检索结果-南通市图书馆

prediction Model of Wax Deposition Rate in Waxy Crude Oil Pipelines by Elman Neural Network Based on Improved Reptile Search Algorithm

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Energy Engineering 2024年第4期121卷 1007-1026页

作者： Zhuo Chen Ningning Wang Wenbo Jin Dui Li The Second Oil Production Plant Sinopec Northwest Oilfield CompanyUrumqi830011China Yingmaili Oil and Gas Production Management Area PetroChina Tarim Oilfield CompanyKorla841001China College of Petroleum Engineering Xi’an Shiyou UniversityXi’an710065China

A hard problem that hinders the movement of waxy crude oil is wax deposition in oil *** ensure the safe operation of crude oil pipelines,an accurate model must be developed to predict the rate of wax deposition in crude oil *** at the shortcomings of the ENN prediction model,which easily falls into the local minimum value and weak generalization ability in the implementation process,an optimized ENN prediction model based on the IRSA is *** validity of the new model was confirmed by the accurate prediction of two sets of experimental data on wax deposition in crude oil *** two groups of crude oil wax deposition rate case prediction results showed that the average absolute percentage errors of IRSA-ENN prediction models is 0.5476% and 0.7831%,***,it shows a higher prediction accuracy compared to the ENN prediction *** fact,the new model established by using the IRSA to optimize ENN can optimize the initial weights and thresholds in the prediction process,which can overcome the shortcomings of the ENN prediction model,such as weak generalization ability and tendency to fall into the local minimum value,so that it has the advantages of strong implementation and high prediction accuracy.

关键词： Waxy crude oil wax deposition rate chaotic map improved reptile search algorithm Elman neural network prediction accuracy

Using machine learning to improve the accuracy of genomic prediction of reproduction traits in pigs

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Animal Science and Biotechnology 2022年第5期13卷 1293-1304页

作者： Xue Wang Shaolei Shi Guijiang Wang Wenxue Luo Xia Wei Ao Qiu Fei Luo Xiangdong Ding Key Laboratory of Animal Genetics and Breeding of Ministry of Agriculture and Rural Affairs National Engineering Laboratory of Animal BreedingCollege of Animal Science and TechnologyChina Agricultural UniversityBeijingChina Hebei Province Animal Husbandry and Improved Breeds Work Station ShijiazhuangHebeiChina Zhangjiakou Dahao Heshan New Agricultural Development Co. LtdZhangjiakouHebeiChina

Background:Recently,machine learning(ML)has become attractive in genomic prediction,but its superiority in genomic prediction over conventional(ss)GBLUP methods and the choice of optimal ML methods need to be ***:In this study,2566 Chinese Yorkshire pigs with reproduction trait records were genotyped with the GenoBaits Porcine SNP 50 K and PorcineSNP50 *** ML methods,including support vector regression(SVR),kernel ridge regression(KRR),random forest(RF)and Adaboost.R2 were *** 20 replicates of fivefold cross-validation(CV)and one prediction for younger individuals,the utility of ML methods in genomic prediction was *** CV,compared with genomic BLUP(GBLUP),single-step GBLUP(ssGBLUP)and the Bayesian method BayesHE,ML methods significantly outperformed these conventional *** methods improved the genomic prediction accuracy of GBLUP,ssGBLUP,and BayesHE by 19.3%,15.0% and 20.8%,*** addition,ML methods yielded smaller mean squared error(MSE)and mean absolute error(MAE)in all *** yielded an improvement of 3.8% on average in accuracy compared to that of GBLUP,and the accuracy of BayesHE was close to that of *** genomic prediction of younger individuals,RF and Adaboost.R2_KRR performed better than GBLUP and BayesHE,while ssGBLUP performed comparably with RF,and ssGBLUP yielded slightly higher accuracy and lower MSE than Adaboost.R2_KRR in the prediction of total number of piglets born,while for number of piglets born alive,Adaboost.R2_KRR performed significantly better than *** ML methods,Adaboost.R2_KRR consistently performed well in our *** findings also demonstrated that optimal hyperparameters are useful for ML *** tuning hyperparameters in CV and in predicting genomic outcomes of younger individuals,the average improvement was 14.3% and 21.8% over those using default hyperparameters,***:Our findings demonstrated that ML methods had better

关键词： Genomic prediction Machine learning Pig prediction accuracy

Stock prediction Based on Technical Indicators Using Deep Learning Model

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第1期70卷 287-304页

作者： Manish Agrawal Piyush Kumar Shukla Rajit Nair Anand Nayyar Mehedi Masud Department of Computer Science&Engineering University Institute of TechnologyRajiv Gandhi Proudyogiki VishwavidyalayaBhopal-462033Madhya PradeshIndia Faculty of Department of Computer Science&Engineering University Institute of TechnologyRajiv Gandhi Proudyogiki VishwavidyalayaBhopal-462033Madhya PradeshIndia Faculty of Department of Computer Science&Engineering School of Engineering and TechnologyJagran Lakecity UniversityBhopal462026Madhya PradeshIndia Graduate School Duy Tan UniversityDa Nang550000Vietnam Faculty of Information Technology Duy Tan UniversityDa Nang550000Vietnam Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia

Stock market trends forecast is one of the most current topics and a significant research challenge due to its dynamic and unstable *** stock data is usually non-stationary,and attributes are non-correlative to each *** traditional Stock Technical Indicators(STIs)may incorrectly predict the stockmarket *** study the stock market characteristics using STIs and make efficient trading decisions,a robust model is *** paper aims to build up an Evolutionary Deep Learning Model(EDLM)to identify stock trends’prices by using *** proposed model has implemented the Deep Learning(DL)model to establish the concept of *** analysis of the dataset of three most popular banking organizations obtained from the live stock market based on the National Stock exchange(NSE)-India,a Long Short Term Memory(LSTM)is *** datasets encompassed the trading days from the 17^(th) of Nov 2008 to the 15^(th) of Nov *** work also conducted exhaustive experiments to study the correlation of various STIs with stock price *** model built with an EDLM has shown significant improvements over two benchmark ML models and a deep learning *** proposed model aids investors in making profitable investment decisions as it presents trend-based forecasting and has achieved a prediction accuracy of 63.59%,56.25%,and 57.95%on the datasets of HDFC,Yes Bank,and SBI,*** indicate that the proposed EDLA with a combination of STIs can often provide improved results than the other state-of-the-art algorithms.

关键词： Long short term memory evolutionary deep learning model national stock exchange stock technical indicators predictive modelling prediction accuracy

A New Method for Quarterly-Data predictions Based on the Extended Grey Model GM(1,1,exp×sin,exp×cos)and Its Application in China's Quarterly GDP prediction

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Systems Science and Information 2023年第1期11卷 109-123页

作者： Maolin CHENG Bin LIU School of Mathematical Sciences Suzhou University of Science and TechnologySuzhou 215009China School of Business Suzhou University of Science and TechnologySuzhou 215009China

Grey prediction is vital in statistical prediction with wide ***,most grey prediction methods focus on annual predictions of the monotonic time series instead of the seasonal time *** paper uses the extended model of the grey GM(1,1)model to predict the seasonal time *** improvements have been made in two aspects to improve the prediction accuracy of the model.1)We introduce seasonal multiple factors to transform the original time series,which improves the adaptability of the seasonal data to the *** transformed series conforms to the law presented by the model.2)The seasonal data are in superimposed sine and cosine fluctuations with ***,the paper extends the grey action quantity of the traditional GM(1,1)*** newly extended grey model is called the GM(1,1,exp×sin,exp×cos)model,which is provided with the parameter optimization methods and time response *** to the proposed modeling method,we establish a GM(1,1,exp×sin,exp×cos)model for China's quarterly gross domestic product(GDP)with high accuracy.

关键词： GM(1,1,exp×sin,exp×cos)model parameter estimation time-response equation prediction accuracy

A novel AC turning on behavior model based on survival analysis

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Building Simulation 2023年第7期16卷 1203-1218页

作者： Yuxin Lu Xinyu Yang Xin Zhou Jingjing An Xiaomin Wang Kun Zhang Da Yan School of Architecture Southeast UniversityNanjingJiangsu Province 210096China School of Environment and Energy Engineering Beijing University of Civil Engineering and ArchitectureBeijing 100084China Jiangsu Architectural Design and Research Institute Co. Ltd.NanjingJiangsu Province 210096China School of Architecture Tsinghua UniversityBeijing 100084China

Occupant control behavior is a key factor affecting the energy consumption of building air-conditioners(ACs).The operating behavior of ACs and their models in office buildings have been investigated ***,although the thermal sensation of occupants is affected by their previous thermal experience,few researchers have attempted to incorporate this effect quantitatively in models of AC turning on *** considering the cumulative effect may result in inaccurate ***,in this study,a survival model is proposed to describe AC turning on behavior in office buildings under the cumulative dimension of *** on a dataset containing environmental parameters and occupant behavior information,as well as considering occupants entering a room as the starting event and turning on an air-conditioner as the end event,the endurance time before an AC is turned on is investigated,and a survival model is used to predict the probability of the AC turning on due to environmental *** on a switch curve,confusion matrix,and tolerance–time curve,the prediction results of the survival model are analyzed and *** results show that a tolerance temperature of 29℃and a tolerance duration setting of 1 h can effectively model the turning on behavior of the *** addition,based on comparison results of different models,the survival model presents a more stable switching curve,a higher F1 score,and a tolerance curve that is more similar to *** tolerance durations,as well as static and dynamic tolerance temperature settings,are considered to optimize the ***,the AC energy consumption is calculated under the survival model and the traditional Weibull *** results were compared with measurement,and the survival model verified the improvement effect of prediction accuracy by 8%than the Weibull *** considering the time-transformed accumulation of physical environmental factors,the accuracy of AC turnin

关键词： AC status AC turning on behavior survival models time dependent models prediction accuracy

Research on Federated Learning Data Sharing Scheme Based on Differential Privacy

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第3期74卷 5069-5085页

作者： Lihong Guo Department of Information and Communications Engineering Nanjing Institute of TechnologyNanjing211167China

To realize data sharing,and to fully use the data value,breaking the data island between institutions to realize data collaboration has become a new sharing *** paper proposed a distributed data security sharing scheme based on C/S communication mode,and constructed a federated learning architecture that uses differential privacy technology to protect training *** do not need to share local data,and they only need to upload the trained model parameters to achieve data *** the process of training,a distributed parameter update mechanism is *** server is mainly responsible for issuing training commands and parameters,and aggregating the local model parameters uploaded by the *** client mainly uses the stochastic gradient descent algorithm for gradient trimming,updates,and transmits the trained model parameters back to the server after differential *** test the performance of the scheme,in the application scenario where many medical institutions jointly train the disease detection system,the model is tested from multiple perspectives by taking medical data as an *** the testing results,we can know that for this specific test dataset,when the parameters are properly configured,the lowest prediction accuracy rate is 90.261%and the highest accuracy rate is up to *** shows that the performance of the model is *** results also show that this scheme realizes data sharing while protecting data privacy,completes accurate prediction of diseases,and has a good effect.

关键词： Federated learning C/S mode differential privacy gradient descent prediction accuracy

Earlier Detection of Alzheimer’s Disease Using 3D-Convolutional Neural Networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第8期46卷 2601-2618页

作者： V.P.Nithya N.Mohanasundaram R.Santhosh Department of Computer Science and Engineering Karpagam Academy of Higher EducationCoimbatoreIndia

The prediction of mild cognitive impairment or Alzheimer’s disease(AD)has gained the attention of huge researchers as the disease occurrence is increasing,and there is a need for earlier ***,due to the highdimensionality nature of neural data and the least available samples,modelling an efficient computer diagnostic system is highly *** approaches,specifically deep learning approaches,are essential in disease *** Learning(DL)approaches are successfully demonstrated for their higher-level performance in various fields like medical imaging.A novel 3D-Convolutional Neural Network(3D-CNN)architecture is proposed to predict AD with Magnetic resonance imaging(MRI)*** proposed model predicts the AD occurrence while the existing approaches lack prediction accuracy and perform binary *** proposed prediction model is validated using the Alzheimer’s disease Neuro-Imaging Initiative(ADNI)*** outcomes demonstrate that the anticipated model attains superior prediction accuracy and works better than the brain-image dataset’s general *** predicted model reduces the human effort during the prediction process and makes it easier to diagnose it intelligently as the feature learning is ***’experimentation is carried out,and the model’s superiority is compared with various advanced approaches for multi-level *** proposed model gives better prediction accuracy,precision,recall,and F-measure than other systems like Long Short Term Memory-Recurrent Neural Networks(LSTM-RNN),Stacked Autoencoder with Deep Neural Networks(SAE-DNN),Deep Convolutional Neural Networks(D-CNN),Two Dimensional Convolutional Neural Networks(2D-CNN),Inception-V4,ResNet,and Two Dimensional Convolutional Neural Networks(3D-CNN).

关键词： Alzheimer’s disease 3D CNN ADNI prediction accuracy highdimensionality data

Adaptive Learning Video Streaming with QoE in Multi-Home Heterogeneous Networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第9期46卷 2881-2897页

作者： S.Vijayashaarathi S.NithyaKalyani Department of Electronics and Communication Sona College of TechnologySalem636005Tamil NaduIndia Department of Information Technology K.S.R.College of EngineeringTiruchengode637215Tamil NaduIndia

In recent years,real-time video streaming has grown in *** growing popularity of the Internet of Things(IoT)and other wireless heterogeneous networks mandates that network resources be carefully apportioned among versatile users in order to achieve the best Quality of Experience(QoE)and performance *** researchers focused on Forward Error Correction(FEC)techniques when attempting to strike a balance between QoE and ***,as network capacity increases,the performance degrades,impacting the live visual ***,Deep Learning(DL)algorithms have been successfully integrated with FEC to stream videos across multiple heterogeneous *** these algorithms need to be changed to make the experience better without sacrificing packet loss and delay *** address the previous challenge,this paper proposes a novel intelligent algorithm that streams video in multi-home heterogeneous networks based on network-centric *** proposed framework contains modules such as Intelligent Content Extraction Module(ICEM),Channel Status Monitor(CSM),and Adaptive FEC(AFEC).This framework adopts the Cognitive Learning-based Scheduling(CLS)Module,which works on the deep Reinforced Gated Recurrent Networks(RGRN)principle and embeds them along with the FEC to achieve better *** complete framework was developed using the Objective Modular Network Testbed in C++(OMNET++),Internet networking(INET),and Python 3.10,with Keras as the front end and Tensorflow 2.10 as the back *** extensive experimentation,the proposed model outperforms the other existing intelligentmodels in terms of improving the QoE,minimizing the End-to-End Delay(EED),and maintaining the highest accuracy(98%)and a lower Root Mean Square Error(RMSE)value of 0.001.

关键词： Real-time video streaming IoT multi-home heterogeneous networks forward error coding deep reinforced gated recurrent networks QoE prediction accuracy RMSE

Modelling an Efficient URL Phishing Detection Approach Based on a Dense Network Model

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第11期47卷 2625-2641页

作者： A.Aldo Tenis R.Santhosh Department of Computer Science and Engineering Faculty of EngineeringKarpagam Academy of Higher EducationCoimbatoreTamil NaduIndia

The social engineering cyber-attack is where culprits mislead the users by getting the login details which provides the information to the evil server called *** deep learning approaches and the machine learning are compared in the proposed system for presenting the methodology that can detect phishing websites via Uniform Resource Locator(URLs)*** legal class is composed of the home pages with no inclusion of login forms in most of the present modern solutions,which deals with the detection of ***,the URLs in both classes from the login page due,considering the representation of a real case scenario and the demonstration for obtaining the rate of false-positive with the existing approaches during the legal login pages provides the test having *** addition,some model reduces the accuracy rather than training the base model and testing the latest *** addition,a feature analysis is performed on the present phishing domains to identify various approaches to using the phishers in the campaign.A new dataset called the MUPD dataset is used for ***,a prediction model,the Dense forward-backwards Long Short Term Memory(LSTM)model(d−FBLSTM),is presented for combining the forward and backward propagation of LSMT to obtain the accuracy of 98.5%on the initiated login URL dataset.

关键词： Cyber-attack URL phishing attack attention model prediction accuracy