Publications of Sadi Evren SEKER

A. International Indexed Journals: A1. I. Ocak, S. E. SEKER (2012), Estimation of Elastic Modulus of Intact Rocks by Artificial Neural Network, Rock Mechanics and Rock Engineering, Springer, DOI: 10.1007/s00603-012-0236-z, Available from: Abstract : The modulus of elasticity of intact rock (E i) is an important rock property that is used as an input parameter in the design stage of engineering projects such as dams, slopes, foundations, tunnel constructions and mining excavations. However, it is sometimes difficult to determine the modulus of elasticity in laboratory tests because high-quality cores are required. For this reason, various methods for predicting E i have been popular research topics in recently published literature. In this study, the relationships between the uniaxial compressive strength, unit weight (γ) and E i for different types of rocks were analyzed, employing an artificial neural network and 195 data obtained from laboratory tests carried out on cores obtained from drilling holes within the area of three metro lines in Istanbul, Turkey. Software was developed in Java language using Weka class libraries for the study. To determine the prediction capacity of the proposed technique, the root-mean-square error and the root relative squared error indices were calculated as 0.191 and 92.587, respectively. Both coefficients indicate that the prediction capacity of the study is high for practical use. A2. I. Ocak, S. E. SEKER (2013), Calculation of surface settlements caused by EPBM tunneling using artificial neural network, SVM, and Gaussian processes, Environmental Earth Sciences, Springer-Verlag, DOI: 10.1007/s12665-012-2214-x, Available from: Abstract : Increasing demand on infrastructures increases attention to shallow soft ground tunneling methods in urbanized areas. Especially in metro tunnel excavations, due to their large diameters, it is important to control the surface settlements observed before and after excavation, which may cause damage to surface structures. In order to solve this problem, earth pressure balance machines (EPBM) and slurry balance machines have been widely used throughout the world. There are numerous empirical, analytical, and numerical analysis methods that can be used to predict surface settlements. But substantially fewer approaches have been developed for artificial neural network-based prediction methods especially in EPBM tunneling. In this study, 18 different parameters have been collected by municipal authorities from field studies pertaining to EPBM operation factors, tunnel geometric properties, and ground properties. The data source has a preprocess phase for the selection of the most effective parameters for surface settlement prediction. This paper focuses on surface settlement prediction using three different methods: artificial neural network (ANN), support vector machines (SVM), and Gaussian processes (GP). The success of the study has decreased the error rate to 13, 12.8, and 9, respectively, which is relatively better than contemporary research. A3. Sadi Evren SEKER (2013), Temporal Logic Extension for Self Referring, non-existance, Multiple Recurrence and Anterior Past, Turkish Journal of Electirical Engineering and Computer Sciences, TUBITAK, DOI:10.3906/elk-1208-93, (Accepted and online Since April 03,2013) Available from: Abstract : This study focuses on the possible extensions of current temporal logics. Four extensions are proposed in this study which are self referring events, non-existing events, multiple recurrence of events and an improvement on anterior past events. Each of these extensions are on different levels of the temporal logics. The main motivation behind the extensions is the temporal analysis of the Turkish natural language. Similar to the temporal logic studies built on other natural languages, like French, Ukrainian, Italian, Korean, English or Romanian, it is first time the Turkish language has been deeply questioned in the sense of computable temporal logic by using the view of a standardized temporal markup language. This study keeps the methodology of TimeML and researches the Turkish natural language from the perspectives of Reichenbach and Allen’s temporal logics. The Reichenbach temporal logic is perfectly capable of handling the anterior temporal feeling, but it is not enough to handle the sense of "learnt" or "study" which are two past tenses in Turkish. Also Allen’s temporal logic can not handle two events following each other continuously, which case is named as recurring events in this study first time. Finally, depending on the experiences from a 4 year PhD. study on the natural language texts, this study underlines the absence of self-referring or a reference to non-existing events in temporal logics. After adding the above extensions on a computable temporal logic, the capability of tagging the events on Turkish texts has been measured an increase from 18% to 100% for a first time created Turkish corpus. Also, a new software has been implemented to visualize the tagged events and a previous software has been developed to handle events tagged for Turkish. A4. Sadi Evren SEKER, Cihan Mert, Khaled Al-Naami, Nuri Ozalp, Ugur Ayan (2013), Correlation between the Economy News and Stock Market in Turkey., International Journal of Business Intelligence and Review (IJBIR), XXX, (Accepted awaiting publication) Abstract :Depending on the market strength and structure, it is a known fact that there is a correlation between the stock market values and the content in newspapers. The correlation increases in weak and speculative markets, while they never get reduced to zero in the strongest markets. This research focuses on the correlation between the economic news published in a highly circulating newspaper in Turkey and the stock market closing values in Turkey. In the research several feature extraction methodologies are implemented on both of the data sources, which are the stock market values and economic news. Since the economic news is in natural language format, the text mining technique, term frequency – inverse document frequency is implemented. On the other hand, the time series analysis methods like random walk, Bollinger band, moving average or difference are applied over the stock market values. After the feature extraction step, the classification methods are built on the well-known classifiers support vector machine, k-nearest neighborhood and decision tree. Moreover, an ensemble classifier based on majority voting is implemented on top of these classifiers. The success rates show that the results are satisfactory to claim the methods implemented in this study can be spread to future research with similar data sets from other countries. A5. Mehmet Lutfi ARSLAN, Sadi Evren SEKER (2013), Web Based Reputation Index of Turkish Universities, International Journal of e-Education, e-Business, e-Management and e-Learning (IJEEEE), XXX (Accepted waiting for publication) Abstract : This paper attempts to develop an online reputation index of Turkish universities through their online impact and effectiveness. Using 16 different web based parameters and employing normalization process of the results, we have ranked websites of Turkish universities in terms of their web presence. This index is first attempt to determine the tools of reputation of Turkish academic websites and would be a basis for further studies to examine the relation between reputation and the online effectiveness of the universities. A6. Sadi Evren SEKER, Cihan Mert, Khaled Al-Naami, Nuri OZALP, Ugur AYAN (2013), Time Series Analysis on Stock Market for Text Mining Correlation of Economy News, (Accepted waiting for publication) Abstract : This paper proposes an information retrieval method for the economy news. The effect of economy news, are researched in the word level and stock market values are considered as the ground proof. The correlation between stock market prices and economy news is an already addressed problem for most of the countries. The most well-known approach is applying the text mining approaches to the news and some time series analysis techniques over stock market closing values in order to apply classification or clustering algorithms over the features extracted. This study goes further and tries to ask the question what are the available time series analysis techniques for the stock market closing values and which one is the most suitable? In this study, the news and their dates are collected into a database and text mining is applied over the news, the text mining part has been kept simple with only term frequency – inverse document frequency method. For the time series analysis part, we have studied 10 different methods such as random walk, moving average, acceleration, Bollinger band, price rate of change, periodic average, difference, momentum or relative strength index and their variation. In this study we have also explained these techniques in a comparative way and we have applied the methods over Turkish Stock Market closing values for more than a 2 year period. On the other hand, we have applied the term frequency – inverse document frequency method on the economy news of one of the high-circulating newspapers in Turkey. A7. Mehmet Lutfi ARSLAN, Sadi Evren SEKER (2013), The Impact of Employment Web Sites’ Traffic on Unemployment: A Cross Country Comparison, (Accepted awaiting publication) Abstract : Although employment web sites have recently become the main source for re- cruitment and selection process, the relation between those sites and unemploy- ment rates is seldom addressed. Deriving data from ... countries and ... web sites, this study explores the correlation between unemployment rates of European countries and the attractiveness of country specific employment web sites. It also compares the changes in unemployment rates and traffic on all the aforemen- tioned web sites. The results showed that there is a strong correlation between web sites traffic and unemployment rates. A8. Cevdet Kizil, Mehmet Lutfi ARSLAN, Sadi Evren SEKER (2013), Correlation between Intellectual Capital and Web Trends of Top 30 Companies in Turkey, (Accepted awaiting publication) Abstract : This study focuses on the correlation between intellectual capital and web trends of the index BIST-30, which holds the top 30 companies in Istanbul Stock Market (BIST). The trends of web sites and companies are collected separately via web tools. Also, intellectual capital is studied and measured based on two methods, which are Market Value / Book Value and Value Added Intellectual Coefficient (VAIC) techniques. Data required for studying and measuring intellectual capital is gathered from web sites, firm annual reports, company financial statements and public lightening platform published by the BIST administration. B. International Conference Papers (Printed in Proceedings): B1. Sadi Evren SEKER, Ender Ozcan, Z. Ilknur Karadeniz, (2004) GENERATING JAVA CLASS SKELETON USING A NATURAL LANGUAGE INTERFACE, ICEIS, NLUCS Abstract : An intelligent natural language interface based on Turkish Language is designed for creating Java class skeleton, listing the class and its members. This interface is developed as a part of a project named as TUJA, a tool for producing Java programs using Turkish sentences. Turkish sentences are converted into instances of schemata. There are three types of schemata: class definition schema, member method schema and member attribute schema. Concept hierarchies are utilized for building the classes and their hierarchical representation for Java class skeleton generation. In this paper, the details of the design and the implementation are described. B2. Sadi Evren SEKER, Banu DİRİ , (2010) "Event Ordering for Turkish Natural Language Texts" , CSW 2010 Abstract : Besides the natural languages in Latin family, Turkish has its own temporal logic to model the order of events. TimeML is one of the challenging markup language for temporal expressions and event orders. In this study, we have researched the philosophy behind TimeML which are Reichenbach and Allen’s temporal logics and we have adapted Turkish temporal logic to these philosophical approaches. Also we have applied this philosophical improvement on TimeML applications and tested our success on a corpus created during this study, since there is no previous work on the temporal logic field of Turkish. The test results showed that, the success of TimeML modeling capability increased from 53% to 91%. B3. Sadi Evren SEKER, Banu DİRİ (2010) , "TimeML and Turkish Temporal Logic" ICAI 2010, WolrdComp 2010,( July 12-15, 2010, USA) Regular Research Paper Abstract : Turkish is one of the widely used and relatively difficult natural language for machine processing. One of the challenges in Turkish is the temporal logic and processing the time of events. For the Latin family natural languages, there are quite successful solutions like TimeML which is built on the Reichenbach tense analysis and Allen‟s temporal logic. Unfortunately, there is no previous work on Turkish languages up until now. This paper covers the basic temporal models of Reichenbach and Allen and then proceeds to the improvement of these models to cover temporal logic behind Turkish natural language. In order to test the success of this study, we have also created a corpus from child stories and tested the success of new implementation. B4. Sadi Evren SEKER, "A Novel Temporal Visualization Framework for Relational Event Representation"
, MSV12, Modelling and Simulation, 2012 , CSREA Press, USA, ISBN: 1-60132-226-7, Pages 258-264
B5. Sadi Evren SEKER, "Web Spider Performance and Data Structure Analysis", SWWS12, Semantic Web and Web Services, 2012,ISBN:1-60132-232-1, Pages: 73-77
B6. Sadi Evren SEKER, "Turkish Query Engine on Library Ontology", IKE12, Internet Knowledge Engineering, 2012, ISBN:1-60132-222-4, Pages:26-33
B7. Sadi Evren SEKER, "Performance Evaluation of a Regular Expression Crawler and Indexer", ICOMP12, Internet Computing, 2012, CSREA Press, USA, ISBN: 1-60132-220-8, Pages: 33-39
B8. Sadi Evren SEKER, Cihan Mert "Reverse Factorization and Comparison of Factorization Algorithms in Attack to RSA", International Conference on Scientific Computing, 2013, Accepted, Waiting for Publication Abstract : Factorization algorithms have a major role in the computer security and cryptography. Most of the widely used crypto- graphic algorithms, like RSA, are built on the mathematical difficulty of factorization for big prime numbers. This re- search, proposes a new approach to the factorization by using two new enhancements. The new approach is also compared with six different factorization algorithms and evaluated the performance on a big data environment. The algorithms covered are elliptic curve method, quadratic sieve, Fermat’s method, trial division and Pollard rho methods. Success rates are compared over a million of integer numbers with different difficulties. We have im- plemented our own algorithm for random number genera- tion, which is also explained in the paper. We also empiri- cally show that the new approach has an advantage on the factorization attack to RSA. B9. Sadi Evren SEKER, Khaled Al-Naami "Sentimental Analysis on Turkish Blogs via Ensemble Classifier", International Conference on Data Mining (ICDM13), 2013, Abstract : Sentimental analysis on web-mined data has an increasing impact on most of the studies. Sentimental influence of any content on the web is one of the most curios questions by the authors of content and publishers. In this study, we have researched the impact of the comments collected from five different web sites in Turkish with more than 1.6 million comments in total. The web sites are from newspapers; movie reviews, e-marketing web site and a literature web site. We mix all the comments into a single file. The com- ments also have a like or dislike number, which we use as ground proof of the impact of the comment, as the senti- mental of the comment. We try to correlate the text of comment and the like / dislike grade of the comment. We use three classifiers as support vector machine, k-nearest neighborhood and C4.5 decision tree classifier. On top of them, we add an ensemble classifier based on the majority voting. For the feature extraction from the text, we use the term frequency – inverse document frequency approach and limit the top most features depending on their infor- mation gain. The result of study shows that there are about 62% correlation between the blogs and comments and their like / dislike score depending on our classification model. B9. Sadi Evren SEKER, Khaled Al-Naami "S-Box Hashing for Text Mining", International Symposium on Computing in Informatics and Mathematics (ISCIM13), 2013 Abstract : One of the crucial points in the text mining studies is the feature hashing step. Most of the text mining studies starts with a text data source and processes a feature extraction methodology over the text. Most of the time the feature extraction method should be decided wisely, because, most of the times, it directly effects the results and performance. Another well-known approach is using any feature extraction method, together with the feature hashing. By the way, the feature extraction can be executed without worrying about the performance and the feature hashing reduces the size of the extracted feature vector. Today, one of the widely used hashing algorithms in text mining is the modern hashing algorithms like MD5 or SHA1, which are built over substitution permutation networks (SPN) or Fiestel Networks. The common property of most of the modern hashing algorithms is the implicitly implemented s-boxes. One of the drawbacks of the modern hashing algorithms is the collision free purpose of the algorithm. The permutation step in most of the time is implemented for this purpose and the correlation between the input text and output bits is completely obfuscated. This study focuses on the possible implementations of the s-boxes for the feature hashing. The purpose feature hashing in this study is reducing the feature vector, while keeping the correlation between the input text and the output bits. B10. Sadi Evren SEKER, Cihan MERT, Khaled Al-Naami, Ugur AYAN, Nuri OZALP, "Ensemble classification over stock market time series and economy news", Intelligence and Security Informatics (ISI), 2013 IEEE International Conference Abstract : Aim of this study is applying the ensemble classification methods over the stock market closing values, which can be assumed as time series and finding out the relation between the economy news. In order to keep the study back ground clear, the majority voting method has been applied over the three classification algorithms, which are the k-nearest neighborhood, support vector machine and the C4.5 tree. The results gathered from two different feature extraction methods are correlated with majority voting meta classifier (ensemble method) which is running over three classifiers. The results show the success rates are increased after the ensemble at least 2 to 3 percent success rate. B11. Sadi Evren SEKER, Khaled Al-NAAMI, Latifur KHAN, " Author Attribution on Streaming Data", IEEE IRI 2013 Abstract : The concept of novel authors occurring in streaming data source, such as evolving social media, is an unaddressed problem up until now. Existing author attribution techniques deals with the datasets, where the total number of authors do not change in the training or the testing time of the classifiers. This study focuses on the question, "what happens if new authors are added into the system by time?". Moreover in this study we are also dealing with the problems that some of the authors may not stay and may disappear by time or may re-appear after a while. In this study stream mining approaches are proposed to solve the problem. The test scenarios are created over the existing IMDB62 data set, which is widely used by author attribution algorithms already. We used our own shuffling algorithms to create the effect of novel authors. Also before the stream mining, POS tagging approaches and the TF-IDF methods are applied for the feature extraction. And we have applied bi-tag approach where two consecutive tags are considered as a new feature in our approach. By the help of novel techniques, first time proposed in this paper, the success rate has been increased from 35% to 61% for the authorship attribution on streaming text data. C. International Book Chapters C1. Harun Pirim and Sadi Evren Seker (2012). Ensemble Clustering for Biological Datasets, Chapter 13, Bioinformatics, Horacio Pérez-Sánchez (Ed.), ISBN: 978-953-51-0878-8, InTech, DOI: 10.5772/49956. Available from : DOI: D. National Reviewed Journal Publications : D1. Sadi Evren SEKER, Banu Diri, (2010) Türkçe Metinler için Olay Sıralaması, syf. 63-75, Bilgisayar Mühendisleri Bölüm BaSkanları Dergisi Abstract : Aim of this study is advancing current event ordering methodologies to cover Turkish temporal logic. Currently, some additional operations are required to demonstrate the relation between events or ordering events in a natural language text, after outputting the semantical representation. There are some systematic studies based on English temporal logic and covering most of the Latin family. There are some differences between temporal logics in the languages in addition to common temporal properties. In this study, the temporal logics in the literature are researched. Some of these temporal logics are suitable for machine computation and some are suitable for natural language processing. An optimization is suggested on these computable and natural laguage processing suitable temporal logics to cover Turkish temporal logic. E. National Conference Papers printed in Proceedings: E1. Sadi Evren SEKER, A. C. Cem Say, Birol Aygun, (2003) "Türkçe Dogal Dil Arayüzlü bir KiSisel Takvim Programının, Tasarim ve Kodlamasi",TAINN E2. Sadi Evren SEKER, Banu Diri, (2006) DavranıSsal Türkçe Metin Sınıflandırılması ve Kodlanması,ASYU E3. Ender Ozcan, Alpay Alkan, Seniz Demir, Mesut Ali Ergin, Hakan Kul, and Sadi Evren Seker. (2003) STARS - Student Transcript and Registration System: an Open Source Internet Application. In Akademik Bilisim 2003, pages E-ref:87, E4. Sadi Evren SEKER, Banu DİRİ, (2010) "Reichenbach ve Allen Zamansal Mantığı ileTimeML", Akademik BiliSim 2010 E-ref:88 F. Books: F1. SEKER, Sadi Evren "Programlama ve Veri Yapılarına GiriS JAVA, C, C++ dilleri ile" , ISBN 978-9944-62-782-5, Publication Date: Feb 2009 F2. Sadi Evren SEKER, "İS Zekası ve Veri Madenciliği (WEKA ile)", 250 pp., İstanbul, Cinius Yayınları, ISBN , Publication Date: 2013 F3. İbrahim AKSEL, Mehmet Lütfi ARSLAN, Cevdet KIZIL, Mehmet Emin OKUR, Sadi Evren SEKER, "Dijital İSletme", 250 pp., İstanbul, Cinius Yayınları, Publication Date: 2013 For more information