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

{"title":"Comparison of Machine Learning Methods for Code Smell Detection Using Reduced Features","authors":"Kanita Karađuzović-Hadžiabdić, Rialda Spahic","doi":"10.1109/UBMK.2018.8566561","DOIUrl":"https://doi.org/10.1109/UBMK.2018.8566561","url":null,"abstract":"We examine a machine learning approach for detecting common Class and Method level code smells (Data Class and God Class, Feature Envy and Long Method). The focus of the work is selection of reduced set of features that will achieve high classification accuracy. The proposed features may be used by the developers to develop better quality software since the selected features focus on the most critical parts of the code that is responsible for creation of common code smells. We obtained a high accuracy results for all four code smells using the selected features: 98.57% for Data Class, 97.86% for God Class, 99.67% for Feature Envy, and 99.76% for Long Method.","PeriodicalId":293249,"journal":{"name":"2018 3rd International Conference on Computer Science and Engineering (UBMK)","volume":"12 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":"127587754","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":"Edge Computing Security Application: Kılıç","authors":"Ebu Yusuf Güven, A. Çamurcu","doi":"10.1109/UBMK.2018.8566521","DOIUrl":"https://doi.org/10.1109/UBMK.2018.8566521","url":null,"abstract":"Intelligent systems change familiar objects as well as rapidly change common technologies. Internet of Things (IoT) applications are made with Cloud Computing can not meet the expectation of service quality due to bandwidth and network delays. It focuses on solving these needs in real-time intelligent applications that use Edge Computing, which is introduced as a new platform between the cloud and the objects. Security and privacy concerns are a major obstacle to the widespread use of intelligent objects. Edge Computing has both its proximity to objects and sufficient resources are available to provide an environment for the operation of security applications. In this study, Edge Computing is introduced. Edge Computing Security Aplication Kılıç is recommend, which works on the Edge Layer. To illustrate the effective use of the Kılıç, the real-time industry application has been shown in the context of the Smart Factory.","PeriodicalId":293249,"journal":{"name":"2018 3rd International Conference on Computer Science and Engineering (UBMK)","volume":"41 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":"133083062","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":"CEP Rule Extraction From Unlabeled Data in IoT","authors":"M. Simsek, S. Özdemir","doi":"10.1109/UBMK.2018.8566255","DOIUrl":"https://doi.org/10.1109/UBMK.2018.8566255","url":null,"abstract":"With the recent development of the Internet of Things, produced data are increasing day by day. These data have to be analyzed in real time. To provide real time analysis, Complex Event Processing is proposed to analyze the continuous and timely annotated data. Complex event processing detects complex events from atomic events via predefined rules which are mostly determined by domain experts. Determining complex event processing rules requires thorough knowledge of the data and data relations among data sources. It will be difficult to define a rule when it is considered that the scope and quantity of data is increased. Therefore, there is a need for extracting rules automatically. In this paper, we propose a novel model that extracts rules from unlabeled data by using clustering and rule mining algorithms. The model is evaluated in terms of classification performance and the results show that the proposed model is a promising solution for extracting complex event processing rules.","PeriodicalId":293249,"journal":{"name":"2018 3rd International Conference on Computer Science and Engineering (UBMK)","volume":"108 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":"133457495","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":"Automatic Posture Evaluation for Professional Voice Users","authors":"Çagatay Demirel, H. Aydan, I. Koçak, G. Ince","doi":"10.1109/UBMK.2018.8566520","DOIUrl":"https://doi.org/10.1109/UBMK.2018.8566520","url":null,"abstract":"Voice trainings are executed mostly by therapists to their knowledge, experiences and skills. In these therapies, tension spots of a body are evaluated. A body is relieved with guidance of a therapist and physical exercises. However, voice quality evaluation of professional voice users are implemented subjectively. Classical voice evaluations can not be done by an objective approach, yet done with therapists’ intuition. In this study, a measurement system was proposed to evaluate voice quality objectively by using the posture of a patient. Different machine learning algorithms were used to classify objective voice quality and posture quality, yet Artificial Neural Network models were found as best classifiers. Two models were tested using individual test sets and accuracies of voice quality and posture quality estimations were found to be 83.35% and 78.27%.","PeriodicalId":293249,"journal":{"name":"2018 3rd International Conference on Computer Science and Engineering (UBMK)","volume":"7 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":"132293963","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":"Implementation of Change Point Detection Algorithm in the Analysis of Security Attacks in Smart Cars","authors":"S. Okul, M. Aydin, Fatih Keles","doi":"10.1109/UBMK.2018.8566341","DOIUrl":"https://doi.org/10.1109/UBMK.2018.8566341","url":null,"abstract":"In this study, the results of applying the Change Point Detection algorithm in the analysis of security attacks on intelligent vehicles are examined. Two data sets were synthetically created to simulate security attacks. In these data sets, the results of the 4 elements belonging to the intermediary are examined in a certain period. These factors can be listed as the speed value, the speed of the motor per minute, the rate of gas pedal depression, and the amount of fuel. The values of these elements in a certain period are evaluated in the CPD algorithm and it is investigated whether or not the vehicle is under attack. As a result, the attack detection rate was found to increase as the CPD algorithm moved to high attack rate data sets.","PeriodicalId":293249,"journal":{"name":"2018 3rd International Conference on Computer Science and Engineering (UBMK)","volume":"7 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132733086","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":"Implementation of Passif Secure RFID Protocol","authors":"Mehmet Yavuz Yağci, M. Aydin","doi":"10.1109/UBMK.2018.8566271","DOIUrl":"https://doi.org/10.1109/UBMK.2018.8566271","url":null,"abstract":"RFID(Radio Frequency Identification) systems are being used in areas such as identification and authorization. However, RFID systems have many security problems. RFID systems are divided into active tag and passive tag. Due to the computational power of active RFID tags, many studies have been made on them and solutions have been produced. Since passive tags have no computational power, solutions based on strong algorithms can not be produced on these tags. One of the security problems with passive tags, card copying has become possible with devices that anyone can access. The inability to identify the copy card allows continuous access to unwanted areas by unwanted persons. The suggested solution is to override passive RFID tags when they are copied, along with estimating the copy card. The tag holds the value of the new hash, which is randomly generated from the central computer in every successful reading. The generated hash value does not constitute a specific order because it is composed of hash of random texts. With the modified hash value in each reading, the first card read will be treated as the current card, and if another card with the same card number is read, it will be labeled as the copy card.","PeriodicalId":293249,"journal":{"name":"2018 3rd International Conference on Computer Science and Engineering (UBMK)","volume":"91 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":"133118329","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":"Extending FOAF and Relationship Ontologies with Consent Ontology","authors":"Emre Olca, Özgü Can","doi":"10.1109/UBMK.2018.8566297","DOIUrl":"https://doi.org/10.1109/UBMK.2018.8566297","url":null,"abstract":"Paper-based systems are being transported to electronic platforms with the development of technology. The Internet usage of people is increasing day by day. While the number of smartphone users is 2.1 billion in 2016, it is estimated that this number will be 2.8 billion in 2020. According to another study, the number of smartphone users in 2020 is estimated to be 6.8 billion. Personal data pass to the digital world because of the intensive use of the Internet and electronic systems. Person’s consent is necessary to use the data that has passed to the digital platform. In this study, a Consent ontology is developed by providing a semantic solution to the consent management in order to control the approval of persons. The developed Consent ontology imports Friend of a Friend (FOAF) and Relationship ontologies. The FOAF and Relationship ontologies are extended in Consent ontology in order to handle persons’ consent management. Thus, consent management could be provided by ensuring data privacy.","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":"131297021","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":"On the Data Stream Processing Frameworks: A Case Study","authors":"Jasser Dhaouadi, M. Aktaş","doi":"10.1109/UBMK.2018.8566457","DOIUrl":"https://doi.org/10.1109/UBMK.2018.8566457","url":null,"abstract":"We are living in a technological era where everything is computerized and processed with high precision. The key feature of such a revolution is data. Data is everywhere, it brings crucial information which can be used for the prosperity of our society. In response to our needs, data is growing exponentially and the speed, at which data is generated, is increasing at an unbelievably rapid pace. Dealing with large-scale data is challenging since it requires new approaches and new architectures to the way data is processed. Streaming data came up with a bright concept: processing and analyzing different types of data from various sources in a real-time manner. It creates new dimensions for the way we interact with data. In this study, we investigate a data stream processing approach that can be utilized to process click stream data for targeted advertisements. We collect click stream events from e-commerce websites and process these events to identify predefined patterns. We introduce a software architecture that can be used one layer above the open source data stream processing frameworks. We discuss the details of the prototype of the proposed architecture. We evaluate the prototype with an experimental study. The results are promising.","PeriodicalId":293249,"journal":{"name":"2018 3rd International Conference on Computer Science and Engineering (UBMK)","volume":"31 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":"133803861","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":"Data Mining Library for Big Data Processing Platforms: A Case Study-Sparkling Water Platform","authors":"Elif Cansu Yıldız, M. Aktaş, O. Kalipsiz, Alper Nebi Kanlı, Umut Orçun Turgut","doi":"10.1109/UBMK.2018.8566278","DOIUrl":"https://doi.org/10.1109/UBMK.2018.8566278","url":null,"abstract":"Nowadays, many data from millions of websites, applications, social media resources, surveys, video surveillance platforms, and many other sources are obtained in a very large amount. By processing large datasets that occur every day, useful information can be derived. Distributed data processing platforms are needed to handle large amounts of data. For big data processing and analytics platforms such as Hadoop and Spark, there are machine learning libraries that operates distributed and exploits the advantages of distributed computing. For example; The Mahout library uses the Hadoop platform, while the Spark-MLLib library uses the Spark platform. However, for these platforms, it seems that there is no implementation for the algorithms included in the data mining steps, or there is only the implementation for some of the steps’ algorithms. Within the scope of this research, algorithms in different data mining steps on a large data platform will be implemented and a performance evaluation will be performed. In the context of this research, as a case study, the Sparkling Water platform was chosen as a major data processing platform. The banking data set was used for the tests of the implemented data mining algorithms. A software layer containing all data mining steps was developed on the Sparkling Water platform and performance evaluation was conducted. As a result of the evaluation, it has been observed that performance enhancement which comes with distributed data processing has been successful.","PeriodicalId":293249,"journal":{"name":"2018 3rd International Conference on Computer Science and Engineering (UBMK)","volume":"26 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":"115385933","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":"Classification of Mammography Images by Machine Learning Techniques","authors":"B. Bektaş, I. Emre, Elif Kartal, Sevinc Gulsecen","doi":"10.1109/UBMK.2018.8566380","DOIUrl":"https://doi.org/10.1109/UBMK.2018.8566380","url":null,"abstract":"Early diagnosis and accurate treatment is crucial in increasing the survival rate of diseases that can result in death, such as breast cancer. Therefore, there is a greater need for artificial intelligence systems that will help doctors make decisions in health care, especially in fatal diseases. Because these systems are not affected by human nature factors such as distraction, stress etc. so that they can distinguish small and important issues that could be overlooked, especially in the scan results of the patient. The aim of this study is to predict whether a mass can be identified in breast and whether the mass found in the breast is benign or malignant with the help of machine learning which is a sub-study area of artificial intelligence. In this study, the images in the mini-MIAS database are used. Firstly, unwanted areas were eliminated. Then Gauss, Average, Median and Wiener filters were applied to reduce noise and smoothing the images and an algorithm based on Contrast-Limited Adaptive Histogram Equalization (CLAHE) was applied to make suspicious areas more visible. New data sets were created by using HOG (Histogram of Oriented Gradients), LBP (Local Binary Pattern), GLCM (Gray Level Co-occurrence Matrices) for feature extraction and correlation (COR) for feature selection. Selected features were classified in three different categories (normal, benign, malignant) and two different categories (normal, abnormal) using. Different machine learning algorithms (C5.0 (normal and boosted), Naive Bayes, CART and Random Forest) were applied to the data sets and the performances were compared. According to the research findings, to decide whether there was a breast mass, the highest accuracy value was calculated by applying Median and Wiener filters together, equating histogram with CLAHE and using the GLCM feature extraction method on the data set and the accuracy was found 0.657 with Naive Bayes algorithm. When trying to find out whether the mass found in the breast is benign or malignant, Median was applied together with Weiner Filter, equating histogram with CLAHE and HOG feature extraction method was used, and the accuracy was calculated as 0,660 with Random Forest algorithm.","PeriodicalId":293249,"journal":{"name":"2018 3rd International Conference on Computer Science and Engineering (UBMK)","volume":"49 12 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":"126001242","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}