检索结果-南通市图书馆

Deep Convolutional Neural Network Based Churn Prediction for Telecommunication Industry

在线全文

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2022年第12期43卷 1255-1270页

作者： Nasebah Almufadi Ali mustafa Qamar Department of Computer Science College of ComputerQassim UniversityBuraydahSaudi Arabia Department of Computing School of Electrical Engineering and Computer ScienceNational University of Sciences and Technology(NUST)IslamabadPakistan

Currently,mobile communication is one of the widely used means of ***,it is quite challenging for a telecommunication company to attract new *** recent concept of mobile number portability has also aggravated the problem of customer *** need to identify beforehand the customers,who could potentially churn out to the *** the telecommunication industry,such identification could be done based on call detail *** research presents an extensive experimental study based on various deep learning models,such as the 1D convolutional neural network(CNN)model along with the recurrent neural network(RNN)and deep neural network(DNN)for churn *** use the mobile telephony churn prediction dataset obtained from ***,containing the data for around 100,000 individuals,out of which 86,000 are non-churners,whereas 14,000 are churned *** imbalanced data are handled using undersampling and *** accuracy for CNN,RNN,and DNN is 91%,93%,and 96%,***,DNN got 99%for ROC.

关键词： Deep learning machine learning churn prediction convolutional neural network recurrent neural network

Rough Sets Hybridization with Mayfly Optimization for Dimensionality Reduction

维普期刊数据库评论

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 2022年第10期73卷 1087-1108页

作者： Ahmad Taher Azar mustafa Samy Elgendy mustafa Abdul Salam Khaled M.Fouad Faculty of Computers and Artificial Intelligence Benha UniversityBenha13518Egypt College of Computer and Information Sciences Prince Sultan UniversityRiyadh11586Saudi Arabia Faculty of Computer Studies Arab Open UniversityCairoEgypt Faculty of Information Technology and Computer Science Nile UniversityShikh ZaidEgypt

Big data is a vast amount of structured and unstructured data that must be dealt with on a regular *** reduction is the process of converting a huge set of data into data with tiny dimensions so that equal information may be expressed *** tactics are frequently utilized to improve classification or regression challenges while dealing with machine learning *** achieve dimensionality reduction for huge data sets,this paper offers a hybrid particle swarm optimization-rough set PSO-RS and Mayfly algorithm-rough set MA-RS.A novel hybrid strategy based on the Mayfly algorithm(MA)and the rough set(RS)is proposed in *** performance of the novel hybrid algorithm MA-RS is evaluated by solving six different data sets from the *** simulation results and comparison with common reduction methods demonstrate the proposed MARS algorithm’s capacity to handle a wide range of data ***,the rough set approach,as well as the hybrid optimization techniques PSO-RS and MARS,were applied to deal with the massive data ***-hybrid RS’s method beats other classic dimensionality reduction techniques,according to the experimental results and statistical testing studies.

关键词： Dimensionality reduction metaheuristics optimization algorithm mayfly particle swarm optimizer feature selection

Pile end bearing capacity in rock mass using cavity expansion theory

维普期刊数据库评论

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 Rock Mechanics and Geotechnical Engineering 2020年第5期12卷 1103-1111页

作者： Haythem Gharsallaoui mustafa Jafari Alain Holeyman Department of Civil and Environmental Engineering(GCE) Institute of MechanicsMaterials and Civil engineering(iMMC)UniversitéCatholique de Louvain(UCLouvain)Louvain-la-NeuveBelgium

Much empiricism is involved in design of rock-socketed piles in rock *** light of this,an analytical solution based on the cavity expansion theory is proposed for calculating the ultimate bearing capacity at the tip of a pile embedded in rock masses obeying the Hoek-Brown failure *** ultimate end bearing capacity is evaluated by assuming that the pressure exerted at the boundaries of a pressure bulb immediately beneath the pile tip is equal to the limit pressure required to expand a spherical *** addition,a relationship is derived to predict the pile load-settlement *** demonstrate the applicability of the presented solution,the results of this study were compared to those of 91 field tests from technical *** the limitations,it is found that the end bearing resistance computed by the present work is in good agreement with the field test results.

关键词： Hoek-Brown failure criterion Spherical cavity Limit pressure End bearing capacity

Model-based cross section calculations on production of 43,34Sc,45Ti, 51Cr, 54Mn, and 55Fe radioisotopes

在线全文

学校读者我要写书评

暂无评论

Nuclear Science and Techniques 2018年第4期29卷 128-136页

作者： mustafa Yigit Department of Physics Aksaray University 68100 AksarayTurkey

A cross section database on excitation functions of reactions produced by charged particles is essential for many areas of nuclear research. Particularly, accurate knowledge on nuclear cross sections for the cyclotron production of radioisotopes is very important for nuclear medicine. In the present paper, the cross section calculations for the production of^(43),^(34)Sc,^(45)Ti,^(51)Cr,^(54)Mn, and^(55) Fe radioisotopes were carried out by the use of ALICE/ASH code using the Fermi gas model, Kataria Ramamurthy Fermi gas model, and superfluid nuclear model for nuclear level density. Thereby, these model calculations were compared with the available measured data.

关键词： Radioisotope production Scandium-44 Chromium-51 Superfluid nuclear model Cross section

Low-temperature electrochemical synthesis and characterization of ultrafine Y(OH)_3 and Y_2O_3 nanoparticles

在线全文

学校读者我要写书评

暂无评论

Journal of Rare Earths 2012年第3期30卷 236-240页

作者： mustafa AGHAZADEH Taher YOUSEFI Mehdi GHAEMI Laser and Optic Research School NSTRI P.O. Box 11365-8486 Tehran Iran Material Research School NSTRI P.O. Box 14395-836 Tehran Iran Department of Chemistry Science Faculty Golestan University P.O. Box 49138-15739 Gorgan Iran

Ultrafine Y（OH）3 nanoparticles were successfully deposited from an additive-free 0.005 mol/L YCl3 low-temperature bath on the steel cathode at the current density of 0.5 mA/cm2 and bath temperature of 10 oC. Heat treatment of the prepared Y（OH）3 nanoparticles at 600 oC in air led to the formation of Y2O3 nanoparticles. Thermal behavior and phase transformation during the heat treatment of Y（OH）3 were investigated by differential scanning calorimetry （DSC） and thermogramimetric analysis （TGA）. The morphologies, crystal structures and compositions of the prepared materials were examined by means of scanning and transmission electron microscopy （SEM and TEM） as well as X-ray diffraction （XRD） and FT-IR spectroscopy. The results showed that the prepared Y（OH）3 nanoparticles was essentially amorphous and composed of well dispersed ultrafine particles with size of 4 nm. After heat treatment, the obtained oxide product was well crystallized cubic phase of Y2O3 nanoparticles with the grain size of around 5 nm. It was concluded that low-temperature cathodic electrodeposition offered a facile and feasible way for preparation of ultrafine Y（OH）3 and Y2O3 nanoparticles.

关键词： Y(OH)3 Y2O3 cathodic electrodeposition heat treatment nanoparticles rare earths

Efects of Die Corner Radius and Temperature on the Formability of AA7075-T6 Alloy

在线全文

学校读者我要写书评

暂无评论

Acta Metallurgica Sinica(English Letters) 2013年第5期26卷 623-629页

作者： Hatice Evlen brahim Kad mustafa Ya sar Technology Faculty Karabuk University

This study focused on the formability of aluminium alloy（7075-T6） sheets through hydroforming route. Formability of these sheets was tested using a warm forming setup at three diferent temperatures and four diferent die corner radii. Forming limit diagrams（FLD） were generated by measuring the grids of the sheet formed. The results show that the forming limit of AA7075-T6 can be significantly improved when the blank was heated to 140–250℃. It was also observed that as the temperature increases above 140℃, dome height began to decrease. Also the results indicated that both the die corner radius and temperature have a significant efect on the stress-strain curve and warm forming of AA7075-T6 sheets. Thus, with the temperature increased from room temperature（RT） to 140℃, the flow stress decreased and the strain increased, hence, the formability is enhanced. However, further increase in temperature causes decreases the flow stress and strain. Similar changes of the flow curve were seen in die corner radius. Decreasing the die corner radius decreases the flow stress and increase the strain. Moreover, an equation was obtained by establishing correlations between the experimental parameters and their results. In this way, it became possible to make predictions.

关键词： Al-Zn-Mg-Cu Alloy Drawing process Formability Forming limit curve Deformation

The effect of Some Boron Derivatives on Kanamycin Resistance and Survival of *** and *** in Lake Water

在线全文

学校读者我要写书评

暂无评论

Biomedical and Environmental Sciences 2012年第4期25卷 476-482页

作者： Cihan DARCAN mustafa KAHYAOGLU Department of Biology Faculty of Art and SciencesDumlupinar University Faculty of Education Siirt University

Objective To study MIC value of 7 boron derivatives namely [Boric acid （H3BO3）, Anhydrous Borax （Na2B407）, Sodium Borate （NaBO2）, Diammonium Tetraborate （NH4）2B4O7, Sodium Perborate （NaBO3）, Boron Trioxide （B203）, Potassium Tetraborate （K2B407）] on E. coil and P. aeruginosa and their effects on survival of bacteria in lake water and resistance against kanamycin antibiotic. Methods MIC values of Boron derivatives and antibiotic were studied by broth microdilution method. The effect of boron derivatives on survival of bacteria in lake water were also determined with plate count. Results Sodium perborate was determined as the substances. Effectiveness increased as temperature most effective substance among the studied increased. E. coil was more affected from P. aeruginosa in 8 mg/mL sodium perborate concentration in lake water. Moreover, it was determined that MIC value of kanamycin antibiotic decreased 200 times by especially treating P. aeruginosa with sodium perborate in lake water. However, it can be stated that this change in resistance did not arise from microorganisms. Conclusion Sodium perborate solution can be used supportedly in kanamycin antibiotic applications for P. aeruginosa. Future studies are necessary to explore the relation between sodium perborate and kanamycin which is effective on P. aeruginosa in lake water.

关键词： Boron Lake water Kanamycin E. coli P. aeruginosa

A Model Predictive Control for Microgrids Considering Battery Aging

在线全文

学校读者我要写书评

暂无评论

Journal of Modern Power Systems and Clean Energy 2020年第2期8卷 296-304页

作者： Ugur Can Yilmaz mustafa Erdem Sezgin Murat Gol Department of Electrical and Electronics Engineering Middle East Technical UniversityAnkaraTurkey

The increasing number of distributed energy resources(DERs),advancing communication and computation technologies,and reliability concerns of the customers have caused an intense interest in the concept of *** DERs are the biggest motivation of the microgrids due to their intermittent generation characteristics,they constitute a risk for system *** storage systems(BSSs)stand as one of the most effective solutions for this reliability ***,the inappropriate use of BSS creates other operational problems in power *** order to deal with these concerns explicitly in microgrids,an optimized microgrid central controller(MGCC)is the key factor,which controls the realtime operation of a *** work proposes a model predictive control(MPC)based MGCC that will provide optimal control of the microgrid,considering economic and operational *** proposed system will minimize the energy cost of the microgrid by utilizing mixed-integer linear programming(MILP)assuming the presence of DERs and BSS as well as the bi-directional grid ***,the aging effect of BSS will be considered in the proposed optimization problem which will provide an up-to-date system *** proposed method is evaluated using real load and photovoltaic(PV)generation data.

关键词： Microgrid optimization battery storage model predictive control mixed-integer linear programming

A new approach for prediction of the wear loss of PTA surface coatings using artificial neural network and basic,kernel-based,and weighted extreme learning machine

在线全文

学校读者我要写书评

暂无评论

Friction 2020年第6期8卷 1102-1116页

作者： mustafa ULAS Osman ALTAY Turan GURGENC Cihan OZEL Department of the Software Engineering Firat UniversityElazig 23119Turkey Department of the Automotive Engineering Firat UniversityElazig 23119Turkey Department of the Mechanical Engineering Firat UniversityElazig 23119Turkey

Wear tests are essential in the design of parts intended to work in environments that subject a part to high *** tests involve high cost and lengthy experiments,and require special test *** use of machine learning algorithms for wear loss quantity predictions is a potentially effective means to eliminate the disadvantages of experimental methods such as cost,labor,and *** this study,wear loss data of AISI 1020 steel coated by using a plasma transfer arc welding(PTAW)method with FeCrC,FeW,and FeB powders mixed in different ratios were obtained experimentally by some of the researchers in our *** mechanical properties of the coating layers were detected by microhardness measurements and dry sliding wear *** wear tests were performed at three different loads(19.62,39.24,and 58.86 N)over a sliding distance of 900 *** this study,models have been developed by using four different machine learning algorithms(an artificial neural network(ANN),extreme learning machine(ELM),kernel-based extreme learning machine(KELM),and weighted extreme learning machine(WELM))on the data set obtained from the wear test *** R2 value was calculated as 0.9729 in the model designed with WELM,which obtained the best performance among the models evaluated.

关键词： wear loss prediction surface coating plasma transferred arc welding artificial neural network extreme learning machine