A modified stochastic model for LS+AR hybrid method and its application in polar motion short-term prediction

Short-term(up to 30 days)predictions of Earth Rotation Parameters(ERPs)such as Polar Motion(PM:PMX and PMY)play an essential role in real-time applications related to high-precision reference frame conversion.Currently,least squares(LS)+auto-regressive(AR)hybrid method is one of the main techniques of PM prediction.Besides,the weighted LS+AR hybrid method performs well for PM short-term prediction.However,the corresponding covariance information of LS fitting residuals deserves further exploration in the AR model.In this study,we have derived a modified stochastic model for the LS+AR hybrid method,namely the weighted LS+weighted AR hybrid method.By using the PM data products of IERS EOP 14 C04,the numerical results indicate that for PM short-term forecasting,the proposed weighted LS+weighted AR hybrid method shows an advantage over both the LS+AR hybrid method and the weighted LS+AR hybrid method.Compared to the mean absolute errors(MAEs)of PMX/PMY sho rt-term prediction of the LS+AR hybrid method and the weighted LS+AR hybrid method,the weighted LS+weighted AR hybrid method shows average improvements of 6.61%/12.08%and 0.24%/11.65%,respectively.Besides,for the slopes of the linear regression lines fitted to the errors of each method,the growth of the prediction error of the proposed method is slower than that of the other two methods.

Development and validation of a circulating tumor DNA-based optimization-prediction model for short-term postoperative recurrence of endometrial cancer

BACKGROUND Endometrial cancer(EC)is a common gynecological malignancy that typically requires prompt surgical intervention;however,the advantage of surgical management is limited by the high postoperative recurrence rates and adverse outcomes.Previous studies have highlighted the prognostic potential of circulating tumor DNA(ctDNA)monitoring for minimal residual disease in patients with EC.AIM To develop and validate an optimized ctDNA-based model for predicting shortterm postoperative EC recurrence.METHODS We retrospectively analyzed 294 EC patients treated surgically from 2015-2019 to devise a short-term recurrence prediction model,which was validated on 143 EC patients operated between 2020 and 2021.Prognostic factors were identified using univariate Cox,Lasso,and multivariate Cox regressions.A nomogram was created to predict the 1,1.5,and 2-year recurrence-free survival(RFS).Model performance was assessed via receiver operating characteristic(ROC),calibration,and decision curve analyses(DCA),leading to a recurrence risk stratification system.RESULTS Based on the regression analysis and the nomogram created,patients with postoperative ctDNA-negativity,postoperative carcinoembryonic antigen 125(CA125)levels of<19 U/mL,and grade G1 tumors had improved RFS after surgery.The nomogram’s efficacy for recurrence prediction was confirmed through ROC analysis,calibration curves,and DCA methods,highlighting its high accuracy and clinical utility.Furthermore,using the nomogram,the patients were successfully classified into three risk subgroups.CONCLUSION The nomogram accurately predicted RFS after EC surgery at 1,1.5,and 2 years.This model will help clinicians personalize treatments,stratify risks,and enhance clinical outcomes for patients with EC.

Slope stability prediction based on a long short-term memory neural network:comparisons with convolutional neural networks,support vector machines and random forest models

The numerical simulation and slope stability prediction are the focus of slope disaster research.Recently,machine learning models are commonly used in the slope stability prediction.However,these machine learning models have some problems,such as poor nonlinear performance,local optimum and incomplete factors feature extraction.These issues can affect the accuracy of slope stability prediction.Therefore,a deep learning algorithm called Long short-term memory(LSTM)has been innovatively proposed to predict slope stability.Taking the Ganzhou City in China as the study area,the landslide inventory and their characteristics of geotechnical parameters,slope height and slope angle are analyzed.Based on these characteristics,typical soil slopes are constructed using the Geo-Studio software.Five control factors affecting slope stability,including slope height,slope angle,internal friction angle,cohesion and volumetric weight,are selected to form different slope and construct model input variables.Then,the limit equilibrium method is used to calculate the stability coefficients of these typical soil slopes under different control factors.Each slope stability coefficient and its corresponding control factors is a slope sample.As a result,a total of 2160 training samples and 450 testing samples are constructed.These sample sets are imported into LSTM for modelling and compared with the support vector machine(SVM),random forest(RF)and convo-lutional neural network(CNN).The results show that the LSTM overcomes the problem that the commonly used machine learning models have difficulty extracting global features.Furthermore,LSTM has a better prediction performance for slope stability compared to SVM,RF and CNN models.

Transformer-based correction scheme for short-term bus load prediction in holidays

To tackle the problem of inaccurate short-term bus load prediction,especially during holidays,a Transformer-based scheme with tailored architectural enhancements is proposed.First,the input data are clustered to reduce complexity and capture inherent characteristics more effectively.Gated residual connections are then employed to selectively propagate salient features across layers,while an attention mechanism focuses on identifying prominent patterns in multivariate time-series data.Ultimately,a pre-trained structure is incorporated to reduce computational complexity.Experimental results based on extensive data show that the proposed scheme achieves improved prediction accuracy over comparative algorithms by at least 32.00%consistently across all buses evaluated,and the fitting effect of holiday load curves is outstanding.Meanwhile,the pre-trained structure drastically reduces the training time of the proposed algorithm by more than 65.75%.The proposed scheme can efficiently predict bus load results while enhancing robustness for holiday predictions,making it better adapted to real-world prediction scenarios.

DPAL-BERT:A Faster and Lighter Question Answering Model

Recent advancements in natural language processing have given rise to numerous pre-training language models in question-answering systems.However,with the constant evolution of algorithms,data,and computing power,the increasing size and complexity of these models have led to increased training costs and reduced efficiency.This study aims to minimize the inference time of such models while maintaining computational performance.It also proposes a novel Distillation model for PAL-BERT(DPAL-BERT),specifically,employs knowledge distillation,using the PAL-BERT model as the teacher model to train two student models:DPAL-BERT-Bi and DPAL-BERTC.This research enhances the dataset through techniques such as masking,replacement,and n-gram sampling to optimize knowledge transfer.The experimental results showed that the distilled models greatly outperform models trained from scratch.In addition,although the distilled models exhibit a slight decrease in performance compared to PAL-BERT,they significantly reduce inference time to just 0.25%of the original.This demonstrates the effectiveness of the proposed approach in balancing model performance and efficiency.

Prediction of discharge in a tidal river using the LSTM-based sequence-to-sequence models

The complexity of river-tide interaction poses a significant challenge in predicting discharge in tidal rivers.Long short-term memory(LSTM)networks excel in processing and predicting crucial events with extended intervals and time delays in time series data.Additionally,the sequence-to-sequence(Seq2Seq)model,known for handling temporal relationships,adapting to variable-length sequences,effectively capturing historical information,and accommodating various influencing factors,emerges as a robust and flexible tool in discharge forecasting.In this study,we introduce the application of LSTM-based Seq2Seq models for the first time in forecasting the discharge of a tidal reach of the Changjiang River(Yangtze River)Estuary.This study focuses on discharge forecasting using three key input characteristics:flow velocity,water level,and discharge,which means the structure of multiple input and single output is adopted.The experiment used the discharge data of the whole year of 2020,of which the first 80%is used as the training set,and the last 20%is used as the test set.This means that the data covers different tidal cycles,which helps to test the forecasting effect of different models in different tidal cycles and different runoff.The experimental results indicate that the proposed models demonstrate advantages in long-term,mid-term,and short-term discharge forecasting.The Seq2Seq models improved by 6%-60%and 5%-20%of the relative standard deviation compared to the harmonic analysis models and improved back propagation neural network models in discharge prediction,respectively.In addition,the relative accuracy of the Seq2Seq model is 1%to 3%higher than that of the LSTM model.Analytical assessment of the prediction errors shows that the Seq2Seq models are insensitive to the forecast lead time and they can capture characteristic values such as maximum flood tide flow and maximum ebb tide flow in the tidal cycle well.This indicates the significance of the Seq2Seq models.

Comparison of Two Recurrent Neural Networks for Rainfall-Runoff Modeling in the Zou River Basin at Atchérigbé (Bénin)

Hydrological models are developed to simulate river flows over a watershed for many practical applications in the field of water resource management. The present paper compares the performance of two recurrent neural networks for rainfall-runoff modeling in the Zou River basin at Atchérigbé outlet. To this end, we used daily precipitation data over the period 1988-2010 as input of the models, such as the Long Short-Term Memory (LSTM) and Recurrent Gate Networks (GRU) to simulate river discharge in the study area. The investigated models give good results in calibration (R2 = 0.888, NSE = 0.886, and RMSE = 0.42 for LSTM;R2 = 0.9, NSE = 0.9 and RMSE = 0.397 for GRU) and in validation (R2 = 0.865, NSE = 0.851, and RMSE = 0.329 for LSTM;R2 = 0.9, NSE = 0.865 and RMSE = 0.301 for GRU). This good performance of LSTM and GRU models confirms the importance of models based on machine learning in modeling hydrological phenomena for better decision-making.

Deep Learning-Based Stock Price Prediction Using LSTM Model

The stock market is a vital component of the broader financial system,with its dynamics closely linked to economic growth.The challenges associated with analyzing and forecasting stock prices have persisted since the inception of financial markets.By examining historical transaction data,latent opportunities for profit can be uncovered,providing valuable insights for both institutional and individual investors to make more informed decisions.This study focuses on analyzing historical transaction data from four banks to predict closing price trends.Various models,including decision trees,random forests,and Long Short-Term Memory(LSTM)networks,are employed to forecast stock price movements.Historical stock transaction data serves as the input for training these models,which are then used to predict upward or downward stock price trends.The study’s empirical results indicate that these methods are effective to a degree in predicting stock price movements.The LSTM-based deep neural network model,in particular,demonstrates a commendable level of predictive accuracy.This conclusion is reached following a thorough evaluation of model performance,highlighting the potential of LSTM models in stock market forecasting.The findings offer significant implications for advancing financial forecasting approaches,thereby improving the decision-making capabilities of investors and financial institutions.

Long Short-Term Memory Recurrent Neural Network-Based Acoustic Model Using Connectionist Temporal Classification on a Large-Scale Training Corpus

A Long Short-Term Memory(LSTM) Recurrent Neural Network(RNN) has driven tremendous improvements on an acoustic model based on Gaussian Mixture Model(GMM). However, these models based on a hybrid method require a forced aligned Hidden Markov Model(HMM) state sequence obtained from the GMM-based acoustic model. Therefore, it requires a long computation time for training both the GMM-based acoustic model and a deep learning-based acoustic model. In order to solve this problem, an acoustic model using CTC algorithm is proposed. CTC algorithm does not require the GMM-based acoustic model because it does not use the forced aligned HMM state sequence. However, previous works on a LSTM RNN-based acoustic model using CTC used a small-scale training corpus. In this paper, the LSTM RNN-based acoustic model using CTC is trained on a large-scale training corpus and its performance is evaluated. The implemented acoustic model has a performance of 6.18% and 15.01% in terms of Word Error Rate(WER) for clean speech and noisy speech, respectively. This is similar to a performance of the acoustic model based on the hybrid method.

A mathematical model of synaptotagmin 7 revealing functional importance of short-term synaptic plasticity

Synaptotagmin 7(Syt7), a presynaptic calcium sensor, has a significant role in the facilitation in shortterm synaptic plasticity: Syt7 knock out mice show a significant reduction in the facilitation. The functional importance of short-term synaptic plasticity such as facilitation is not well understood. In this study, we attempt to investigate the potential functional relationship between the short-term synaptic plasticity and postsynaptic response by developing a mathematical model that captures the responses of both wild-type and Syt7 knock-out mice. We then studied the model behaviours of wild-type and Syt7 knock-out mice in response to multiple input action potentials. These behaviors could establish functional importance of short-term plasticity in regulating the postsynaptic response and related synaptic properties. In agreement with previous modeling studies, we show that release sites are governed by non-uniform release probabilities of neurotransmitters. The structure of non-uniform release of neurotransmitters makes shortterm synaptic plasticity to act as a high-pass filter. We also propose that Syt7 may be a modulator for the long-term changes of postsynaptic response that helps to train the target frequency of the filter. We have developed a mathematical model of short-term plasticity which explains the experimental data.

A hybrid model for short-term rainstorm forecasting based on a back-propagation neural network and synoptic diagnosis

Rainstorms are one of the most important types of natural disaster in China.In order to enhance the ability to forecast rainstorms in the short term,this paper explores how to combine a back-propagation neural network(BPNN)with synoptic diagnosis for predicting rainstorms,and analyzes the hit rates of rainstorms for the above two methods using the county of Tianquan as a case study.Results showed that the traditional synoptic diagnosis method still has an important referential meaning for most rainstorm types through synoptic typing and statistics of physical quantities based on historical cases,and the threat score(TS)of rainstorms was more than 0.75.However,the accuracy for two rainstorm types influenced by low-level easterly inverted troughs was less than 40%.The BPNN method efficiently forecasted these two rainstorm types;the TS and equitable threat score(ETS)of rainstorms were 0.80 and 0.79,respectively.The TS and ETS of the hybrid model that combined the BPNN and synoptic diagnosis methods exceeded the forecast score of multi-numerical simulations over the Sichuan Basin without exception.This kind of hybrid model enhanced the forecasting accuracy of rainstorms.The findings of this study provide certain reference value for the future development of refined forecast models with local features.

An Empirical Examination of the Arbitrage Pricing Theory:Evidences from the U.S.Stock Market

This study investigates the effects of changes in local macroeconomic risk factors on returns on the banking,chemicals,insurance,telecommunication,and utilities industries in the U.S.market.Using a multifactor pricing model and data from 1998:01 to 2017:12,empirical results show that the banking,chemical,and telecommunication industries show more differences in their stock reactions to local macroeconomic risk factors.The insurance and telecommunication industries do not react significantly to risk factors.However,all the industries show strong reactions to local market portfolio.

A STUDY ON THE RELIABILITY OF SHORT-TERM AFB_(1)-INDUCED HEPATOCARCINOGENESIS TEST MODEL

In order to test the reliability of γ-GT foci(γ-glutamyltranspeptidase positive hepatocyticfoci) as a preneoplastic marker in AFB-inducedhepatocarcinogenesis, this experiment was car-ried out for a long period after a short-term invivo test model of AFB-induced hepatocarcino-

Short-Term and Long-Term Price Forecasting Models for the Future Exchange of Mongolian Natural Sea Buckthorn Market

Sea buckthorn market floated uncertainly within a narrow range. The market situation provided upward pressure on prices, and producer and consumer interest were poor, coupled with weak prices in the regional markets. The objectives of the study are: 1) to estimate the relationship between wild Sea buckthorn (SB) price and Supply, Demand, while some other factors of crude oil price and exchange rate by using simultaneous Supply-Demand and Price system equation and Vector Error Correction Method (VECM);2) to forecast the short-term and long-term SB price;3) to compare and evaluate the price forecasting models. Firstly, the data was analyzed by Ferris and Engle-Granger’s procedure;secondly, both price forecasting methodologies were tested by Pindyck-Rubinfeld and Makridakis’s procedure. The result shows that the VECM model is more efficient using yearly data;a short-term price forecast decreases, and a long-term price forecast is predicted to increase the Mongolian Sea buckthorn market.

Joint On-Demand Pruning and Online Distillation in Automatic Speech Recognition Language Model Optimization

Automatic speech recognition(ASR)systems have emerged as indispensable tools across a wide spectrum of applications,ranging from transcription services to voice-activated assistants.To enhance the performance of these systems,it is important to deploy efficient models capable of adapting to diverse deployment conditions.In recent years,on-demand pruning methods have obtained significant attention within the ASR domain due to their adaptability in various deployment scenarios.However,these methods often confront substantial trade-offs,particularly in terms of unstable accuracy when reducing the model size.To address challenges,this study introduces two crucial empirical findings.Firstly,it proposes the incorporation of an online distillation mechanism during on-demand pruning training,which holds the promise of maintaining more consistent accuracy levels.Secondly,it proposes the utilization of the Mogrifier long short-term memory(LSTM)language model(LM),an advanced iteration of the conventional LSTM LM,as an effective alternative for pruning targets within the ASR framework.Through rigorous experimentation on the ASR system,employing the Mogrifier LSTM LM and training it using the suggested joint on-demand pruning and online distillation method,this study provides compelling evidence.The results exhibit that the proposed methods significantly outperform a benchmark model trained solely with on-demand pruning methods.Impressively,the proposed strategic configuration successfully reduces the parameter count by approximately 39%,all the while minimizing trade-offs.

Research on Welding Quality Traceability Model of Offshore Platform Block Construction Process

Quality traceability plays an essential role in assembling and welding offshore platform blocks.The improvement of the welding quality traceability system is conducive to improving the durability of the offshore platform and the process level of the offshore industry.Currently,qualitymanagement remains in the era of primary information,and there is a lack of effective tracking and recording of welding quality data.When welding defects are encountered,it is difficult to rapidly and accurately determine the root cause of the problem from various complexities and scattered quality data.In this paper,a composite welding quality traceability model for offshore platform block construction process is proposed,it contains the quality early-warning method based on long short-term memory and quality data backtracking query optimization algorithm.By fulfilling the training of the early-warning model and the implementation of the query optimization algorithm,the quality traceability model has the ability to assist enterprises in realizing the rapid identification and positioning of quality problems.Furthermore,the model and the quality traceability algorithm are checked by cases in actual working conditions.Verification analyses suggest that the proposed early-warningmodel for welding quality and the algorithmfor optimizing backtracking requests are effective and can be applied to the actual construction process.

Short-Term Mindfulness Intervention on Adolescents’ Negative Emotion under Global Pandemic

Objective:In this research,we tried to explore how short-term mindfulness(STM)intervention affects adoles-cents’anxiety,depression,and negative and positive emotion during the COVID-19 pandemic.Design:10 classes were divided into experiment groups(5 classes;n=238)and control(5 classes;n=244)randomly.Hospital Anxi-ety and Depression Scale(HADS)and Positive and Negative Affect Schedule(PANAS)were used to measure par-ticipants’dependent variables.In the experiment group,we conducted STM practice interventions every morning in theirfirst class from March to November 2020.No interventions were conducted in the control group.Methods:Paired-sample t-tests were used to identify if a significant difference exists between every time point of the experimental and control groups.Repeated ANOVA and Growth Mixture Model(GMM)were used to analyze the tendency of positive and negative emotions,anxiety,and depression in the experimental group.Results and Conclusions:(1)With the intervention of STM,there was a significant decrease in negative emotions and an increase in positive emotions in the experimental group,whereas there were non-significant differences in the control group.(2)To explore the heterogeneity trajectories of dependent variables,we built a GMM and found there were two latent growth classes in the trajectories.(3)The results of the models showed their trajec-tories were downward,which meant that the levels of anxiety,depression,and negative emotions of participants decreased during the STM training period.Nonetheless,the score of positive affect showed upward in three loops of intervention,which indicated that the level of the participants’positive affect increased through the STM inter-vention.(4)This research indicated that STM should be given increasing consideration to enhance mental health during the worldwide outbreak of COVID-19.

基于CEEMD-LSTM-Adaboost模型的白糖期货跨期套利策略

以白糖期货合约SR2201和SR2109的5 min高频数据为研究对象,在验证二者存在长期均衡关系的条件下,构建GARCH模型来刻画残差的ARCH效应,将互补集合经验模态分解(CEEMD)方法与长短期记忆网络(LSTM)、自适应提升算法(Adaboost)相结合,通过预测价差涨跌进行套利操作,设置不同开平仓阈值,在样本区间内进行4种神经网络套利策略对比研究。结果表明:基于CEEMD-LSTM-Adaboost模型的神经网络套利策略应用于白糖期货市场可行有效,并且其在模型预测精度和套利效果方面均比BP、LSTM和LSTM-Adaboost神经网络更具优势。

Convolution Neural Network-based Load Model Parameter Selection Considering Short-term Voltage Stability

The recently proposed ambient signal-based load modeling approach offers an important and effective idea to study the time-varying and distributed characteristics of power loads.Meanwhile,it also brings new problems.Since the load model parameters of power loads can be obtained in real-time for each load bus,the numerous identified parameters make parameter application difficult.In order to obtain the parameters suitable for off-line applications,load model parameter selection(LMPS)is first introduced in this paper.Meanwhile,the convolution neural network(CNN)is adopted to achieve the selection purpose from the perspective of short-term voltage stability.To begin with,the field phasor measurement unit(PMU)data from China Southern Power Grid are obtained for load model parameter identification,and the identification results of different substations during different times indicate the necessity of LMPS.Meanwhile,the simulation case of Guangdong Power Grid shows the process of LMPS,and the results from the CNNbased LMPS confirm its effectiveness.

Short-term prognostic factors for hepatitis B virus-related acute-onchronic liver failure

BACKGROUND Acute-on-chronic liver failure(ACLF)is the abrupt exacerbation of declined hepatic function in patients with chronic liver disease.AIM To explore the independent predictors of short-term prognosis in patients with hepatitis B virus(HBV)-related ACLF and to establish a predictive short-term prognosis model for HBV-related ACLF.METHODS From January 2016 to December 2019,207 patients with HBV-related ACLF attending the 910^(th) Hospital of Chinese People's Liberation Army were continuously included in this retrospective study.Patients were stratified based on their survival status 3 mo after diagnosis.Information was collected regarding gender and age;coagulation function in terms of prothrombin time and international normalized ratio(INR);hematological profile in terms of neutrophil-tolymphocyte ratio(NLR)and platelet count(PLT);blood biochemistry in terms of alanine aminotransferase,aspartate aminotransferase,total bilirubin(Tbil),albumin,cholinesterase,blood urea nitrogen(BUN),creatinine,blood glucose,and sodium(Na);tumor markers including alpha-fetoprotein(AFP)and Golgi protein 73(GP73);virological indicators including HBV-DNA,HBsAg,HBeAg,Anti-HBe,and Anti-HBc;and complications including hepatic encephalopathy,hepatorenal syndrome,spontaneous peritonitis,gastrointestinal bleeding,and pulmonary infection.RESULTS There were 157 and 50 patients in the survival and death categories,respectively.Univariate analysis revealed significant differences in age,PLT,Tbil,BUN,NLR,HBsAg,AFP,GP73,INR,stage of liver failure,classification of liver failure,and incidence of complications(pulmonary infection,hepatic encephalopathy,spontaneous bacterial peritonitis,and upper gastrointestinal bleeding)between the two groups(P<0.05).GP73[hazard ratio(HR):1.009,95%confidence interval(CI):1.005-1.013,P=0.000],middle stage of liver failure(HR:5.056,95%CI:1.792-14.269,P=0.002),late stage of liver failure(HR:22.335,95%CI:8.544-58.388,P=0.000),pulmonary infection(HR:2.056,95%CI:1.145-3.690,P=0.016),hepatorenal syndrome(HR:6.847,95%CI:1.930-24.291,P=0.003),and HBsAg(HR:0.690,95%CI:0.524-0.908,P=0.008)were independent risk factors for short-term prognosis in patients with HBV-related ACLF.Following binary logistics regression analysis,we arrived at the following formula for predicting short-term prognosis:Logit(P)=Ln(P/1-P)=0.013×(GP73 ng/mL)+1.907×(middle stage of liver failure)+4.146×(late stage of liver failure)+0.734×(pulmonary infection)+22.320×(hepatorenal syndrome)-0.529×(HBsAg)-5.224.The predictive efficacy of the GP73-ACLF score was significantly better than that of the Model for End-Stage Liver Disease(MELD)and MELD-Na score models(P<0.05).CONCLUSION The stage of liver failure,presence of GP73,pulmonary infection,hepatorenal syndrome,and HBsAg are independent predictors of short-term prognosis in patients with HBV-related ACLF,and the GP73-ACLF model has good predictive value among these patients.