{"title":"On reducing space complexity of fuzzy neighborhood based clustering algorithms","authors":"C. Atilgan, E. Nasibov","doi":"10.1109/UBMK.2017.8093467","DOIUrl":"https://doi.org/10.1109/UBMK.2017.8093467","url":null,"abstract":"Using fuzzy neighborhood relations in density-based clustering, like in Fuzzy Joint Points (FJP) algorithm, yields more robust and autonomous algorithms. Even though the fuzzy neighborhood based clustering methods are proven to be fast enough, such that tens of thousands of data can be handled under a second, the space complexity is still a limiting factor. In this study, a transformed FJP algorithm with low space complexity is proposed.","PeriodicalId":201903,"journal":{"name":"2017 International Conference on Computer Science and Engineering (UBMK)","volume":"161 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125232258","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}
{"title":"Correlation analysis of egg gender determination data","authors":"Ünsal Gökdağ, Esra Çinar","doi":"10.1109/UBMK.2017.8093448","DOIUrl":"https://doi.org/10.1109/UBMK.2017.8093448","url":null,"abstract":"“EGGSORT: Avian Egg Gender Classification in Early Stages of Incubation” is an R&D project supported by TÜBİTAK and aims to find differentiating information on avian egg gender. Current study is about measuring performance of spectroscopy differentiation methods on egg white and egg yolk and the effect of eggshell on these measurements. Preprocessing methods and correlation measurements between preprocessed results are presented in this article. The proposed method shows significant success in differentiating egg white and egg yolk but failed to show enough information between egg white and egg yolk under eggshell presence.","PeriodicalId":201903,"journal":{"name":"2017 International Conference on Computer Science and Engineering (UBMK)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125562821","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}
Buket Erşahin, Özlem Aktaş, Deniz Kılınç, Ceyhun Akyol
{"title":"Twitter fake account detection","authors":"Buket Erşahin, Özlem Aktaş, Deniz Kılınç, Ceyhun Akyol","doi":"10.1109/UBMK.2017.8093420","DOIUrl":"https://doi.org/10.1109/UBMK.2017.8093420","url":null,"abstract":"Social networking sites such as Twitter and Facebook attracts millions of users across the world and their interaction with social networking has affected their life. This popularity in social networking has led to different problems including the possibility of exposing incorrect information to their users through fake accounts which results to the spread of malicious content. This situation can result to a huge damage in the real world to the society. In our study, we present a classification method for detecting the fake accounts on Twitter. We have preprocessed our dataset using a supervised discretization technique named Entropy Minimization Discretization (EMD) on numerical features and analyzed the results of the Naïve Bayes algorithm.","PeriodicalId":201903,"journal":{"name":"2017 International Conference on Computer Science and Engineering (UBMK)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126219661","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}
{"title":"An experimental comparison of software effort estimation methods of ORM based 4GL software applications","authors":"Muhammed Tanriverdi, Ö. Ö. Tanriöver","doi":"10.1109/UBMK.2017.8093382","DOIUrl":"https://doi.org/10.1109/UBMK.2017.8093382","url":null,"abstract":"Software effort estimation is important in planning and project budgeting for both developers and customers. Although there are many popular effort estimation techniques which have gone through significant developments in the past, software development methodologies and technologies are developing rapidly as a result of the need to improve the existing models. To this end, this paper compares and analyses three popular methods, namely COCOMO II, COSYSMO and Advanced COSTMO-4GL when used with ORM based fourth-generation-language software applications. COSYSMO is found to give better estimation than COSTMO-4GL for both pure 4GL and with ORM components included.","PeriodicalId":201903,"journal":{"name":"2017 International Conference on Computer Science and Engineering (UBMK)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126063180","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}
{"title":"Remote controllable electronic signboard","authors":"Sabri Gültekin, C. Karakuzu","doi":"10.1109/UBMK.2017.8093561","DOIUrl":"https://doi.org/10.1109/UBMK.2017.8093561","url":null,"abstract":"In this study, an embedded system has been developed to provide remote control of dot matrix signboards widely used nowadays. With this developed system, it is possible to control and use one or more signboards anywhere. The developed electronic signboard can be in the desired dimensions by connecting the unit modules in many different forms thanks to the electronic circuit realized for the dot matrix display. The electronic circuit of the unit modules can be controlled with Raspberry pi and Tinker mini computers. In addition, three different application softwares (desktop, mobile and web) have been developed to control the electronic signboard by both desktop computer and mobile devices with Android or IOS operating systems. The system is executed by realizing the prototype.","PeriodicalId":201903,"journal":{"name":"2017 International Conference on Computer Science and Engineering (UBMK)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129218523","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}
{"title":"Sentiment classification of social media data for telecommunication companies in Turkey","authors":"Ismail Iseri, Ömer Faruk Atasoy, Harun Alçiçek","doi":"10.1109/UBMK.2017.8093419","DOIUrl":"https://doi.org/10.1109/UBMK.2017.8093419","url":null,"abstract":"In recent years, the huge amount of data that has emerged in the world as a result of a very rapid increase in digital data has brought about the storage, processing and analysis of data into business intelligence solutions. One of the biggest sources of this large-scale data that has emerged and continues to grow is the data produced from social media tools. The average daily amount generated by Twitter social media is around 7 terabytes and this value increases day by day. Twitter is a social media tool that users express their feelings and thoughts about commercial companies, about social events, or sharing in any subject. In this study, a sentiment classification study was carried out on the tweets that were taken in the two selected date ranges of two major telecommunication companies serving in Turkey. The feature vectors obtained by two different feature extraction methods from the tweets where the users shared are classified as “positive / negative” by using KNN classifier. In this way, Twitter users' thoughts and satisfaction about three telecommunication companies in Turkey were determined in two selected dates.","PeriodicalId":201903,"journal":{"name":"2017 International Conference on Computer Science and Engineering (UBMK)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129519943","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}
{"title":"Cloud-based E-health systems: Security and privacy challenges and solutions","authors":"M. Dawoud, D. Altilar","doi":"10.1109/UBMK.2017.8093549","DOIUrl":"https://doi.org/10.1109/UBMK.2017.8093549","url":null,"abstract":"For a long time, the sensitivity and criticality of data storage, processing, and transmission have hindered the wide utilization of IT and networks in the health care systems. Recently, the high availability, reachability, reliability, efficiency, usability and automation provided by the different cloud computing models paved the way to integrate the e-health systems with these cloud services to improve their efficiencies. However, security and privacy still constitute the main concern in the current models of cloud computing for cloud-based e-health care systems. The convergence and integration of different services with different capabilities and ownerships means high risks on security and privacy of the data, which are not negotiable in e-health care systems. There have been many proposals to solve some of these concerns specifically or among other protocols. In this paper we define differents cenarios for the integration of the e-health systems with the cloud computing systems. We also define the security and privacy requirements for these scenarios as well as the guidelines of the proposed solutions for the presented security and privacy problems.","PeriodicalId":201903,"journal":{"name":"2017 International Conference on Computer Science and Engineering (UBMK)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129733009","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}
{"title":"Image classification with caffe deep learning framework","authors":"Emine Cengil, A. Cinar, E. Özbay","doi":"10.1109/UBMK.2017.8093433","DOIUrl":"https://doi.org/10.1109/UBMK.2017.8093433","url":null,"abstract":"Image classification is one of the important problems in the field of machine learning. Deep learning architectures are used in many machine learning applications such as image classification and object detection. The ability to manipulate large image clusters and implement them quickly makes deep learning a popular method in classifying images. This study points out the success of the convolutional neural networks which is the architecture of deep learning, in solving image classification problems. In the study, the convolutional neural network model of the winner of ilsvrc12 competition is implemented. The method distinguishes 1.2 million images with 1000 categories in success. The application is performed with the caffe library, and the image classification process is employed. In the application that uses the speed facility provided by GPU, the test operation is performed by using the images in Caltech-101 dataset.","PeriodicalId":201903,"journal":{"name":"2017 International Conference on Computer Science and Engineering (UBMK)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130074220","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}
{"title":"Prediction of heart disease using neural network","authors":"Tülay Karayılan, Özkan Kiliç","doi":"10.1109/UBMK.2017.8093512","DOIUrl":"https://doi.org/10.1109/UBMK.2017.8093512","url":null,"abstract":"Heart disease is a deadly disease that large population of people around the world suffers from. When considering death rates and large number of people who suffers from heart disease, it is revealed how important early diagnosis of heart disease. Traditional way of diagnosis is not sufficient for such an illness. Developing a medical diagnosis system based on machine learning for prediction of heart disease provides more accurate diagnosis than traditional way. In this paper, a heart disease prediction system which uses artificial neural network backpropagation algorithm is proposed. 13 clinical features were used as input for the neural network and then the neural network was trained with backpropagation algorithm to predict absence or presence of heart disease with accuracy of 95%.","PeriodicalId":201903,"journal":{"name":"2017 International Conference on Computer Science and Engineering (UBMK)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128869819","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}
{"title":"The effect of genetic algorithm parameters in the solution of the course timetable problem","authors":"R. Çolak, T. Yi̇ği̇t","doi":"10.1109/UBMK.2017.8093488","DOIUrl":"https://doi.org/10.1109/UBMK.2017.8093488","url":null,"abstract":"Course timetabiling is a process that must be done at the beginning of the education period in all educational institutions. The purpose of the timetabling is to bring together classrooms, lectures, students and lecturers at the same time without any conflicts. Course timetabiling is a difficult problem to solve when classroom constraints, teaching staff preferences, course restrictions are taken into consideration. With a deterministic approach, it can take a lot of time to try all the possibilities and reach a definite solution, and in cases where there are a lot of constraints, no definite solution can be found. In this study, the solving effect of the genetic algorithm parameters, which is an heuristic approach used in the course timetabiling problem, is investigated. Tests were performed for different iteration of different population size with different crossover and mutation rates. As a result of the experiments, it has been observed that the election operator who decides on the new generation will be effective. The selection operator can be set up as a function that depends on the number of individuals, so that better results can be obtained.","PeriodicalId":201903,"journal":{"name":"2017 International Conference on Computer Science and Engineering (UBMK)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116027891","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}