Accurate forecasting of time series is crucial across various domains.Many prediction tasks rely on effectively segmenting,matching,and time series data alignment.For instance,regardless of time series with the same g...Accurate forecasting of time series is crucial across various domains.Many prediction tasks rely on effectively segmenting,matching,and time series data alignment.For instance,regardless of time series with the same granularity,segmenting them into different granularity events can effectively mitigate the impact of varying time scales on prediction accuracy.However,these events of varying granularity frequently intersect with each other,which may possess unequal durations.Even minor differences can result in significant errors when matching time series with future trends.Besides,directly using matched events but unaligned events as state vectors in machine learning-based prediction models can lead to insufficient prediction accuracy.Therefore,this paper proposes a short-term forecasting method for time series based on a multi-granularity event,MGE-SP(multi-granularity event-based short-termprediction).First,amethodological framework for MGE-SP established guides the implementation steps.The framework consists of three key steps,including multi-granularity event matching based on the LTF(latest time first)strategy,multi-granularity event alignment using a piecewise aggregate approximation based on the compression ratio,and a short-term prediction model based on XGBoost.The data from a nationwide online car-hailing service in China ensures the method’s reliability.The average RMSE(root mean square error)and MAE(mean absolute error)of the proposed method are 3.204 and 2.360,lower than the respective values of 4.056 and 3.101 obtained using theARIMA(autoregressive integratedmoving average)method,as well as the values of 4.278 and 2.994 obtained using k-means-SVR(support vector regression)method.The other experiment is conducted on stock data froma public data set.The proposed method achieved an average RMSE and MAE of 0.836 and 0.696,lower than the respective values of 1.019 and 0.844 obtained using the ARIMA method,as well as the values of 1.350 and 1.172 obtained using the k-means-SVR method.展开更多
The prediction for Multivariate Time Series(MTS)explores the interrelationships among variables at historical moments,extracts their relevant characteristics,and is widely used in finance,weather,complex industries an...The prediction for Multivariate Time Series(MTS)explores the interrelationships among variables at historical moments,extracts their relevant characteristics,and is widely used in finance,weather,complex industries and other fields.Furthermore,it is important to construct a digital twin system.However,existing methods do not take full advantage of the potential properties of variables,which results in poor predicted accuracy.In this paper,we propose the Adaptive Fused Spatial-Temporal Graph Convolutional Network(AFSTGCN).First,to address the problem of the unknown spatial-temporal structure,we construct the Adaptive Fused Spatial-Temporal Graph(AFSTG)layer.Specifically,we fuse the spatial-temporal graph based on the interrelationship of spatial graphs.Simultaneously,we construct the adaptive adjacency matrix of the spatial-temporal graph using node embedding methods.Subsequently,to overcome the insufficient extraction of disordered correlation features,we construct the Adaptive Fused Spatial-Temporal Graph Convolutional(AFSTGC)module.The module forces the reordering of disordered temporal,spatial and spatial-temporal dependencies into rule-like data.AFSTGCN dynamically and synchronously acquires potential temporal,spatial and spatial-temporal correlations,thereby fully extracting rich hierarchical feature information to enhance the predicted accuracy.Experiments on different types of MTS datasets demonstrate that the model achieves state-of-the-art single-step and multi-step performance compared with eight other deep learning models.展开更多
Financial time series prediction,whether for classification or regression,has been a heated research topic over the last decade.While traditional machine learning algorithms have experienced mediocre results,deep lear...Financial time series prediction,whether for classification or regression,has been a heated research topic over the last decade.While traditional machine learning algorithms have experienced mediocre results,deep learning has largely contributed to the elevation of the prediction performance.Currently,the most up-to-date review of advanced machine learning techniques for financial time series prediction is still lacking,making it challenging for finance domain experts and relevant practitioners to determine which model potentially performs better,what techniques and components are involved,and how themodel can be designed and implemented.This review article provides an overview of techniques,components and frameworks for financial time series prediction,with an emphasis on state-of-the-art deep learning models in the literature from2015 to 2023,including standalonemodels like convolutional neural networks(CNN)that are capable of extracting spatial dependencies within data,and long short-term memory(LSTM)that is designed for handling temporal dependencies;and hybrid models integrating CNN,LSTM,attention mechanism(AM)and other techniques.For illustration and comparison purposes,models proposed in recent studies are mapped to relevant elements of a generalized framework comprised of input,output,feature extraction,prediction,and related processes.Among the state-of-the-artmodels,hybrid models like CNNLSTMand CNN-LSTM-AM in general have been reported superior in performance to stand-alone models like the CNN-only model.Some remaining challenges have been discussed,including non-friendliness for finance domain experts,delayed prediction,domain knowledge negligence,lack of standards,and inability of real-time and highfrequency predictions.The principal contributions of this paper are to provide a one-stop guide for both academia and industry to review,compare and summarize technologies and recent advances in this area,to facilitate smooth and informed implementation,and to highlight future research directions.展开更多
Ocean temperature is an important physical variable in marine ecosystems,and ocean temperature prediction is an important research objective in ocean-related fields.Currently,one of the commonly used methods for ocean...Ocean temperature is an important physical variable in marine ecosystems,and ocean temperature prediction is an important research objective in ocean-related fields.Currently,one of the commonly used methods for ocean temperature prediction is based on data-driven,but research on this method is mostly limited to the sea surface,with few studies on the prediction of internal ocean temperature.Existing graph neural network-based methods usually use predefined graphs or learned static graphs,which cannot capture the dynamic associations among data.In this study,we propose a novel dynamic spatiotemporal graph neural network(DSTGN)to predict threedimensional ocean temperature(3D-OT),which combines static graph learning and dynamic graph learning to automatically mine two unknown dependencies between sequences based on the original 3D-OT data without prior knowledge.Temporal and spatial dependencies in the time series were then captured using temporal and graph convolutions.We also integrated dynamic graph learning,static graph learning,graph convolution,and temporal convolution into an end-to-end framework for 3D-OT prediction using time-series grid data.In this study,we conducted prediction experiments using high-resolution 3D-OT from the Copernicus global ocean physical reanalysis,with data covering the vertical variation of temperature from the sea surface to 1000 m below the sea surface.We compared five mainstream models that are commonly used for ocean temperature prediction,and the results showed that the method achieved the best prediction results at all prediction scales.展开更多
The growing global requirement for food and the need for sustainable farming in an era of a changing climate and scarce resources have inspired substantial crop yield prediction research.Deep learning(DL)and machine l...The growing global requirement for food and the need for sustainable farming in an era of a changing climate and scarce resources have inspired substantial crop yield prediction research.Deep learning(DL)and machine learning(ML)models effectively deal with such challenges.This research paper comprehensively analyses recent advancements in crop yield prediction from January 2016 to March 2024.In addition,it analyses the effectiveness of various input parameters considered in crop yield prediction models.We conducted an in-depth search and gathered studies that employed crop modeling and AI-based methods to predict crop yield.The total number of articles reviewed for crop yield prediction using ML,meta-modeling(Crop models coupled with ML/DL),and DL-based prediction models and input parameter selection is 125.We conduct the research by setting up five objectives for this research and discussing them after analyzing the selected research papers.Each study is assessed based on the crop type,input parameters employed for prediction,the modeling techniques adopted,and the evaluation metrics used for estimatingmodel performance.We also discuss the ethical and social impacts of AI on agriculture.However,various approaches presented in the scientific literature have delivered impressive predictions,they are complicateddue to intricate,multifactorial influences oncropgrowthand theneed for accuratedata-driven models.Therefore,thorough research is required to deal with challenges in predicting agricultural output.展开更多
Traditional research believes that the filling body can effectively control stress concentration while ignoring the problems of unknown stability and the complex and changeable stress distribution of the filling body...Traditional research believes that the filling body can effectively control stress concentration while ignoring the problems of unknown stability and the complex and changeable stress distribution of the filling body–surrounding rock combination under high-stress conditions.Current monitoring data processing methods cannot fully consider the complexity of monitoring objects,the diversity of monitoring methods,and the dynamics of monitoring data.To solve this problem,this paper proposes a phase space reconstruction and stability prediction method to process heterogeneous information of backfill–surrounding rock combinations.The three-dimensional monitoring system of a large-area filling body–surrounding rock combination in Longshou Mine was constructed by using drilling stress,multipoint displacement meter,and inclinometer.Varied information,such as the stress and displacement of the filling body–surrounding rock combination,was continuously obtained.Combined with the average mutual information method and the false nearest neighbor point method,the phase space of the heterogeneous information of the filling body–surrounding rock combination was then constructed.In this paper,the distance between the phase point and its nearest point was used as the index evaluation distance to evaluate the stability of the filling body–surrounding rock combination.The evaluated distances(ED)revealed a high sensitivity to the stability of the filling body–surrounding rock combination.The new method was then applied to calculate the time series of historically ED for 12 measuring points located at Longshou Mine.The moments of mutation in these time series were at least 3 months ahead of the roadway return dates.In the ED prediction experiments,the autoregressive integrated moving average model showed a higher prediction accuracy than the deep learning models(long short-term memory and Transformer).Furthermore,the root-mean-square error distribution of the prediction results peaked at 0.26,thus outperforming the no-prediction method in 70%of the cases.展开更多
Due to the impact of source-load prediction power errors and uncertainties,the actual operation of the park will have a wide range of fluctuations compared with the expected state,resulting in its inability to achieve...Due to the impact of source-load prediction power errors and uncertainties,the actual operation of the park will have a wide range of fluctuations compared with the expected state,resulting in its inability to achieve the expected economy.This paper constructs an operating simulation model of the park power grid operation considering demand response and proposes a multi-time scale operating simulation method that combines day-ahead optimization and model predictive control(MPC).In the day-ahead stage,an operating simulation plan that comprehensively considers the user’s side comfort and operating costs is proposed with a long-term time scale of 15 min.In order to cope with power fluctuations of photovoltaic,wind turbine and conventional load,MPC is used to track and roll correct the day-ahead operating simulation plan in the intra-day stage to meet the actual operating operation status of the park.Finally,the validity and economy of the operating simulation strategy are verified through the analysis of arithmetic examples.展开更多
This paper examines the effectiveness of the Differential autoregressive integrated moving average (ARIMA) model in comparison to the Long Short Term Memory (LSTM) neural network model for predicting Wordle user-repor...This paper examines the effectiveness of the Differential autoregressive integrated moving average (ARIMA) model in comparison to the Long Short Term Memory (LSTM) neural network model for predicting Wordle user-reported scores. The ARIMA and LSTM models were trained using Wordle data from Twitter between 7th January 2022 and 31st December 2022. User-reported scores were predicted using evaluation metrics such as MSE, RMSE, R2, and MAE. Various regression models, including XG-Boost and Random Forest, were used to conduct comparison experiments. The MSE, RMSE, R2, and MAE values for the ARIMA(0,1,1) and LSTM models are 0.000, 0.010, 0.998, and 0.006, and 0.000, 0.024, 0.987, and 0.013, respectively. The results indicate that the ARIMA model is more suitable for predicting Wordle user scores than the LSTM model.展开更多
Remaining useful life(RUL) prediction is one of the most crucial elements in prognostics and health management(PHM). Aiming at the imperfect prior information, this paper proposes an RUL prediction method based on a n...Remaining useful life(RUL) prediction is one of the most crucial elements in prognostics and health management(PHM). Aiming at the imperfect prior information, this paper proposes an RUL prediction method based on a nonlinear random coefficient regression(RCR) model with fusing failure time data.Firstly, some interesting natures of parameters estimation based on the nonlinear RCR model are given. Based on these natures,the failure time data can be fused as the prior information reasonably. Specifically, the fixed parameters are calculated by the field degradation data of the evaluated equipment and the prior information of random coefficient is estimated with fusing the failure time data of congeneric equipment. Then, the prior information of the random coefficient is updated online under the Bayesian framework, the probability density function(PDF) of the RUL with considering the limitation of the failure threshold is performed. Finally, two case studies are used for experimental verification. Compared with the traditional Bayesian method, the proposed method can effectively reduce the influence of imperfect prior information and improve the accuracy of RUL prediction.展开更多
Graphics Processing Units(GPUs)are used to accelerate computing-intensive tasks,such as neural networks,data analysis,high-performance computing,etc.In the past decade or so,researchers have done a lot of work on GPU ...Graphics Processing Units(GPUs)are used to accelerate computing-intensive tasks,such as neural networks,data analysis,high-performance computing,etc.In the past decade or so,researchers have done a lot of work on GPU architecture and proposed a variety of theories and methods to study the microarchitectural characteristics of various GPUs.In this study,the GPU serves as a co-processor and works together with the CPU in an embedded real-time system to handle computationally intensive tasks.It models the architecture of the GPU and further considers it based on some excellent work.The SIMT mechanism and Cache-miss situation provide a more detailed analysis of the GPU architecture.In order to verify the GPU architecture model proposed in this article,10 GPU kernel_task and an Nvidia GPU device were used to perform experiments.The experimental results showed that the minimum error between the kernel task execution time predicted by the GPU architecture model proposed in this article and the actual measured kernel task execution time was 3.80%,and the maximum error was 8.30%.展开更多
In order to improve the performance degradation prediction accuracy of proton exchange membrane fuel cell(PEMFC),a fusion prediction method(CKDG)based on adaptive noise complete ensemble empirical mode decomposition(C...In order to improve the performance degradation prediction accuracy of proton exchange membrane fuel cell(PEMFC),a fusion prediction method(CKDG)based on adaptive noise complete ensemble empirical mode decomposition(CEEMDAN),kernel principal component analysis(KPCA)and dual attention mechanism gated recurrent unit neural network(DA-GRU)was proposed.CEEMDAN and KPCA were used to extract the input feature data sequence,reduce the influence of random factors,and capture essential feature components to reduce the model complexity.The DA-GRU network helps to learn the feature mapping relationship of data in long time series and predict the changing trend of performance degradation data more accurately.The actual aging experimental data verify the performance of the CKDG method.The results show that under the steady-state condition of 20%training data prediction,the CKDA method can reduce the root mean square error(RMSE)by 52.7%and 34.6%,respectively,compared with the traditional LSTM and GRU neural networks.Compared with the simple DA-GRU network,RMSE is reduced by 15%,and the degree of over-fitting is reduced,which has higher accuracy.It also shows excellent prediction performance under the dynamic condition data set and has good universality.展开更多
As one of the most widespread renewable energy sources,wind energy is now an important part of the power system.Accurate and appropriate wind speed forecasting has an essential impact on wind energy utilisation.Howeve...As one of the most widespread renewable energy sources,wind energy is now an important part of the power system.Accurate and appropriate wind speed forecasting has an essential impact on wind energy utilisation.However,due to the stochastic and un-certain nature of wind energy,more accurate forecasting is necessary for its more stable and safer utilisation.This paper proposes a Legendre multiwavelet‐based neural network model for non‐linear wind speed prediction.It combines the excellent properties of Legendre multi‐wavelets with the self‐learning capability of neural networks,which has rigorous mathematical theory support.It learns input‐output data pairs and shares weights within divided subintervals,which can greatly reduce computing costs.We explore the effectiveness of Legendre multi‐wavelets as an activation function.Mean-while,it is successfully being applied to wind speed prediction.In addition,the appli-cation of Legendre multi‐wavelet neural networks in a hybrid model in decomposition‐reconstruction mode to wind speed prediction problems is also discussed.Numerical results on real data sets show that the proposed model is able to achieve optimal per-formance and high prediction accuracy.In particular,the model shows a more stable performance in multi‐step prediction,illustrating its superiority.展开更多
The price prediction task is a well-studied problem due to its impact on the business domain.There are several research studies that have been conducted to predict the future price of items by capturing the patterns o...The price prediction task is a well-studied problem due to its impact on the business domain.There are several research studies that have been conducted to predict the future price of items by capturing the patterns of price change,but there is very limited work to study the price prediction of seasonal goods(e.g.,Christmas gifts).Seasonal items’prices have different patterns than normal items;this can be linked to the offers and discounted prices of seasonal items.This lack of research studies motivates the current work to investigate the problem of seasonal items’prices as a time series task.We proposed utilizing two different approaches to address this problem,namely,1)machine learning(ML)-based models and 2)deep learning(DL)-based models.Thus,this research tuned a set of well-known predictive models on a real-life dataset.Those models are ensemble learning-based models,random forest,Ridge,Lasso,and Linear regression.Moreover,two new DL architectures based on gated recurrent unit(GRU)and long short-term memory(LSTM)models are proposed.Then,the performance of the utilized ensemble learning and classic ML models are compared against the proposed two DL architectures on different accuracy metrics,where the evaluation includes both numerical and visual comparisons of the examined models.The obtained results show that the ensemble learning models outperformed the classic machine learning-based models(e.g.,linear regression and random forest)and the DL-based models.展开更多
Due to fast-growing urbanization,the traffic management system becomes a crucial problem owing to the rapid growth in the number of vehicles The research proposes an Intelligent public transportation system where info...Due to fast-growing urbanization,the traffic management system becomes a crucial problem owing to the rapid growth in the number of vehicles The research proposes an Intelligent public transportation system where informa-tion regarding all the buses connecting in a city will be gathered,processed and accurate bus arrival time prediction will be presented to the user.Various linear and time-varying parameters such as distance,waiting time at stops,red signal duration at a traffic signal,traffic density,turning density,rush hours,weather conditions,number of passengers on the bus,type of day,road type,average vehi-cle speed limit,current vehicle speed affecting traffic are used for the analysis.The proposed model exploits the feasibility and applicability of ELM in the travel time forecasting area.Multiple ELMs(MELM)for explicitly training dynamic,road and trajectory information are used in the proposed approach.A large-scale dataset(historical data)obtained from Kerala State Road Transport Corporation is used for training.Simulations are carried out by using MATLAB R2021a.The experiments revealed that the efficiency of MELM is independent of the time of day and day of the week.It can manage huge volumes of data with less human intervention at greater learning speeds.It is found MELM yields prediction with accuracy in the range of 96.7%to 99.08%.The MAE value is between 0.28 to 1.74 minutes with the proposed approach.The study revealed that there could be regularity in bus usage and daily bus rides are predictable with a better degree of accuracy.The research has proved that MELM is superior for arrival time pre-dictions in terms of accuracy and error,compared with other approaches.展开更多
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
Emotion has a nearly decisive role in behavior, which will directly affect netizens’ views on food safety public opinion events, thereby affecting the development direction of public opinion on the event, and it is o...Emotion has a nearly decisive role in behavior, which will directly affect netizens’ views on food safety public opinion events, thereby affecting the development direction of public opinion on the event, and it is of great significance for food safety network public opinion to predict emotional trends to do a good job in food safety network public opinion guidance. In this paper, the dynamic text representation method XLNet is used to generate word vectors with context-dependent dependencies to distribute the text information of food safety network public opinion. Then, the word vector is input into the CNN-BiLSTM network for local semantic feature and context semantic extraction. The attention mechanism is introduced to give different weights according to the importance of features, and the emotional tendency analysis is carried out. Based on sentiment analysis, sentiment value time series data is obtained, and a time series model is constructed to predict sentiment trends. The sentiment analysis model proposed in this paper can well classify the sentiment of food safety network public opinion, and the time series model has a good effect on the prediction of food safety network public opinion sentiment trend. .展开更多
The methods to determine time delays and embedding dimensions in the phase space delay reconstruction of multivariate chaotic time series are proposed. Three nonlinear prediction methods of multivariate chaotic tim...The methods to determine time delays and embedding dimensions in the phase space delay reconstruction of multivariate chaotic time series are proposed. Three nonlinear prediction methods of multivariate chaotic time series including local mean prediction, local linear prediction and BP neural networks prediction are considered. The simulation results obtained by the Lorenz system show that no matter what nonlinear prediction method is used, the prediction error of multivariate chaotic time series is much smaller than the prediction error of univariate time series, even if half of the data of univariate time series are used in multivariate time series. The results also verify that methods to determine the time delays and the embedding dimensions are correct from the view of minimizing the prediction error.展开更多
To improve the prediction accuracy of chaotic time series, a new methodformed on the basis of local polynomial prediction is proposed. The multivariate phase spacereconstruction theory is utilized to reconstruct the p...To improve the prediction accuracy of chaotic time series, a new methodformed on the basis of local polynomial prediction is proposed. The multivariate phase spacereconstruction theory is utilized to reconstruct the phase space firstly, and on its basis, apolynomial function is applied to construct the prediction model, then the parameters of the modelaccording to the data matrix built with the embedding dimensions are estimated and a one-stepprediction value is calculated. An estimate and one-step prediction value is calculated. Finally,the mean squared root statistics are used to estimate the prediction effect. The simulation resultsobtained by the Lorenz system and the prediction results of the Shanghai composite index show thatthe local polynomial prediction errors of the multivariate chaotic time series are small and itsprediction accuracy is much higher than that of the univariate chaotic time series.展开更多
A new method of predicting chaotic time series is presented based on a local Lyapunov exponent, by quantitatively measuring the exponential rate of separation or attraction of two infinitely close trajectories in stat...A new method of predicting chaotic time series is presented based on a local Lyapunov exponent, by quantitatively measuring the exponential rate of separation or attraction of two infinitely close trajectories in state space. After recon- structing state space from one-dimensional chaotic time series, neighboring multiple-state vectors of the predicting point are selected to deduce the prediction formula by using the definition of the locaI Lyapunov exponent. Numerical simulations are carded out to test its effectiveness and verify its higher precision over two older methods. The effects of the number of referential state vectors and added noise on forecasting accuracy are also studied numerically.展开更多
Real time multi step prediction of BP network based on dynamical compensation of system characteristics is suggested by introducing the first and second derivatives of the system and network outputs into the network i...Real time multi step prediction of BP network based on dynamical compensation of system characteristics is suggested by introducing the first and second derivatives of the system and network outputs into the network input layer, and real time multi step prediction control is proposed for the BP network with delay on the basis of the results of real time multi step prediction, to achieve the simulation of real time fuzzy control of the delayed time system.展开更多
基金funded by the Fujian Province Science and Technology Plan,China(Grant Number 2019H0017).
文摘Accurate forecasting of time series is crucial across various domains.Many prediction tasks rely on effectively segmenting,matching,and time series data alignment.For instance,regardless of time series with the same granularity,segmenting them into different granularity events can effectively mitigate the impact of varying time scales on prediction accuracy.However,these events of varying granularity frequently intersect with each other,which may possess unequal durations.Even minor differences can result in significant errors when matching time series with future trends.Besides,directly using matched events but unaligned events as state vectors in machine learning-based prediction models can lead to insufficient prediction accuracy.Therefore,this paper proposes a short-term forecasting method for time series based on a multi-granularity event,MGE-SP(multi-granularity event-based short-termprediction).First,amethodological framework for MGE-SP established guides the implementation steps.The framework consists of three key steps,including multi-granularity event matching based on the LTF(latest time first)strategy,multi-granularity event alignment using a piecewise aggregate approximation based on the compression ratio,and a short-term prediction model based on XGBoost.The data from a nationwide online car-hailing service in China ensures the method’s reliability.The average RMSE(root mean square error)and MAE(mean absolute error)of the proposed method are 3.204 and 2.360,lower than the respective values of 4.056 and 3.101 obtained using theARIMA(autoregressive integratedmoving average)method,as well as the values of 4.278 and 2.994 obtained using k-means-SVR(support vector regression)method.The other experiment is conducted on stock data froma public data set.The proposed method achieved an average RMSE and MAE of 0.836 and 0.696,lower than the respective values of 1.019 and 0.844 obtained using the ARIMA method,as well as the values of 1.350 and 1.172 obtained using the k-means-SVR method.
基金supported by the China Scholarship Council and the CERNET Innovation Project under grant No.20170111.
文摘The prediction for Multivariate Time Series(MTS)explores the interrelationships among variables at historical moments,extracts their relevant characteristics,and is widely used in finance,weather,complex industries and other fields.Furthermore,it is important to construct a digital twin system.However,existing methods do not take full advantage of the potential properties of variables,which results in poor predicted accuracy.In this paper,we propose the Adaptive Fused Spatial-Temporal Graph Convolutional Network(AFSTGCN).First,to address the problem of the unknown spatial-temporal structure,we construct the Adaptive Fused Spatial-Temporal Graph(AFSTG)layer.Specifically,we fuse the spatial-temporal graph based on the interrelationship of spatial graphs.Simultaneously,we construct the adaptive adjacency matrix of the spatial-temporal graph using node embedding methods.Subsequently,to overcome the insufficient extraction of disordered correlation features,we construct the Adaptive Fused Spatial-Temporal Graph Convolutional(AFSTGC)module.The module forces the reordering of disordered temporal,spatial and spatial-temporal dependencies into rule-like data.AFSTGCN dynamically and synchronously acquires potential temporal,spatial and spatial-temporal correlations,thereby fully extracting rich hierarchical feature information to enhance the predicted accuracy.Experiments on different types of MTS datasets demonstrate that the model achieves state-of-the-art single-step and multi-step performance compared with eight other deep learning models.
基金funded by the Natural Science Foundation of Fujian Province,China (Grant No.2022J05291)Xiamen Scientific Research Funding for Overseas Chinese Scholars.
文摘Financial time series prediction,whether for classification or regression,has been a heated research topic over the last decade.While traditional machine learning algorithms have experienced mediocre results,deep learning has largely contributed to the elevation of the prediction performance.Currently,the most up-to-date review of advanced machine learning techniques for financial time series prediction is still lacking,making it challenging for finance domain experts and relevant practitioners to determine which model potentially performs better,what techniques and components are involved,and how themodel can be designed and implemented.This review article provides an overview of techniques,components and frameworks for financial time series prediction,with an emphasis on state-of-the-art deep learning models in the literature from2015 to 2023,including standalonemodels like convolutional neural networks(CNN)that are capable of extracting spatial dependencies within data,and long short-term memory(LSTM)that is designed for handling temporal dependencies;and hybrid models integrating CNN,LSTM,attention mechanism(AM)and other techniques.For illustration and comparison purposes,models proposed in recent studies are mapped to relevant elements of a generalized framework comprised of input,output,feature extraction,prediction,and related processes.Among the state-of-the-artmodels,hybrid models like CNNLSTMand CNN-LSTM-AM in general have been reported superior in performance to stand-alone models like the CNN-only model.Some remaining challenges have been discussed,including non-friendliness for finance domain experts,delayed prediction,domain knowledge negligence,lack of standards,and inability of real-time and highfrequency predictions.The principal contributions of this paper are to provide a one-stop guide for both academia and industry to review,compare and summarize technologies and recent advances in this area,to facilitate smooth and informed implementation,and to highlight future research directions.
基金The National Key R&D Program of China under contract No.2021YFC3101603.
文摘Ocean temperature is an important physical variable in marine ecosystems,and ocean temperature prediction is an important research objective in ocean-related fields.Currently,one of the commonly used methods for ocean temperature prediction is based on data-driven,but research on this method is mostly limited to the sea surface,with few studies on the prediction of internal ocean temperature.Existing graph neural network-based methods usually use predefined graphs or learned static graphs,which cannot capture the dynamic associations among data.In this study,we propose a novel dynamic spatiotemporal graph neural network(DSTGN)to predict threedimensional ocean temperature(3D-OT),which combines static graph learning and dynamic graph learning to automatically mine two unknown dependencies between sequences based on the original 3D-OT data without prior knowledge.Temporal and spatial dependencies in the time series were then captured using temporal and graph convolutions.We also integrated dynamic graph learning,static graph learning,graph convolution,and temporal convolution into an end-to-end framework for 3D-OT prediction using time-series grid data.In this study,we conducted prediction experiments using high-resolution 3D-OT from the Copernicus global ocean physical reanalysis,with data covering the vertical variation of temperature from the sea surface to 1000 m below the sea surface.We compared five mainstream models that are commonly used for ocean temperature prediction,and the results showed that the method achieved the best prediction results at all prediction scales.
文摘The growing global requirement for food and the need for sustainable farming in an era of a changing climate and scarce resources have inspired substantial crop yield prediction research.Deep learning(DL)and machine learning(ML)models effectively deal with such challenges.This research paper comprehensively analyses recent advancements in crop yield prediction from January 2016 to March 2024.In addition,it analyses the effectiveness of various input parameters considered in crop yield prediction models.We conducted an in-depth search and gathered studies that employed crop modeling and AI-based methods to predict crop yield.The total number of articles reviewed for crop yield prediction using ML,meta-modeling(Crop models coupled with ML/DL),and DL-based prediction models and input parameter selection is 125.We conduct the research by setting up five objectives for this research and discussing them after analyzing the selected research papers.Each study is assessed based on the crop type,input parameters employed for prediction,the modeling techniques adopted,and the evaluation metrics used for estimatingmodel performance.We also discuss the ethical and social impacts of AI on agriculture.However,various approaches presented in the scientific literature have delivered impressive predictions,they are complicateddue to intricate,multifactorial influences oncropgrowthand theneed for accuratedata-driven models.Therefore,thorough research is required to deal with challenges in predicting agricultural output.
基金the National Key R&D Program of China(No.2022YFC2904103)the Key Program of the National Natural Science Foundation of China(No.52034001)+1 种基金the 111 Project(No.B20041)the China National Postdoctoral Program for Innovative Talents(No.BX20230041)。
文摘Traditional research believes that the filling body can effectively control stress concentration while ignoring the problems of unknown stability and the complex and changeable stress distribution of the filling body–surrounding rock combination under high-stress conditions.Current monitoring data processing methods cannot fully consider the complexity of monitoring objects,the diversity of monitoring methods,and the dynamics of monitoring data.To solve this problem,this paper proposes a phase space reconstruction and stability prediction method to process heterogeneous information of backfill–surrounding rock combinations.The three-dimensional monitoring system of a large-area filling body–surrounding rock combination in Longshou Mine was constructed by using drilling stress,multipoint displacement meter,and inclinometer.Varied information,such as the stress and displacement of the filling body–surrounding rock combination,was continuously obtained.Combined with the average mutual information method and the false nearest neighbor point method,the phase space of the heterogeneous information of the filling body–surrounding rock combination was then constructed.In this paper,the distance between the phase point and its nearest point was used as the index evaluation distance to evaluate the stability of the filling body–surrounding rock combination.The evaluated distances(ED)revealed a high sensitivity to the stability of the filling body–surrounding rock combination.The new method was then applied to calculate the time series of historically ED for 12 measuring points located at Longshou Mine.The moments of mutation in these time series were at least 3 months ahead of the roadway return dates.In the ED prediction experiments,the autoregressive integrated moving average model showed a higher prediction accuracy than the deep learning models(long short-term memory and Transformer).Furthermore,the root-mean-square error distribution of the prediction results peaked at 0.26,thus outperforming the no-prediction method in 70%of the cases.
基金supported by the Science and Technology Project of State Grid Shanxi Electric Power Research Institute:Research on Data-Driven New Power System Operation Simulation and Multi Agent Control Strategy(52053022000F).
文摘Due to the impact of source-load prediction power errors and uncertainties,the actual operation of the park will have a wide range of fluctuations compared with the expected state,resulting in its inability to achieve the expected economy.This paper constructs an operating simulation model of the park power grid operation considering demand response and proposes a multi-time scale operating simulation method that combines day-ahead optimization and model predictive control(MPC).In the day-ahead stage,an operating simulation plan that comprehensively considers the user’s side comfort and operating costs is proposed with a long-term time scale of 15 min.In order to cope with power fluctuations of photovoltaic,wind turbine and conventional load,MPC is used to track and roll correct the day-ahead operating simulation plan in the intra-day stage to meet the actual operating operation status of the park.Finally,the validity and economy of the operating simulation strategy are verified through the analysis of arithmetic examples.
文摘This paper examines the effectiveness of the Differential autoregressive integrated moving average (ARIMA) model in comparison to the Long Short Term Memory (LSTM) neural network model for predicting Wordle user-reported scores. The ARIMA and LSTM models were trained using Wordle data from Twitter between 7th January 2022 and 31st December 2022. User-reported scores were predicted using evaluation metrics such as MSE, RMSE, R2, and MAE. Various regression models, including XG-Boost and Random Forest, were used to conduct comparison experiments. The MSE, RMSE, R2, and MAE values for the ARIMA(0,1,1) and LSTM models are 0.000, 0.010, 0.998, and 0.006, and 0.000, 0.024, 0.987, and 0.013, respectively. The results indicate that the ARIMA model is more suitable for predicting Wordle user scores than the LSTM model.
基金supported by National Natural Science Foundation of China (61703410,61873175,62073336,61873273,61773386,61922089)。
文摘Remaining useful life(RUL) prediction is one of the most crucial elements in prognostics and health management(PHM). Aiming at the imperfect prior information, this paper proposes an RUL prediction method based on a nonlinear random coefficient regression(RCR) model with fusing failure time data.Firstly, some interesting natures of parameters estimation based on the nonlinear RCR model are given. Based on these natures,the failure time data can be fused as the prior information reasonably. Specifically, the fixed parameters are calculated by the field degradation data of the evaluated equipment and the prior information of random coefficient is estimated with fusing the failure time data of congeneric equipment. Then, the prior information of the random coefficient is updated online under the Bayesian framework, the probability density function(PDF) of the RUL with considering the limitation of the failure threshold is performed. Finally, two case studies are used for experimental verification. Compared with the traditional Bayesian method, the proposed method can effectively reduce the influence of imperfect prior information and improve the accuracy of RUL prediction.
文摘Graphics Processing Units(GPUs)are used to accelerate computing-intensive tasks,such as neural networks,data analysis,high-performance computing,etc.In the past decade or so,researchers have done a lot of work on GPU architecture and proposed a variety of theories and methods to study the microarchitectural characteristics of various GPUs.In this study,the GPU serves as a co-processor and works together with the CPU in an embedded real-time system to handle computationally intensive tasks.It models the architecture of the GPU and further considers it based on some excellent work.The SIMT mechanism and Cache-miss situation provide a more detailed analysis of the GPU architecture.In order to verify the GPU architecture model proposed in this article,10 GPU kernel_task and an Nvidia GPU device were used to perform experiments.The experimental results showed that the minimum error between the kernel task execution time predicted by the GPU architecture model proposed in this article and the actual measured kernel task execution time was 3.80%,and the maximum error was 8.30%.
基金funded by Shaanxi Province Key Industrial Chain Project(2023-ZDLGY-24)Industrialization Project of Shaanxi Provincial Education Department(21JC018)+1 种基金Shaanxi Province Key Research and Development Program(2021ZDLGY13-02)the Open Foundation of State Key Laboratory for Advanced Metals and Materials(2022-Z01).
文摘In order to improve the performance degradation prediction accuracy of proton exchange membrane fuel cell(PEMFC),a fusion prediction method(CKDG)based on adaptive noise complete ensemble empirical mode decomposition(CEEMDAN),kernel principal component analysis(KPCA)and dual attention mechanism gated recurrent unit neural network(DA-GRU)was proposed.CEEMDAN and KPCA were used to extract the input feature data sequence,reduce the influence of random factors,and capture essential feature components to reduce the model complexity.The DA-GRU network helps to learn the feature mapping relationship of data in long time series and predict the changing trend of performance degradation data more accurately.The actual aging experimental data verify the performance of the CKDG method.The results show that under the steady-state condition of 20%training data prediction,the CKDA method can reduce the root mean square error(RMSE)by 52.7%and 34.6%,respectively,compared with the traditional LSTM and GRU neural networks.Compared with the simple DA-GRU network,RMSE is reduced by 15%,and the degree of over-fitting is reduced,which has higher accuracy.It also shows excellent prediction performance under the dynamic condition data set and has good universality.
基金funded by Fundamental and Advanced Research Project of Chongqing CSTC of China(No.cstc2019jcyj‐msxmX0386 and No.cstc2020jcyj‐msxmX0232)National Statistical Science Research Project(No.2020LY100).
文摘As one of the most widespread renewable energy sources,wind energy is now an important part of the power system.Accurate and appropriate wind speed forecasting has an essential impact on wind energy utilisation.However,due to the stochastic and un-certain nature of wind energy,more accurate forecasting is necessary for its more stable and safer utilisation.This paper proposes a Legendre multiwavelet‐based neural network model for non‐linear wind speed prediction.It combines the excellent properties of Legendre multi‐wavelets with the self‐learning capability of neural networks,which has rigorous mathematical theory support.It learns input‐output data pairs and shares weights within divided subintervals,which can greatly reduce computing costs.We explore the effectiveness of Legendre multi‐wavelets as an activation function.Mean-while,it is successfully being applied to wind speed prediction.In addition,the appli-cation of Legendre multi‐wavelet neural networks in a hybrid model in decomposition‐reconstruction mode to wind speed prediction problems is also discussed.Numerical results on real data sets show that the proposed model is able to achieve optimal per-formance and high prediction accuracy.In particular,the model shows a more stable performance in multi‐step prediction,illustrating its superiority.
文摘The price prediction task is a well-studied problem due to its impact on the business domain.There are several research studies that have been conducted to predict the future price of items by capturing the patterns of price change,but there is very limited work to study the price prediction of seasonal goods(e.g.,Christmas gifts).Seasonal items’prices have different patterns than normal items;this can be linked to the offers and discounted prices of seasonal items.This lack of research studies motivates the current work to investigate the problem of seasonal items’prices as a time series task.We proposed utilizing two different approaches to address this problem,namely,1)machine learning(ML)-based models and 2)deep learning(DL)-based models.Thus,this research tuned a set of well-known predictive models on a real-life dataset.Those models are ensemble learning-based models,random forest,Ridge,Lasso,and Linear regression.Moreover,two new DL architectures based on gated recurrent unit(GRU)and long short-term memory(LSTM)models are proposed.Then,the performance of the utilized ensemble learning and classic ML models are compared against the proposed two DL architectures on different accuracy metrics,where the evaluation includes both numerical and visual comparisons of the examined models.The obtained results show that the ensemble learning models outperformed the classic machine learning-based models(e.g.,linear regression and random forest)and the DL-based models.
文摘Due to fast-growing urbanization,the traffic management system becomes a crucial problem owing to the rapid growth in the number of vehicles The research proposes an Intelligent public transportation system where informa-tion regarding all the buses connecting in a city will be gathered,processed and accurate bus arrival time prediction will be presented to the user.Various linear and time-varying parameters such as distance,waiting time at stops,red signal duration at a traffic signal,traffic density,turning density,rush hours,weather conditions,number of passengers on the bus,type of day,road type,average vehi-cle speed limit,current vehicle speed affecting traffic are used for the analysis.The proposed model exploits the feasibility and applicability of ELM in the travel time forecasting area.Multiple ELMs(MELM)for explicitly training dynamic,road and trajectory information are used in the proposed approach.A large-scale dataset(historical data)obtained from Kerala State Road Transport Corporation is used for training.Simulations are carried out by using MATLAB R2021a.The experiments revealed that the efficiency of MELM is independent of the time of day and day of the week.It can manage huge volumes of data with less human intervention at greater learning speeds.It is found MELM yields prediction with accuracy in the range of 96.7%to 99.08%.The MAE value is between 0.28 to 1.74 minutes with the proposed approach.The study revealed that there could be regularity in bus usage and daily bus rides are predictable with a better degree of accuracy.The research has proved that MELM is superior for arrival time pre-dictions in terms of accuracy and error,compared with other approaches.
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.
文摘Emotion has a nearly decisive role in behavior, which will directly affect netizens’ views on food safety public opinion events, thereby affecting the development direction of public opinion on the event, and it is of great significance for food safety network public opinion to predict emotional trends to do a good job in food safety network public opinion guidance. In this paper, the dynamic text representation method XLNet is used to generate word vectors with context-dependent dependencies to distribute the text information of food safety network public opinion. Then, the word vector is input into the CNN-BiLSTM network for local semantic feature and context semantic extraction. The attention mechanism is introduced to give different weights according to the importance of features, and the emotional tendency analysis is carried out. Based on sentiment analysis, sentiment value time series data is obtained, and a time series model is constructed to predict sentiment trends. The sentiment analysis model proposed in this paper can well classify the sentiment of food safety network public opinion, and the time series model has a good effect on the prediction of food safety network public opinion sentiment trend. .
文摘The methods to determine time delays and embedding dimensions in the phase space delay reconstruction of multivariate chaotic time series are proposed. Three nonlinear prediction methods of multivariate chaotic time series including local mean prediction, local linear prediction and BP neural networks prediction are considered. The simulation results obtained by the Lorenz system show that no matter what nonlinear prediction method is used, the prediction error of multivariate chaotic time series is much smaller than the prediction error of univariate time series, even if half of the data of univariate time series are used in multivariate time series. The results also verify that methods to determine the time delays and the embedding dimensions are correct from the view of minimizing the prediction error.
文摘To improve the prediction accuracy of chaotic time series, a new methodformed on the basis of local polynomial prediction is proposed. The multivariate phase spacereconstruction theory is utilized to reconstruct the phase space firstly, and on its basis, apolynomial function is applied to construct the prediction model, then the parameters of the modelaccording to the data matrix built with the embedding dimensions are estimated and a one-stepprediction value is calculated. An estimate and one-step prediction value is calculated. Finally,the mean squared root statistics are used to estimate the prediction effect. The simulation resultsobtained by the Lorenz system and the prediction results of the Shanghai composite index show thatthe local polynomial prediction errors of the multivariate chaotic time series are small and itsprediction accuracy is much higher than that of the univariate chaotic time series.
基金Project supported by the National Natural Science Foundation of China (Grant No. 61201452)
文摘A new method of predicting chaotic time series is presented based on a local Lyapunov exponent, by quantitatively measuring the exponential rate of separation or attraction of two infinitely close trajectories in state space. After recon- structing state space from one-dimensional chaotic time series, neighboring multiple-state vectors of the predicting point are selected to deduce the prediction formula by using the definition of the locaI Lyapunov exponent. Numerical simulations are carded out to test its effectiveness and verify its higher precision over two older methods. The effects of the number of referential state vectors and added noise on forecasting accuracy are also studied numerically.
文摘Real time multi step prediction of BP network based on dynamical compensation of system characteristics is suggested by introducing the first and second derivatives of the system and network outputs into the network input layer, and real time multi step prediction control is proposed for the BP network with delay on the basis of the results of real time multi step prediction, to achieve the simulation of real time fuzzy control of the delayed time system.