2018 3rd International Conference on Computer Science and Engineering (UBMK)最新文献

Variational Autoencoded Compositional Pattern Generative Adversarial Network for Handwritten Super Resolution Image Generation 用于手写超分辨率图像生成的变分自编码组合模式生成对抗网络

2018 3rd International Conference on Computer Science and Engineering (UBMK) Pub Date : 2018-09-01 DOI: 10.1109/UBMK.2018.8566539

Caren Güzel Turhan, H. Ş. Bilge

{"title":"Variational Autoencoded Compositional Pattern Generative Adversarial Network for Handwritten Super Resolution Image Generation","authors":"Caren Güzel Turhan, H. Ş. Bilge","doi":"10.1109/UBMK.2018.8566539","DOIUrl":"https://doi.org/10.1109/UBMK.2018.8566539","url":null,"abstract":"Since generative adversarial training has been decleared as one of the most exciting topics of the last 10 years by the pioneers, many researchers have focused on the Generative Adversarial Network (GAN) in their studies. On the otherhand, Variational Autoencoders (VAE) had gain autoencoders' popularity back. Due to some restrictions of GAN models and their lack of inference mechanism, hybrid models of GAN and VAE have emerged for image generation problem in nowadays. With the influence of these views and improvements, we have focused on addressing not only generating synthetic handwritten images but also their high-resolution version. For these tasks, Compositional Pattern Producing Networks (CPPN), VAE and GAN models are combined inspired by an existing model with some modification of its objective function. With this model, the idea behind the inspired study for generating high-resolution images are combined with the feature-wise reconstruction objective of a VAE/GAN hybrid model instead of pixel-like reconstruction approach of traditional VAE. For evaluating the model efficiency, our VAE/CPGAN model is compared with its basis models (GAN, VAE and VAE/GAN) and inspired model accoording to inception score. In this study, it is clearly seen that the proposed model is able to converge much faster than compared models for modeling the underlying distribution of handwritten image data.","PeriodicalId":293249,"journal":{"name":"2018 3rd International Conference on Computer Science and Engineering (UBMK)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117153058","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}

引用次数: 5

Classification of Brain Responses to the Various Spice Odors 大脑对各种香料气味反应的分类

2018 3rd International Conference on Computer Science and Engineering (UBMK) Pub Date : 2018-09-01 DOI: 10.1109/UBMK.2018.8566558

Önder Aydemir, Hilal Altun, Ebru Ergün

引用次数: 0

UBMK 2018 Copyright Page UBMK 2018版权页面

2018 3rd International Conference on Computer Science and Engineering (UBMK) Pub Date : 2018-09-01 DOI: 10.1109/ubmk.2018.8566492

引用次数: 0

Survey of Cross Device Matching Approaches with a Case Study on a Novel Database 跨设备匹配方法综述——以新型数据库为例

2018 3rd International Conference on Computer Science and Engineering (UBMK) Pub Date : 2018-09-01 DOI: 10.1109/UBMK.2018.8566307

Can Karakaya, Hakan Toğuç, R. Kuzu, A. H. Büyüklü

引用次数: 5

An Undergraduate Curriculum for Deep Learning 深度学习本科课程

2018 3rd International Conference on Computer Science and Engineering (UBMK) Pub Date : 2018-09-01 DOI: 10.1109/UBMK.2018.8566575

Guzin Tirkes, C. Ekin, Gökhan engul, Atila Bostan, M. Karakaya

引用次数: 2

Sanal Zorbalik Iceren Sosyal Medya Mesajlarinim Tespiti [Not available in English]

2018 3rd International Conference on Computer Science and Engineering (UBMK) Pub Date : 2018-09-01 DOI: 10.1109/ubmk.2018.8566529

引用次数: 1

Identifing of Alphanumerical Codes in Promotional products by Using of Deep Neural Network 利用深度神经网络识别促销商品中的字母数字代码

2018 3rd International Conference on Computer Science and Engineering (UBMK) Pub Date : 2018-09-01 DOI: 10.1109/UBMK.2018.8566404

Çağrı Gider, S. Albayrak

{"title":"Identifing of Alphanumerical Codes in Promotional products by Using of Deep Neural Network","authors":"Çağrı Gider, S. Albayrak","doi":"10.1109/UBMK.2018.8566404","DOIUrl":"https://doi.org/10.1109/UBMK.2018.8566404","url":null,"abstract":"Using the codes in promotional products was often considered a waste of time. For this reason most codes are not used and promotions do not show sufficient effectiveness. The theme of the project was to identify the promotional code on the product using artificial neural networks and deep learning methods. Bu projede, karakterlerin tanımlanması için, Keras ve Tensorflow kütüphaneleri kullanılarak Convolutional Neural Network (CNN) yapısında bir yapay sinir ağı kullanılmıştır. The project was created in the direction of the Optical Character Recognition application (OCR) requirement that emerged in a software for a customer company in adesso Turkey. The client company’s requirement is that a program to recognize characters with a special font. A mobile application has been implemented in the iOS environment to increase the efficiency and ease of implementation of the project. The OCR (Optical Character Recognition) library created in the project has been converted to Objective-C. Then the Objective-C library used in iOS program to use the Python model. In the system where the number of samples used in the training set is 7091, the model accuracy for 1200 test data is 99.7%.","PeriodicalId":293249,"journal":{"name":"2018 3rd International Conference on Computer Science and Engineering (UBMK)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128508348","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}

引用次数: 0

Determining Big Data Complexity Using Hierarchical Structure of Groups and Clusters in Decision Tree 利用决策树中的群和聚类层次结构确定大数据复杂性

2018 3rd International Conference on Computer Science and Engineering (UBMK) Pub Date : 2018-09-01 DOI: 10.1109/UBMK.2018.8566398

H. Erol, Recep Erol

引用次数: 1

Classification of Breast Cancer Images by Using of Convolutional Attribute of ANN 基于神经网络卷积属性的乳腺癌图像分类

2018 3rd International Conference on Computer Science and Engineering (UBMK) Pub Date : 2018-09-01 DOI: 10.1109/UBMK.2018.8566624

Fatih Özyurt, Mesut Toğaçar, E. Avci, Derya Avcı

引用次数: 1

The Effect of Nonlinear Wavelet Transform Based De-noising in Sperm Abnormality Classification 基于非线性小波变换的去噪方法在精子异常分类中的应用

2018 3rd International Conference on Computer Science and Engineering (UBMK) Pub Date : 2018-09-01 DOI: 10.1109/UBMK.2018.8566489

Hamza Osman Ilhan, I. O. Sigirci, Gorkem Serbes, N. Aydin

{"title":"The Effect of Nonlinear Wavelet Transform Based De-noising in Sperm Abnormality Classification","authors":"Hamza Osman Ilhan, I. O. Sigirci, Gorkem Serbes, N. Aydin","doi":"10.1109/UBMK.2018.8566489","DOIUrl":"https://doi.org/10.1109/UBMK.2018.8566489","url":null,"abstract":"Morphological sperm analysis is one of the crucial steps in the male-based infertility diagnosis. Currently, analyses are mostly performed by visual assessment technique because of its easy implementation, quick response and cheapness properties. However, the expertise level of the observer has great importance in the visual assessment technique. Results can be different and misleading according to the observer analysis capability. Therefore, human factor should be eliminated and the analysis should be performed by an objective computerized system. In this study, we used descriptor-based features in the classification of the normal, abnormal and non-sperm patches. Additionally, we investigated the effects of two de-noising techniques in the classification performance due to the presence of noises in the patches. Results indicate that the de-noising processes have great importance in the classification performance. Moreover, a wavelet based adaptive de-noising approach dramatically increased the performance to 86% with support vector machine polynomial kernel classifier.","PeriodicalId":293249,"journal":{"name":"2018 3rd International Conference on Computer Science and Engineering (UBMK)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132017730","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}

引用次数: 5