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.

Optimization and Deployment of Memory-Intensive Operations in Deep Learning Model on Edge

As a large amount of data is increasingly generated from edge devices,such as smart homes,mobile phones,and wearable devices,it becomes crucial for many applications to deploy machine learning modes across edge devices.The execution speed of the deployed model is a key element to ensure service quality.Considering a highly heterogeneous edge deployment scenario,deep learning compiling is a novel approach that aims to solve this problem.It defines models using certain DSLs and generates efficient code implementations on different hardware devices.However,there are still two aspects that are not yet thoroughly investigated yet.The first is the optimization of memory-intensive operations,and the second problem is the heterogeneity of the deployment target.To that end,in this work,we propose a system solution that optimizes memory-intensive operation,optimizes the subgraph distribution,and enables the compiling and deployment of DNN models on multiple targets.The evaluation results show the performance of our proposed system.

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.

On the long-term memory characteristic in land surface air temperatures:How well do CMIP6 models perform?

利用去趋势涨落分析(DFA)方法计算序列的长程记忆性(LTM),以CRUTEM5数据集的结果作为观测参照,评估了60个参与第六次国际耦合模式比较计划(CMIP6)的气候模式对地表气温LTM的再现能力.结果表明:大部分模式可以再现全球平均地表气温序列的LTM特征,其中AWI-ESM-1-1-LR和E3SM-1-0的模拟效果最好;60个模式均能模拟LTM随纬度带的变化;综合来说,全球水平上CNRM-CM6-1和HadGEM3-GC31-LL对地表气温LTM的模拟性能最好;多模式平均相比单一模式模拟性能更好;多模式平均与观测结果的偏差以及模式之间的模拟差异显著体现在赤道和沿海区域,这种偏差可能源于模式对海气耦合过程的模拟差异.

基于DACO-Bi-LSTM的交通流量预测

针对交通流量预测任务存在预测精度低、泛化性不足且对深度学习模型调参不全面等问题,提出了一种基于改进蚁群优化算法的双向LSTM交通流量预测模型,利用改进蚁群算法的全局寻优能力对Bi-LSTM网络的层数、神经元个数、批次大小、训练次数进行优化调参。在英国高速公路和深圳政府开放平台发布的宝安区日车流量两个公开数据集上进行实验,以RMSE、MAE为评估指标,结果表明:DACO-Bi-LSTM模型具有较强的寻优能力,同时表现出更好的预测性能。

基于改进Bi-LSTM-CRF的农业问答系统研究

针对农业领域问答系统面临的实体识别困难的问题,提出一种基于改进Bi-LSTM-CRF的实体识别方法。首先通过BERT预训练模型的预处理,生成基于上下文信息的词向量,然后将训练出的词向量输入Bi-LSTM-CRF做进一步的训练处理,最后,利用Python的Django框架设计农业领域的实体识别、实体查询、农知问答等子系统。经过试验对比,所提出的改进的Bi-LSTM-CRF在农业信息领域具有更好的实体识别能力,在农业信息语料库上的精确率、召回率和F1值分别为93.23%、91.08%和92.16%。实现农业领域实体识别和农业信息问答的知识图谱网站演示,对农业信息化的发展具有重要意义。

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 macroscopic multi-mechanism based constitutive model for the thermo-mechanical cyclic degeneration of shape memory effect of NiTi shape memory alloy

A macroscopic based multi-mechanism constitutive model is constructed in the framework of irreversible thermodynamics to describe the degeneration of shape memory effect occurring in the thermo-mechanical cyclic deformation of NiTi shape memory alloys (SMAs). Three phases, austenite A, twinned martensite and detwinned martensite , as well as the phase transitions occurring between each pair of phases (, , , , and are considered in the proposed model. Meanwhile, two kinds of inelastic deformation mechanisms, martensite transformation-induced plasticity and reorientation-induced plasticity, are used to explain the degeneration of shape memory effects of NiTi SMAs. The evolution equations of internal variables are proposed by attributing the degeneration of shape memory effect to the interaction between the three phases (A, , and and plastic deformation. Finally, the capability of the proposed model is verified by comparing the predictions with the experimental results of NiTi SMAs. It is shown that the degeneration of shape memory effect and its dependence on the loading level can be reasonably described by the proposed model.

Modeling size-dependent thermo-mechanical behaviors of shape memory polymer Bernoulli-Euler microbeam

The objective of this paper is to model the size-dependent thermo-mechanical behaviors of a shape memory polymer (SMP) microbeam.Size-dependent constitutive equations,which can capture the size effect of the SMP,are proposed based on the modified couple stress theory (MCST).The deformation energy expression of the SMP microbeam is obtained by employing the proposed size-dependent constitutive equation and Bernoulli-Euler beam theory.An SMP microbeam model,which includes the formulations of deflection,strain,curvature,stress and couple stress,is developed by using the principle of minimum potential energy and the separation of variables together.The sizedependent thermo-mechanical and shape memory behaviors of the SMP microbeam and the influence of the Poisson ratio are numerically investigated according to the developed SMP microbeam model.Results show that the size effects of the SMP microbeam are significant when the dimensionless height is small enough.However,they are too slight to be necessarily considered when the dimensionless height is large enough.The bending flexibility and stress level of the SMP microbeam rise with the increasing dimensionless height,while the couple stress level declines with the increasing dimensionless height.The larger the dimensionless height is,the more obvious the viscous property and shape memory effect of the SMP microbeam are.The Poisson ratio has obvious influence on the size-dependent behaviors of the SMP microbeam.The paper provides a theoretical basis and a quantitatively analyzing tool for the design and analysis of SMP micro-structures in the field of biological medicine,microelectronic devices and micro-electro-mechanical system (MEMS) self-assembling.

Quantitative Metal Magnetic Memory Reliability Modeling for Welded Joints

Metal magnetic memory（MMM） testing has been widely used to detect welded joints. However, load levels, environmental magnetic field, and measurement noises make the MMM data dispersive and bring difficulty to quantitative evaluation. In order to promote the development of quantitative MMM reliability assessment, a new MMM model is presented for welded joints. Steel Q235 welded specimens are tested along the longitudinal and horizontal lines by TSC-2M-8 instrument in the tensile fatigue experiments. The X-ray testing is carried out synchronously to verify the MMM results. It is found that MMM testing can detect the hidden crack earlier than X-ray testing. Moreover, the MMM gradient vector sum K_（vs） is sensitive to the damage degree, especially at early and hidden damage stages. Considering the dispersion of MMM data, the K_（vs） statistical law is investigated, which shows that K_（vs） obeys Gaussian distribution. So K_（vs） is the suitable MMM parameter to establish reliability model of welded joints. At last, the original quantitative MMM reliability model is first presented based on the improved stress strength interference theory. It is shown that the reliability degree R gradually decreases with the decreasing of the residual life ratio T, and the maximal error between prediction reliability degree R_1 and verification reliability degree R_2 is 9.15%. This presented method provides a novel tool of reliability testing and evaluating in practical engineering for welded joints.

Simple General Atmospheric Circulation and Climate Models with Memory

This article examines some general atmospheric circulation and climate models in the context of the notion of “memory”. Two kinds of memories are defined： statistical memory and deterministic memory. The former is defined through the autocorrelation characteristic of the process if it is random （chaotic）, while for the latter, a special memory function is introduced. Three of the numerous existing models are selected as examples. For each of the models, asymptotic （at t →∞） expressions are derived. In this way, the transients are filtered out and that which remains concerns the final behaviour of the models.

Thermoviscoelastic Modeling Approach for Predicting the Recovery Behaviors of Thermally Activated Amorphous Shape Memory Polymers

A thermoviscoelastic modeling approach is developed to predict the recovery behaviors of the thermally activated amorphous shape memory polymers(SMPs)based on the generalized finite deformation viscoelasticity theory.In this paper,a series of moduli and relaxation times of the generalized Maxwell model is estimated from the stress relaxation master curve by using the nonlinear regression(NLREG)method.Assuming that the amorphous SMPs are approximately incompressible isotropic elastomers in the rubbery state,the hyperelastic response of the materials is well modeled with a hyperelastic model in Ogden form.In addition,the Williams-Landel-Ferry(WLF)equation is used to describe the horizontal shift factor obtained with time-temperature superposition principle(TTSP).The finite element simulations show good agreement with the experimental thermomechanical behaviors.Moreover,the possibility of developing a temperature-responsive intravascular stent with the SMP studied here is investigated in terms of its thermomechanical property.Therefore,it can be concluded that the model has good prediction capabilities for the recovery behaviors of amorphous SMPs.

Three-dimensional constitutive model for magneto-mechanical deformation of NiMnGa ferromagnetic shape memory alloy single crystals

Existing experimental results have shown that four types of physical mechanisms, namely, martensite transformation, martensite reorientation, magnetic domain wall motion and magnetization vector rotation, can be activated during the magneto-mechanical deformation of NiMnGa ferromagnetic shape memory alloy (FSMA) single crystals. In this work, based on irreversible thermodynamics, a three-dimensional (3D) single crystal constitutive model is constructed by considering the aforementioned four mechanisms simultaneously. Three types of internal variables, i.e., the volume fraction of each martensite variant, the volume fraction of magnetic domain in each variant and the deviation angle between the magnetization vector, and easy axis are introduced to characterize the magneto-mechanical state of the single crystals. The thermodynamic driving force of each mechanism and the thermodynamic constraints on the constitutive model are obtained from Clausius's dissipative inequality and constructed Gibbs free energy. Then, thermodynamically consistent kinetic equations for the four mechanisms are proposed, respectively. Finally, the ability of the proposed model to describe the magneto-mechanical deformation of NiMnGa FSMA single crystals is verified by comparing the predictions with corresponding experimental results. It is shown that the proposed model can quantitatively capture the main experimental phenomena. Further, the proposed model is used to predict the deformations of the single crystals under the non-proportional mechanical loading conditions.

Pruned Volterra Models with Memory Effects for Nonlinear Power Amplifiers

In this letter, a novel model is proposed for modeling the nonlinearity and memory effects of power amplifiers. The classical Volterra model is modified through a function of the sum of nonlinearity order with sum of memory length. The parameters of this model can be extracted in digital domain since the model is analyzed based on the envelope signals. The model we proposed enables a substantial reduction in the number of coefficients involved, and with excellent accuracy.

Three-Dimensional Simulations of RESET Operation in Phase-Change Random Access Memory with Blade-Type Like Phase Change Layer by Finite Element Modeling

An optimized device structure for reducing the RESET current of phase-change random access memory （PCRAM） with blade-type like （BTL） phase change layer is proposed. The electrical thermal analysis of the BTL cell and the blade heater contactor structure by three-dimensional finite element modeling are compared with each other during RESET operation. The simulation results show that the programming region of the phase change layer in the BTL cell is much smaller, and thermal electrical distributions of the BTL cell are more concentrated on the TiN/GST interface. The results indicate that the BTL cell has the superiorities of increasing the heating efficiency, decreasing the power consumption and reducing the RESET current from 0.67mA to 0.32mA. Therefore, the BTL cell will be appropriate for high performance PCRAM device with lower power consumption and lower RESET current.

Effects of ginsenoside of stem and leaf combined with choline on learning and memory ability of rat models with Alzheimer diseases

BACKGROUND： Central adrenergic nerve and 5-serotonergic nerve can influence central cholinergic nerve on learning and memory and make easy for study; however, ginsenoside of stem and leaf （GSL） can improve functions of central adrenergic nerve; moreover, 5-serotonergic nerve and the combination with choline can produce synergistic effect and enhance learning and memory ability so as to improve learning and memory disorder of patients with Alzheimer disease （AD）. OBJECTIVE ： To observe the effects of GSL combining with choline on learning and memory of AD model rats DESIGN ： Randomized grouping design and controlled animal study SETIING ： Department of Pharmacology, Taishan Medical College MATERIALS ： The experiment was carried out in the Pharmacological Department of Medical College of Jilin University from October 1996 to January 1997. Forty healthy male Wistar rats of clean grade were randomly divided into 5 groups, including sham-injury group, model group, GSL group, choline group and combination group, with 8 rats in each group. Main medications： GSL with the volume more than 92.8% was provided by Department of Chemistry, Norman Bethune Medical College of Jilin University. Panaxatriol, the main component, was detected with thin layer scanning technique and regarded as the index of GSL quality [（55±1）%, CV= 2%, n = 5]. Choline was provided by the Third Shanghai Laboratory Factory. METHODS ： 150 nmol quinolinic acid was used to damage bilateral Meynert basal nuclei of adult rats so as to establish AD models. Rats in GSL, choline and combination groups were intragastric administrated with 400 mg/kg GSL, 200 mg/kg choline （20 mL/kg）, and both respectively last for 17 days starting from two days before operation. Rats in sham-injury group and model group were perfused with the same volume of distilled water once in each morning for the same days. （1） Passive avoidance step-down test： Five minutes later, rats jumped up safe platform when they were shocked with 36 V alternating current. If rats jumped down from the platform and the feet touched railings, the response was wrong. Numbers of wrong response were recorded within 3 minutes, and then the test was redone after 24 hours. （2） Morris water-maze spatial localization task： Swimming from jumping-off to platform directly was regarded as right response. Additionally, 4 successively right responses were regarded as the standard. Each rat was trained 10 times a day with 120 s per time for 3 successive days. The interval was 30 s. Three days later, numbers of right response were recorded. The training times were increased to 30 for unlearned rats. （3） Measurement of activity of choline acetylase in cerebral cortex： Rats were sacrificed at 17 days after operation to obtain cerebral cortex to measure activity of choline acetylase with radiochemistry technique. （4） Synergistic effect： It was expressed as Q value： Q value = factual incorporative effect/anticipant incorporative effect; Q ≥ 1 was regarded as synergistic effect. Anticipant incorporative effect = （EA＋EB-EA·EB）, EA and EB were single timing effect, respectively in GSL group and choline group. E（step-down test and Morris water maze test） = （x in model group - factual value in medicine groups）/x in model group; E （activity of choline acetylase） = （factual value in medicine groups -xin model group）/xin model group. MAIN OUTCOME MEASURES ： （1） Passive avoidance step-down test and Morris water-maze spatial localization task in the study of learning and memory; （2） activity of choline acetylase. RESULTS ： All 40 rats were involved in the final analysis. （1） Passive avoidance response： At learning phase on first day and retesting phase on the next day, numbers of wrong responses within 3 minutes were more in model group than sham operation group, and there was significant difference [（5.88±1.46）, （2.25±0.87） times; （2.63±1.06）, （0.50±0.53） times; P 〈 0.01]; numbers of wrong responses within 3 minutes were less in combination group than model group, and there was significant difference [learning phase： （1.12±0.83）, （5.88±1.46） times; retesting phase： （0.38±0.74）, （2.63±1.06）times, P 〈 0.01]; moreover, effect was stronger than that in GSL group and choline group. The Q value was 1.07 and 1.59, respectively and it showed synergistic effect. Spatial localization task： Training times were more in model group than sham operation group, and there was significant difference [（2.9±2.5）, （12.6±3.5） times; P 〈 0.01]. Training times were less in combination group than model group, and there was significant difference [（11.8±2.4）, （27.9±2.5） times, P 〈 0.01]; moreover, effect was stronger than that in GSL group and choline group. The Q value was 1.07 and it showed synergistic effect. （3） Activity of choline acetylase： Activity was lower in model group than sham operation group, and there was significant difference [（30.56±8.33）, （61.11 ±8.33） nkat/g; P 〈 0.01]. Activity was higher in combination group than model group and there was significant difference [（50.00±8.33）, （30.56±8.33） nkat/g, P 〈 0.01];moreover, effect was stronger than that in GSL group and choline group. The Q value was 1.5 and it showed synergistic effect. CONCLUSZON： GSL in combination with choline can synergically improve the disorder of learning and memory of AD model rats. Its mechanism may be involved in enhancing the function of central cholinergic system.

Target morphology and cell memory:a model of regenerative pattern formation

Despite the growing body of work on molecular components required for regenerative repair,we still lack a deep understanding of the ability of some animal species to regenerate their appropriate complex anatomical structure following damage.A key question is how regenerating systems know when to stop growth and remodeling-what mechanisms implement recognition of correct morphology that signals a stop condition？In this work,we review two conceptual models of pattern regeneration that implement a kind of pattern memory.In the first one,all cells communicate with each other and keep the value of the total signal received from the other cells.If a part of the pattern is amputated,the signal distribution changes.The difference fromthe original signal distribution stimulates cell proliferation and leads to pattern regeneration,in effect implementing an error minimization process that uses signaling memory to achieve pattern correction.In the second model,we consider a more complex pattern organization with different cell types.Each tissue contains a central（coordinator）cell that controls the tissue and communicates with the other central cells.Each of them keeps memory about the signals received from other central cells.The values of these signals depend on the mutual cell location,and the memory allows regeneration of the structure when it is modified.The purpose of these models is to suggest possible mechanisms of pattern regeneration operating on the basis of cell memory which are compatible with diverse molecular implementation mechanisms within specific organisms.

Metal magnetic memory field characterization at early fatigue damage based on modified Jiles-Atherton model

In order to propel the development of metal magnetic memory(MMM) technique in fatigue damage detection,the Jiles-Atherton model(J-A model) was modified to describe MMM mechanism in elastic stress stage.A series of rotating bending fatigue experiments were conducted to study the stress-magnetization relationship and verify the correctness of modified J-A model.In MMM detection,the magnetization of material irreversibly approaches to the local equilibrium state M0 instead of global equilibrium state Man under cyclic stress,and the M0-σ curves are loops around the Man-σ curve.The modified J-A model is constructed by replacing Man in J-A model with M0,and it can describe the magnetomechanical effect well at low external magnetic field.In the rotating bending fatigue experiments,the MMM field distribution in normal direction around cylinder specimen is similar to the stress distribution,and the calculation result of model coincides with experiment result after some necessary modifications.The MMM field variation with time at a certain point in fatigue process is divided into three stages with the variation of stable stress-stain hysteresis loop,and the calculation results of model can explain not only the three stages of MMM field changes,but also the different change laws when the applied magnetic field and initial magnetic field are different.The MMM field distribution in normal direction along specimen axis reflects stress concentration effect at artificial defect,and the magnetic signal fluctuates around the defect at late fatigue stage.The calculation results coincide with the initial MMM principle and can explain signal fluctuates around the defect.The modified J-A model can explain experiment results well,and it is fit for MMM field characterization.

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.

Constitutive model for shape memory alloy torsion actuator

Shape memory alloy ( SMA) torsion actuator is one of the key approaches realizing adaptive wings in airplanes. In this paper,the actuator is made up of SMA wires and a thin-walled tube,in which the SMA wires are twisted and affixed around the surface of the tube at an angle referenced to the center axis of the tube. A thermo-mechanical constitutive model is developed to predict the thermo-mechanical behaviors of the SMA torsion actuator based on the knowledge of solid mechanics. The relationship between the torsion-angle and tem- perature is numerically calculated by using the thermo-mechanical constitutive model coupled with the SMA phase transformation model developed by Zhou and Yoon. The numerical results are compared with the relative experimental results finished by Xiong and Shen. Influences of the twist-angle of SMA wires and geometrical factors on the primary actuation performances of the SMA torsion actuator are also numerically investigated based on the thermo-mechanical constitutive model coupled with the SMA phase transformation model developed by Zhou and Yoon. Results show that the thermo-mechanical constitutive model can well predict the thermo-mechanical behaviors of the SMA torsion actuator.