Pub Date : 2019-04-30DOI: 10.35377/SAUCIS.02.01.541366
P. Erdoğmuş
In this study, the recent medical studies with deep learning between 2009-2019 have been researched for observing the performance of deep learning on medical images, data and signal. Recent studies attained from Web of Science have been evaluated and selected according to the citation numbers. Studies have been listed as a table, according to the publication year, deep network structure, database used training and testing, evaluation metric and results. The studies have also been classified into the organs and the types of important diagnosis. The results have shown that the deep learning network structures, applied on fundus images, have attained nearly %99 percent accuracy. Although most of the studies between the range, made by Radiology and Nuclear Medicine Imaging, the accuracy of the results are 80-90% range. The current studies especially focus on automatic detection or classification of the tumor as benign or malign. Studies are mostly on medical CT, ultrasound, radiography and MRI images. This results show that computer aided medical diagnosis systems will be used in a very near future with fully performance.
本研究以2009-2019年深度学习医学研究为研究对象，观察深度学习在医学图像、数据和信号上的表现。根据引用数对Web of Science上获得的最新研究进行了评价和选择。已列出的研究成果按发表年份、深度网络结构、数据库使用的训练和测试、评价指标和结果分列。研究还将其分类为器官类型和重要诊断。结果表明，深度学习网络结构在眼底图像上的应用达到了近99%的准确率。虽然大多数研究的范围介于放射学和核医学成像之间，但结果的准确性都在80-90%的范围内。目前的研究主要集中在肿瘤的良性或恶性的自动检测或分类上。研究主要集中在医学CT、超声、x线摄影和MRI图像上。这一结果表明，计算机辅助医疗诊断系统将在不久的将来得到全面应用。
{"title":"Deep Learning Performance on Medical Image, Data and Signals","authors":"P. Erdoğmuş","doi":"10.35377/SAUCIS.02.01.541366","DOIUrl":"https://doi.org/10.35377/SAUCIS.02.01.541366","url":null,"abstract":"In this study, the recent medical studies with deep learning between 2009-2019 have been researched for observing the performance of deep learning on medical images, data and signal. Recent studies attained from Web of Science have been evaluated and selected according to the citation numbers. Studies have been listed as a table, according to the publication year, deep network structure, database used training and testing, evaluation metric and results. The studies have also been classified into the organs and the types of important diagnosis. The results have shown that the deep learning network structures, applied on fundus images, have attained nearly %99 percent accuracy. Although most of the studies between the range, made by Radiology and Nuclear Medicine Imaging, the accuracy of the results are 80-90% range. The current studies especially focus on automatic detection or classification of the tumor as benign or malign. Studies are mostly on medical CT, ultrasound, radiography and MRI images. This results show that computer aided medical diagnosis systems will be used in a very near future with fully performance.","PeriodicalId":257636,"journal":{"name":"Sakarya University Journal of Computer and Information Sciences","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121192526","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-04-30DOI: 10.35377/SAUCIS.02.01.538249
Murat Uçar, Emine Uçar
Chest X-Rays are most accessible medical imaging technique for diagnosing abnormalities in the heart and lung area. Automatically detecting these abnormalities with high accuracy could greatly enhance real world diagnosis processes. In this study we aim to improve the accuracy of convolutional deep learning by using Laplacian of Gaussian filtering. In this study, we have used the publicly available Japanese Society of Radiological Technology dataset including 247 radiograms. For improving the performance of convolutional neural networks we used LoG filter and also we used an advanced version of AlexNet and GoogleNet to compare our results. The results indicated that, convolutional neural network with Laplacian of Gaussian filter model produced the best results with 82.43% accuracy. Convolutional neural network with Laplacian of Gaussian filter model is followed by convolutional neural network with an accuracy of 72.97%, followed by GoogleNet model with an accuracy of 68.92%. Out of the four model types utilized, the AlexNet model produced the lowest accuracy with a value of 64.86%. The results obtained here demonstrate that the pre-processing technique like Laplacian of Gaussian filter can improve the accuracy.
{"title":"Computer-Aided Detection of Lung Nodules in Chest X-Rays using Deep Convolutional Neural Networks","authors":"Murat Uçar, Emine Uçar","doi":"10.35377/SAUCIS.02.01.538249","DOIUrl":"https://doi.org/10.35377/SAUCIS.02.01.538249","url":null,"abstract":"Chest X-Rays are most accessible medical imaging technique for diagnosing abnormalities in the heart and lung area. Automatically detecting these abnormalities with high accuracy could greatly enhance real world diagnosis processes. In this study we aim to improve the accuracy of convolutional deep learning by using Laplacian of Gaussian filtering. In this study, we have used the publicly available Japanese Society of Radiological Technology dataset including 247 radiograms. For improving the performance of convolutional neural networks we used LoG filter and also we used an advanced version of AlexNet and GoogleNet to compare our results. The results indicated that, convolutional neural network with Laplacian of Gaussian filter model produced the best results with 82.43% accuracy. Convolutional neural network with Laplacian of Gaussian filter model is followed by convolutional neural network with an accuracy of 72.97%, followed by GoogleNet model with an accuracy of 68.92%. Out of the four model types utilized, the AlexNet model produced the lowest accuracy with a value of 64.86%. The results obtained here demonstrate that the pre-processing technique like Laplacian of Gaussian filter can improve the accuracy.","PeriodicalId":257636,"journal":{"name":"Sakarya University Journal of Computer and Information Sciences","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127597038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-04-30DOI: 10.35377/SAUCIS.02.01.517930
G. Gündüz, İ. H. Cedimoğlu
Buyuk verilerin buyuk hizlarla islendigi cagimizda milyarlarca veriden farkli parametreler cikararak cesitli problemlerin cozumune kolaylik getirmek icin derin ogrenme algoritmalari kullanilmaktadir. Bu calismada, mevcut veri setlerinde bulunan kadin, erkek, yasli, genc, cocuk, bebek fotograflarinin derin ogrenme algoritmalari ile cinsiyetlerini tespit etmek amaclanmistir. Bu tahminleme algoritmasini gerceklestirmek icin cesitli derin ogrenme kutuphanelerinden faydalanilmis ve derin ogrenme modellerinden Alex Net ve VGG-16 ile yeni gelistirilen bir modelin diger modellerle kiyaslanmasi yapilmistir. Uygulamada kullanilan veri seti, kadin ve erkek fotograflarindan olusturulmustur ve her fotograf, kisi cinsiyetine ve yasina gore etiketlendirilmistir. Bu veri seti, 3170 egitim verisi ve 318 test verisi icermektedir. Calistirilan uc farkli model sonuclari karsilastirilmistir. Makalede, derin ogrenme algoritmalarini kullanarak cinsiyet tahmini yapilmasi ayrintili bir sekilde incelenmis ve yapilacak olan literatur calismalarina yol gosterilmesi, katki saglanmasi hedeflenmistir.
{"title":"Derin Öğrenme Algoritmalarını Kullanarak Görüntüden Cinsiyet Tahmini","authors":"G. Gündüz, İ. H. Cedimoğlu","doi":"10.35377/SAUCIS.02.01.517930","DOIUrl":"https://doi.org/10.35377/SAUCIS.02.01.517930","url":null,"abstract":"Buyuk verilerin buyuk hizlarla islendigi cagimizda milyarlarca veriden farkli parametreler cikararak cesitli problemlerin cozumune kolaylik getirmek icin derin ogrenme algoritmalari kullanilmaktadir. Bu calismada, mevcut veri setlerinde bulunan kadin, erkek, yasli, genc, cocuk, bebek fotograflarinin derin ogrenme algoritmalari ile cinsiyetlerini tespit etmek amaclanmistir. Bu tahminleme algoritmasini gerceklestirmek icin cesitli derin ogrenme kutuphanelerinden faydalanilmis ve derin ogrenme modellerinden Alex Net ve VGG-16 ile yeni gelistirilen bir modelin diger modellerle kiyaslanmasi yapilmistir. Uygulamada kullanilan veri seti, kadin ve erkek fotograflarindan olusturulmustur ve her fotograf, kisi cinsiyetine ve yasina gore etiketlendirilmistir. Bu veri seti, 3170 egitim verisi ve 318 test verisi icermektedir. Calistirilan uc farkli model sonuclari karsilastirilmistir. Makalede, derin ogrenme algoritmalarini kullanarak cinsiyet tahmini yapilmasi ayrintili bir sekilde incelenmis ve yapilacak olan literatur calismalarina yol gosterilmesi, katki saglanmasi hedeflenmistir.","PeriodicalId":257636,"journal":{"name":"Sakarya University Journal of Computer and Information Sciences","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121619184","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-12-18DOI: 10.35377/saucis.01.03.475565
P. Erdoğmuş
The aim of this study is to bring a new perspective for the solutions of non-linear equation systems. So this study handles the non-linear equation systems as a constrained optimization problem, while generally is handled unconstrained optimization problem or multi objective optimization problem. The object is to minimize the sum of the squares of nonlinear equations under the nonlinear equality constraints. A recently developed heuristic optimization algorithm called Grey Wolf Optimizer (GWO) is proposed for the solution of nonlinear equation systems. Two results were obtained. Firstly, it has been seen that GWO can be an alternative solution technique for the solution of nonlinear equation systems. Secondly, modelling the systems of nonlinear equations as constrained optimization gives better results.
{"title":"A New Solution Approach for Non-Linear Equation Systems with Grey Wolf Optimizer","authors":"P. Erdoğmuş","doi":"10.35377/saucis.01.03.475565","DOIUrl":"https://doi.org/10.35377/saucis.01.03.475565","url":null,"abstract":"The aim of this study is to bring a new perspective for the solutions of non-linear equation systems. So this study handles the non-linear equation systems as a constrained optimization problem, while generally is handled unconstrained optimization problem or multi objective optimization problem. The object is to minimize the sum of the squares of nonlinear equations under the nonlinear equality constraints. A recently developed heuristic optimization algorithm called Grey Wolf Optimizer (GWO) is proposed for the solution of nonlinear equation systems. Two results were obtained. Firstly, it has been seen that GWO can be an alternative solution technique for the solution of nonlinear equation systems. Secondly, modelling the systems of nonlinear equations as constrained optimization gives better results.","PeriodicalId":257636,"journal":{"name":"Sakarya University Journal of Computer and Information Sciences","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127693665","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-12-18DOI: 10.35377/saucis.01.03.468380
M. Ozcan, Mehmet Yildirim
Capital investment cost is the major obstacle to the increasing share of electricity from renewable energy sources (RES-E). Therefore, RES-E incentive mechanisms are incorporated into markets to compensate cost-related barriers and to increase RES-E deployment rate. In this study, t he impact of direct capital investment subsidy on RES-E in generation expansion planning (GEP) has been analyzed and deployment rates of renewable power plants have been defined. The effect of current subsidy mechanisms on the installed power capacity of various sources has also been analyzed and policy recommendations have been put forth in the light of the characteristics of Turkey’s current subsidization mechanism and its outcomes. Genetic algorithm was applied to solve the GEP problem. The share of non-hydro renewable power plants for future additions in overall installed power was determined as 9.45% without the proposed incentive, while it was estimated to rise to 13.65% when it was promoted by direct capital investment subsidy of 50%. The deployment rates of renewable power plants are expected to grow as the imported coal share in total installed power is expected to decline after applying the proposed subsidy.
{"title":"The Impact of Capital Subsidy Incentive on Renewable Energy Deployment in Long-Term Power Generation Expansion Planning","authors":"M. Ozcan, Mehmet Yildirim","doi":"10.35377/saucis.01.03.468380","DOIUrl":"https://doi.org/10.35377/saucis.01.03.468380","url":null,"abstract":"Capital investment cost is the major obstacle to the increasing share of electricity from renewable energy sources (RES-E). Therefore, RES-E incentive mechanisms are incorporated into markets to compensate cost-related barriers and to increase RES-E deployment rate. In this study, t he impact of direct capital investment subsidy on RES-E in generation expansion planning (GEP) has been analyzed and deployment rates of renewable power plants have been defined. The effect of current subsidy mechanisms on the installed power capacity of various sources has also been analyzed and policy recommendations have been put forth in the light of the characteristics of Turkey’s current subsidization mechanism and its outcomes. Genetic algorithm was applied to solve the GEP problem. The share of non-hydro renewable power plants for future additions in overall installed power was determined as 9.45% without the proposed incentive, while it was estimated to rise to 13.65% when it was promoted by direct capital investment subsidy of 50%. The deployment rates of renewable power plants are expected to grow as the imported coal share in total installed power is expected to decline after applying the proposed subsidy.","PeriodicalId":257636,"journal":{"name":"Sakarya University Journal of Computer and Information Sciences","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121915916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-08-01DOI: 10.35377/SAUCIS.01.02.443999
M. Tosun, Mustafa Erginli, Ömer Kasim, Burak Uğraş, Şems Tanrıverdi, Tayfun Kavak
Son yillarda teknolojinin gelismesi sonucunda beyin bilgisayar arayuzu ile ilgili calismalar artmistir. Beyin Bilgisayar Arayuzu (Brain Computer Interface-BCI) yontemlerinde Elektroansefalogram (Electroencephalogram-EEG) isaretleri yaygin olarak kullanilmaktadir. EEG verileri kullanilarak fiziksel hareketle hareketin hayali siniflandirilabilmektedir. Bu calismada sag elini kullanan ve hastalik durumu olmayan 21 yasindaki bir erkege ait EEG verileri kullanilmistir. Bu verilerin bir kismi sol ve sag elin ileri-geri hareketi esnasinda kaydedilen EEG verileridir. Diger veriler ise herhangi bir fiziksel hareket yapilmadan, hareketin hayal edilmesi durumu ile ilgili kayitlardir. Welch metodu kullanilarak EEG verilerinin 1-48 Hz arasindaki frekanslarinin guc yogunluklari hesaplanmistir. Elde edilen veri setleri tasarlanan Geri Yayilimli Sinir Agi (Backpropagation Neural Network- BPNN) ‘ na uygulanmistir. Agin egitimi sonunda 4.6731x10-23 ortalama karesel hata (Mean Squared Error -MSE) degerine ulasilmistir. Hayal ile hareket verilerinden olusan test veri seti egitilen aga uygulandiginda, hayal ile hareket verileri % 99.9975 dogrulukla siniflandirilmistir.
{"title":"EEG Verileri Kullanılarak Fiziksel El Hareketleri ve Bu Hareketlerin Hayalinin Yapay Sinir Ağları İle Sınıflandırılması","authors":"M. Tosun, Mustafa Erginli, Ömer Kasim, Burak Uğraş, Şems Tanrıverdi, Tayfun Kavak","doi":"10.35377/SAUCIS.01.02.443999","DOIUrl":"https://doi.org/10.35377/SAUCIS.01.02.443999","url":null,"abstract":"Son yillarda teknolojinin gelismesi sonucunda beyin bilgisayar arayuzu ile ilgili calismalar artmistir. Beyin Bilgisayar Arayuzu (Brain Computer Interface-BCI) yontemlerinde Elektroansefalogram (Electroencephalogram-EEG) isaretleri yaygin olarak kullanilmaktadir. EEG verileri kullanilarak fiziksel hareketle hareketin hayali siniflandirilabilmektedir. Bu calismada sag elini kullanan ve hastalik durumu olmayan 21 yasindaki bir erkege ait EEG verileri kullanilmistir. Bu verilerin bir kismi sol ve sag elin ileri-geri hareketi esnasinda kaydedilen EEG verileridir. Diger veriler ise herhangi bir fiziksel hareket yapilmadan, hareketin hayal edilmesi durumu ile ilgili kayitlardir. Welch metodu kullanilarak EEG verilerinin 1-48 Hz arasindaki frekanslarinin guc yogunluklari hesaplanmistir. Elde edilen veri setleri tasarlanan Geri Yayilimli Sinir Agi (Backpropagation Neural Network- BPNN) ‘ na uygulanmistir. Agin egitimi sonunda 4.6731x10-23 ortalama karesel hata (Mean Squared Error -MSE) degerine ulasilmistir. Hayal ile hareket verilerinden olusan test veri seti egitilen aga uygulandiginda, hayal ile hareket verileri % 99.9975 dogrulukla siniflandirilmistir.","PeriodicalId":257636,"journal":{"name":"Sakarya University Journal of Computer and Information Sciences","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133175644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-08-01DOI: 10.35377/SAUCIS.01.02.447931
Orhan Er, Cemil Altin
Gunumuzde bircok arac otonom olarak kontrol edilmek istenmektedir. Bu calismalarin en onemli uygulama alanlarinin basinda askeri ve saglik alanlari olmasi munasebeti oncelik arz etmektedir. Bunun amac icin simulasyon ortamlarinin gelistirilmesi hem zaman hem de ekonomik olarak daha elverisli araclar ve imkanlar sunmaktadir. Buradan hareketle gelistirilen bir 3D sanal gerceklik yazilimi sayesinde farkli kullanicidan alinan hem EEG hem de EMG sinyalleri paralel olarak MATLAB ortamina aktarilmis olup bu sinyaller siniflandirilarak sanal oyuna komut olarak aktarilmis ve insansiz hava araci uzaktan yonlendirile bilinmistir. Sistemin basarisini test etmek icin farkli denekler uzerinde olusturulan farkli rotalar kullanilarak performans analizleri yapilmistir. Bu sayede donanimdan bagimsiz olarak insandan elde edilen sinyaller ile sanal gerceklik ortami butunlestirilmis ve yapilan deneyler sonucunda basarili bir sekilde kullanilabilecegi sonucuna varilmistir.
{"title":"İnsansız Hava Araçlarının (İHA) Sanal Gerçeklik Yazılımı ile Modellenmesi ve Farklı Kullanıcılar için Performans Analizleri","authors":"Orhan Er, Cemil Altin","doi":"10.35377/SAUCIS.01.02.447931","DOIUrl":"https://doi.org/10.35377/SAUCIS.01.02.447931","url":null,"abstract":"Gunumuzde bircok arac otonom olarak kontrol edilmek istenmektedir. Bu calismalarin en onemli uygulama alanlarinin basinda askeri ve saglik alanlari olmasi munasebeti oncelik arz etmektedir. Bunun amac icin simulasyon ortamlarinin gelistirilmesi hem zaman hem de ekonomik olarak daha elverisli araclar ve imkanlar sunmaktadir. Buradan hareketle gelistirilen bir 3D sanal gerceklik yazilimi sayesinde farkli kullanicidan alinan hem EEG hem de EMG sinyalleri paralel olarak MATLAB ortamina aktarilmis olup bu sinyaller siniflandirilarak sanal oyuna komut olarak aktarilmis ve insansiz hava araci uzaktan yonlendirile bilinmistir. Sistemin basarisini test etmek icin farkli denekler uzerinde olusturulan farkli rotalar kullanilarak performans analizleri yapilmistir. Bu sayede donanimdan bagimsiz olarak insandan elde edilen sinyaller ile sanal gerceklik ortami butunlestirilmis ve yapilan deneyler sonucunda basarili bir sekilde kullanilabilecegi sonucuna varilmistir.","PeriodicalId":257636,"journal":{"name":"Sakarya University Journal of Computer and Information Sciences","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132047001","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.35377/saucis.01.03.496233
A. Dalcalı, Onursal Çetin, C. Ocak, Feyzullah Temurtaş
The force on the projectile in the electromagnetic launchers varies according to the the excitation value and the position of the projectile in the winding. In this study, 3D model of coil and projectile used in electromagnetic launchers have been created and analyzed by finite element method. The force characteristic on the projectile has been obtained by changing the excitation value of the winding and the position of the projectile using parametric solution method. In finite element analysis, more accurate analysis can be performed by defining smaller solution steps. However, the analysis time is prolonged due to the increase in the number of variables. Taking into consideration the duration of analysis, the force prediction has been carried out using multilayer neural network models consisting of one hidden layer and two hidden layers. Successful results have been obtained in the force prediction studies with multilayer neural networks.
{"title":"Prediction of the Force on a Projectile in an Electromagnetic Launcher Coil with Multilayer Neural Network","authors":"A. Dalcalı, Onursal Çetin, C. Ocak, Feyzullah Temurtaş","doi":"10.35377/saucis.01.03.496233","DOIUrl":"https://doi.org/10.35377/saucis.01.03.496233","url":null,"abstract":"The force on the projectile in the electromagnetic launchers varies according to the the excitation value and the position of the projectile in the winding. In this study, 3D model of coil and projectile used in electromagnetic launchers have been created and analyzed by finite element method. The force characteristic on the projectile has been obtained by changing the excitation value of the winding and the position of the projectile using parametric solution method. In finite element analysis, more accurate analysis can be performed by defining smaller solution steps. However, the analysis time is prolonged due to the increase in the number of variables. Taking into consideration the duration of analysis, the force prediction has been carried out using multilayer neural network models consisting of one hidden layer and two hidden layers. Successful results have been obtained in the force prediction studies with multilayer neural networks.","PeriodicalId":257636,"journal":{"name":"Sakarya University Journal of Computer and Information Sciences","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129522095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：