Survey on Research of RNN-Based Spatio-Temporal Sequence Prediction Algorithms

In the past few years,deep learning has developed rapidly,and many researchers try to combine their subjects with deep learning.The algorithm based on Recurrent Neural Network(RNN)has been successfully applied in the fields of weather forecasting,stock forecasting,action recognition,etc.because of its excellent performance in processing Spatio-temporal sequence data.Among them,algorithms based on LSTM and GRU have developed most rapidly because of their good design.This paper reviews the RNN-based Spatio-temporal sequence prediction algorithm,introduces the development history of RNN and the common application directions of the Spatio-temporal sequence prediction,and includes precipitation nowcasting algorithms and traffic flow forecasting algorithms.At the same time,it also compares the advantages and disadvantages,and innovations of each algorithm.The purpose of this article is to give readers a clear understanding of solutions to such problems.Finally,it prospects the future development of RNN in the Spatio-temporal sequence prediction algorithm.

A cloud model target damage effectiveness assessment algorithm based on spatio-temporal sequence finite multilayer fragments dispersion

To solve the problem of target damage assessment when fragments attack target under uncertain projectile and target intersection in an air defense intercept,this paper proposes a method for calculating target damage probability leveraging spatio-temporal finite multilayer fragments distribution and the target damage assessment algorithm based on cloud model theory.Drawing on the spatial dispersion characteristics of fragments of projectile proximity explosion,we divide into a finite number of fragments distribution planes based on the time series in space,set up a fragment layer dispersion model grounded in the time series and intersection criterion for determining the effective penetration of each layer of fragments into the target.Building on the precondition that the multilayer fragments of the time series effectively assail the target,we also establish the damage criterion of the perforation and penetration damage and deduce the damage probability calculation model.Taking the damage probability of the fragment layer in the spatio-temporal sequence to the target as the input state variable,we introduce cloud model theory to research the target damage assessment method.Combining the equivalent simulation experiment,the scientific and rational nature of the proposed method were validated through quantitative calculations and comparative analysis.

Multi-Scale Location Attention Model for Spatio-Temporal Prediction of Disease Incidence

Due to the increasingly severe challenges brought by various epidemic diseases,people urgently need intelligent outbreak trend prediction.Predicting disease onset is very important to assist decision-making.Most of the exist-ing work fails to make full use of the temporal and spatial characteristics of epidemics,and also relies on multi-variate data for prediction.In this paper,we propose a Multi-Scale Location Attention Graph Neural Networks(MSLAGNN)based on a large number of Centers for Disease Control and Prevention(CDC)patient electronic medical records research sequence source data sets.In order to understand the geography and timeliness of infec-tious diseases,specific neural networks are used to extract the geography and timeliness of infectious diseases.In the model framework,the features of different periods are extracted by a multi-scale convolution module.At the same time,the propagation effects between regions are simulated by graph convolution and attention mechan-isms.We compare the proposed method with the most advanced statistical methods and deep learning models.Meanwhile,we conduct comparative experiments on data sets with different time lengths to observe the predic-tion performance of the model in the face of different degrees of data collection.We conduct extensive experi-ments on real-world epidemic-related data sets.The method has strong prediction performance and can be readily used for epidemic prediction.

Prediction of the Helix/Sheet Content of Proteins from Their Primary Sequences by Neural Network Method

The amino acid composition and the biased auto-correlation function are considered as features, BP neural network algorithm is used to synthesize these features. The prediction accuracy of this method is verified by using the independent non-homologous protein database. It is shown that the average absolute errors for resubstitution test are 0.070 and 0.068 with the standard deviations 0.049 and 0.047 for the prediction of the content of α-helix and β-sheet respectively. For cross-validation test, the average absolute errors are 0.075 and 0.070 with the standard deviations 0.050 and 0.049 for the prediction of the content of α-helix and β-sheet respectively. Compared with the other methods currently available, the BP neural network method combined with the amino acid composition and the biased auto-correlation function features can effectively improve the prediction accuracy.

Hysteretic energy prediction method for mainshock-aftershock sequences

Structures located in seismically active regions may be subjected to mainshock-aftershock（MSAS）sequences.present study selected two kinds of MSAS sequences,with one aftershock and two aftershocks,respectively.The aftershocksThe MSAS sequence with one aftershock exhibited a 10%to 30%hysteretic energy increase,whereas the MSAS sequence with two aftershocks presented a 20%to 40%hysteretic energy increase.Finally,a hysteretic energy prediction equation is proposed as a function of the vibration period,ductility value,and damping ratio to estimate hysteretic energy for mainshockaftershock sequences.

Improving the accuracy of genomic prediction for meat quality traits using whole genome sequence data in pigs

Background Pork quality can directly affect customer purchase tendency and meat quality traits have become valu-able in modern pork production.However,genetic improvement has been slow due to high phenotyping costs.In this study,whole genome sequence(WGS)data was used to evaluate the prediction accuracy of genomic best linear unbiased prediction(GBLUP)for meat quality in large-scale crossbred commercial pigs.Results We produced WGS data(18,695,907 SNPs and 2,106,902 INDELs exceed quality control)from 1,469 sequenced Duroc×(Landrace×Yorkshire)pigs and developed a reference panel for meat quality including meat color score,marbling score,L*(lightness),a*(redness),and b*(yellowness)of genomic prediction.The prediction accuracy was defined as the Pearson correlation coefficient between adjusted phenotypes and genomic estimated breeding values in the validation population.Using different marker density panels derived from WGS data,accuracy differed substantially among meat quality traits,varied from 0.08 to 0.47.Results showed that MultiBLUP outperform GBLUP and yielded accuracy increases ranging from 17.39%to 75%.We optimized the marker density and found medium-and high-density marker panels are beneficial for the estimation of heritability for meat quality.Moreover,we conducted genotype imputation from 50K chip to WGS level in the same population and found average concord-ance rate to exceed 95%and r^(2)=0.81.Conclusions Overall,estimation of heritability for meat quality traits can benefit from the use of WGS data.This study showed the superiority of using WGS data to genetically improve pork quality in genomic prediction.

Accurate Plant MicroRNA Prediction Can Be Achieved Using Sequence Motif Features

MicroRNAs (miRNAs) are short (~21 nt) nucleotide sequences that are either co-transcribed during the production of mRNA or are organized in intergenic regions transcribed by RNA polymerase II. In animals, Drosha, and in plants DCL1 recognize pre-miRNAs which set themselves apart by their characteristic stem loop (hairpin) structure. This structure appears important for their recognition during the process of maturation leading to functioning mature miRNAs. A large body of research is available for computational pre-miRNA detection in animals, but less within the plant kingdom. For the prediction of pre-miRNAs, usually machine learning approaches are employed. Therefore, it is necessary to convert the pre-miRNAs into a set of features that can be calculated and many such features have been described. We here select a subset of the previously described features and add sequence motifs as new features. The resulting model which we called MotifmiRNAPred was tested on known pre-miRNAs listed in miRBase and its accuracy was compared to existing approaches in the field. With an accuracy of 99.95% for the generalized plant model, it distinguishes itself from previously published results which reach an average accuracy between 74% and 98%. We believe that our approach is useful for prediction of pre-miRNAs in plants without per species adjustment.

Geneticprogrammingforpredictionofearth┐quakesequencetype

The genetic programming for the prediction of earthquake sequence type was studied, and the reliability for a group of samples was tested. The results show that the performance of the genetic programming is good, and therefore it might be referred as an effective technique for the prediction of earthquake sequence type.

Method discussion for quick response grey prediction of stronger aftershocks of an earthquake sequence

In this paper, we take occurrence process of early strong aftershocks of a main after shock type′s earthquake sequence as a complex grey system, and introduce predicting method for its stronger aftershocks by grey predicting theory. Through inspection prediction for 1998 Zhangbei M S=6.2 earthquake sequence, it shows that the grey predicting method maybe has active significance for the investigation of quick response prediction problems of stronger aftershocks of an earthquake sequence.

Researchonpredictionofthefolowingnotice┐ableshocksofearthquakesequences

This paper shows the characteristics of noticeable shocks of 37 earthquake sequences with M ≥6 and the research on the tracing prediction method of them. The result shows that the variation of the strain release of the tracing earthquake sequence with time is an important means for predicting the following noticeable shocks. Predicting ultra late strong aftershocks needs to investigate the regional seismicities.

Grain Yield Prediction of Henan Province Based on Spatio-temporal Regression Model

By using correlation analysis method,regression analysis method and time sequence method,we combine time and space,to establish grain yield spatio-temporal regression prediction model of Henan Province and all prefecture-level cities.At first,we use the grain yield in prefecture-level cities of Henan in the year 2000 and 2005,to establish regression model,and then taking the grain yield in one year as independent variable,we predict the grain yield in the fifth year afterwards.Taking the dependent variable value as independent variable again,we predict the grain yield at an interval of the same years,and based on this,predict year by year forward until the year we need.The research shows that the grain yield of Henan Province in the year 2015 and 2020 is 59.849 6 and 67.929 3 million t respectively,consistent with the research results of other scholars to some extent.

Spatio-temporal epidemic type aftershock sequence model for Tangshan aftershock sequence

Shallow earthquakes usually show obvious spatio-temporal clustering patterns. In this study, several spatio-temporal point process models are applied to investigate the clustering characteristics of the well-known Tangshan sequence based on classical empirical laws and a few assumptions. The relative fit of competing models is compared by Akalke Information Criterion. The spatial clustering pattern is well characterized by the model which gives the best fit to the data. A simulated aftershock sequence is generated by thinning algorithm and compared with the real seismicity.

Smart Development Process Enactment Based on Context Sensitive Sequence Prediction

Actual software development processes define the different steps developers have to perform during a development project. Usually these development steps are not described independently from each other—a more or less formal flow of development step is an essential part of the development process definition. In practice, we observe that often the process definitions are hardly used and very seldom “lived”. One reason is that the predefined general process flow does not reflect the specific constraints of the individual project. For that reasons we claim to get rid of the process flow definition as part of the development process. Instead we describe in this paper an approach to smartly assist developers in software process execution. The approach observes the developer’s actions and predicts his next development step based on the project process history. Therefore we apply machine learning resp. sequence learning approaches based on a general rule based process model and its semantics. Finally we show two evaluations of the presented approach: The data of the first is derived from a synthetic scenario. The second evaluation is based on real project data of an industrial enterprise.

Click-Through Rate Prediction Network Based on User Behavior Sequences and Feature Interactions

In recent years,deep learning has been widely applied in the fields of recommendation systems and click-through rate(CTR)prediction,and thus recommendation models incorporating deep learning have emerged.In addition,the design and implementation of recommendation models using information related to user behavior sequences is an important direction of current research in recommendation systems,and models calculate the likelihood of users clicking on target items based on their behavior sequence information.In order to explore the relationship between features,this paper improves and optimizes on the basis of deep interest network(DIN)proposed by Ali’s team.Based on the user behavioral sequences information,the attentional factorization machine(AFM)is integrated to obtain richer and more accurate behavioral sequence information.In addition,this paper designs a new way of calculating attention weights,which uses the relationship between the cosine similarity of any two vectors and the absolute value of their modal length difference to measure their relevance degree.Thus,a novel deep learning CTR prediction mode is proposed,that is,the CTR prediction network based on user behavior sequence and feature interactions deep interest and machines network(DIMN).We conduct extensive comparison experiments on three public datasets and one private music dataset,which are more recognized in the industry,and the results show that the DIMN obtains a better performance compared with the classical CTR prediction model.

Spectrum sensing sequence prediction in cognitive radio networks

Spectrum sensing is one of the key issues in cognitive radio networks. Most of previous work concenates on sensing the spectrum in a single spectrum band. In this paper, we propose a spectrum sensing sequence prediction scheme for cognitive radio networks with multiple spectrum bands to decrease the spectrum sensing time and increase the throughput of secondary users. The scheme is based on recent advances in computational learning theory, which has shown that prediction is synonymous with data compression. A Ziv-Lempel data compression algorithm is used to design our spectrum sensing sequence prediction scheme. The spectrum band usage history is used for the prediction in our proposed scheme. Simulation results show that the proposed scheme can reduce the average sensing time and improve the system throughput significantly.

Prediction of the Earlier Strong Aftershocks in the Earthquake Sequences by the Pseudo-Periodicity Method

We propose the pseudo-periodicity method and its quantitative prediction indexes for the occurrence time of earlier strong aftershock. We conducted tests of regressive prediction, and the R-value of the tests is 0.45, indicating that this method is effective for prediction.

Reservoir Prediction Restricted by Sequence Stratigraphy--A Case Study of Bioclastic Shoal Reservoir in Changxing Formation of Jiannan Area

Bioclastic shoal reservoir in Changxing Formation of Jiannan area is characterized by small thickness and strong heterogeneity. The uncertainty of the reservoir distribution pattern has confined the effective development of this area, so the accurate bioclastic shoal reservoir prediction would be the key to achieve development breakthroughs. Based on drilling, well-log, seismic and core analysis data, this article conducted exquisite sequence stratigraphic classification and established isochronal regional stratigraphic framework of Changxing Formation in Jiannan area. The reservoir seismic corresponding features were determined by exquisite calibrating bioclastic shoal reservoir in Changxing Formation. Therefore, seismic processing methods, such as multiple attribute analysis and amplitude inversion, were applied to attain more reliable reservoir prediction results, which indicated the distribution of vertical reservoir in SSQ2, the IV sequence order and the distribution of horizontal reservoir around Well J43 and JZ1 in the platform margin of the study area.

Assessments of Data-Driven Deep Learning Models on One-Month Predictions of Pan-Arctic Sea Ice Thickness

In recent years,deep learning methods have gradually been applied to prediction tasks related to Arctic sea ice concentration,but relatively little research has been conducted for larger spatial and temporal scales,mainly due to the limited time coverage of observations and reanalysis data.Meanwhile,deep learning predictions of sea ice thickness(SIT)have yet to receive ample attention.In this study,two data-driven deep learning(DL)models are built based on the ConvLSTM and fully convolutional U-net(FC-Unet)algorithms and trained using CMIP6 historical simulations for transfer learning and fine-tuned using reanalysis/observations.These models enable monthly predictions of Arctic SIT without considering the complex physical processes involved.Through comprehensive assessments of prediction skills by season and region,the results suggest that using a broader set of CMIP6 data for transfer learning,as well as incorporating multiple climate variables as predictors,contribute to better prediction results,although both DL models can effectively predict the spatiotemporal features of SIT anomalies.Regarding the predicted SIT anomalies of the FC-Unet model,the spatial correlations with reanalysis reach an average level of 89%over all months,while the temporal anomaly correlation coefficients are close to unity in most cases.The models also demonstrate robust performances in predicting SIT and SIE during extreme events.The effectiveness and reliability of the proposed deep transfer learning models in predicting Arctic SIT can facilitate more accurate pan-Arctic predictions,aiding climate change research and real-time business applications.

Comparisons of improved genomic predictions generated by different imputation methods for genotyping by sequencing data in livestock populations

Background:Genotyping by sequencing(GBS)still has problems with missing genotypes.Imputation is important for using GBS for genomic predictions,especially for low depths,due to the large number of missing genotypes.Minor allele frequency(MAF)is widely used as a marker data editing criteria for genomic predictions.In this study,three imputation methods(Beagle,IMPUTE2 and FImpute software)based on four MAF editing criteria were investigated with regard to imputation accuracy of missing genotypes and accuracy of genomic predictions,based on simulated data of livestock population.Results:Four MAFs(no MAF limit,MAF≥0.001,MAF≥0.01 and MAF≥0.03)were used for editing marker data before imputation.Beagle,IMPUTE2 and FImpute software were applied to impute the original GBS.Additionally,IMPUTE2 also imputed the expected genotype dosage after genotype correction(GcIM).The reliability of genomic predictions was calculated using GBS and imputed GBS data.The results showed that imputation accuracies were the same for the three imputation methods,except for the data of sequencing read depth(depth)=2,where FImpute had a slightly lower imputation accuracy than Beagle and IMPUTE2.GcIM was observed to be the best for all of the imputations at depth=4,5 and 10,but the worst for depth=2.For genomic prediction,retaining more SNPs with no MAF limit resulted in higher reliability.As the depth increased to 10,the prediction reliabilities approached those using true genotypes in the GBS loci.Beagle and IMPUTE2 had the largest increases in prediction reliability of 5 percentage points,and FImpute gained 3 percentage points at depth=2.The best prediction was observed at depth=4,5 and 10 using GcIM,but the worst prediction was also observed using GcIM at depth=2.Conclusions:The current study showed that imputation accuracies were relatively low for GBS with low depths and high for GBS with high depths.Imputation resulted in larger gains in the reliability of genomic predictions for GBS with lower depths.These results suggest that the application of IMPUTE2,based on a corrected GBS(GcIM)to improve genomic predictions for higher depths,and FImpute software could be a good alternative for routine imputation.

Improving genomic predictions by correction of genotypes from genotyping by sequencing in livestock populations

Background: Genotyping by sequencing(GBS) is a robust method to genotype markers. Many factors can influence the genotyping quality. One is that heterozygous genotypes could be wrongly genotyped as homozygotes,dependent on the genotyping depths. In this study, a method correcting this type of genotyping error was demonstrated. The efficiency of this correction method and its effect on genomic prediction were assessed using simulated data of livestock populations.Results: Chip array(Chip) and four depths of GBS data was simulated. After quality control(call rate ≥ 0.8 and MAF ≥ 0.01), the remaining number of Chip and GBS SNPs were both approximately 7,000, averaged over 10 replicates. GBS genotypes were corrected with the proposed method. The reliability of genomic prediction was calculated using GBS, corrected GBS(GBSc), true genotypes for the GBS loci(GBSr) and Chip data. The results showed that GBSc had higher rates of correct genotype calls and higher correlations with true genotypes than GBS. For genomic prediction, using Chip data resulted in the highest reliability. As the depth increased to 10, the prediction reliabilities using GBS and GBSc data approached those using true GBS data. The reliabilities of genomic prediction using GBSc data were 0.604, 0.672, 0.684 and 0.704 after genomic correction, with the improved values of 0.013, 0.009, 0.006 and 0.001 at depth = 2, 4, 5 and 10, respectively.Conclusions: The current study showed that a correction method for GBS data increased the genotype accuracies and, consequently, improved genomic predictions. These results suggest that a correction of GBS genotype is necessary, especially for the GBS data with low depths.