从“Long time no see”说起

前几天，我在20多年前教过的一位学生来看我。我们谈话时，他随手拿起我书桌上的一本英语口语教材翻看，他说：“呀，老师，教材里怎么有错句?”我拿起教材一看，是“Long time no see”。我笑了。“老师，我清楚地记得，我们在中学时，您不止一次地在黑板上纠正过类似的错句，怎么20年后它又成对的了?”我说：“你问得好。”接着我对此作了解释。

Origin of “Long time,no see”

"Long time no see" is a very interesting English expression used as a greeting by people who have not seen each other for a while. The essay shows how Chinese people and native English speaker think about "Long time no see". Meanwhile, it does research upon the historical appearances of the phrase.

A Time Series Intrusion Detection Method Based on SSAE,TCN and Bi-LSTM

In the fast-evolving landscape of digital networks,the incidence of network intrusions has escalated alarmingly.Simultaneously,the crucial role of time series data in intrusion detection remains largely underappreciated,with most systems failing to capture the time-bound nuances of network traffic.This leads to compromised detection accuracy and overlooked temporal patterns.Addressing this gap,we introduce a novel SSAE-TCN-BiLSTM(STL)model that integrates time series analysis,significantly enhancing detection capabilities.Our approach reduces feature dimensionalitywith a Stacked Sparse Autoencoder(SSAE)and extracts temporally relevant features through a Temporal Convolutional Network(TCN)and Bidirectional Long Short-term Memory Network(Bi-LSTM).By meticulously adjusting time steps,we underscore the significance of temporal data in bolstering detection accuracy.On the UNSW-NB15 dataset,ourmodel achieved an F1-score of 99.49%,Accuracy of 99.43%,Precision of 99.38%,Recall of 99.60%,and an inference time of 4.24 s.For the CICDS2017 dataset,we recorded an F1-score of 99.53%,Accuracy of 99.62%,Precision of 99.27%,Recall of 99.79%,and an inference time of 5.72 s.These findings not only confirm the STL model’s superior performance but also its operational efficiency,underpinning its significance in real-world cybersecurity scenarios where rapid response is paramount.Our contribution represents a significant advance in cybersecurity,proposing a model that excels in accuracy and adaptability to the dynamic nature of network traffic,setting a new benchmark for intrusion detection systems.

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.

Binaural Speech Separation Algorithm Based on Long and Short Time Memory Networks

Speaker separation in complex acoustic environment is one of challenging tasks in speech separation.In practice,speakers are very often unmoving or moving slowly in normal communication.In this case,the spatial features among the consecutive speech frames become highly correlated such that it is helpful for speaker separation by providing additional spatial information.To fully exploit this information,we design a separation system on Recurrent Neural Network(RNN)with long short-term memory(LSTM)which effectively learns the temporal dynamics of spatial features.In detail,a LSTM-based speaker separation algorithm is proposed to extract the spatial features in each time-frequency(TF)unit and form the corresponding feature vector.Then,we treat speaker separation as a supervised learning problem,where a modified ideal ratio mask(IRM)is defined as the training function during LSTM learning.Simulations show that the proposed system achieves attractive separation performance in noisy and reverberant environments.Specifically,during the untrained acoustic test with limited priors,e.g.,unmatched signal to noise ratio(SNR)and reverberation,the proposed LSTM based algorithm can still outperforms the existing DNN based method in the measures of PESQ and STOI.It indicates our method is more robust in untrained conditions.

Long-time Convergence of Numerical Approximations for Semilinear Parabolic Equations (Ⅱ)

In this article we extend ours framework of long time convergence for numeracal approximations of semilinear parabolic equations prorided in “Wu Haijun and Li Ronghua, Northeast. Math. J., 16(1)(2000), 1—28”, to the Gauss Ledendre full discretization. When apply the result to the Crank Nicholson finiteelement full discretization of the Navier Stokes equations, we can remore the grid ratio restriction of “Heywood, J. G. and Rannacher, R., SIAM J. Numer. Anal., 27(1990), 353—384”, and weaken the stability condition on the continuous solution.

基于MIC-CFS-LSTM的SCR出口NO_(x)浓度动态预测

针对燃煤机组选择性催化还原(SCR)系统出口氮氧化物(NO_(x))预测模型精度不高的问题,提出一种基于最大信息系数(MIC)和长短期记忆(LSTM)神经网络的预测模型方法。首先采用MIC估计各变量的延迟时间,对数据进行时延重构;然后采用重构后数据的MIC值作为评价各输入变量和输出变量间相关性大小的指标,并结合基于关联性的特征选择算法(CFS)进行输入变量筛选;最后基于时延重构和变量筛选后的数据,采用LSTM神经网络建立了SCR出口氮氧化物浓度动态预测模型。该模型被用于广东某320 MW燃煤机组实际运行数据分析。结果表明,经时延重构和变量筛选后所建立的LSTM预测模型具有较高精度,优于深度神经网络(DNN)模型和径向基函数(RBF)神经网络模型,平均绝对百分比误差达2.58%,均方根误差达2.02,可满足现场运用要求。

Asymptotics of estimators for nonparametric multivariate regression models with long memory

In this paper,a nonparametric multivariate regression model with long memory covariates and long memory errors is considered.We approximate the nonparametric multivariate regression function by the weighted additive one-dimensional functions.The local linear smoothing and least squares method are proposed for the one-dimensional regression estimation and the weight parameters estimation,respectively.The asymptotic behaviors of the proposed estimators are investigated.

Time Series Forecasting Fusion Network Model Based on Prophet and Improved LSTM

Time series forecasting and analysis are widely used in many fields and application scenarios.Time series historical data reflects the change pattern and trend,which can serve the application and decision in each application scenario to a certain extent.In this paper,we select the time series prediction problem in the atmospheric environment scenario to start the application research.In terms of data support,we obtain the data of nearly 3500 vehicles in some cities in China fromRunwoda Research Institute,focusing on the major pollutant emission data of non-road mobile machinery and high emission vehicles in Beijing and Bozhou,Anhui Province to build the dataset and conduct the time series prediction analysis experiments on them.This paper proposes a P-gLSTNet model,and uses Autoregressive Integrated Moving Average model(ARIMA),long and short-term memory(LSTM),and Prophet to predict and compare the emissions in the future period.The experiments are validated on four public data sets and one self-collected data set,and the mean absolute error(MAE),root mean square error(RMSE),and mean absolute percentage error(MAPE)are selected as the evaluationmetrics.The experimental results show that the proposed P-gLSTNet fusion model predicts less error,outperforms the backbone method,and is more suitable for the prediction of time-series data in this scenario.

Dynamics and Long Time Convergence of the Extended Fisher-Kolmogorov Equation under Numerical Discretization

We present a numerical study of the long time behavior of approxima- tion solution to the Extended Fisher-Kolmogorov equation with periodic boundary conditions. The unique solvability of numerical solution is shown. It is proved that there exists a global attractor of the discrete dynamical system. Furthermore, we obtain the long-time stability and convergence of the difference scheme and the upper semicontinuity d（Ah,τ, .A） → O. Our results show that the difference scheme can effectively simulate the infinite dimensional dynamical systems.

Non-stationary Buffeting Response Analysis of Long Span Suspension Bridge Under Strong Wind Loading

The non-stationary buffeting response of long span suspension bridge in time domain under strong wind loading is computed. Modeling method for generating non-stationary fluctuating winds with probabilistic model for non-stationary strong wind fields is first presented. Non-stationary wind forces induced by strong winds on bridge deck and tower are then given a brief introduction. Finally,Non-stationary buffeting response of Pulite Bridge in China,a long span suspension bridge,is computed by using ANSYS software under four working conditions with different combination of time-varying mean wind and time-varying variance. The case study further confirms that it is necessity of considering non-stationary buffeting response for long span suspension bridge under strong wind loading,rather than only stationary buffeting response.

Source time functions of the 1999, Jiji (Chi-Chi) earthquake from GDSN long period waveform data using aftershocks as empirical Green's functions

A large earthquake (Mw=7.6) occurred in Jiji (Chi-Chi), Taiwan, China on September 20, 1999, and was followed by many moderate-size shocks in the following days. Two of the largest aftershocks with the magnitudes of Mw=6.1 and Mw=6.2, respectively, were used as empirical Green's functions (EGFs) to obtain the source time functions (STFs) of the main shock from long-period waveform data of the Global Digital Seismograph Network (GDSN) including IRIS, GEOSCOPE and CDSN. For the Mw=6.1 aftershock of September 22, there were 97 pairs of phases clear enough from 78 recordings of 26 stations; for the Mw=6.2 aftershock of September 25, there were 81 pairs of phases clear enough from 72 recordings of 24 stations. For each station, 2 types of STFs were retrieved, which are called P-STF and S-STF due to being from P and S phases, respectively. Totally, 178 STF individuals were obtained for source-process analysis of the main shock. It was noticed that, in general, STFs from most of the stations had similarities except that those in special azimuths looked different or odd due to the mechanism difference between the main shock and the aftershocks; and in detail, the shapes of the STFs varied with azimuth. Both of them reflected the stability and reliability of the retrieved STFs. The comprehensive analysis of those STFs suggested that this event consisted of two sub-events, the total duration time was about 26 s, and on the average, the second event was about 7 s later than the first one, and the moment-rate amplitude of the first event was about 15% larger than that of the second one.

Longtime Convergence of Numerical Approximations for Semilinear Parabolic Equations (Ⅰ)

The numerical approximations of the dynamical systems governed by semilinear parabolic equations are considered. An abstract framework for long time error estimates is established. When applied to reaction diffusion equation, Navier Stokes equations and Chan Hilliard equation, approximated by Galerkin and nonlinear Galerkin methods in space and by Runge Kutta method in time, our framework yields error estimates uniform in time.

Expression signatures of long non-coding RNA and mRNA in human traumatic brain injury

Long non-coding RNAs(lncRNAs) play a key role in craniocerebral disease, although their expression profiles in human traumatic brain injury are still unclear. In this regard, in this study, we examined brain injury tissue from three patients of the 101 st Hospital of the People's Liberation Army, China(specifically, a 36-year-old male, a 52-year-old female, and a 49-year-old female), who were diagnosed with traumatic brain injury and underwent brain contusion removal surgery. Tissue surrounding the brain contusion in the three patients was used as control tissue to observe expression characteristics of lncRNAs and mRNAs in human traumatic brain injury tissue. Volcano plot filtering identified 99 lncRNAs and 63 mRNAs differentially expressed in frontotemporal tissue of the two groups(P < 0.05, fold change > 1.2). Microarray analysis showed that 43 lncRNAs were up-regulated and 56 lncRNAs were down-regulated. Meanwhile, 59 mRNAs were up-regulated and 4 mRNAs were down-regulated. Gene Ontology(GO) and Kyoto Encyclopedia of Genes and Genomes(KEGG) analyses revealed 27 signaling pathways associated with target genes and, in particular, legionellosis and influenza A signaling pathways. Subsequently, a lncRNA-gene network was generated, which showed an absolute correlation coefficient value > 0.99 for 12 lncRNA-mRNA pairs. Finally, quantitative real-time polymerase chain reaction confirmed different expression of the five most up-regulated mRNAs within the two groups, which was consistent with the microarray results. In summary, our results show that expression profiles of mRNAs and lncRNAs are significantly different between human traumatic brain injury tissue and surrounding tissue, providing novel insight regarding lncRNAs' involvement in human traumatic brain injury. All participants provided informed consent. This research was registered in the Chinese Clinical Trial Registry(registration number: ChiCTR-TCC-13004002) and the protocol version number is 1.0.

Seismic analysis of long-span continuous rigid frame bridges in cold regions:a case study of Bridge 1 in north of international tourism resort in Changbai Mountain

It is helpful to improve the seismic design theory of long-span continuous bridges for studying the seismic performance of each cantilever construction state.Taking the Bridge 1 in the north of Changbai-Mountain international tourism resort as an example,the authors studied it in shutdown phase and the cantilever construction process,established the simulation model by using Midas / civil,and analyzed time-history of each construction stage for the bridge.The study shows that long-span bridge cantilever construction in northeastern China can be divided into two-year tasks for construction(suspending in winter).It is needed to think about seismic stability of the cantilever position in shut-down phase of winter.The effect of longitudinal vibration is the most disadvantageous influence to bridge,and its calculation results can provide reference for seismic design of similar bridges in the future.

RHEOLOGICAL BEHAVIOUR FOR AN ANHYDRITE SPECIMEN AND DETERMINATION OF ITS LONG TIME STRENGTH

Based on the method of torsional creep, the creep laws of ananhydrite specimen are studied in this paper. When a shearing stressapplied to the specimen is less than a value, only the primary stagetakes place. How- ever, when the shearing stress is more than anothervalue, all the three stages of a creep curve, i. e. primary, steady-state and accelerated are exhibited.

Long-time limit behavior of the solution to an atom's master equation

We study the long-time limit behavior of the solution to an atom＇s master equation. For the first time we derive that the probability of the atom being in the α-th （α = j ＋ 1 -jz, j is the angular momentum quantum number, jz is the z-component of angular momentum） state is {（1 - K/G）/[1 - （K/G）2j＋1]}（K/G）^α-1 as t → ＋∞, which coincides with the fact that when K/G 〉 1, the larger the a is, the larger the probability of the atom being in the α-th state （the lower excited state） is. We also consider the case for some possible generaizations of the atomic master equation.

LONG-TIME CONVERGENCE OF GENERALIZED DIFFERENCE METHOD FOR NAVIER-STOKES EQUATIONS

In this paper, we first provide a generalized difference method for the 2-dimensional Navier-Stokes equations by combing the ideas of staggered scheme m and generalized upwind scheme in space, and by backward Euler time-stepping. Then we apply the abstract framework of to prove its long-time convergence. Finally, a numerical example for solving driven cavity flows is given.

Analysis of long-term dependence phenomenon in Benue River flow process and its hypothesis testing

在这篇论文，描绘水文学和另外的地球物理的时间系列的长期的依赖现象(林中小丘效果) 被学习。长期的记忆在 Makurdi 为日报和 Benue 河的每月的流速及流水量系列被分析，由使用启发式的方法并且明确地在每月的流动系列测试短期的记忆的空假设的尼日利亚。使用启发式的过程获得的结果显示可以有在吝啬的每日的流动系列的长期的记忆部件的存在，但是没有看得清的原因每月在平均月刊和最大值怀疑存在流动系列(极端事件) 。假设测试被使用重新可伸缩的范围统计数值的原来、修改的版本进行。当修改重新可伸缩的范围，在系列说明短期的记忆，被使用时，空假设为平均月刊和最大的月刊被接受流动系列，在系列显示很少或长期的记忆的没有可能的存在。一个相同结论也在为每月的流动系列的独立的第二个空假设什么时候被测试被到达。因此除了吝啬的每日的流动系列，几乎没有在在 Makurdi 的 Benue 河流速及流水量系列的长期的依赖的小证据。就使用的数据的有限长度而言，然而，结果是不确定的。

Time distribution characteristics of regional macroseismic activity in the Sichuan-Yunnan region and its significance to mid-long term prediction

The earthquakes with Ms≥6.0 are often gathered into belts or clusters and are roughly consistent with tectonic structure trends in the Sichuan-Yunnan (Chuan-Dian) region. The middle south part(98°-106°E, 21°-34°N) of South-North Seismic Zone can be zoned into seven small areas. There all were strong quakes with M_s≥7.0 historically in each small area. Ten earthquakes with M_s≥7.0 have occurred in this region since 1970 and they appeared in five small areas respectively. The relationships between occurrence-time and cumulative frequencies of strong quakes in these five areas are shown to be an exponential distribution or power function. By examining the inner coincidence it is indicated that these relationships are of definite significance to mid-long term macroseismic prediction of each area.