Comparative study on the performance of ConvLSTM and ConvGRU in classification problems-taking early warning of short-duration heavy rainfall as an example

卷积长短期记忆单元ConvLSTM和卷积门控循环单元ConvGRU是两种广泛应用的深度学习单元,通过将循环机制与卷积运算相结合,常常用于时空序列的预测.为了明确上述两种模型的收敛速度和分类能力,需要使用相同的模型架构对相同的分类问题进行预测.本研究将北京短时强降水区级预警问题看作深度学习中的二分类问题,使用京津冀雷达网的组合反射率数据和北京区域内的自动气象站降雨数据进行深度学习模型的训练和评估.结果表明,ConvGRU的收敛速度比ConvLSTM快约25%.ConvLSTM和ConvGRU的预警性能随地区,时间,降雨强度的变化趋势相似,但大部分ConvLSTM的得分较高,少数情况下ConvGRU的得分较高.

Short-and long-term behaviors of drifts in the Callovo-Oxfordian claystone at the Meuse/Haute-Marne Underground Research Laboratory

Since 2000, the French National Radioactive Waste Management Agency （ANDRA） has been constructing an Underground Research Laboratory （URL） at Bure （east of the Paris Basin） to perform experiments in order to obtain in situ data necessary to demonstrate the feasibility of geological repository in the Callovo- Oxfordian claystone. An important experimental program is planned to characterize the response of the rock to different drift construction methods, Before 2008, at the main level of the laboratory, most of the drifts were excavated using pneumatic hammer and supported with rock bolts, sliding steel arches and fiber shotcrete. Other techniques, such as road header techniques, stiff and flexible supports, have also been used to characterize their impacts. The drift network is developed following the in situ major stresses. The parallel drifts are separated enough so as they can be considered independently when their hydromechanical （HM） behaviors are compared. Mine-by experiments have been performed to measure the HM response of the rock and the mechanical loading applied to the support system due to the digging and after excavation. Drifts exhibit extensional （mode I） and shear fractures （modes II and III） induced by excavation works. The extent of the induced fracture networks depends on the drift orientation versus the in situ stress field. This paper describes the drift convergence and deformation in the surrounding rock walls as function of time and the impact of different support methods on the rock mass behavior. An observation based method is finally applied to distinguish the instantaneous and time-dependent parts of the rock mass deformation around the drifts.

Trends of Inequalities in the Use of Long-Term Reversible Contraceptives in Burkina Faso between 2010 and 2015

Background: Efforts have been made in Burkina Faso, a French-speaking country, since 2010 to improve healthcare access and provide affordable contraceptive methods to women. With the increasing prevalence of modern contraceptives in Burkina Faso, it is important to examine the socio-demographic factors that contribute to this new pattern of contraceptive use. This study aims to analyze the changes in socio-demographic factors associated with long-term contraceptive use and provide scientific evidence to guide policy development and action planning in family planning. Data and Methods: We utilized data from the 2010 Demographic and Health Survey, which included 17,087 women aged 15 - 49 years, and the 2015 Demographic and Health Module, which included 11,504 women in the same age group. For the analysis of contraceptive use, we focused on women who were in need of contraception (either met or unmet), of reproductive age, non-pregnant, and either married or sexually active but not married. We included users of modern reversible methods and excluded non-users, as well as users of traditional or permanent methods. Results: Our findings revealed a high prevalence of long-term contraceptive use across all categories;however, certain challenges were identified, such as lower levels of information about contraceptive methods among users and the persistence of inequalities. Family planning discussions and partner approval did not influence long-term contraceptive choice. Additionally, some providers selectively offered specific methods based on women’s life course characteristics, such as parity and marital status, despite evidence suggesting that young and nulliparous women can effectively use long-term methods. Conclusion: Given the high effectiveness of long-term contraceptive methods, it is crucial to address barriers that hinder their utilization among young and nulliparous women, as well as those who desire to delay pregnancy. Efforts should focus on improving knowledge and dispelling misconceptions surrounding long-term methods. Providers play a pivotal role in this process by adopting counseling strategies that enhance users’ understanding and facilitate informed decision-making regarding contraceptive options.

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.

Predicting and Curing Depression Using Long Short Term Memory and Global Vector

In today’s world, there are many people suffering from mentalhealth problems such as depression and anxiety. If these conditions are notidentified and treated early, they can get worse quickly and have far-reachingnegative effects. Unfortunately, many people suffering from these conditions,especially depression and hypertension, are unaware of their existence until theconditions become chronic. Thus, this paper proposes a novel approach usingBi-directional Long Short-Term Memory (Bi-LSTM) algorithm and GlobalVector (GloVe) algorithm for the prediction and treatment of these conditions.Smartwatches and fitness bands can be equipped with these algorithms whichcan share data with a variety of IoT devices and smart systems to betterunderstand and analyze the user’s condition. We compared the accuracy andloss of the training dataset and the validation dataset of the two modelsnamely, Bi-LSTM without a global vector layer and with a global vector layer.It was observed that the model of Bi-LSTM without a global vector layer hadan accuracy of 83%,while Bi-LSTMwith a global vector layer had an accuracyof 86% with a precision of 86.4%, and an F1 score of 0.861. In addition toproviding basic therapies for the treatment of identified cases, our model alsohelps prevent the deterioration of associated conditions, making our methoda real-world solution.

Optimizing the LSTM Deep Learning Model for Arctic Sea Ice Melting Prediction

The National Oceanic and Atmospheric Administration reports a 95% decline in the oldest Arctic ice over the last 33 years [1], while the National Aeronautics and Space Administration states that summer Arctic Sea Ice Extent (SIE) is shrinking by 12.2% per decade since 1979 due to warmer temperatures [2]. Given the rapidly changing Arctic conditions, accurate prediction models are crucial. Deep learning models developed for Arctic forecasts primarily focus on exploring convolutional neural networks (CNN) and convolutional Long Short-Term Memory (LSTM) networks, while the exploration of the power of LSTM networks is limited. In this research, we focus on enhancing the performance of an LSTM network for predicting monthly Arctic SIE. We leverage five climate and atmospheric variables, validated for their correlation with SIE in prior studies [3]. We utilize the Spearman’s rank correlation and ExtraTrees regressor to enhance our understanding of the importance of the five variables in predicting SIE. We further enhance our predictor variables with seasonal information, lagged time steps, and a linear regression simulated SIE that accounts for the influence of past SIE on current SIE. Statistical methods guide our selection of data scalers and best evaluation metrics for our model. By experimenting with hyperparameter optimization and advanced deep learning training techniques, such as batch sizes, number of neurons, early stopping, and model checkpoint, our model achieved a Mean Absolute Error (MAE) of 0.191 and R2 of 0.996, underscoring its ability to account for nearly all the variance in our data and holds great promise for the prediction of SIE.

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.

Tool Health Condition Recognition Method for High Speed Milling of Titanium Alloy Based on Principal Component Analysis (PCA) and Long Short Term Memory (LSTM)

The healthy condition of the milling tool has a very high impact on the machining quality of the titanium components.Therefore,it is important to recognize the healthy condition of the tool and replace the damaged cutter at the right time.In order to recognize the health condition of the milling cutter,a method based on the long short term memory(LSTM)was proposed to recognize tool health state in this paper.The various signals collected in the tool wear experiments were analyzed by time-domain statistics,and then the extracted data were generated by principal component analysis(PCA)method.The preprocessed data extracted by PCA is transmitted to the LSTM model for recognition.Compared with back propagation neural network(BPNN)and support vector machine(SVM),the proposed method can effectively utilize the time-domain regulation in the data to achieve higher recognition speed and accuracy.

一种基于long short-term memory的唇语识别方法

唇动视觉信息是说话内容的重要载体。受嘴唇外观、背景信息和说话习惯等影响,即使说话者说相同的内容,唇动视觉信息也会相差很大。为解决唇语视觉信息多样性的问题,提出一种基于long short-term memory(LSTM)的新的唇语识别方法。以往大多数的方法从嘴唇外表信息入手。本方法用嘴唇关键点坐标描述嘴唇形变信息作为唇语视频的特征,它具有类内一致性和类间区分性的特点。然后利用LSTM对特征进行时序编码,它能学习具有区分性和泛化性的空间-时序特征。在公开的唇语数据集GRID、MIRACL-VC和Oulu VS上对本方法做了针对分割的单词或短语的说话者独立的唇语识别评估。在GRID和MIRACL-VC上,本方法的准确率比传统方法至少高30%;在Oulu VS上,本方法的准确率接近于最优结果。以上实验结果表明,本文提出的基于LSTM的唇语识别方法有效地解决了唇语视觉信息多样性的问题。

Short Term Traffic Flow Prediction Using Hybrid Deep Learning

Traffic flow prediction in urban areas is essential in the IntelligentTransportation System (ITS). Short Term Traffic Flow (STTF) predictionimpacts traffic flow series, where an estimation of the number of vehicleswill appear during the next instance of time per hour. Precise STTF iscritical in Intelligent Transportation System. Various extinct systems aim forshort-term traffic forecasts, ensuring a good precision outcome which was asignificant task over the past few years. The main objective of this paper is topropose a new model to predict STTF for every hour of a day. In this paper,we have proposed a novel hybrid algorithm utilizing Principal ComponentAnalysis (PCA), Stacked Auto-Encoder (SAE), Long Short Term Memory(LSTM), and K-Nearest Neighbors (KNN) named PALKNN. Firstly, PCAremoves unwanted information from the dataset and selects essential features.Secondly, SAE is used to reduce the dimension of input data using onehotencoding so the model can be trained with better speed. Thirdly, LSTMtakes the input from SAE, where the data is sorted in ascending orderbased on the important features and generates the derived value. Finally,KNN Regressor takes information from LSTM to predict traffic flow. Theforecasting performance of the PALKNN model is investigated with OpenRoad Traffic Statistics dataset, Great Britain, UK. This paper enhanced thetraffic flow prediction for every hour of a day with a minimal error value.An extensive experimental analysis was performed on the benchmark dataset.The evaluated results indicate the significant improvement of the proposedPALKNN model over the recent approaches such as KNN, SARIMA, LogisticRegression, RNN, and LSTM in terms of root mean square error (RMSE)of 2.07%, mean square error (MSE) of 4.1%, and mean absolute error (MAE)of 2.04%.

Short-TermWind Power Prediction Based on Combinatorial Neural Networks

Wind power volatility not only limits the large-scale grid connection but also poses many challenges to safe grid operation.Accurate wind power prediction can mitigate the adverse effects of wind power volatility on wind power grid connections.For the characteristics of wind power antecedent data and precedent data jointly to determine the prediction accuracy of the prediction model,the short-term prediction of wind power based on a combined neural network is proposed.First,the Bi-directional Long Short Term Memory(BiLSTM)network prediction model is constructed,and the bi-directional nature of the BiLSTM network is used to deeply mine the wind power data information and find the correlation information within the data.Secondly,to avoid the limitation of a single prediction model when the wind power changes abruptly,the Wavelet Transform-Improved Adaptive Genetic Algorithm-Back Propagation(WT-IAGA-BP)neural network based on the combination of the WT-IAGA-BP neural network and BiLSTM network is constructed for the short-term prediction of wind power.Finally,comparing with LSTM,BiLSTM,WT-LSTM,WT-BiLSTM,WT-IAGA-BP,and WT-IAGA-BP&LSTM prediction models,it is verified that the wind power short-term prediction model based on the combination of WT-IAGA-BP neural network and BiLSTM network has higher prediction accuracy.

Conditional Random Field Tracking Model Based on a Visual Long Short Term Memory Network

In dense pedestrian tracking,frequent object occlusions and close distances between objects cause difficulty when accurately estimating object trajectories.In this study,a conditional random field tracking model is established by using a visual long short term memory network in the three-dimensional(3D)space and the motion estimations jointly performed on object trajectory segments.Object visual field information is added to the long short term memory network to improve the accuracy of the motion related object pair selection and motion estimation.To address the uncertainty of the length and interval of trajectory segments,a multimode long short term memory network is proposed for the object motion estimation.The tracking performance is evaluated using the PETS2009 dataset.The experimental results show that the proposed method achieves better performance than the tracking methods based on the independent motion estimation.

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.

The Function of Oxytocin in Memory —A General Review of Oxytocin’s Effect on Memory

Introduction: While oxytocin (OT) is widely recognized for its pivotal role in reproductive behavior and the formation of social bonds, there remains a significant gap in our understanding of its potential influence on learning and memory processes, encompassing both social and non-social aspects. Thus this paper serves as an attempt to investigate the comprehensive role of OT in Physiological, Cognitive, and Behavioral processes. Method: A comprehensive literature review was conducted to assemble evidence related to the influence of OT on learning and memory. Studies encompassing both social and non-social memory were incorporated into the analysis. Additionally, molecular mechanisms through which OT could potentially impact neuronal activity in the hippocampus and amygdala, consequently affecting learning and memory, were also investigated. Results: Our review reveals a spectrum of evidence that both supports and contradicts the theory that OT plays a significant role in social and non-social memory. While certain studies suggest a positive impact of OT on memory, others present findings that argue otherwise. However, multiple potential molecular mechanisms were discovered that may elucidate OT’s effects on learning and memory, particularly its potential to modulate neuronal activity in the hippocampus and amygdala. Conclusion: Despite the mixed evidence, OT might have a significant role in both social and non-social memory. Identified molecular mechanisms propose potential ways in which OT could influence learning and memory. The key role appears to be the modulation of neuronal activity in the hippocampus and amygdala by OT. Furthermore, it is plausible that OT’s function in memory is crucial for the social behaviors previously associated with it. Future research is necessitated to fully unravel the exact mechanisms and implications of OT’s role in learning and memory.

ADS-B Reception Error Correction Based on the LSTM Neural-Network Model

Standard automatic dependent surveillance broadcast (ADS-B) reception algorithms offer considerable performance at high signal-to-noise ratios (SNRs). However, the performance of ADS-B algorithms in applications can be problematic at low SNRs and in high interference situations, as detecting and decoding techniques may not perform correctly in such circumstances. In addition, conventional error correction algorithms have limitations in their ability to correct errors in ADS-B messages, as the bit and confidence values may be declared inaccurately in the event of low SNRs and high interference. The principal goal of this paper is to deploy a Long Short-Term Memory (LSTM) recurrent neural network model for error correction in conjunction with a conventional algorithm. The data of various flights are collected and cleaned in an initial stage. The clean data is divided randomly into training and test sets. Next, the LSTM model is trained based on the training dataset, and then the model is evaluated based on the test dataset. The proposed model not only improves the ADS-B In packet error correction rate (PECR), but it also enhances the ADS-B In terms of sensitivity. The performance evaluation results reveal that the proposed scheme is achievable and efficient for the avionics industry. It is worth noting that the proposed algorithm is not dependent on conventional algorithms’ prerequisites.

Short-Term Relay Quality Prediction Algorithm Based on Long and Short-Term Memory

The fraction defective of semi-finished products is predicted to optimize the process of relay production lines, by which production quality and productivity are increased, and the costs are decreased. The process parameters of relay production lines are studied based on the long-and-short-term memory network. Then, the Keras deep learning framework is utilized to build up a short-term relay quality prediction algorithm for the semi-finished product. A simulation model is used to study prediction algorithm. The simulation results show that the average prediction absolute error of the fraction is less than 5%. This work displays great application potential in the relay production lines.

Long Term Application of a Vehicle-Based Health Monitoring System to Short and Medium Span Bridges and Damage Detection Sensitivity

Largest portion of the bridge stock in almost any country and bridge owning organisation consists on ordinary bridges that has short or medium spans and are now deteriorating due to aging, etc. Therefore, it is becoming an important social concern to develop and put to practical use simple and efficient health monitoring systems for existing short and medium span (10 - 30 m) bridges. In this paper, one practical solution to the problem for condition assessment of short and medium span bridges was discussed. A vehicle-based measurement with a public bus as part of a public transit system (called “Bus monitoring system”) has been developed to be capable of detecting damage that may affect the structural safety of a bridge from long term vibration measurement data collected while the vehicle (bus) crossed the target bridges. This paper systematically describes how the system has been developed. The bus monitoring system aims to detect the transition from the damage acceleration period, in which the structural safety of an aged bridge declines sharply, to the deterioration period by continually monitoring the bridge of interest. To evaluate the practicality of the newly developed bus monitoring system, it has been field-tested over a period of about four years by using an in-service fixed-route bus operating on a bus route in the city of Ube, Yamaguchi Prefecture, Japan. The verification results thus obtained are also described in this paper. This study also evaluates the sensitivity of “characteristic deflection”, which is a bridge (health) condition indicator used by the bus monitoring system, in damage detection. Sensitivity of “characteristic deflection” is verified by introducing artificial damage into a bridge that has ended its service life and is awaiting removal. As the results, it will be able to make a rational long-term health monitoring system for existing short and mediumspan bridges, and then the system helps bridge administrators to establish the rational maintenance strategies.

Mobile Phone Usage and the Risk of Brain Tumors

Purpose: This literature review investigated the possible association between the use of mobile phones and brain tumors. Methods: In brief, 11 publications were retrieved from JSTOR, PubMed, Google Scholar and Summon in order to compare the association between the usage of mobile phones in patients with a brain tumor and those without. Papers published in English, and after 2001 were selected for. There was no limit on age, gender, geographical location and type of brain tumor. Results: For regular mobile phone usage, the combined odds ratios (OR) (95% confidence intervals) for three studies are: 1.5 (1.2 - 1.8), 1.3 (0.95 - 1.9), and 1.1 (0.8 - 1.4), respectively. Furthermore, the odds ratio did not increase, regardless of mobile phone use duration. Additionally, Lonn et al. (2005) observed that the risk also did not significantly increase when assessing the laterality (ipsilateral or contralateral) of the tumor in relation to side of head used for the mobile phone. Kan et al. (2007) observed an OR of 1.22 when comparing analog phone to digital phone use. Conclusion: This review concludes that there is no current association between mobile phone use and the development of brain tumors. Although certain studies speak in favor of an increased risk, many are plagued with either: sampling bias, misclassification bias, or issues concerning risk estimates. Further research needs to be done in order to evaluate the long-term effect of mobile phone usage on the risk of developing a brain tumor.

Statistical Transformation Indicators of Short-Term to Long-Term Using Flood Regional Coefficients (Case Study: East Azarbaijan Province, Iran)

Changing contexts in a long-term and short-term perspective should be managed within an integrated risk management framework that accounts for both temporary management strategies and permanent preventive measures to reduce the impact of natural hazard processes. In this study, statistical transformation indicators of short-term (20 year) to long-term (30 year) used flood regional coefficients. After the tests of data validation and the reconstruction of missing and outlier data, the data of 18 hydrometric stations were completed for 30 years (1985 to 2014). In the next phase, the return period values were prepared for 20-year and 30-year statistical periods (1985 to 2004 and 1985 to 2014) using the HYFA software. Thus the 20-year to 30-year ratio for various return period discharges obtained and these dimensionless values were plotted for the return periods of 2, 5, 10, 20, 50 and 100 years, also fitted the logarithmic trend line and the values of coefficients of the relationship were obtained. The statistics including average, standard deviation, coefficient of variation (CV), skewness coefficient (CS) and Kurtosis coefficient (CK) were calculated for 20-year data period for each station and we identified the statistics as independent parameters and the coefficients of A and B as dependent parameter, thus analyzed using linear multivariate regression, and regional factors were obtained. In the hydrometric station with 17-027 code, the discharge using the regional factors was calculated and compared with the discharge values of 30 years data. The results showed that there is little difference between the observed and estimated values from regional factors thus this method can be used in projects that require at least 30 years of data.

Analyses of fear memory in Arc/Arg3.1-deficient mice: intact short-term memory and impaired long-term and remote memory

Activity-regulated cytoskeleton-associated protein (Arc/Arg3.1) was originally identified in patients with seizures. It is densely distributed in the hip-pocampus and amygdala in particular. Because the expression of Arc/Arg3.1 is regulated by nerve in-puts, it is thought to be an immediate early gene. As shown both in vitro and in vivo, Arc/Arg3.1 is in-volved in synaptic consolidation and regulates some forms of learning and memory in rats and mice [1,2]. Furthermore, a recent study suggests that Arc/Arg3.1 may play a significant role in signal transmission via AMPA-type glutamate receptors [3-5]. Therefore, we conducted a detailed analysis of fear memory in Arc/Arg3.1-deficient mice. As previously reported, the knockout animals exhib-ited impaired fear memory in both contextual and cued test situations. Although Arc/Arg3.1-deficient mice showed almost the same performance as wild-type littermates 4 hr after a conditioning trial, their performance was impaired in the retention test after 24 hr or longer, either with or without reconsolidation. Immunohistochemical analyses showed an abnormal density of GluR1 in the hip-pocampus of Arc/Arg3.1-deficient mice;however, an application of AMPA potentiator did not improve memory performance in the mutant mice. Memory impairment in Arc/Arg3.1-deficient mice is so ro-bust that the mice provide a useful tool for devel-oping treatments for memory impairment.