Bilgisayar Mühendisliği Bölümü

Permanent URI for this communityhttps://hdl.handle.net/20.500.12416/13

Browse

Now showing 1 - 10 of 10

Citation - Scopus: 0
A Data Fusion Approach In Protein Homology Detection
(2008) Oğul, Hasan; Polatkan, A.C.; Oǧul, H.; Sever, Hayri; Sever, H.; 11916; Bilgisayar Mühendisliği
The discriminative framework for protein remote homology detection based on support vector machines (SVMs) is reconstructed by the fusion of sequence based features. In this respect, n-peptide compositions are partitioned and fed into separate SVMs. The SVM outputs are evaluated with different techniques and tested to discern their ability for SCOP protein super family classification on a common benchmarking set. It reveals that the fusion approach leads to an improvement in prediction accuracy with a remarkable gain on computer memory usage. © 2008 IEEE.
Citation - WoS: 3
Citation - Scopus: 6
A shallow 3D convolutional neural network for violence detection in videos
(Cairo Univ, Fac Computers & information, 2024) Dündar, Naz; Dundar, Naz; Keceli, Ali Seydi; Sever, Hayri; Kaya, Aydin; Sever, Hayri; 366608; 11916; Yazılım Mühendisliği; Bilgisayar Mühendisliği
With the recent worldwide statistical rise in the amount of public violence, automated violence detection in surveillance cameras has become a matter of high importance. This work introduces an end-to-end, trainable 3D Convolutional Neural Network (3D CNN) for detecting violence in video footage. The proposed network is inherently capable of processing both spatial and temporal information, thereby obviating the need for additional models that would introduce higher computational requirements and complexity. This work has two main contributions: 1) developing a lightweight 3D CNN suitable for inference on edge devices as mobile systems, and 2) a comprehensive explanation of all components comprising a CNN model, thereby enhances model interpretability. Experiments were conducted to assess the performance of the proposed model using a consolidated dataset combining four benchmark datasets. The results of the experiments support the asserted contributions, which are discussed in detail.
Citation - Scopus: 2
Application of Artificial Intelligence in Early–Stage Diagnosis of Sepsis
(Association for Computing Machinery, 2022) Par, O.E.; Sever, Hayri; Sezer, E.A.; Sever, H.; 11916; Bilgisayar Mühendisliği
Patient care is a critical task, which requires a lot of effort. Medical practitioners face many challenges, especially during diagnosing different diseases. Sepsis is one of the riskiest diseases, which proves to be lethal for Intensive Care Unit (ICU) patients. World Health Organization (WHO) has declared it a major cause of death worldwide. Early-stage diagnosis of sepsis can help in terminating it in the start. But unfortunately, medical practitioners encounter hitches in the early-stage diagnosis of sepsis. The study used SOFA (Sequential Organ Failure Assessment) for measuring the severity of sepsis in patients. The study employs artificial intelligence techniques such as Multilayer Perceptron (MLP) and Random Forest (RF) to diagnose early-stage of sepsis. The study compared the performance of MLP (connected and non-connected) and Random Forest (connected and non-connected) algorithms. The results indicate that for both of the algorithms, the connected method yielded better results than the non-connected method. Further, it was found that RF both connected and non-connected algorithms yielded better results than MLP algorithms and the Random Forest connected algorithm yielded highly accurate results for diagnosing early-stage sepsis in the 3rd hour. © 2022 ACM.
Citation - WoS: 2
Citation - Scopus: 2
Binary background model with geometric mean for author-independent authorship verification
(Sage Publications Ltd, 2023) Canbay, Pelin; Sever, Hayri; Sezer, Ebru A.; Sever, Hayri; 11916; Bilgisayar Mühendisliği
Authorship verification (AV) is one of the main problems of authorship analysis and digital text forensics. The classical AV problem is to decide whether or not a particular author wrote the document in question. However, if there is one and relatively short document as the author's known document, the verification problem becomes more difficult than the classical AV and needs a generalised solution. Regarding to decide AV of the given two unlabeled documents (2D-AV), we proposed a system that provides an author-independent solution with the help of a Binary Background Model (BBM). The BBM is a supervised model that provides an informative background to distinguish document pairs written by the same or different authors. To evaluate the document pairs in one representation, we also proposed a new, simple and efficient document combination method based on the geometric mean of the stylometric features. We tested the performance of the proposed system for both author-dependent and author-independent AV cases. In addition, we introduced a new, well-defined, manually labelled Turkish blog corpus to be used in subsequent studies about authorship analysis. Using a publicly available English blog corpus for generating the BBM, the proposed system demonstrated an accuracy of over 90% from both trained and unseen authors' test sets. Furthermore, the proposed combination method and the system using the BBM with the English blog corpus were also evaluated with other genres, which were used in the international PAN AV competitions, and achieved promising results.
Citation - WoS: 3
Citation - Scopus: 4
Block size analysis for discrete wavelet watermarking and embedding a vector image as a watermark
(Zarka Private Univ, 2019) Sever, Hayri; Sever, Hayri; Senol, Ahmet; Elbasi, Ersin; 11916; Bilgisayar Mühendisliği
As telecommunication and computer technologies proliferate, most data are stored and transferred in digital format. Content owners, therefore, are searching for new technologies to protect copyrighted products in digital form. Image watermarking emerged as a technique for protecting image copyrights. Early studies on image watermarking used the pixel domain whereas modern watermarking methods convert a pixel based image to another domain and embed a watermark in the transform domain. This study aims to use, Block Discrete Wavelet Transform (BDWT) as the transform domain for embedding and extracting watermarks. This study consists of 2 parts. The first part investigates the effect of dividing an image into non overlapping blocks and transforming each image block to a DWT domain, independently. Then, effect of block size on watermark success and, how it is related to block size, are analyzed. The second part investigates embedding a vector image logo as a watermark. Vector images consist of geometric objects such as lines, circles and splines. Unlike pixel-based images, vector images do not lose quality due to scaling. Vector watermarks deteriorate very easily if the watermarked image is processed, such as compression or filtering. Special care must be taken when the embedded watermark is a vector image, such as adjusting the watermark strength or distributing the watermark data into the image. The relative importance of watermark data must be taken into account. To the best of our knowledge this study is the first to use a vector image as a watermark embedded in a host image.
Citation - WoS: 2
Citation - Scopus: 2
Clinical Decision Support Systems: From the Perspective of Small and Imbalanced Data Set
(Ios Press, 2019) Par, Oznur Esra; Sever, Hayri; Akcapinar Sezer, Ebru; Sever, Hayri; 11916; Bilgisayar Mühendisliği
Clinical decision support systems are data analysis software that supports health professionals' decision - making the process to reach their ultimate outcome, taking into account patient information. However, the need for decision support systems cannot be denied because of most activities in the field of health care within the decision-making process. Decision support systems used for diagnosis are designed based on disease due to the complexity of diseases, symptoms, and disease-symptoms relationships. In the design and implementation of clinical decision support systems, mathematical modeling, pattern recognition and statistical analysis techniques of large databases and data mining techniques such as classification are also widely used. Classification of data is difficult in case of the small and / or imbalanced data set and this problem directly affects the classification performance. Small and/or imbalance dataset has become a major problem in data mining because classification algorithms are developed based on the assumption that the data sets are balanced and large enough. Most of the algorithms ignore or misclassify examples of the minority class, focus on the majority class. Most health data are small and imbalanced by nature. Learning from imbalanced and small data sets is an important and unsettled problem. Within the scope of the study, the publicly accessible data set, hepatitis was oversampled by distance-based data generation methods. The oversampled data sets were classified by using four different machine learning algorithms. Considering the classification scores of four different machine learning algorithms (Artificial Neural Networks, Support Vector Machines, Naive Bayes and Decision Tree), optimal synthetic data generation rate is recommended.
Citation - WoS: 7
Citation - Scopus: 10
Extending a sentiment lexicon with synonym-antonym datasets: SWNetTR plus
(Tubitak Scientific & Technological Research Council Turkey, 2019) Saglam, Fatih; Sever, Hayri; Genc, Burkay; Sever, Hayri; 11916; Bilgisayar Mühendisliği
In our previous studies on developing a general-purpose Turkish sentiment lexicon, we constructed SWNetTR-PLUS, a sentiment lexicon of 37K words. In this paper, we show how to use Turkish synonym and antonym word pairs to extend SWNetTR-PLUS by almost 33% to obtain SWNetTR++, a Turkish sentiment lexicon of 49K words. The extension was done by transferring the problem into the graph domain, where nodes are words, and edges are synonym- antonym relations between words, and propagating the existing tone and polarity scores to the newly added words using an algorithm we have developed. We tested the existing and new lexicons using a manually labeled Turkish news media corpus of 500 news texts. The results show that our method yielded a significantly more accurate lexicon than SWNetTR-PLUS, resulting in an accuracy increase from 72.2% to 80.4%. At this level, we have now maximized the accuracy rates of translation-based sentiment analysis approaches, which first translate a Turkish text to English and then do the analysis using English sentiment lexicons.
Citation - WoS: 1
Modeling the symptom-disease relationship by using rough set theory and formal concept analysis
(World Acad Sci, Eng & Tech-waset, 2007) Bal, Mert; Sever, Hayri; Sever, Hayri; Kalipsiz, Oya; 11916; Bilgisayar Mühendisliği
Medical Decision Support Systems (MDSSs) are sophisticated, intelligent systems that can provide inference due to lack of information and uncertainty. In such systems, to model the uncertainty various soft computing methods such as Bayesian networks, rough sets, artificial neural networks, fuzzy logic, inductive logic programming and genetic algorithms and hybrid methods that formed from the combination of the few mentioned methods are used. In this study, symptom-disease relationships are presented by a framework which is modeled with a formal concept analysis and theory, as diseases, objects and attributes of symptoms. After a concept lattice is formed, Bayes theorem can be used to determine the relationships between attributes and objects. A discernibility relation that forms the base of the rough sets can be applied to attribute data sets in order to reduce attributes and decrease the complexity of computation.
Production and retrieval off rough classes in multi relations
(IEEE Computer Soc, 2007) Sever, Hayri; Görür, Abdül Kadir; Görür, Abdül Kadir; 11916; 107251; Bilgisayar Mühendisliği
Organizational memory in today's business world forms basis for organizational learning, which is the ability of an organization to gain insight and understanding from experience through experimentation, observation, analysis, and a willingness to examine both successes and failures. This basically requires consideration of different aspects of knowledge that may reside on top of a conventional information management system. Of them, representation, retrieval and production issues of meta patterns constitute to the main theme of this article. Particularly we are interested in a formal approach to handle rough concepts. We utilize rough classifiers to propose a preliminary framework based on minimal term sets with p-norms to extract meta patterns. We describe a relational rule induction approach, which is called rila. Experimental results are provided on the mutagenesis, and the KDD Cup 2001 genes data sets.
Citation - Scopus: 1
Text-Based Fake News Detection via Machine Learning
(Springer Science and Business Media Deutschland GmbH, 2021) Mertoğlu, U.; Sever, Hayri; Genç, B.; Sever, H.; 11916; Bilgisayar Mühendisliği
The nature of information literacy is changing as people incline more towards using digital media to consume content. Consequently, this easier way of consuming information has sparked off a challenge called “Fake News”. One of the risky effects of this notorious term is to influence people’s views of the world as in the recent example of coronavirus misinformation that is flooding the internet. Nowadays, it seems the world needs “information hygiene” more than anything. Yet real-world solutions in practice are not qualified to determine verifiability of the information circulating. Presenting an automated solution, our work provides an adaptable solution to detect fake news in practice. Our approach proposes a set of carefully selected features combined with word-embeddings to predict fake or valid texts. We evaluated our proposed model in terms of efficacy through intensive experimentation. Additionally, we present an analysis linked with linguistic features for detecting fake and valid news content. An overview of text-based fake news detection guidance derived from experiments including promising results of our work is also presented in this work. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Browse

Browsing Bilgisayar Mühendisliği Bölümü by Author "11916"