A Time Series Short-Term Prediction Method Based on Multi-Granularity Event Matching and Alignment

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.

Deep Learning for Financial Time Series Prediction:A State-of-the-Art Review of Standalone and HybridModels

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.

AFSTGCN:Prediction for multivariate time series using an adaptive fused spatial-temporal graph convolutional network

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.

Prediction of three-dimensional ocean temperature in the South China Sea based on time series gridded data and a dynamic spatiotemporal graph neural network

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.

Multiple Extreme Learning Machines Based Arrival Time Prediction for Public Bus Transport

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.

Short‐time wind speed prediction based on Legendre multi‐wavelet neural network

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.

Remaining useful life prediction based on nonlinear random coefficient regression model with fusing failure time data

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.

Bus Arrival Time Prediction Based on Mixed Model

How to predict the bus arrival time accurately is a crucial problem to be solved in Internet of Vehicle. Existed methods cannot solve the problem effectively for ignoring the traffic delay jitter. In this paper,a three-stage mixed model is proposed for bus arrival time prediction. The first stage is pattern training. In this stage,the traffic delay jitter patterns(TDJP)are mined by K nearest neighbor and K-means in the historical traffic time data. The second stage is the single-step prediction,which is based on real-time adjusted Kalman filter with a modification of historical TDJP. In the third stage,as the influence of historical law is increasing in long distance prediction,we combine the single-step prediction dynamically with Markov historical transfer model to conduct the multi-step prediction. The experimental results show that the proposed single-step prediction model performs better in accuracy and efficiency than short-term traffic flow prediction and dynamic Kalman filter. The multi-step prediction provides a higher level veracity and reliability in travel time forecasting than short-term traffic flow and historical traffic pattern prediction models.

Collaborative prediction for bus arrival time based on CPS

To improve the accuracy of real-time public transport information release system, a collaborative prediction model was proposed based on cyber-physical systems architecture. In the model, the total bus travel time was divided into three parts: running time, dwell time and intersection delay time, and the data were divided into three categories of historical data, static data and real-time data. The bus arrival time was obtained by fusion computing the real-time data in perception layer together with historical data and static data in collaborative layer. The validity of the collaborative model was verified by the data of a typical urban bus line in Shanghai, and 1538 sets of data were collected and analyzed from three different perspectives. By comparing the experimental results with the actual results, it is shown that the experimental results are with higher prediction accuracy, and the collaborative prediction model adopted is able to meet the demand for bus arrival prediction.

Route Temporal⁃Spatial Information Based Residual Neural Networks for Bus Arrival Time Prediction

Bus arrival time prediction contributes to the quality improvement of public transport services.Passengers can arrange departure time effectively if they know the accurate bus arrival time in advance.We proposed a machine⁃learning approach,RTSI⁃ResNet,to forecast the bus arrival time at target stations.The residual neural network framework was employed to model the bus route temporal⁃spatial information.It was found that the bus travel time on a segment between two stations not only had correlation with the preceding buses,but also had common change trends with nearby downstream/upstream segments.Two features about bus travel time and headway were extracted from bus route including target section in both forward and reverse directions to constitute the route temporal⁃spatial information,which reflects the road traffic conditions comprehensively.Experiments on the bus trajectory data of route No.10 in Shenzhen public transport system demonstrated that the proposed RTSI⁃ResNet outperformed other well⁃known methods(e.g.,RNN/LSTM,SVM).Specifically,the advantage was more significant when the distance between bus and the target station was farther.

Price Prediction of Seasonal Items Using Time Series Analysis

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.

Vehicle Density Prediction in Low Quality Videos with Transformer Timeseries Prediction Model(TTPM)

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.

Research on Prediction of Sentiment Trend of Food Safety Public Opinion

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. .

An Integrated Analysis of Yield Prediction Models:A Comprehensive Review of Advancements and Challenges

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.

TSCND:Temporal Subsequence-Based Convolutional Network with Difference for Time Series Forecasting

Time series forecasting plays an important role in various fields, such as energy, finance, transport, and weather. Temporal convolutional networks (TCNs) based on dilated causal convolution have been widely used in time series forecasting. However, two problems weaken the performance of TCNs. One is that in dilated casual convolution, causal convolution leads to the receptive fields of outputs being concentrated in the earlier part of the input sequence, whereas the recent input information will be severely lost. The other is that the distribution shift problem in time series has not been adequately solved. To address the first problem, we propose a subsequence-based dilated convolution method (SDC). By using multiple convolutional filters to convolve elements of neighboring subsequences, the method extracts temporal features from a growing receptive field via a growing subsequence rather than a single element. Ultimately, the receptive field of each output element can cover the whole input sequence. To address the second problem, we propose a difference and compensation method (DCM). The method reduces the discrepancies between and within the input sequences by difference operations and then compensates the outputs for the information lost due to difference operations. Based on SDC and DCM, we further construct a temporal subsequence-based convolutional network with difference (TSCND) for time series forecasting. The experimental results show that TSCND can reduce prediction mean squared error by 7.3% and save runtime, compared with state-of-the-art models and vanilla TCN.

Performance Degradation Prediction of Proton Exchange Membrane Fuel Cell Based on CEEMDAN-KPCA and DA-GRU Networks

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.

Effect and mechanism of on-chip electrostatic discharge protection circuit under fast rising time electromagnetic pulse

The electrostatic discharge(ESD)protection circuit widely exists in the input and output ports of CMOS digital circuits,and fast rising time electromagnetic pulse(FREMP)coupled into the device not only interacts with the CMOS circuit,but also acts on the protection circuit.This paper establishes a model of on-chip CMOS electrostatic discharge protection circuit and selects square pulse as the FREMP signals.Based on multiple physical parameter models,it depicts the distribution of the lattice temperature,current density,and electric field intensity inside the device.At the same time,this paper explores the changes of the internal devices in the circuit under the injection of fast rising time electromagnetic pulse and describes the relationship between the damage amplitude threshold and the pulse width.The results show that the ESD protection circuit has potential damage risk,and the injection of FREMP leads to irreversible heat loss inside the circuit.In addition,pulse signals with different attributes will change the damage threshold of the circuit.These results provide an important reference for further evaluation of the influence of electromagnetic environment on the chip,which is helpful to carry out the reliability enhancement research of ESD protection circuit.

Prognostic prediction models for postoperative patients with stageⅠtoⅢcolorectal cancer based on machine learning

BACKGROUND Colorectal cancer(CRC)is characterized by high heterogeneity,aggressiveness,and high morbidity and mortality rates.With machine learning(ML)algorithms,patient,tumor,and treatment features can be used to develop and validate models for predicting survival.In addition,important variables can be screened and different applications can be provided that could serve as vital references when making clinical decisions and potentially improving patient outcomes in clinical settings.AIM To construct prognostic prediction models and screen important variables for patients with stageⅠtoⅢCRC.METHODS More than 1000 postoperative CRC patients were grouped according to survival time(with cutoff values of 3 years and 5 years)and assigned to training and testing cohorts(7:3).For each 3-category survival time,predictions were made by 4 ML algorithms(all-variable and important variable-only datasets),each of which was validated via 5-fold cross-validation and bootstrap validation.Important variables were screened with multivariable regression methods.Model performance was evaluated and compared before and after variable screening with the area under the curve(AUC).SHapley Additive exPlanations(SHAP)further demonstrated the impact of important variables on model decision-making.Nomograms were constructed for practical model application.RESULTS Our ML models performed well;the model performance before and after important parameter identification was consistent,and variable screening was effective.The highest pre-and postscreening model AUCs 95%confidence intervals in the testing set were 0.87(0.81-0.92)and 0.89(0.84-0.93)for overall survival,0.75(0.69-0.82)and 0.73(0.64-0.81)for disease-free survival,0.95(0.88-1.00)and 0.88(0.75-0.97)for recurrence-free survival,and 0.76(0.47-0.95)and 0.80(0.53-0.94)for distant metastasis-free survival.Repeated cross-validation and bootstrap validation were performed in both the training and testing datasets.The SHAP values of the important variables were consistent with the clinicopathological characteristics of patients with tumors.The nomograms were created.CONCLUSION We constructed a comprehensive,high-accuracy,important variable-based ML architecture for predicting the 3-category survival times.This architecture could serve as a vital reference for managing CRC patients.

Heterogeneous information phase space reconstruction and stability prediction of filling body–surrounding rock combination

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.

Multi-Time Scale Operation and Simulation Strategy of the Park Based on Model Predictive Control

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.