• Efficient Test Collection Construction via Active Learning 

  Rahman, M.M.; Kutlu, Mücahid; Elsayed, T.; Lease, M.a (Association for Computing Machinery, 2020-09)

  To create a new IR test collection at low cost, it is valuable to carefully select which documents merit human relevance judgments. Shared task campaigns such as NIST TREC pool document rankings from many participating ...

• A Novel FPGA-Based High Throughput Accelerator for Binary Search Trees 

  Melikoglu, O.; Ergin, Oğuz; Salami, B.; Pavon, J.; Unsal, O.; Cristal, A. (Institute of Electrical and Electronics Engineers Inc., 2019-07)

  This paper presents a deeply pipelined and massively parallel Binary Search Tree (BST) accelerator for Field Programmable Gate Arrays (FPGAs). Our design relies on the extremely parallel on-chip memory, or Block RAMs (BRAMs) ...

• Are we secure from bots? Investigating vulnerabilities of botometer 

  Bugra Torusdag, M.; Kutlu, Mücahid; Selçuk, Ali Aydın (Institute of Electrical and Electronics Engineers Inc., 2020-09)

  Social media platforms such as Twitter provide an incredibly efficient way to communicate with people. While these platforms have many benefits, they can also be used for deceiving people, spreading misinformation, ...

• Predicting the number of bidders in public procurement 

  Gorgun, M.K.; Kutlu, Mücahid; Tas, B.K.O. (Institute of Electrical and Electronics Engineers Inc., 2020-09)

  Public procurement constitutes an important part of economical activities. In order to effectively use public resources, increasing competition among firms participating in public procurement is essential. In this work, ...

• Building Test Collections using Bandit Techniques: A Reproducibility Study 

  Altun, Bahadir; Kutlu, Mücahid (Association for Computing Machinery, 2020-10)

  The high cost of constructing test collections led many researchers to develop intelligent document selection methods to find relevant documents with fewer judgments than the standard pooling method requires. In this paper, ...

• On Existence of Equilibrium Under Social Coalition Structures 

  Çaşkurlu, Buğra; Ekici, Ozgun; Kizilkaya, Fatih Erdem (Springer Science and Business Media Deutschland GmbH, 2020-10)

  In a strategic form game, a strategy profile is an equilibrium if no viable coalition of agents benefits (in the Pareto sense) from jointly changing their strategies. Weaker or stronger equilibrium notions can be defined ...

• ArTest: The First Test Collection for Arabic Web Search with Relevance Rationales 

  Hasanain, M.; Barkallah, Y.; Suwaileh, R.; Kutlu, Mücahid; Elsayed, T. (Association for Computing Machinery, Inc, 2020-07)

  The scarcity of Arabic test collections has long hindered information retrieval (IR) research over the Arabic Web. In this work, we present ArTest, the first large-scale test collection designed for the evaluation of ...

• Annotator rationales for labeling tasks in crowdsourcing 

  Kutlu, Mücahid; McDonnell, T.; Elsayed, T.c; Lease, M. (AI Access Foundation, 2020)

  When collecting item ratings from human judges, it can be difficult to measure and enforce data quality due to task subjectivity and lack of transparency into how judges make each rating decision. To address this, we ...

• Deep Learning Based Hybrid Computational Intelligence Models for Options Pricing 

  Arin, Efe; Özbayoğlu, Ahmet Murat (SPRINGER, 2020-11)

  Options are commonly used by traders and investors for hedging their investments. They also allow the traders to execute leveraged trading opportunities. Meanwhile accurately pricing the intended option is crucial to perform ...

• Security-Aware Database Migration Planning 

  Subramani, K.; Çaşkurlu, Buğra; Acikalin, U.U. (Springer Science and Business Media Deutschland GmbH, 2020-08)

  Database migration is an important problem faced by companies dealing with big data. Not only is migration a costly procedure, it involves serious security risks as well. For some institutions, the primary focus is on ...

• Distinguishing True and False Buy/Sell Triggers from Financial Technical Indicators 

  Tüfekci, Zeynep; Abul, Osman (Institute of Electrical and Electronics Engineers Inc., 2020-10)

  The objective of this study is to develop a method to distinguish True and False Buy/Sell recommendations. Various recommendation schemes, like 30/70 RSI (Relative Strength Index) scheme, are effectively used by many ...

• An Experimental Study of Reduced-Voltage Operation in Modern FPGAs for Neural Network Acceleration 

  Salami, B.; Onural, E.B.; Yuksel, I.E.; Koc, F.; Ergin, Oğuz; Cristal Kestelman, A.; , Unsal, O.; Sarbazi-Azad, H.; Mutlu, O. (Institute of Electrical and Electronics Engineers Inc., 2020-07)

  We empirically evaluate an undervolting technique, i.e., underscaling the circuit supply voltage below the nominal level, to improve the power-efficiency of Convolutional Neural Network (CNN) accelerators mapped to Field ...

• Financial Trading Model with Stock Bar Chart Image Time Series with Deep Convolutional Neural Networks 

  Sezer, Omer Berat; Özbayoğlu, Ahmet Murat (Tech Science Press, 2020)

  Even though computational intelligence techniques have been extensively utilized in financial trading systems, almost all developed models use the time series data for price prediction or identifying buy-sell points. ...

• Comparison of Gross Calorific Value Estimation of Turkish Coals using Regression and Neural Networks Techniques 

  Özbayoğlu, Ahmet Murat; Özbayoğlu, Mehmet Evren; Özbayoğlu, Gülhan (Metso,Vale,Tata Steel,ESSAR STEEL,TATA CONSULTANCY SERVICE, 2012-09)

  Gross calorific value (GCV) of coals was estimated using artificial neural networks, linear and non- linear regression techniques. Proximate and ultimate analysis results were collected for 187 different coal samples. ...

• Eşdeğer Sirkülasyon Basıncının Yapay Zeka Yöntemleri ile Tespiti ve Performans Karşılaştırması 

  Özbayoğlu, Ahmet Murat; Erge, Öney; Özbayoğlu, M. Evren (Petrol Mühendisleri Odası, 2020-11-19)

  Sondaj operasyonlarında kuyu dibi basıncının hassas bir şekilde tespiti, operasyonların emniyeti ve operasyonlarla doğrudan ilişkili birtakım mühendislik tasarımları açısından kritik bir öneme sahiptir. Kuyu ...

• Mitigation of H.264 and H.265 Video Compression for Reliable PRNU Estimation 

  Altinisik, Enes; Tasdemir, Kasim; Sencar, Hüsrev Taha (Institute of Electrical and Electronics Engineers Inc., 2020)

  The photo-response non-uniformity (PRNU) is a distinctive image sensor characteristic, and an imaging device inadvertently introduces its sensor's PRNU into all media it captures. Therefore, the PRNU can be regarded as a ...

• On efficient computation of equilibrium under social coalition structures 

  Çaşkurlu, Buğra; Ekici, Ozgun; Kizilkaya, Fatih Erdem (Turkiye Klinikleri, 2020)

  In game-theoretic settings the key notion of analysis is an equilibrium, which is a profile of agent strategies such that no viable coalition of agents can improve upon their coalitional welfare by jointly changing their ...

• A study on public perception and preferences about IoT security 

  Tok, M.S.; Selçuk, Ali Aydın (Institute of Electrical and Electronics Engineers Inc., 2019-09)

  Configuring internet of things (IoT) devices with easy or default passwords leads to serious vulnerabilities. In recent years, malware (Mirai etc.) which are capable of creating IoT botnets and organizing distributed denial ...

• HSV Color Histogram Based Image Retrieval with Background Elimination 

  Erkut, U.; Bostancioglu, F.; Erten, M.; Özbayoğlu, Ahmet Murat; Solak, E. (Institute of Electrical and Electronics Engineers Inc., 2019-11)

  In this study, a new content based image retrieval (CBIR) method, which uses HSV histogram data is proposed. The model uses the HSV histogram to find the background from the image by analyzing the peaks in the histogram data ...

• JpgScraper : An Advanced Carver for JPEG Files 

  Uzun, Erkam; Sencar, Hüsrev Taha (Institute of Electrical and Electronics Engineers Inc., 2020)

  Orphaned file fragment carving is concerned with recovering contents of encoded data in the absence of any coding metadata. Constructing an orphaned file carver requires addressing three challenges: a specialized decoder ...

View more