A Novel Predictive Model for Edge Computing Resource Scheduling Based on Deep Neural Network

Currently,applications accessing remote computing resources through cloud data centers is the main mode of operation,but this mode of operation greatly increases communication latency and reduces overall quality of service(QoS)and quality of experience(QoE).Edge computing technology extends cloud service functionality to the edge of the mobile network,closer to the task execution end,and can effectivelymitigate the communication latency problem.However,the massive and heterogeneous nature of servers in edge computing systems brings new challenges to task scheduling and resource management,and the booming development of artificial neural networks provides us withmore powerfulmethods to alleviate this limitation.Therefore,in this paper,we proposed a time series forecasting model incorporating Conv1D,LSTM and GRU for edge computing device resource scheduling,trained and tested the forecasting model using a small self-built dataset,and achieved competitive experimental results.

Cybernet Model:A New Deep Learning Model for Cyber DDoS Attacks Detection and Recognition

Cyberspace is extremely dynamic,with new attacks arising daily.Protecting cybersecurity controls is vital for network security.Deep Learning(DL)models find widespread use across various fields,with cybersecurity being one of the most crucial due to their rapid cyberattack detection capabilities on networks and hosts.The capabilities of DL in feature learning and analyzing extensive data volumes lead to the recognition of network traffic patterns.This study presents novel lightweight DL models,known as Cybernet models,for the detection and recognition of various cyber Distributed Denial of Service(DDoS)attacks.These models were constructed to have a reasonable number of learnable parameters,i.e.,less than 225,000,hence the name“lightweight.”This not only helps reduce the number of computations required but also results in faster training and inference times.Additionally,these models were designed to extract features in parallel from 1D Convolutional Neural Networks(CNN)and Long Short-Term Memory(LSTM),which makes them unique compared to earlier existing architectures and results in better performance measures.To validate their robustness and effectiveness,they were tested on the CIC-DDoS2019 dataset,which is an imbalanced and large dataset that contains different types of DDoS attacks.Experimental results revealed that bothmodels yielded promising results,with 99.99% for the detectionmodel and 99.76% for the recognition model in terms of accuracy,precision,recall,and F1 score.Furthermore,they outperformed the existing state-of-the-art models proposed for the same task.Thus,the proposed models can be used in cyber security research domains to successfully identify different types of attacks with a high detection and recognition rate.

A creep model for ultra-deep salt rock considering thermal-mechanical damage under triaxial stress conditions

To investigate the specific creep behavior of ultra-deep buried salt during oil and gas exploitation,a set of triaxial creep experiments was conducted at elevated temperatures with constant axial pressure and unloading confining pressure conditions.Experimental results show that the salt sample deforms more significantly with the increase of applied temperature and deviatoric loading.The accelerated creep phase is not occurring until the applied temperature reaches 130℃,and higher temperature is beneficial to the occurrence of accelerated creep.To describe the specific creep behavior,a novel three-dimensional(3D)creep constitutive model is developed that incorporates the thermal and mechanical variables into mechanical elements.Subsequently,the standard particle swarm optimization(SPSO)method is adopted to fit the experimental data,and the sensibility of key model parameters is analyzed to further illustrate the model function.As a result,the model can accurately predict the creep behavior of salt under the coupled thermo-mechanical effect in deep-buried condition.Based on the research results,the creep mechanical behavior of wellbore shrinkage is predicted in deep drilling projects crossing salt layer,which has practical implications for deep rock mechanics problems.

Quantitative prediction model for the depth limit of oil accumulation in the deep carbonate rocks:A case study of Lower Ordovician in Tazhong area of Tarim Basin

With continuous hydrocarbon exploration extending to deeper basins,the deepest industrial oil accumulation was discovered below 8,200 m,revealing a new exploration field.Hence,the extent to which oil exploration can be extended,and the prediction of the depth limit of oil accumulation(DLOA),are issues that have attracted significant attention in petroleum geology.Since it is difficult to characterize the evolution of the physical properties of the marine carbonate reservoir with burial depth,and the deepest drilling still cannot reach the DLOA.Hence,the DLOA cannot be predicted by directly establishing the relationship between the ratio of drilling to the dry layer and the depth.In this study,by establishing the relationships between the porosity and the depth and dry layer ratio of the carbonate reservoir,the relationships between the depth and dry layer ratio were obtained collectively.The depth corresponding to a dry layer ratio of 100%is the DLOA.Based on this,a quantitative prediction model for the DLOA was finally built.The results indicate that the porosity of the carbonate reservoir,Lower Ordovician in Tazhong area of Tarim Basin,tends to decrease with burial depth,and manifests as an overall low porosity reservoir in deep layer.The critical porosity of the DLOA was 1.8%,which is the critical geological condition corresponding to a 100%dry layer ratio encountered in the reservoir.The depth of the DLOA was 9,000 m.This study provides a new method for DLOA prediction that is beneficial for a deeper understanding of oil accumulation,and is of great importance for scientific guidance on deep oil drilling.

Hybrid model for BOF oxygen blowing time prediction based on oxygen balance mechanism and deep neural network

The amount of oxygen blown into the converter is one of the key parameters for the control of the converter blowing process,which directly affects the tap-to-tap time of converter. In this study, a hybrid model based on oxygen balance mechanism (OBM) and deep neural network (DNN) was established for predicting oxygen blowing time in converter. A three-step method was utilized in the hybrid model. First, the oxygen consumption volume was predicted by the OBM model and DNN model, respectively. Second, a more accurate oxygen consumption volume was obtained by integrating the OBM model and DNN model. Finally, the converter oxygen blowing time was calculated according to the oxygen consumption volume and the oxygen supply intensity of each heat. The proposed hybrid model was verified using the actual data collected from an integrated steel plant in China, and compared with multiple linear regression model, OBM model, and neural network model including extreme learning machine, back propagation neural network, and DNN. The test results indicate that the hybrid model with a network structure of 3 hidden layer layers, 32-16-8 neurons per hidden layer, and 0.1 learning rate has the best prediction accuracy and stronger generalization ability compared with other models. The predicted hit ratio of oxygen consumption volume within the error±300 m^(3)is 96.67%;determination coefficient (R^(2)) and root mean square error (RMSE) are0.6984 and 150.03 m^(3), respectively. The oxygen blow time prediction hit ratio within the error±0.6 min is 89.50%;R2and RMSE are0.9486 and 0.3592 min, respectively. As a result, the proposed model can effectively predict the oxygen consumption volume and oxygen blowing time in the converter.

Unified deep learning model for predicting fundus fluorescein angiography image from fundus structure image

The prediction of fundus fluorescein angiography(FFA)images from fundus structural images is a cutting-edge research topic in ophthalmological image processing.Prediction comprises estimating FFA from fundus camera imaging,single-phase FFA from scanning laser ophthalmoscopy(SLO),and three-phase FFA also from SLO.Although many deep learning models are available,a single model can only perform one or two of these prediction tasks.To accomplish three prediction tasks using a unified method,we propose a unified deep learning model for predicting FFA images from fundus structure images using a supervised generative adversarial network.The three prediction tasks are processed as follows:data preparation,network training under FFA supervision,and FFA image prediction from fundus structure images on a test set.By comparing the FFA images predicted by our model,pix2pix,and CycleGAN,we demonstrate the remarkable progress achieved by our proposal.The high performance of our model is validated in terms of the peak signal-to-noise ratio,structural similarity index,and mean squared error.

Framework to Model User Request Access Patterns in the World Wide Web

In this paper, we present a novel approach to model user request patterns in the World Wide Web. Instead of focusing on the user traffic for web pages, we capture the user interaction at the object level of the web pages. Our framework model consists of three sub-models: one for user file access, one for web pages, and one for storage servers. Web pages are assumed to consist of different types and sizes of objects, which are characterized using several categories: articles, media, and mosaics. The model is implemented with a discrete event simulation and then used to investigate the performance of our system over a variety of parameters in our model. Our performance measure of choice is mean response time and by varying the composition of web pages through our categories, we find that our framework model is able to capture a wide range of conditions that serve as a basis for generating a variety of user request patterns. In addition, we are able to establish a set of parameters that can be used as base cases. One of the goals of this research is for the framework model to be general enough that the parameters can be varied such that it can serve as input for investigating other distributed applications that require the generation of user request access patterns.

Integrated Machine Learning and Deep Learning Models for Cardiovascular Disease Risk Prediction: A Comprehensive Comparative Study

Cardiovascular Diseases (CVDs) pose a significant global health challenge, necessitating accurate risk prediction for effective preventive measures. This comprehensive comparative study explores the performance of traditional Machine Learning (ML) and Deep Learning (DL) models in predicting CVD risk, utilizing a meticulously curated dataset derived from health records. Rigorous preprocessing, including normalization and outlier removal, enhances model robustness. Diverse ML models (Logistic Regression, Random Forest, Support Vector Machine, K-Nearest Neighbor, Decision Tree, and Gradient Boosting) are compared with a Long Short-Term Memory (LSTM) neural network for DL. Evaluation metrics include accuracy, ROC AUC, computation time, and memory usage. Results identify the Gradient Boosting Classifier and LSTM as top performers, demonstrating high accuracy and ROC AUC scores. Comparative analyses highlight model strengths and limitations, contributing valuable insights for optimizing predictive strategies. This study advances predictive analytics for cardiovascular health, with implications for personalized medicine. The findings underscore the versatility of intelligent systems in addressing health challenges, emphasizing the broader applications of ML and DL in disease identification beyond cardiovascular health.

Exploration of the Construction and Path Selection of the Deep Integration Model of Industry-Education in Universities

Against the backdrop of continuous development in the field of education,universities are encouraged to innovate their talent cultivation systems and objectives.The deep integration of industry and education has emerged as an effective strategy,aligning with the basic requirements of the new engineering education initiative and exerting a positive impact on socioeconomic development.However,an analysis of the current state of industry-education integration in universities reveals several issues that require optimization,affecting the ultimate effectiveness of integration.To optimize this phenomenon and achieve high-quality development,universities need to further explore the construction of a deep integration model of industry and education,adhering to corresponding principles to form a comprehensive system.On this basis,pathways for deep industry-education integration can be summarized.

基于24Model-D-ISM的地铁站火灾疏散影响因素研究

为预防地铁站火灾事故,深入了解地铁站火灾人员疏散影响因素间的内在联系与层次结构,基于第6版“2-4”模型(24Model)分析63起地铁站火灾疏散事故,充分考虑各个因素之间的交互作用,提取19个影响地铁站人员疏散的关键因素,建立地铁站火灾人员疏散影响因素指标体系;采用算子客观赋权法(C-OWA)改进决策试验与评价实验法(DEMATEL),确定地铁站火灾人员疏散的重要影响因素;在此基础上,采用解释结构模型(ISM)分析各个因素间的层次结构及相互作用路径,构建地铁站火灾人员疏散影响因素的多级递阶结构模型。研究结果表明:疏散引导、恐慌从众行为、人员拥挤为地铁站火灾人员疏散的关键影响因素;地铁站火灾人员疏散受表层因素、中间层因素、深层因素共同作用的影响,其中,疏散教育与培训、设施维护与检查、疏散预案等因素是根源影响因素,重视根源影响因素的改善有利于从本质上预防和控制事故的发生。

基于改进Wide&Deep的卷烟焦油指标预测模型

针对卷烟焦油指标预测任务中历史卷烟数据样本具有小样本和高维度的特点,导致模型预测准确度偏低的问题,提出一种基于改进Wide&Deep的卷烟焦油指标预测模型。首先通过多个机器学习模型对数据样本进行预测,并将得到的结果作为模型新特征;然后将机器学习模型得到的新特征输入到Wide&Deep模型的Wide端,同时构建融合特征输入到Wide&Deep模型的Deep端,并在Deep端通过引入二阶特征和注意力机制构建注意力特征交叉层实现特征的高阶组合以提高模型预测的准确度。实验结果表明,所提模型与未经过改进的Wide&Deep模型相比,平均绝对误差(MAE)降低了23.4%,均方根误差(RMSE)降低了21.8%;与基于卷积神经网络提取特征的改进Wide&Deep模型相比,MAE降低了15.0%,RMSE降低了16.4%;有效提升了卷烟焦油指标预测任务的准确度。

A post-peak dilatancy model for soft rock and its application in deep tunnel excavation

The dilation angle is the most commonly used parameter to study nonlinear post-peak dilatancy(PPD)behavior and simulate surrounding rock deformation;however,simplified or constant dilatancy models are often used in numerical calculations owing to their simple mathematical forms.This study developed a PPD model for rocks(rock masses)based on the Alejanoe-Alonso(A-A)dilatancy model.The developed model comprehensively reflects the influences of confining pressure(σ_(3))and plastic shear strain(γ^(p)),with the advantages of a simple mathematical form,while requiring fewer parameters and demonstrating a clear physical significance.The overall fitting accuracy of the PPD model for 11 different rocks was found to be higher than that of the A-A model,particularly for Witwatersrand quartzite and jointed granite.The applicability and reliability of the PPD model to jointed granites and different scaled Moura coals were also investigated,and the model was found to be more suitable for the soft and large-scale rocks,e.g.deep rock mass.The PPD model was also successfully applied in studying the mechanical response of a circular tunnel excavated in strain-softening rock mass,and the developed semi-analytical solution was compared and verified with existing analytical solutions.The sensitivities of the rock dilatancy to γ^(p) and σ_(3) showed significant spatial variabilities along the radial direction of the surrounding rock,and the dilation angle did not exhibit a monotonical increasing or decreasing law from the elasticeplastic boundary to the tunnel wall,thereby presenting the σ3-or γ^(p)-dominated differential effects of rock dilatancy.Tunnel deformation parabolically or exponentially increased with increasing in situ stress(buried depth).The developed PPD model is promising to conduct refined numerical and analytical analyses for deep tunneling,which produces extensive plastic deformation and exhibits significant nonlinear post-peak behavior.

基于改进DeeplabV3+的遥感图像道路分割模型

针对遥感图像道路分割边界模糊和遮挡难以区分的问题,提出了基于改进DeeplabV3+的遥感图像道路分割模型。该模型在主干网络中引入MobileNetV3和高效通道注意力机制(ECA),减少了参数量并关注连续的道路特征信息。在解码过程中采用多级上采样,增强了编码器和解码器之间的紧密连接,全面保留了细节信息。同时,在ASPP模块中采用深度可分离膨胀卷积DS-ASPP,显著减少了参数量。实验结果表明,该模型在Massachusetts Roads数据集上的交并比达到了83.71%,准确率达到了93.71%,分割精度最优,模型参数量为55.57×10^(6),能够有效地避免边界模糊和遮挡导致的错漏检问题,在遥感道路分割中提高了精度和速度。

Modeling of Optimal Deep Learning Based Flood Forecasting Model Using Twitter Data

Aflood is a significant damaging natural calamity that causes loss of life and property.Earlier work on the construction offlood prediction models intended to reduce risks,suggest policies,reduce mortality,and limit property damage caused byfloods.The massive amount of data generated by social media platforms such as Twitter opens the door toflood analysis.Because of the real-time nature of Twitter data,some government agencies and authorities have used it to track natural catastrophe events in order to build a more rapid rescue strategy.However,due to the shorter duration of Tweets,it is difficult to construct a perfect prediction model for determiningflood.Machine learning(ML)and deep learning(DL)approaches can be used to statistically developflood prediction models.At the same time,the vast amount of Tweets necessitates the use of a big data analytics(BDA)tool forflood prediction.In this regard,this work provides an optimal deep learning-basedflood forecasting model with big data analytics(ODLFF-BDA)based on Twitter data.The suggested ODLFF-BDA technique intends to anticipate the existence offloods using tweets in a big data setting.The ODLFF-BDA technique comprises data pre-processing to convert the input tweets into a usable format.In addition,a Bidirectional Encoder Representations from Transformers(BERT)model is used to generate emotive contextual embed-ding from tweets.Furthermore,a gated recurrent unit(GRU)with a Multilayer Convolutional Neural Network(MLCNN)is used to extract local data and predict theflood.Finally,an Equilibrium Optimizer(EO)is used tofine-tune the hyper-parameters of the GRU and MLCNN models in order to increase prediction performance.The memory usage is pull down lesser than 3.5 MB,if its compared with the other algorithm techniques.The ODLFF-BDA technique’s performance was validated using a benchmark Kaggle dataset,and thefindings showed that it outperformed other recent approaches significantly.

耦合优化蚁群算法与P-Median model的选址模型设计

为节省城建部门对于公共体育设施的投入成本以及提高城市人民生活质量,以运动场所优化选址为例,提出一种新型设施选址模型。该模型主要基于P-Median model(最小化阻抗模型)根据需求点数量从全部候选设施选址中选择设施空间位置,让用户达到离自己最近设施距离成本总和最小的目的,对选址的基本原则和实际情况提出要求,构造目标函数用于优化后蚁群算法求解进行选址工作。优化蚁群算法实现基于Python语言模块,通过改进蚁群原始信息素,提升原有算法的收敛速度,求出目标函数最优解,可以很好地模拟对于运动场所的选址。用二者耦合进行优势互补所设计的选址模型来搜寻研究区蚁群信息素浓度残留最大的栅格像元,从而确定未被已有设施点服务半径覆盖的最佳设施点建立位置。实验结果表明,该新型选址模型相较于最小化阻抗模型与最大化覆盖模型,新增优化设施点使整体服务半径覆盖率分别高出10.42%和6.95%,适合求解较为精确且小规模空间下的选址问题。

Chaotic Flower Pollination with Deep Learning Based COVID-19 Classification Model

The Coronavirus Disease(COVID-19)pandemic has exposed the vulnerabilities of medical services across the globe,especially in underdeveloped nations.In the aftermath of the COVID-19 outbreak,a strong demand exists for developing novel computer-assisted diagnostic tools to execute rapid and cost-effective screenings in locations where many screenings cannot be executed using conventional methods.Medical imaging has become a crucial component in the disease diagnosis process,whereas X-rays and Computed Tomography(CT)scan imaging are employed in a deep network to diagnose the diseases.In general,four steps are followed in image-based diagnostics and disease classification processes by making use of the neural networks,such as network training,feature extraction,model performance testing and optimal feature selection.The current research article devises a Chaotic Flower Pollination Algorithm with a Deep Learning-Driven Fusion(CFPADLDF)approach for detecting and classifying COVID-19.The presented CFPA-DLDF model is developed by integrating two DL models to recognize COVID-19 in medical images.Initially,the proposed CFPA-DLDF technique employs the Gabor Filtering(GF)approach to pre-process the input images.In addition,a weighted voting-based ensemble model is employed for feature extraction,in which both VGG-19 and the MixNet models are included.Finally,the CFPA with Recurrent Neural Network(RNN)model is utilized for classification,showing the work’s novelty.A comparative analysis was conducted to demonstrate the enhanced performance of the proposed CFPADLDF model,and the results established the supremacy of the proposed CFPA-DLDF model over recent approaches.

Mshpy23:a user-friendly,parameterized model of magnetosheath conditions

Lunar Environment heliospheric X-ray Imager(LEXI)and Solar wind−Magnetosphere−Ionosphere Link Explorer(SMILE)will observe magnetosheath and its boundary motion in soft X-rays for understanding magnetopause reconnection modes under various solar wind conditions after their respective launches in 2024 and 2025.Magnetosheath conditions,namely,plasma density,velocity,and temperature,are key parameters for predicting and analyzing soft X-ray images from the LEXI and SMILE missions.We developed a userfriendly model of magnetosheath that parameterizes number density,velocity,temperature,and magnetic field by utilizing the global Magnetohydrodynamics(MHD)model as well as the pre-existing gas-dynamic and analytic models.Using this parameterized magnetosheath model,scientists can easily reconstruct expected soft X-ray images and utilize them for analysis of observed images of LEXI and SMILE without simulating the complicated global magnetosphere models.First,we created an MHD-based magnetosheath model by running a total of 14 OpenGGCM global MHD simulations under 7 solar wind densities(1,5,10,15,20,25,and 30 cm)and 2 interplanetary magnetic field Bz components(±4 nT),and then parameterizing the results in new magnetosheath conditions.We compared the magnetosheath model result with THEMIS statistical data and it showed good agreement with a weighted Pearson correlation coefficient greater than 0.77,especially for plasma density and plasma velocity.Second,we compiled a suite of magnetosheath models incorporating previous magnetosheath models(gas-dynamic,analytic),and did two case studies to test the performance.The MHD-based model was comparable to or better than the previous models while providing self-consistency among the magnetosheath parameters.Third,we constructed a tool to calculate a soft X-ray image from any given vantage point,which can support the planning and data analysis of the aforementioned LEXI and SMILE missions.A release of the code has been uploaded to a Github repository.

24Model与LCM原因因素定义对比研究

为探究损失致因模型(LCM)原因因素定义与事故致因“2-4”模型(24Model)存在的异同和优缺点,梳理2个模型各层面原因和结果的定义,对比定义内容及其对事故原因分析等安全实务的指导作用,并以一起瓦斯爆炸事故为例加以实证分析,获得二者分析结果之间的差异。研究结果表明:LCM是首个将管理因素纳入事故致因分析的一维事件序列模型,可明确各层面原因因素的定义和因素间的逻辑关系,但部分定义存在交叉重复的问题,并没有揭示安全工作指导思想等深层次事故致因因素;24Model作为系统性事故致因模型,对各类因素的定义均以组织为主体,描述事件、事故、安全的概念内涵,划分个体安全动作、安全能力和组织安全管理体系的类别并给出含义解析,探究组织安全文化层面的问题并以32个元素体现;2个模型的事故原因分析方法均建立在对各层级原因因素定义的基础上,并适用于模型理论体系本身。

Structural characteristics and deep-water hydrocarbon accumulation model of the Scotian Basin, Eastern Canada

Commercial hydrocarbon reservoirs have been discovered in shallow-water areas of the Scotian Basin, Eastern Canada. However, knowledge about the structure and hydrocarbon accumulation characteristics of the basin is still insufficient, which constrains the oil and gas exploration in deep-water areas. Based on comprehensive data of magnetic anomalies, seismic survey, and drilling, this study determines the structure characteristics of the Scotian Basin and its hydrocarbon accumulation conditions in deep waters and evaluates the deep-water hydrocarbon exploration potential. The transform faults and basement structures in the northern basin control the sedimentary framework showing thick strata in east and thin strata in west of the basin. The bowl-shaped depression formed by thermal subsidence during the transitional phase and the confined environment (micro basins) caused by salt tectonics provide favorable conditions for the development of source rocks during the depression stage (also referred to as the depression period sequence) of the basin. The progradation of large shelf-margin deltas during the drift phase and steep continental slope provide favorable conditions for the deposition of slope-floor fans on continental margins of the basin. Moreover, the source-reservoir assemblage comprising the source rocks within the depression stage and the turbidite sandstones on the continental margin in the deep waters may form large deep-water turbidite sandstone reservoirs. This study will provide a valuable reference for the deep-water hydrocarbon exploration in the Scotian Basin.

Geological characteristics and models of fault-foldfracture body in deep tight sandstone of the second member of Upper Triassic Xujiahe Formation in Xinchang structural belt of Sichuan Basin,SW China

In the second member of the Upper Triassic Xujiahe Formation(T_(3)x_(2))in the Xinchang area,western Sichuan Basin,only a low percent of reserves has been recovered,and the geological model of gas reservoir sweet spot remains unclear.Based on a large number of core,field outcrop,test and logging-seismic data,the T_(3)x_(2) gas reservoir in the Xinchang area is examined.The concept of fault-fold-fracture body(FFFB)is proposed,and its types are recognized.The main factors controlling fracture development are identified,and the geological models of FFFB are established.FFFB refers to faults,folds and associated fractures reservoirs.According to the characteristics and genesis,FFFBs can be divided into three types:fault-fracture body,fold-fracture body,and fault-fold body.In the hanging wall of the fault,the closer to the fault,the more developed the effective fractures;the greater the fold amplitude and the closer to the fold hinge plane,the more developed the effective fractures.Two types of geological models of FFFB are established:fault-fold fracture,and matrix storage and permeability.The former can be divided into two subtypes:network fracture,and single structural fracture,and the later can be divided into three subtypes:bedding fracture,low permeability pore,and extremely low permeability pore.The process for evaluating favorable FFFB zones was formed to define favorable development targets and support the well deployment for purpose of high production.The study results provide a reference for the exploration and development of deep tight sandstone oil and gas reservoirs in China.