述问题,提出了一种基于时间序列分析的Web Service QoS预测方法,并实现了相应的Web Service QoS自动预测工具。该工具能够根据Web Service的历史QoS数据,有效地预测未来短期内的QoS信息。以17832个Web Service的历史数据为基础,设计了相关实验,并验证了方法的有效性。
