Recent advancement in low-cost cameras has facilitated surveillance in various developing towns in India.The video obtained from such surveillance are of low quality.Still counting vehicles from such videos are necess...Recent advancement in low-cost cameras has facilitated surveillance in various developing towns in India.The video obtained from such surveillance are of low quality.Still counting vehicles from such videos are necessity to avoid traf-fic congestion and allows drivers to plan their routes more precisely.On the other hand,detecting vehicles from such low quality videos are highly challenging with vision based methodologies.In this research a meticulous attempt is made to access low-quality videos to describe traffic in Salem town in India,which is mostly an un-attempted entity by most available sources.In this work profound Detection Transformer(DETR)model is used for object(vehicle)detection.Here vehicles are anticipated in a rush-hour traffic video using a set of loss functions that carry out bipartite coordinating among estimated and information acquired on real attributes.Every frame in the traffic footage has its date and time which is detected and retrieved using Tesseract Optical Character Recognition.The date and time extricated and perceived from the input image are incorporated with the length of the recognized objects acquired from the DETR model.This furnishes the vehicles report with timestamp.Transformer Timeseries Prediction Model(TTPM)is proposed to predict the density of the vehicle for future prediction,here the regular NLP layers have been removed and the encoding temporal layer has been modified.The proposed TTPM error rate outperforms the existing models with RMSE of 4.313 and MAE of 3.812.展开更多
Reference Evapotranspiration(ETo)iswidely used to assess totalwater loss between land and atmosphere due to its importance in maintaining the atmospheric water balance,especially in agricultural and environmental mana...Reference Evapotranspiration(ETo)iswidely used to assess totalwater loss between land and atmosphere due to its importance in maintaining the atmospheric water balance,especially in agricultural and environmental management.Accurate estimation of ETo is challenging due to its dependency onmultiple climatic variables,including temperature,humidity,and solar radiation,making it a complexmultivariate time-series problem.Traditional machine learning and deep learning models have been applied to forecast ETo,achieving moderate success.However,the introduction of transformer-based architectures in time-series forecasting has opened new possibilities formore precise ETo predictions.In this study,a novel algorithm for ETo forecasting is proposed,focusing on four transformer-based models:Vanilla Transformer,Informer,Autoformer,and FEDformer(Frequency Enhanced Decomposed Transformer),applied to an ETo dataset from the Andalusian region.The novelty of the proposed algorithm lies in determining optimized window sizes based on seasonal trends and variations,which were then used with each model to enhance prediction accuracy.This custom window-sizing method allows the models to capture ETo’s unique seasonal patterns more effectively.Finally,results demonstrate that the Informer model outperformed other transformer-based models,achievingmean square error(MSE)values of 0.1404 and 0.1445 for forecast windows(15,7)and(30,15),respectively.The Vanilla Transformer also showed strong performance,closely following the Informermodel.These findings suggest that the proposed optimized window-sizing approach,combined with transformer-based architectures,is highly effective for ETo modelling.This novel strategy has the potential to be adapted in othermultivariate time-series forecasting tasks that require seasonality-sensitive approaches.展开更多
The notion that investors shift to gold during economic market crises remains unverified for many cryptocurrency markets.This paper investigates the connectedness between the 10 most traded cryptocurrencies and gold a...The notion that investors shift to gold during economic market crises remains unverified for many cryptocurrency markets.This paper investigates the connectedness between the 10 most traded cryptocurrencies and gold as well as crude oil markets pre-COVID-19 and during COVID-19.Through the application of various statistical techniques,including cointegration tests,vector autoregressive models,vector error correction models,autoregressive distributed lag models,and Granger causality analyses,we explore the relationship between these markets and assess the safe-haven properties of gold and crude oil for cryptocurrencies.Our findings reveal that during the COVID-19 pandemic,gold is a strong safe-haven for Bitcoin,Litecoin,and Monero while demonstrating a weaker safe-haven potential for Bitcoin Cash,EOS,Chainlink,and Cardano.In contrast,gold only exhibits a strong safe-haven characteristic before the pandemic for Litecoin and Monero.Additionally,Brent crude oil emerges as a strong safe-haven for Bitcoin during COVID-19,while West Texas Intermediate and Brent crude oils demonstrate weaker safe-haven properties for Ether,Bitcoin Cash,EOS,and Monero.Furthermore,the Granger causality analysis indicates that before the COVID-19 pandemic,the causal relationship predominantly flowed from gold and crude oil toward the cryptocurrency markets;however,during the COVID-19 period,the direction of causality shifted,with cryptocurrencies exerting influence on the gold and crude oil markets.These findings provide subtle implications for policymakers,hedge fund managers,and individual or institutional cryptocurrency investors.Our results highlight the need to adapt risk exposure strategies during financial turmoil,such as the crisis precipitated by the COVID-19 pandemic.展开更多
In this paper the influence of the differently distributed phase-randontized to the data obtained in dynamic analysis for critical value is studied.The calculation results validate that the sufficient phase-randomized...In this paper the influence of the differently distributed phase-randontized to the data obtained in dynamic analysis for critical value is studied.The calculation results validate that the sufficient phase-randomized of the different distributed random numbers are less influential on the critical value . This offers the theoretical foundation of the feasibility and practicality of the phase-randomized method.展开更多
In this paper surrogate data method of phase-randomized is proposed to identify the random or chaotic nature of the data obtained in dynamic analysis: The calculating results validate the phase-randomized method to be...In this paper surrogate data method of phase-randomized is proposed to identify the random or chaotic nature of the data obtained in dynamic analysis: The calculating results validate the phase-randomized method to be useful as it can increase the extent of accuracy of the results. And the calculating results show that threshold values of the random timeseries and nonlinear chaotic timeseries have marked difference.展开更多
In this paper,determination of the characteristics of futures market in China is presented by the method of the phase-randomized surrogate data.There is a significant difference in the obtained critical values when th...In this paper,determination of the characteristics of futures market in China is presented by the method of the phase-randomized surrogate data.There is a significant difference in the obtained critical values when this method is used for random timeseries and for nonlinear chaotic timeseries.The singular value decomposition is used to reduce noise in the chaotic timeseries.The phase space of chaotic timeseries is decomposed into range space and null noise space.The original chaotic timeseries in range space is restructured.The method of strong disturbance based on the improved general constrained randomized method is further adopted to re-deternination.With the calculated results,an analysis on the trend of futures market of commodity is made in this paper.The results indicate that China＇s futures market of commodity is a complicated nonlinear system with obvious nonlinear chaotic characteristic.展开更多
A method of modifying the architecture of fractional least mean square （FLMS） algorithm is presented to work with nonlinear time series prediction. Here we incorporate an adjustable gain parameter in the weight adap...A method of modifying the architecture of fractional least mean square （FLMS） algorithm is presented to work with nonlinear time series prediction. Here we incorporate an adjustable gain parameter in the weight adaptation equation of the original FLMS algorithm and absorb the gamma function in the fractional step size parameter. This approach provides an interesting achievement in the performance of the filter in terms of handling the nonlinear problems with less computational burden by avoiding the evaluation of complex gamma function. We call this new algorithm as the modified fractional least mean square （MFLMS） algorithm. The predictive performance for the nonlinear Mackey glass chaotic time series is observed and evaluated using the classical LMS, FLMS, kernel LMS, and proposed MFLMS adaptive filters. The simulation results for the time series with and without noise confirm the superiority and improvement in the prediction capability of the proposed MFLMS predictor over its counterparts.展开更多
The non_linear chaotic model reconstruction is the major important quantitative index for describing accurate experimental data obtained in dynamic analysis. A lot of work has been done to distinguish chaos from rando...The non_linear chaotic model reconstruction is the major important quantitative index for describing accurate experimental data obtained in dynamic analysis. A lot of work has been done to distinguish chaos from randomness, to calulate fractral dimension and Lyapunov exponent, to reconstruct the state space and to fix the rank of model. In this paper, a new improved EAR method is presented in modelling and predicting chaotic timeseries, and a successful approach to fast estimation algorithms is proposed. Some illustrative experimental data examples from known chaotic systems are presented, emphasising the increase in predicting error with time. The calculating results tell us that the parameter identification method in this paper can effectively adjust the initial value towards the global limit value of the single peak target function nearby. Then the model paremeter can immediately be obtained by using the improved optimization method rapidly, and non_linear chaotic models can not provide long period superior predictions. Applications of this method are listed to real data from widely different areas.展开更多
On the assumption that random interruptions in the observation process are modelled by a sequence of independent Bernoulli random variables, this paper generalize the extended Kalman filtering （EKF）, the unscented K...On the assumption that random interruptions in the observation process are modelled by a sequence of independent Bernoulli random variables, this paper generalize the extended Kalman filtering （EKF）, the unscented Kalman filtering （UKF） and the Gaussian particle filtering （GPF） to the case in which there is a positive probability that the observation in each time consists of noise alone and does not contain the chaotic signal （These generalized novel algorithms are referred to as GEKF, GUKF and GGPF correspondingly in this paper）. Using weights and network output of neural networks to constitute state equation and observation equation for chaotic time-series prediction to obtain the linear system state transition equation with continuous update scheme in an online fashion, and the prediction results of chaotic time series represented by the predicted observation value, these proposed novel algorithms are applied to the prediction of Mackey-Glass time-series with additive and multiplicative noises. Simulation results prove that the GGPF provides a relatively better prediction performance in comparison with GEKF and GUKF.展开更多
The Lyapunov exponent is important quantitative index for describing chaotic attractors. Since Wolf put up the trajectory algorithm to Lyapunov exponent in 1985, how to calculate the Lyapunov exponent with accuracy ha...The Lyapunov exponent is important quantitative index for describing chaotic attractors. Since Wolf put up the trajectory algorithm to Lyapunov exponent in 1985, how to calculate the Lyapunov exponent with accuracy has become a very important question. Based on the theoretical algorithm of Zuo Binwu, the matric algorithm of Lyapunov exponent is given, and the results with the results of Wolf's algorithm are compared. The calculating results validate that the matric algorithm has sufficient accuracy, and the relationship between the character of attractor and the value of Lyapunov exponent is studied in this paper. The corresponding conclusions are given in this paper.展开更多
The emergence of new resources and services in the electricity system implies that more and more agents need to obtain more accurate forecasts to optimize their operations.It is common for these agents to have differe...The emergence of new resources and services in the electricity system implies that more and more agents need to obtain more accurate forecasts to optimize their operations.It is common for these agents to have different sources of forecasts(from specialized consultants or meteorological services,among others).The proposed approach aims to obtain more accurate predictions by optimally combining a set of predictions obtained by different techniques.In this way it is possible to obtain a resulting prediction that improves the error and uncertainty associated with each of the individual forecasts.The objective is achieved by the analytical minimization of the errors obtained by each of the individual predictors.This allows to obtain dynamically the optimized weights assigned to each of the algorithms so that the combination outperforms the individual behaviour of each of them.The proposed ensemble approach has been successfully tested on a real time series of electric vehicle charging.Likewise,the results obtained have been compared exhaustively with other ensemble techniques consolidated in the literature based on different methods,including dynamic ensembles as machine learning approaches.The results obtained show an appreciable improvement of the errors obtained in the predictions using the proposed techniques.展开更多
Accurate,consistent,and high-resolution Land Use&Cover(LUC)information is fundamental for effectively monitoring landscape dynamics and better apprehending drivers,pressures,state,and impacts on land systems.Never...Accurate,consistent,and high-resolution Land Use&Cover(LUC)information is fundamental for effectively monitoring landscape dynamics and better apprehending drivers,pressures,state,and impacts on land systems.Nevertheless,the availability of such national products with high thematic accuracy is still limited and consequently researchers and policymakers are constrained to work with data that do not necessarily reflect on-the-ground realities impending to correctly capture details of landscape features as well as limiting the identification and quantification of drivers and rate of change.Hereafter,we took advantage of the Switzerland’s official LUC statistical sampling survey and dense time-series of Sentinel-2 data,combining them with Machine and Deep Learning methods to produce an accurate and high spatial resolution land cover map over the Lake Geneva region.Findings suggest that time-first approach is a valuable alternative to space-first approaches,accounting for the intra-annual variability of classes,hence improving classification performances.Results demonstrate that Deep Learning methods outperform more traditional Machine Learning ones such as Random Forest,providing more accurate predictions with lower uncertainty.The produced land cover map has a high accuracy,an improved spatial resolution,while at the same time preserving the statistical significance(i.e.class proportion)of the official national dataset.This work paves the way towards the objective to produce a yearly high resolution land cover map of Switzerland and potentially implement a continuous land change monitoring capability.However further work is required to properly address challenges such as the need for increased temporal resolution for LUC information or the quality of training samples.展开更多
文摘Recent advancement in low-cost cameras has facilitated surveillance in various developing towns in India.The video obtained from such surveillance are of low quality.Still counting vehicles from such videos are necessity to avoid traf-fic congestion and allows drivers to plan their routes more precisely.On the other hand,detecting vehicles from such low quality videos are highly challenging with vision based methodologies.In this research a meticulous attempt is made to access low-quality videos to describe traffic in Salem town in India,which is mostly an un-attempted entity by most available sources.In this work profound Detection Transformer(DETR)model is used for object(vehicle)detection.Here vehicles are anticipated in a rush-hour traffic video using a set of loss functions that carry out bipartite coordinating among estimated and information acquired on real attributes.Every frame in the traffic footage has its date and time which is detected and retrieved using Tesseract Optical Character Recognition.The date and time extricated and perceived from the input image are incorporated with the length of the recognized objects acquired from the DETR model.This furnishes the vehicles report with timestamp.Transformer Timeseries Prediction Model(TTPM)is proposed to predict the density of the vehicle for future prediction,here the regular NLP layers have been removed and the encoding temporal layer has been modified.The proposed TTPM error rate outperforms the existing models with RMSE of 4.313 and MAE of 3.812.
基金funded by Princess Nourah bint Abdulrahman University and Researchers Supporting Project number(PNURSP2024R136),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Reference Evapotranspiration(ETo)iswidely used to assess totalwater loss between land and atmosphere due to its importance in maintaining the atmospheric water balance,especially in agricultural and environmental management.Accurate estimation of ETo is challenging due to its dependency onmultiple climatic variables,including temperature,humidity,and solar radiation,making it a complexmultivariate time-series problem.Traditional machine learning and deep learning models have been applied to forecast ETo,achieving moderate success.However,the introduction of transformer-based architectures in time-series forecasting has opened new possibilities formore precise ETo predictions.In this study,a novel algorithm for ETo forecasting is proposed,focusing on four transformer-based models:Vanilla Transformer,Informer,Autoformer,and FEDformer(Frequency Enhanced Decomposed Transformer),applied to an ETo dataset from the Andalusian region.The novelty of the proposed algorithm lies in determining optimized window sizes based on seasonal trends and variations,which were then used with each model to enhance prediction accuracy.This custom window-sizing method allows the models to capture ETo’s unique seasonal patterns more effectively.Finally,results demonstrate that the Informer model outperformed other transformer-based models,achievingmean square error(MSE)values of 0.1404 and 0.1445 for forecast windows(15,7)and(30,15),respectively.The Vanilla Transformer also showed strong performance,closely following the Informermodel.These findings suggest that the proposed optimized window-sizing approach,combined with transformer-based architectures,is highly effective for ETo modelling.This novel strategy has the potential to be adapted in othermultivariate time-series forecasting tasks that require seasonality-sensitive approaches.
基金the financial support of the Chaire Fintech AMF—Finance Montréal,Canada.Contract number 0007.
文摘The notion that investors shift to gold during economic market crises remains unverified for many cryptocurrency markets.This paper investigates the connectedness between the 10 most traded cryptocurrencies and gold as well as crude oil markets pre-COVID-19 and during COVID-19.Through the application of various statistical techniques,including cointegration tests,vector autoregressive models,vector error correction models,autoregressive distributed lag models,and Granger causality analyses,we explore the relationship between these markets and assess the safe-haven properties of gold and crude oil for cryptocurrencies.Our findings reveal that during the COVID-19 pandemic,gold is a strong safe-haven for Bitcoin,Litecoin,and Monero while demonstrating a weaker safe-haven potential for Bitcoin Cash,EOS,Chainlink,and Cardano.In contrast,gold only exhibits a strong safe-haven characteristic before the pandemic for Litecoin and Monero.Additionally,Brent crude oil emerges as a strong safe-haven for Bitcoin during COVID-19,while West Texas Intermediate and Brent crude oils demonstrate weaker safe-haven properties for Ether,Bitcoin Cash,EOS,and Monero.Furthermore,the Granger causality analysis indicates that before the COVID-19 pandemic,the causal relationship predominantly flowed from gold and crude oil toward the cryptocurrency markets;however,during the COVID-19 period,the direction of causality shifted,with cryptocurrencies exerting influence on the gold and crude oil markets.These findings provide subtle implications for policymakers,hedge fund managers,and individual or institutional cryptocurrency investors.Our results highlight the need to adapt risk exposure strategies during financial turmoil,such as the crisis precipitated by the COVID-19 pandemic.
文摘In this paper the influence of the differently distributed phase-randontized to the data obtained in dynamic analysis for critical value is studied.The calculation results validate that the sufficient phase-randomized of the different distributed random numbers are less influential on the critical value . This offers the theoretical foundation of the feasibility and practicality of the phase-randomized method.
文摘In this paper surrogate data method of phase-randomized is proposed to identify the random or chaotic nature of the data obtained in dynamic analysis: The calculating results validate the phase-randomized method to be useful as it can increase the extent of accuracy of the results. And the calculating results show that threshold values of the random timeseries and nonlinear chaotic timeseries have marked difference.
基金supported by the National Natural Science Foundation of China(No.10632040)
文摘In this paper,determination of the characteristics of futures market in China is presented by the method of the phase-randomized surrogate data.There is a significant difference in the obtained critical values when this method is used for random timeseries and for nonlinear chaotic timeseries.The singular value decomposition is used to reduce noise in the chaotic timeseries.The phase space of chaotic timeseries is decomposed into range space and null noise space.The original chaotic timeseries in range space is restructured.The method of strong disturbance based on the improved general constrained randomized method is further adopted to re-deternination.With the calculated results,an analysis on the trend of futures market of commodity is made in this paper.The results indicate that China＇s futures market of commodity is a complicated nonlinear system with obvious nonlinear chaotic characteristic.
基金Project supported by the Higher Education Commission of Pakistan
文摘A method of modifying the architecture of fractional least mean square （FLMS） algorithm is presented to work with nonlinear time series prediction. Here we incorporate an adjustable gain parameter in the weight adaptation equation of the original FLMS algorithm and absorb the gamma function in the fractional step size parameter. This approach provides an interesting achievement in the performance of the filter in terms of handling the nonlinear problems with less computational burden by avoiding the evaluation of complex gamma function. We call this new algorithm as the modified fractional least mean square （MFLMS） algorithm. The predictive performance for the nonlinear Mackey glass chaotic time series is observed and evaluated using the classical LMS, FLMS, kernel LMS, and proposed MFLMS adaptive filters. The simulation results for the time series with and without noise confirm the superiority and improvement in the prediction capability of the proposed MFLMS predictor over its counterparts.
文摘The non_linear chaotic model reconstruction is the major important quantitative index for describing accurate experimental data obtained in dynamic analysis. A lot of work has been done to distinguish chaos from randomness, to calulate fractral dimension and Lyapunov exponent, to reconstruct the state space and to fix the rank of model. In this paper, a new improved EAR method is presented in modelling and predicting chaotic timeseries, and a successful approach to fast estimation algorithms is proposed. Some illustrative experimental data examples from known chaotic systems are presented, emphasising the increase in predicting error with time. The calculating results tell us that the parameter identification method in this paper can effectively adjust the initial value towards the global limit value of the single peak target function nearby. Then the model paremeter can immediately be obtained by using the improved optimization method rapidly, and non_linear chaotic models can not provide long period superior predictions. Applications of this method are listed to real data from widely different areas.
基金supported by the National Natural Science Foundation of China (Grant No 60774067)the Natural Science Foundation of Fujian Province of China (Grant No 2006J0017)
文摘On the assumption that random interruptions in the observation process are modelled by a sequence of independent Bernoulli random variables, this paper generalize the extended Kalman filtering （EKF）, the unscented Kalman filtering （UKF） and the Gaussian particle filtering （GPF） to the case in which there is a positive probability that the observation in each time consists of noise alone and does not contain the chaotic signal （These generalized novel algorithms are referred to as GEKF, GUKF and GGPF correspondingly in this paper）. Using weights and network output of neural networks to constitute state equation and observation equation for chaotic time-series prediction to obtain the linear system state transition equation with continuous update scheme in an online fashion, and the prediction results of chaotic time series represented by the predicted observation value, these proposed novel algorithms are applied to the prediction of Mackey-Glass time-series with additive and multiplicative noises. Simulation results prove that the GGPF provides a relatively better prediction performance in comparison with GEKF and GUKF.
基金the National Natural Science Foundation of China
文摘The Lyapunov exponent is important quantitative index for describing chaotic attractors. Since Wolf put up the trajectory algorithm to Lyapunov exponent in 1985, how to calculate the Lyapunov exponent with accuracy has become a very important question. Based on the theoretical algorithm of Zuo Binwu, the matric algorithm of Lyapunov exponent is given, and the results with the results of Wolf's algorithm are compared. The calculating results validate that the matric algorithm has sufficient accuracy, and the relationship between the character of attractor and the value of Lyapunov exponent is studied in this paper. The corresponding conclusions are given in this paper.
基金the research project PID2021127550OA–I00 funded by MICIU/AEI/ 10.13039/501100011033 and by ERDF/EU.
文摘The emergence of new resources and services in the electricity system implies that more and more agents need to obtain more accurate forecasts to optimize their operations.It is common for these agents to have different sources of forecasts(from specialized consultants or meteorological services,among others).The proposed approach aims to obtain more accurate predictions by optimally combining a set of predictions obtained by different techniques.In this way it is possible to obtain a resulting prediction that improves the error and uncertainty associated with each of the individual forecasts.The objective is achieved by the analytical minimization of the errors obtained by each of the individual predictors.This allows to obtain dynamically the optimized weights assigned to each of the algorithms so that the combination outperforms the individual behaviour of each of them.The proposed ensemble approach has been successfully tested on a real time series of electric vehicle charging.Likewise,the results obtained have been compared exhaustively with other ensemble techniques consolidated in the literature based on different methods,including dynamic ensembles as machine learning approaches.The results obtained show an appreciable improvement of the errors obtained in the predictions using the proposed techniques.
基金funded by the Data Science Impulse grant of the University of Geneva.
文摘Accurate,consistent,and high-resolution Land Use&Cover(LUC)information is fundamental for effectively monitoring landscape dynamics and better apprehending drivers,pressures,state,and impacts on land systems.Nevertheless,the availability of such national products with high thematic accuracy is still limited and consequently researchers and policymakers are constrained to work with data that do not necessarily reflect on-the-ground realities impending to correctly capture details of landscape features as well as limiting the identification and quantification of drivers and rate of change.Hereafter,we took advantage of the Switzerland’s official LUC statistical sampling survey and dense time-series of Sentinel-2 data,combining them with Machine and Deep Learning methods to produce an accurate and high spatial resolution land cover map over the Lake Geneva region.Findings suggest that time-first approach is a valuable alternative to space-first approaches,accounting for the intra-annual variability of classes,hence improving classification performances.Results demonstrate that Deep Learning methods outperform more traditional Machine Learning ones such as Random Forest,providing more accurate predictions with lower uncertainty.The produced land cover map has a high accuracy,an improved spatial resolution,while at the same time preserving the statistical significance(i.e.class proportion)of the official national dataset.This work paves the way towards the objective to produce a yearly high resolution land cover map of Switzerland and potentially implement a continuous land change monitoring capability.However further work is required to properly address challenges such as the need for increased temporal resolution for LUC information or the quality of training samples.
