198 results
Search Results
Now showing 1 - 10 of 198
Conference Object Citation - Scopus: 34Improving Text Classification With Transformer(Institute of Electrical and Electronics Engineers Inc., 2021) Soyalp,G.; Alar,A.; Ozkanli,K.; Yildiz,B.Huge amounts of text data are produced every day. Processing text data that accumulates and grows exponentially every day requires the use of appropriate automation tools. Text classification, a Natural Language Processing task, has the potential to provide automatic text data processing. Many new models have been proposed to achieve much better results in text classification. The transformer model has been introduced recently to provide superior performance in terms of accuracy and processing speed in deep learning. In this article, we propose an improved Transformer model for text classification. The dataset containing information about the books was collected from an online resource and used to train the models. We witnessed superior performance in our proposed Transformer model compared to previous state-of-art models such as L S T M and CNN. © 2021 IEEEConference Object Citation - Scopus: 1Similarity-Inclusive Link Prediction With Quaternions(Scitepress, 2021) Kurt, Zuhal; Gerek, Omer Nezih; Bilge, Alper; Ozkan, KemalThis paper proposes a Quaternion-based link prediction method, a novel representation learning method for recommendation purposes. The proposed algorithm depends on and computation with Quaternion algebra, benefiting from the expressiveness and rich representation learning capability of the Hamilton products. The proposed method depends on a link prediction approach and reveals the significant potential for performance improvement in top-N recommendation tasks. The experimental results indicate the superior performance of the approach using two quality measurements - hits rate, and coverage - on the Movielens and Hetrec datasets. Additionally, extensive experiments are conducted on three subsets of the Amazon dataset to understand the flexibility of this algorithm to incorporate different information sources and demonstrate the effectiveness of Quaternion algebra in graph-based recommendation algorithms. The proposed algorithms obtain comparatively higher performance, they are improved with similarity factors. The results show that the proposed quaternion-based algorithm can effectively deal with the deficiencies in graph-based recommender system, making it a preferable alternative among the other available methods.Conference Object Assessment of Online Exam System Perception in Covid-19 Pandemic Era(IADIS Press, 2021) Eryılmaz,M.; Genis-Gruber,A.The swift conversion of courses to online exams has labelled the recent Covid-19 pandemic era. In educational agenda, all educators in the globe have faced the obstacles of abrupt adoption of distance education learning methods. Although distance education methods have been exercised in the past decade, the usage was not common. The pandemic has brought not only the sudden transformation of education format, but also online security issues. The online exam solution in e-learning techniques, tools and adoption has been a popular topic to research. Recent literature review shows various analyzes in the field, however the outcome of the research proves that the challenges are similiar in the globe. The aim of this research is to determine the essential problems and develop solutions based on the students perception of online exams which became compulsorily transitioned during the pandemic process. The custom-made survey was conducted on 165 students to have an insight on their approach to e-learning and online exam. Descriptive statistics method is used to describe the features of the data in the study. © 2021Conference Object Exercise Capacity and Activities of Daily Living in Ccpd Patients With Mild and Higher Symptom Scores(European Respiratory Soc Journals Ltd, 2024) Eyuboglu, Filiz; Saglam, Melda; Vardar-Yagli, Naciye; Calik-Kutukcu, Ebru; Coplu, Lutfi; Arikan, Hulya; Inal-Ince, Deniz[No Abstract Available]Conference Object Citation - Scopus: 4Quantum Machine Learning in Intrusion Detection Systems: a Systematic Mapping Study(Springer Science and Business Media Deutschland GmbH, 2024) Faker,O.; Cagiltay,N.E.The integration between quantum computing (QC) and machine learning algorithms (ML) aims to speed up computing processes and increase model accuracy rates, and this is what led developers and researchers to exploit this feature to study improving the performance of intrusion detection systems (IDSs). In this work, we present a systematic mapping review (SMR) of the most important works in the field of using quantum machine learning (QML) to increase the efficiency of anomaly detection techniques, which depend mainly on ML. After defining and applying the research methodology, the preliminary search results amounted to 240 studies from four databases. According to the exclusion and inclusion reports, we obtained 21 main studies. After reviewing and analyzing the results, the four research questions were answered. The review focused on the development of integration of intrusion detection systems with QML, the characteristics of such integration, increasing the efficiency of ML algorithms, and future research opportunities in this field. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.Conference Object Citation - Scopus: 1Extractive Text Summarization for Turkish: Implementation of Tf-Idf and Pagerank Algorithms(Springer Science and Business Media Deutschland GmbH, 2023) Akülker,E.; Turhan,Ç.Due to the massive amount of information available on the web, reaching the desired content has become more and more difficult. Automatic text summarization helps to solve the problem by minimizing the document size while keeping its core information. In this study, two extractive single document automatic text summarization systems for Turkish are presented which implement the statistical-based TF-IDF algorithm as well as the combination of TF-IDF with the graph-based PageRank algorithm. The study aims to reveal the usability and effectiveness of these algorithms for Turkish documents. Moreover, the results of the TF-IDF implementation and the hybrid approach are compared using the co-selection measures, precision, recall, and F-score. In the evaluation phase, the system-generated summaries are categorized and tested based on their word sizes and the predetermined thresholds and compared against the human-generated summaries. The results indicate that the hybrid system performs better than the TF-IDF system even in lower thresholds, and also both systems are inclined to improve average F-scores in higher threshold generated summarization. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.Conference Object Citation - Scopus: 2Statistical Randomness Tests of Long Sequences by Dynamic Partitioning(Institute of Electrical and Electronics Engineers Inc., 2020) Akcengiz,Z.; Aslan,M.; Karabayir,O.; Doganaksoy,A.; Uguz,M.; Sulak,F.Random numbers have a wide usage in the area of cryptography. In practice, pseudo random number generators are used in place of true random number generators, as regeneration of them may be required. Therefore because of generation methods of pseudo random number sequences, statistical randomness tests have a vital importance. In this paper, a randomness test suite is specified for long binary sequences. In literature, there are many randomness tests and test suites. However, in most of them, to apply randomness test, long sequences are partitioned into a certain fixed length and the collection of short sequences obtained is evaluated instead. In this paper, instead of partitioning a long sequence into fixed length subsequences, a concept of dynamic partitioning is introduced in accordance with the random variable in consideration. Then statistical methods are applied. The suggested suite, containing four statistical tests: Collision Tests, Weight Test, Linear Complexity Test and Index Coincidence Test, all of them work with the idea of dynamic partitioning. Besides the adaptation of this approach to randomness tests, the index coincidence test is another contribution of this work. The distribution function and the application of all tests are given in the paper. © 2020 IEEE.Conference Object Citation - WoS: 2Citation - Scopus: 2Solid-State Reduction Studies for Recovery of Iron From Red Mud(Springer international Publishing Ag, 2020) Keskinkilic, Ender; Pournaderi, Saeid; Geveci, Ahmet; Topkaya, Yavuz A.Red mud or bauxite residue can be regarded as a by-product of aluminum extraction process since it contains a significant amount of iron and some valuable elements. Therefore, the treatment of red mud has been a hot topic for some decades. Last year, the authors started a laboratory-scale project dealing with stepwise recovery of valuable elements from red mud of Seydisehir Aluminum Plant, Turkey. The first step is related to the recovery of iron and pyrometallurgical methods (solid-state reduction and smelting) are currently being performed. Nonferrous metals will then be selectively leached in the second step. In TMS 2019, the authors outlined the literature related to the smelting studies for iron recovery from bauxite residue. In the extent of the present work, a literature review relevant to the solid-state reduction studies for recovery of iron from red mud was presented.Conference Object Driving Conditions Leading To Thermal Runaway in Li-Ion Battery EV's(IEEE, 2024) Ertan, H. Bulent; Azuaje-Berbeci, Bernardo J.The adoption of high-energy-density lithium-ion batteries (LIB) as the energy source in electric vehicles (EV) introduces significant safety concerns. Thermal runaway (TR), a self-accelerating rise in battery temperature resulting in catastrophic failure, is a significant safety concern. Cooling system failure within the EV's thermal management system is one of several factors that can trigger TR. Typically, TR is initiated by exceeding a critical temperature threshold under abusive conditions. Understanding the operating conditions that lead to the path of TR is essential for ensuring EV and occupant safety. Recently, a detailed electrochemical-thermal model that incorporates the chemical reactions within the battery until TR is introduced. This paper aims to illustrate how this model can be used to identify the conditions leading to TR under realistic EV driving scenarios. For this purpose, an Advisor/Matlab-based model of a hybrid EV is developed and verified by tests, is used to estimate the current required from the vehicle's battery pack at a given driving condition. This is followed by the prediction of battery thermal response using the mentioned finite-element-analysis-based battery model. Several scenarios are tested in this paper to determine whether TR occurs and to identify the factors contributing to TR. This study aids in comprehending the factors that contribute to TR and the development of preventative measures for battery management system design.Conference Object The Impact of Socioeconomic Status on Clinical Parameters in Female Psa Patients(Clinical & Exper Rheumatology, 2021) Tekeoglu, I.; Nas, K.; Keskin, Y.; Kilic, E.; Sargin, B.; Kasman, Acer S.; Tuncer, T.[No Abstract Available]
