32 results
Search Results
2. Trafik Kaza Süresinin Tahmini İçin Topluluk Ağacı ve Sinir Ağları Performansının Karşılaştırılması.
- Author
-
Korkmaz, Hüseyin, Ertürk, Mehmet Ali, and Adak, Mehmet
- Abstract
Copyright of Journal of Transportation & Logistics / Ulaştırma ve Lojistik Dergisi is the property of Journal of Transportation & Logistics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
- Published
- 2024
- Full Text
- View/download PDF
3. ÇEKİŞMELİ ÜRETİCİ AĞLAR VE TRANSFER ÖĞRENİMİ KULLANILARAK GÖĞÜS X-RAY GÖRÜNTÜLERİNDEN COVID-19 TESPİTİ ÜZERİNE BİR DERLEME.
- Author
-
PEHLİVANOĞLU, Meltem KURT and ARABACI, Uğur Kadir
- Subjects
GENERATIVE adversarial networks ,X-ray imaging ,ARTIFICIAL intelligence ,INFECTIOUS disease transmission ,COVID-19 pandemic - Abstract
Copyright of SDU Journal of Engineering Sciences & Design / Mühendislik Bilimleri ve Tasarım Dergisi is the property of Journal of Engineering Sciences & Design and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
- Published
- 2022
- Full Text
- View/download PDF
4. C PROGRAMLAMA DİLİNDE KAYNAK KOD GÜVENLİĞİ: SECUREC.
- Author
-
KURT PEHLİVANOĞLU, Meltem, ÇALIŞIR, Sinan, GENÇ, Ceren, ODABAŞ, Duygu Evrim, and ÖZTÜRK, Berkehan
- Subjects
SECURITY systems software ,PROGRAMMING languages ,SOURCE code ,DESIGN software ,COMPUTER software security - Abstract
Copyright of SDU Journal of Engineering Sciences & Design / Mühendislik Bilimleri ve Tasarım Dergisi is the property of Journal of Engineering Sciences & Design and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
- Published
- 2022
- Full Text
- View/download PDF
5. A Smart Movie Suitability Rating System Based on Subtitle
- Author
-
Murat IŞIK
- Subjects
machine learning ,deep learning ,natural language processing ,nlp ,subtitles ,movie ratings ,parental guidelines ,Engineering (General). Civil engineering (General) ,TA1-2040 ,Science ,Science (General) ,Q1-390 - Abstract
With the enormous growth rate in the number of movies coming into our lives, it can be very challenging to decide whether a movie is suitable for a family or not. Almost every country has a Movie Rating System that determines movies’ suitability age. But these current movie rating systems require watching the full movie with a professional. In this paper, we developed a model which can determine the rating level of the movie by only using its subtitle without any professional interfere. To convert the text data to numbers, we use TF-IDF vectorizer, WIDF vectorizer and Glasgow Weighting Scheme. We utilized random forest, support vector machine, k-nearest neighbor and multinomial naive bayes to find the best combination that achieves the highest results. We achieved an accuracy of 85%. The result of our classification approach is promising and can be used by the movie rating committee for pre-evaluation. Cautionary Note: In some chapters of this paper may contain some words that many will find offensive or inappropriateness; however, this cannot be avoided owing to the nature of the work
- Published
- 2023
- Full Text
- View/download PDF
6. İÇİ BETON DOLU DAİRESEL KESİTLİ ÇELİK BORULARIN EKSENEL YÜK KAPASİTELERİNİN YAPAY SİNİR AĞLARI VE RASSAL ORMAN YÖNTEMLERİ İLE TAHMİNİ.
- Author
-
COSGUN, Cumhur
- Subjects
AXIAL loads ,LATERAL loads ,COLUMNS ,CONCRETE-filled tubes ,RANDOM forest algorithms ,CONCRETE columns - Abstract
Copyright of SDU Journal of Engineering Sciences & Design / Mühendislik Bilimleri ve Tasarım Dergisi is the property of Journal of Engineering Sciences & Design and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
- Published
- 2023
- Full Text
- View/download PDF
7. DERİN ÖĞRENME VE SAĞLIK ALANINDAKİ UYGULAMALARI.
- Author
-
KELEŞ, Ali
- Subjects
DEEP learning ,MACHINE learning ,HEALTH systems agencies ,GRAPHICS processing units ,ARTIFICIAL intelligence - Abstract
Copyright of Electronic Turkish Studies is the property of Electronic Turkish Studies and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
- Published
- 2018
- Full Text
- View/download PDF
8. Turbofan motorlarının kestirimci bakımında makine öğrenimi algoritmaları performanslarının karşılaştırılması.
- Author
-
Güler, Osman
- Abstract
Copyright of Nigde Omer Halisdemir University Journal of Engineering Sciences / Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi is the property of Nigde Omer Halisdemir Universitesi (NOHU), Muhendislik Fakultesi and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
- Published
- 2024
- Full Text
- View/download PDF
9. A Literature Review on Machine Learning in The Food Industry
- Author
-
Furkan Açıkgöz, Leyla Zeynep Verçin, and Gamze Erdoğan
- Subjects
classification ,food industry ,machine learning ,support vector machine ,Industrial engineering. Management engineering ,T55.4-60.8 ,Business ,HF5001-6182 - Abstract
Machine Learning (ML) has become widespread in the food industry and can be seen as a great opportunity to deal with the various challenges of the field both in the present and near future. In this paper, we analyzed 91 research studies that used at least two ML algorithms and compared them in terms of various performance metrics. China and USA are the leading countries with the most published studies. We discovered that Support Vector Machine (SVM) and Random Forest outperformed other ML algorithms, and accuracy is the most used performance metric.
- Published
- 2023
- Full Text
- View/download PDF
10. An Investigation into Artificial Intelligence (AI) in the English as a Foreign Language (EFL) Context
- Author
-
Şerife Fidan and Yusuf Kasimi
- Subjects
bibliometrics ,web of science (wos) ,artificial intelligence ,teaching english as a second language ,machine learning ,Education - Abstract
Using data from Bibliometrix and Web of Science, this study examined articles in the subject of language and linguistics that dealt with artificial intelligence (AI). The study used bibliometrics to uncover historical trends in AI in EFL. The study utilized Biblioshiny, a web-based tool in the bibliometrix package that analyses bibliographic database data, to examine downloaded Web of Science (WoS) data. The Bibliometrix R Package and Biblioshiny software created tables and graphs. The study searched the WoS website for studies with "Artificial Intelligence (AI)" in the title, abstract, and keywords to find bibliographic data. From 2013 to 2023, WoS focused on Language and Linguistics in Language Education. There were 1693 EFL AI papers. The study chose open-access publications to read the entire text. The present analysis examined 177 publications. Different bibliometric analysis techniques were employed to get the most usable data from research publications. Authors, publishing years, universities, countries, preferred journals, trendy topics, and keyword citation rates were all considered in the analysis. Findings showed an increase in publications over time and a growing interest in AI. Leading universities and prominent authors were identified. Depending on the country, different levels of engagement were observed. The distribution of data was provided via preferred journals. This study helps researchers and decision-makers evaluate AI research in language and linguistics.
- Published
- 2023
- Full Text
- View/download PDF
11. Machine Learning and Data Privacy in Digital Advertising
- Author
-
GÜLPINAR DEMİRCİ, Vildan
- Subjects
Makine Öğrenmesi ,Veri Gizliliği ,Dijital Reklamcılık ,Hedef Reklamcılık ,Yapay Zekâ ,Social Sciences, Interdisciplinary ,Sosyal Bilimler, Disiplinler Arası ,Machine Learning ,Data Privacy ,Digital Advertising ,Targeted Advertising ,Artificial Intelligence - Abstract
Dijital reklamcılık düşük reklam maliyetleri, hızlı ve etkili tüketici geri bildirimi, artan verimlilik ve ayrıntılı müşteri tabanı oluşturma avantajlarından dolayı şirketler için giderek daha önemli hale gelmektedir. Geleneksel reklamcılıkta daha çok sezgiye ve tecrübeye dayanan içerik üretme, dijital reklamcılıkta veriye dayalıdır. Böylece tüketicilerin dijital izlerine göre kişiselleştirilmiş hedef reklamlar sunulmaktadır. Hedef reklamcılık, dijital reklamcılığın odağına yerleşirken, bu alanda geliştirilen yöntemler hem şirketler hem de araştırmacılar için yeni ufuklar açmaktadır. Dijital reklamcılıkta hedefli reklamların sunulmasında teklif verme makineleri veya kişiye özel fiyat ve promosyon sunan fiyatlandırma motoru, genel olarak gelişmiş bir makine öğrenmesi algoritmasıyla gerçekleştirilmektedir. Makine öğrenmesi, şirketlere reklam üzerinde daha fazla kontrol gücü verirken, en önemli tartışma konusu ise reklamların kişiselleştirilmesi ve bunun sonucu olarak veri gizliliği ihlallerinin yaşanabilmesidir. Bu makale, makine öğrenmesi algoritmaları ile hedef reklamcılığın işletmelere sağladığı faydalar yanında, veri gizliliği endişelerine de odaklanarak konuyu bütüncül bir yaklaşımla ele almaktadır. Makalede hedef reklamcılığın getirdiği yüksek karlılığı korurken, tüketicilerin veri gizliliği endişesiyle satın alma davranışından vazgeçmelerini engelleyecek adımların neler olduğu tartışılmıştır. Sonuç olarak tüketici verilerinin dijital reklamcılıkta kullanılmasının önemi ortaya çıkmıştır. Bununla birlikte makine öğrenmesi algoritmaları ile kişiye özgü veri gizlilik ayarlarının yapılarak mahremiyetin, tüketicinin gizlilik sınırları çerçevesinde yapılandırılması gerektiği vurgulanmaktadır. Böylece şirketlerin hem kârlılığı koruması hem de veri gizliliği nedeniyle tüketici kayıplarının önüne geçmesi mümkün olacaktır., Digital advertising provides great advantages such as lower advertising costs, fast and reliable feedbacks from customers, increased efficiency, and the ability to create detailed databases of customers, which make it increasingly more important for companies. Production of contents is mainly based on intuition and experience in conventional advertising, while it is based on data in digital advertising. This makes it possible to offer targeted advertisements that are customized according to the digital trails of consumers. Targeted advertising has become the focus of digital advertising, and methods that have been developed in this field open new horizons both for companies and researchers. To provide targeted advertisements for digital advertising, bidding machines or pricing engines that offer customized prices and promotions are typically generated by means of a machine learning algorithm. Machine learning provides companies with more power to control advertisements; but the most important issue of debate is the customization of advertisements and therefore the possibility that data privacy is compromised. This paper discusses the issue with a holistic approach by focusing on the concerns of data privacy in addition to the benefits of targeted advertisements and machine learning algorithms for businesses. This paper also discusses the steps that would prevent consumers from not proceeding with a purchase due to concerns about data privacy, while maintaining the high level of profitability gained thanks to targeted advertisements. As a result, the importance of using consumer data in digital advertising was emphasized. However, privacy should be configured within the limits of consumer privacy by making personal data privacy settings with machine learning algorithms. Thus, it will be possible for companies both to protect their profitability and prevent consumer losses due to data privacy.
- Published
- 2022
12. Hukuk Analitiği.
- Author
-
ÇAMKERTEN, Ali Semih
- Subjects
SOCIAL network analysis ,MACHINE learning - Abstract
Copyright of Necmettin Erbakan University School of Law Review is the property of Necmettin Erbakan University School of Law Review and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
- Published
- 2023
- Full Text
- View/download PDF
13. YAPAY ZEKÂ VE DİN PSİKOLOJİSİ.
- Author
-
ÇİNİCİ, MURAT and KIZILGEÇİT, MUHAMMED
- Abstract
Copyright of Diyanet Ilmi Dergi is the property of Diyanet Isleri Baskanligi Yayinlari and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
- Published
- 2023
14. İKLİM DEĞİŞİKLİĞİ VE YAPAY ZEKÂ: FIRSATLAR VE SORUNLAR.
- Author
-
TUĞAÇ, Çiğdem
- Subjects
CLIMATE change ,ARTIFICIAL intelligence ,GREENHOUSE gas mitigation ,ECOLOGICAL impact - Abstract
Copyright of Hitit Journal of Social Sciences is the property of Hitit University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
- Published
- 2023
- Full Text
- View/download PDF
15. Performance Analysis of Machine Learning Algorithms in Intrusion Detection Systems
- Author
-
Mustafa İlbaş, Yusuf Sönmez, and Fethi Mustafa Çimen
- Subjects
makine öğrenimi ,ids ,knn ,machine learning ,Technology ,Engineering (General). Civil engineering (General) ,TA1-2040 ,Science ,Science (General) ,Q1-390 - Abstract
With the developing technology, the need for the dissemination and protection of information is becoming increasingly important. Recently, attacks on information systems have increased significantly. In addition to the rise in the number of attacks, attacks of different types pose a great threat to systems. As a result of these attacks, institutions and users suffer serious damages. At this point, Intrusion Detection Systems (IDS) have a very important position. The pre-detection of these attacks on the systems and the preparation of the necessary reports can reduce the impact of the threats that may be encountered in the future. Recent studies are carried out so as to increase the performance of IDS. In this paper, classification was made using NSL-KDD dataset and SVM, KNN, Bayesnet, NavieBayes, J48 and Random Forest algorithms, and it was aimed to compare performance of these classifications by using WEKA. Consequently, it has been reached that the KNN algorithm had the best performance with an accuracy rate of 98.1237 %. In addition, the effect of increasing the number of folds and neighborhoods on the classification result has been examined comparatively.
- Published
- 2021
- Full Text
- View/download PDF
16. İstenmeyen Elektronik Posta (Spam) Tespitinde Karar Ağacı Algoritmalarının Performans Kıyaslaması.
- Author
-
AKÇETİN, Eyüp and ÇELİK, Ufuk
- Abstract
Copyright of Journal of Internet Applications & Management / İnternet Uygulamaları ve Yönetimi Dergisi is the property of Journal of Internet Applications & Management and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
- Published
- 2014
- Full Text
- View/download PDF
17. YAPAY ZEKÂ DESTEKLİ KİŞİSELLEŞTİRME ALGORİTMALARININ TÜKETİCİ ZİHNİNDE FİLTRE BALONU YARATMA ETKİSİNİN İNCELENMESİ.
- Author
-
KARAMAN, Özlem
- Subjects
CONSUMER behavior ,POINT of view (Literature) ,CONSUMER psychology ,ARTIFICIAL intelligence ,MACHINE learning ,INTERNET marketing ,ECONOMIC bubbles - Abstract
Copyright of Visionary E-Journal / Vizyoner Dergisi is the property of Suleyman Demirel University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
- Published
- 2021
- Full Text
- View/download PDF
18. A Machine Learning Based Early Diagnosis System for Mesothelioma Disease
- Author
-
Nagihan Çekiç and Zehra Karapınar Şentürk
- Subjects
erken tanı ,mezotelyoma hastalığı ,makine öğrenmesi ,early diagnosis ,mesothelioma disease ,machine learning ,Technology ,Engineering (General). Civil engineering (General) ,TA1-2040 ,Science ,Science (General) ,Q1-390 - Abstract
Mesothelioma is pleura cancer that cause death in about one year after diagnosis. The disease causes pain and shortness of breath. Patients have a CT (Computed Tomography)-scan and lung x-ray traditionally, but the exact method is biopsy. There are also different biopsy methods for its diagnosis. Its prevalence is one or two in a million around the world, but for Turkey it is disastrous. Five hundred people are diagnosed as mesothelioma every year in Turkey. This serious rate makes early diagnosis systems crucial for mesothelioma. In this paper, a machine learning based early detection system has been proposed for this fatal disease. An open database is used for the experiments and different methods have been applied to the problem of diagnosing mesothelioma disease. Accuracy and sensitivity performance metrics were used for the evaluation of the methods. The results show the diagnostic performance of different machine learning methods and present a successful early diagnosis system.
- Published
- 2020
- Full Text
- View/download PDF
19. ADOKEN: MR İÇİN DERİN ÖĞRENME TABANLI KARAR DESTEK YAZILIMI.
- Author
-
EREN, Hakan Alp, OKYAY, Savaş, and ADAR, Nihat
- Subjects
MAGNETIC resonance imaging ,DEEP learning ,CONVOLUTIONAL neural networks ,MACHINE learning ,MEDICAL research personnel ,VISUAL learning - Abstract
Copyright of SDU Journal of Engineering Sciences & Design / Mühendislik Bilimleri ve Tasarım Dergisi is the property of Journal of Engineering Sciences & Design and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
- Published
- 2021
- Full Text
- View/download PDF
20. A collective learning approach for semi-supervised data classification
- Author
-
Nur Uylaş Satı
- Subjects
semi- supervised data classification ,clustering method ,supervised data classification ,machine learning ,mathematical programming ,yarı-gözetimli veri sınıflandırma ,kümeleme yöntemi ,gözetimli veri sınıflandırma ,makine öğrenme ,matematiksel programlama ,Engineering (General). Civil engineering (General) ,TA1-2040 - Abstract
Semi-supervised data classification is one of significant field of study in machine learning and data mining since it deals with datasets which consists both a few labeled and many unlabeled data. The researchers have interest in this field because in real life most of the datasets have this feature. In this paper we suggest a collective method for solving semi-supervised data classification problems. Examples in R1 presented and solved to gain a clear understanding. For comparison between state of art methods, well-known machine learning tool WEKA is used. Experiments are made on real-world datasets provided in UCI dataset repository. Results are shown in tables in terms of testing accuracies by use of ten fold cross validation.
- Published
- 2018
21. Gerçek hayat tweet analizi için çevrimiçi metin sınıflandırması
- Author
-
Ersin Yar, Ibrahim Delibalta, Suleyman S. Kozat, and Lemi Baruh
- Subjects
Normalization (statistics) ,Tweet analysis ,Noisy text analytics ,business.industry ,Computer science ,Feature vector ,Dimensionality reduction ,Natural language processing ,Feature extraction ,Normalization (image processing) ,020206 networking & telecommunications ,02 engineering and technology ,Machine learning ,computer.software_genre ,Computationally efficient ,Regression ,Big data ,Text processing ,Text classification ,0202 electrical engineering, electronic engineering, information engineering ,Selection (linguistics) ,Artificial intelligence ,business ,computer - Abstract
Date of Conference: 16-19 May 2016 Conference Name: IEEE 24th Signal Processing and Communications Applications Conference, SIU 2016 In this paper, we study multi-class classification of tweets, where we introduce highly efficient dimensionality reduction techniques suitable for online processing of high dimensional feature vectors generated from freely-worded text. As for the real life case study, we work on tweets in the Turkish language, however, our methods are generic and can be used for other languages as clearly explained in the paper. Since we work on a real life application and the tweets are freely worded, we introduce text correction, normalization and root finding algorithms. Although text processing and classification are highly important due to many applications such as emotion recognition, advertisement selection, etc., online classification and regression algorithms over text are limited due to need for high dimensional vectors to represent natural text inputs. We overcome such limitations by showing that randomized projections and piecewise linear models can be efficiently leveraged to significantly reduce the computational cost for feature vector extraction from the tweets. Hence, we can perform multi-class tweet classification and regression in real time. We demonstrate our results over tweets collected from a real life case study where the tweets are freely-worded, e.g., with emoticons, shortened words, special characters, etc., and are unstructured. We implement several well-known machine learning algorithms as well as novel regression methods and demonstrate that we can significantly reduce the computational complexity with insignificant change in the classification and regression performance.
- Published
- 2016
22. IoT Güvenliği İçin Kullanılan Makine Öğrenimi ve Derin Öğrenme Modelleri Üzerine Bir Derleme
- Author
-
Satılmış, Hami, Akleylek, Sedat, OMÜ, Mühendislik Fakültesi, Bilgisyar Mühendisliği Bölümü, Satılmış, Hami, and Akleylek, Sedat
- Subjects
Computer Science, Information System ,machine learning ,IoT güvenliği ,deep learning,IoT security,machine learning ,IoT security ,derin öğrenme,IoT güvenliği,makine öğrenimi ,deep learning ,Bilgisayar Bilimleri, Bilgi Sistemleri ,makine öğrenimi ,derin öğrenme - Abstract
Nesnelerin internetini (internet of things - IoT) oluşturan cihazlar ve bu cihazları birbirine bağlayan ağlar hızlı bir şekilde yaygınlaşmaktadır ve evrim geçirmektedir. Buna paralel olarak, IoT cihazlarına ve ağlarına yönelik saldırılar da hız kesmeden artmaya devam etmektedir. Bu derleme çalışmasında, genel olarak IoT ağlarındaki anormallik tabanlı saldırıları tespit etmek ve azaltmak için önerilen, makine öğrenimi ve derin öğrenme modellerinden oluşan güncel yaklaşımlar özetlenmiştir. Önerilen yaklaşımlar hakkında kısa bilgiler verilmektedir ve bu yaklaşımların avantajlarından ve dezavantajlarından bahsedilmektedir. Bu çalışmanın ana hedefi olarak, önerilen yaklaşımlarda kullanılan makine öğrenimi ve derin öğrenme modelleri ile ilgili, üç araştırma sorusunun yanıtı aranmaktadır. Bu araştırma sorularından birincisi, “IoT güvenliğinde kullanılan makine öğrenimi ve derin öğrenme modelleri, hangi metriklerle değerlendirilmektedir? “, ikincisi, “IoT güvenliği açısından, makine öğrenimi ve derin öğrenme modellerinde hangi veri kümeleri kullanılmaktadır? “ ve üçüncüsü ise, “IoT güvenliğinde hangi makine öğrenimi ve derin öğrenme modelleri kullanılmaktadır ve bunların uygulama alanları nelerdir? “. Bu çalışmada son olarak, incelenen çalışmalardaki eksiklikler tespit edilmektedir. Böylece, IoT güvenliği ile ilgili gelecekteki çalışmalar için bir bakış açısı sağlanmaktadır, Internet of things (IoT) devices and networks connecting these devices are rapidly spreading and evolving. In parallel, attacks against IoT devices and networks continue to increase unabated. In this review, current approaches, consisting of machine learning and deep learning models, which are recommended to detect and mitigate anomaly-based attacks in IoT networks in general, are summarized. Brief information about the proposed approaches is given, and the advantages and disadvantages of these approaches are mentioned. As the main objective of this paper, answers to three research questions about machine learning and deep learning models used in the proposed approaches are sought. The first of these research questions is, “With which metrics are machine learning and deep learning models used in IoT security evaluated? “, the second is, “In terms of IoT security, which datasets are used in machine learning and deep learning models? “ and the third is, “Which machine learning and deep learning models are used in IoT security and what are their application areas? “. Finally, deficiencies encountered in the studies are noted. Thus, a perspective is provided for future work on IoT security.
- Published
- 2021
23. MOBİL AĞLARDA LOKASYON TAHMİNİ
- Author
-
Kılıç, Ahmed Hakan, Boyacı, Ali, Yarkan, Serhan, and Fakülteler, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü
- Subjects
Base Station ,Machine Learning ,RSRP ,Baz İstasyonu ,RSRQ ,Timing Advance (TA) ,Mobil Ağlar ,GPS ,Mobile Networks ,Makine Öğrenmesi - Abstract
This paper reports the location estimation on Mobile networks using Base Station (BTS) data. Processed data have been collected from the field as TA (Timing Advance), RSRP (Reference Signal Received Power), and RSRQ (Reference Signal Received Quality) measurements. We also gathered the corresponding Global Positioning System (GPS) to the measurements. Location estimation results compared to the actual location. We gathered the accurate sites of the users to increase the service quality of the BTS. This article was produced from the thesis titled “Location Estimation on Mobile Networks.” Bu makale, Baz İstasyonu (BTS) verilerini kullanarak Mobil ağlarda konum tahminini raporlamaktadır. İşlenen veriler sahadan TA (Timing Advance), RSRP (Reference Signal Received Power) ve RSRQ (Reference Signal Received Quality) ölçümleri olarak toplanmıştır. Ölçümlere karşılık gelen Global Konumlandırma Sistemi (GPS) verileri de toplanmıştır. Lokasyon tahminleri gerçek lokasyonla (GPS) karşılaştırılmıştır. Baz istasyonunun hizmet kalitesini artırmak amaçlanmıştır. Bu makale “Mobil Ağlarda Lokasyon Tahmini” başlıklı tezden üretilmiştir.
- Published
- 2021
24. Ekonometri ve Makine Öğrenmesi: Tercih Modelleri ve Sınıflandırma Algoritmaları Açısından Değerlendirmeler
- Author
-
Türküz, Elanur and ÇAĞLAYAN AKAY, EBRU
- Subjects
Machine Learning ,Social ,Qualitative Choice Models ,Yüksek Boyutluluk ,Sınıflandırma Algoritmaları ,Ekonometri ,Nitel Tercih Modelleri ,Econometrics ,High Dimensionality ,Ekonometri,Makine Öğrenmesi,Nitel Tercih Modelleri,Sınıflandırma Algoritmaları,Yüksek Boyutluluk ,Makine Öğrenmesi ,Classification Algorithms ,Sosyal - Abstract
Ekonometri ve makine öğrenmesi geniş kullanım alanlarına ve tekniklere sahiptir. Bu çalışmada ekonometride bağımlı değişkenin nitel özellik gösterdiği durumda kullanılan nitel tercih modelleri ile makine öğrenmesinde kullanılan sınıflandırma algoritmalarına yer verilmiş olup, bu doğrultuda ekonometri ile makine öğrenmesi arasında nasıl bir köprü kurulabileceğinin araştırılması amaçlanmıştır. Büyük verilerin ekonometride yarattığı sorunlar ve makine öğrenmesinin yapabileceği katkılar araştırılmış ve kestirim tabanlı sınıflandırma algoritmalarının çekimser kaldığı nedensellik araştırmalarındaki konumu incelenerek ekonometrinin sağlayabileceği katkılar ortaya konulmuştur. Both econometrics and machine learning operate in a broad area of study. Therefore, this paper limits the scope to where the dependent variable is categoric and investigates the relationship between discrete choice models and classification algorithms. In particular, we address the challenges of big data in econometrics and the contributions of machine learning. The article also gives an overview of why classification algorithms have abstained from causality and how the machine learning community could benefit from econometrics
- Published
- 2020
25. Demand forecasting with artificial neural networks: White goods production planning example
- Author
-
Türk, Emre and Kiani, Farzad
- Subjects
Machine Learning ,Engineering ,Production Planning ,Mühendislik ,Üretim Planlama ,Üretim Planlama,Yapay Sinir Ağları,Makine Öğrenmesi ,Yapay Sinir Ağları ,Makine Öğrenmesi ,Artificial Neural Networks ,Production Planning,Artificial Neural Networks,Machine Learning - Abstract
Üretimplanlama için doğru bir talep tahminin yapılması oldukça önemli birparametredir. Müşterilerin gelecekteki talep eğilimleri, piyasa durumu vemevsimsellik gibi birçok faktörden etkilenebilir. Üretim planlama, işletmelerinhedefleri doğrultusunda üretim politikaları, üretim programları ve üretimleilgili süreçlerin planlanmasıdır. Doğru bir talep tahmini yapmak oldukça kritikbir öneme sahip olup kaynakların daha verimli kullanılmasına olanaksağlayabilecektir. Talep tahmin metotları, kantitatif ve kalitatif olarak ikiana başlık altında toplanır. Kantitatif tahmin metodu, insanların kenditecrübelerinden oluşan bilgiye dayanak olarak tahmin yapma yöntemidir.Kalitatif metot ise, sayısal verilerin matematiksel modellemelerledesteklenerek ortaya çıkan sonuçlara dayanarak tahmin yapma yöntemidir. Yapaysinir ağları modeli kantitatif tahmin metotlarının arasında yer alır. Buçerçevede, makine öğrenme yöntemleri özellikle destek vektör makinesi, en yakınn-komşu, regresyon ve yapay sinir ağları ve bayes ağları gibi metotlar vealgoritmaların kullanılması uygun olabilir. Bu makalede yapay sinir ağlarımetodu kullanılarak talep tahmini problemi minimum hatayı veren sinir ağlarıylaçözülmüştür. Yapay sinir ağları metodu, belirli değişkenlere bağlı olan bir taleptahminini önceki örneklerin verileriyle yapay sinir ağlarının öğretilmesiyleileriye dönük doğru talep tahmini yapması hedeflenmektedir., Demand forecastingrepresents an important part of production planning because itcan estimate the future demand of products and services and the amount ofresources that needs to be allocated in order to accomplish that demand. As thedemands can vary as the times passes, the production plan must beable to face those variations. Demand estimation methods are classified undertwo main headings: quantitative and qualitative. The quantitative estimationmethod is a method of estimating the basis of knowledge of people's ownexperiences. The qualitative method is the method of estimating the numericaldata based on the results obtained by supporting the mathematical modeling.Artificial neural network model is among quantitative estimation methods.Therefore, it may be appropriate to use methods and algorithms such as machinelearning methods, especially support vector machine, nearest n-neighbor,regression and artificial neural networks and Bayesian networks. In this paper,we focus on the mining of the time series formed by all the past results usingan artificial neural network-based simulation system that is ableto identify an appropriate production forecast. The results ofthe production simulations are used as historical data in order toforecast the future demands and the amount of time needed to satisfy them. Thetime series forecast results show that data mining can be used in this domainin order to extract patterns that can be used to optimizethe production process.
- Published
- 2019
26. A web application for measuring performance of fire stations through machine learning techniques
- Author
-
Akkol, Ekin, Aydın, Can, and Yönetim Bilişim Sistemleri Ana Bilim Dalı
- Subjects
Bilim ve Teknoloji ,Machine learning ,Dynamic analysis ,Data analysis ,Management information systems ,Web based applications ,Decision support systems ,Science and Technology ,Business intelligence - Abstract
Bilişim sistemlerinde meydana gelen hızlı gelişmeler, verilerin organizasyonların karar verme sürecinde etkin bir şekilde kullanımına olanak sağlamaktadır. Ham verilerin işlenmesi ve analiz edilerek karar verme süreçlerine dahil edilmesi, kamu kurum ve kuruluşlarında daha etkin yönetim, performans ölçümü ve kamu kaynaklarının etkin kullanımı gibi konularda büyük önem taşımaktadır. Bu çalışma kapsamında İzmir İtfaiye Daire Başkanlığı'nın karar verme süreçlerini doğrudan destekleyebilecek yapıda bir sistem tasarlanmıştır. Çalışma, İtfaiye Daire Başkanlığı'ndan yetkili kişilerle sürekli fikir alışverişi yapılarak, tamamen itfaiyenin ihtiyaçları gözetilerek gerçekleştirilmiştir. Karar vericilere karar verme süreçlerinde destek olmayı, anlık ve geleceğe yönelik çıkarımlarla var olan verilerden yararlı bilgiler elde etmeyi amaçlayan web tabanlı bir uygulama geliştirilmiştir. Uygulamanın geliştirilmesi aşamasında İzmir İtfaiye Daire Başkanlığı tarafından oluşturulmuş, kâğıt üzerinde tutulan ve arşivlerde saklanan İtfaiye Yangın Raporu formlarının dijitalleştirilmesi sağlanmıştır. Dijitalleştirilerek veri tabanına kaydedilen formlardan, çeşitli sorgular ve analizler yapılarak itfaiyenin mevcut durumu ve performansı ortaya konulmuştur. Ayrıca geleceğe yönelik tahminlemeler de yapılarak uygulama, mevcut durumun ve performansın yanında, ileriye dönük bilgiler de sunan bir sistem haline getirilmiştir. Geleceğe yönelik tahminlemeler yapılırken zaman serisi analizlerinden ve makine öğrenmesi tekniklerinden yararlanılmıştır. Tüm sorgu, analiz ve tahminlemeler web uygulamasında çeşitli grafikler, haritalar ve sayısal değerler olarak karar vericilere raporlanmıştır. İtfaiye Yangın Raporu formlarının arşivlerde değil veri tabanında saklanması; verilerin kaybolma, deforme olma ve karar verme sürecine etkin olarak katılamaması gibi olası risklerin önüne geçilmesinde önemli bir role sahiptir. Uygulama, veri tabanına kaydedilen ham verilerin yararlı bilgilere dönüştürülmesiyle özellikle stok yönetimi, insan kaynakları yönetimi, itfaiye istasyonu yer seçimi gibi konularda karar verme desteği sağlayacaktır. The rapid development of information systems enables the efficient use of data in decision-making process of organizations. The processing and analysis of raw data and including them in decision-making processes have a great importance for more effective management, performance measurement and effective use of public fundings in public institutions and organizations. Within the scope of this study, a system was designed to support the decision-making processes of the Izmir Fire Department directly. The study was carried out by constantly exchanging ideas with the authorized persons of the Fire Department and taking into consideration the needs of the fire brigade. A web-based application, which aims to support the decision-maker in the decision-making process and to obtain useful information from the existing data by making instant and future inferences, was developed. During the development process of the application, the Fire Report forms, which were created, kept on paper and stored in archives by Izmir Fire Department, were digitized. The current situation and performance of the fire brigade has been revealed by making various queries and analyzes from the forms which are saved to database by digitizing them. In addition, by making forecasts for the future, the application has been turned into a system that provides forward-looking information and shows the current situation and performance. Time series analysis and machine learning techniques were used to make predictions for the future. Queries, analyzes and predictions in this web application were reported to the decision maker with graphs, numerical values and maps. Keeping fire reports forms into databases instead of archives has an important role to prevent risks such as absence of data, having deformed data, and non-particpation of data into decision making process effectively. The application will provide support for decision-making on issues such as stock management, human resource management, fire station location selection, by converting raw data into useful information. 101
- Published
- 2019
27. Meme Kanseri Teşhisi İçin Yeni Bir Skor Füzyon Yaklaşımı
- Author
-
Can Eyüpoğlu and Erdem Yavuz
- Subjects
Score Fusion,Breast Cancer Diagnosis,Neural Network,Feed Forward,Generalized Regression ,Artificial neural network ,business.industry ,Common disease ,Mühendislik ,General Medicine ,Disease ,Machine learning ,computer.software_genre ,medicine.disease ,Performance results ,Score fusion ,Breast cancer ,Engineering ,Skor Füzyon,Meme Kanseri Teşhisi,Sinir Ağı,İleri Besleme,Genel Regresyon ,medicine ,Feedforward neural network ,Artificial intelligence ,business ,computer - Abstract
Early diagnosis of breast cancer disease is critical forpatients to recover from this disease entirely as it is a common disease allover the world. In order to facilitate the diagnosis of the disease, medicaldoctors can benefit from computer-aided expert systems. In this paper, a scorefusion method based on generalized regression neural network (GRNN) and feedforward neural network (FFNN) has been proposed so as to split breast cancerdata samples into benign or malignant classes. The proposed method is tested onthe Wisconsin Diagnostic Breast Cancer (WDBC) dataset. The utilities of thesebasic neural networks and the proposed method are examined and comparative performanceresults are presented. The experimental results show that the proposed methodis promising for the diagnosis of breast cancer and may be used as an assistingtool in the decision-making of medical professionals., Meme kanseri tüm dünyada yaygın birhastalık olması sebebiyle hastalığın erken teşhisi, hastaların bu hastalıktantamamen kurtulabilmeleri açısından kritik öneme sahiptir. Hastalığın teşhisinikolaylaştırmak için tıp doktorları bilgisayar destekli uzman sistemlerdenyararlanabilmektedir. Bu çalışmada meme kanseri veri örneklerini iyi huylu veyakötü huylu sınıflarına ayırmak için genel regresyon sinir ağı (Generalized RegressionNeural Network-GRNN) ve ileri beslemeli sinir ağı (Feed Forward Neural Network-FFNN)temelli bir skor füzyon yöntemi önerilmiştir. Önerilen yöntem Wisconsin TeşhisMeme Kanseri (Wisconsin Diagnostic Breast Cancer-WDBC) veri seti üzerinde testedilmiştir. Bu iki temel ağın ve önerilen yöntemin kullanışlılığı incelenmiş veperformans sonuçları karşılaştırmalı olarak sunulmuştur. Önerilen yöntemsınıflandırma doğruluğu bakımından literatürde WDBC veri setini kullanarakyapılan mevcut çalışmalar ile kıyaslanmıştır. Elde edilen deneysel sonuçlarönerilen yöntemin, meme kanseri teşhisi için umut vadettiğini ve tıpuzmanlarının hastalığa ilişkin karar vermelerinde yardımcı bir araç olarakkullanılabileceğini göstermektedir.
- Published
- 2018
28. Veri bağlanımı için yüksek verimli yinelemeli sinir ağı yapısı
- Author
-
Tolga Ergen and Emir Ceyani
- Subjects
Gradient descent ,business.industry ,Stochastic process ,Computer science ,Long short term memory network ,Matrix factorization ,Ef-operator ,020206 networking & telecommunications ,02 engineering and technology ,Machine learning ,computer.software_genre ,Matrix decomposition ,Nonlinear system ,Exponentiated gradient ,Stochastic gradient descent ,Recurrent neural network ,0202 electrical engineering, electronic engineering, information engineering ,020201 artificial intelligence & image processing ,Artificial intelligence ,Architecture ,business ,computer ,Efficient energy use - Abstract
Date of Conference: 2-5 May 2018 In this paper, we study online nonlinear data regression and propose a highly efficient long short term memory (LSTM) network based architecture. Here, we also introduce on-line training algorithms to learn the parameters of the introduced architecture. We first propose an LSTM based architecture for data regression. To diminish the complexity of this architecture, we use an energy efficient operator (ef-operator) instead of the multiplication operation. We then factorize the matrices of the LSTM network to reduce the total number of parameters to be learned. In order to train the parameters of this structure, we introduce online learning methods based on the exponentiated gradient (EG) and stochastic gradient descent (SGD) algorithms. Experimental results demonstrate considerable performance and efficiency improvements provided by the introduced architecture.
- Published
- 2018
29. Predicting instructor performance by feature selection and machine learning methods
- Author
-
Anadolu Üniversitesi, Çiftçi, Fatih, Kaleli, Cihan, and Günal, Serkan
- Subjects
Machine Learning ,Eğitimsel Veri Madenciliği ,Performance Evaluation ,Öznitelik Seçme ,İnstructor Performance ,Performans Kıymetlendirme ,Feature Selection ,Eğitmen Performansı ,Makine Öğrenmesi ,Educational Data Mining - Abstract
Günümüzde hayatın her sektöründe işlenen veri miktarının artması, veri madenciliğin giderek daha popüler hale gelmesine yol açmış ve yüksek miktarda verinin artan bir karmaşıklıkta işlenmesi ihtiyacı doğmuştur. Finanstan, sağlığa, savunmadan eğitime onlarca sektörün sorunlarını çözmek adına gün geçtikçe farklı yöntemler geliştirilmekte, sosyal, ekonomik, bilimsel birçok problemin çözümü adına veri madenciliği yöntemlerine başvurulmaktadır. Eğitilen ve eğiten sayısının gün geçtikçe arttığı eğitim sektöründe ise, sistemin başarısının geliştirilebilmesi için, gerek eğitilen gerekse eğitimcilerinin performanslarının takip edilmesi ve kıymetlendirilmesi ihtiyacı, eğitimsel veri madenciliği kavramını doğurmuştur. Bu alanda yapılan çalışmalar genel olarak, öğrenci performansı konularına yoğunlaştığından, eğitmen performansı konusunda daha çok çalışmaya ihtiyaç duyulmaktadır. Eğitimsel veri madenciliği alanında öznitelik seçme ile birleştirilmiş makine öğrenmesi kullanan çalışmaların genel olarak öğrenci performansı üzerine yoğunlaştığı, ancak az sayıdaki çalışmanın eğitmen performansı üzerinde durduğu görülmüştür. Bu çalışmamızda, eğitmen performansının eğitimsel veri madenciliği yöntemleriyle nasıl tespit edilebileceği üzerinde durulmuştur. Çalışma kapsamında Gazi Üniversitesi öğrencilerinin eğitmenleri hakkında doldurdukları bir Likert Ölçekli Anket veri seti üzerinde çalışılmış, çeşitli öznitelik indirgeme algoritmaları ve farklı makine öğrenme yöntemleriyle veri seti kıymetlendirilmiş ve eğitmenlerin performansları tahmin edilmiştir. Elde edilen sonuçlara göre genetik algoritma ile öznitelik seçmenin, kullanılan veri seti için diğer yöntemlere kıyasla en iyi sonucu verdiğini göstermiş ve 33 tane öznitelik yerine 19 öznitelik kullanılabileceği ortaya çıkarılmıştır. Genetik algoritma ile birlikte makine öğrenmesi yöntemi olarak derin öğrenme kullanımı ile birlikte %97,70 bir tahmin doğruluk performansına ulaşılmış ve bu değerin tüm özniteliklerin kullanılması ile elde edilebilecek değerden yüksek olduğu görülmüştür. Bu çalışmayı diğerlerinden farklı kılan özelliği ise, indirgenmiş öznitelik sayısı ve makine öğrenmesini birleştirmesinin yanında, eğitmen performanslarının sıralanması işlemini de somut olarak yapmasıdır., Today, increasing amount of data in all sector of life, make data mining more popular, and high amount of data in increasing complexity demanded to acquit. Different methods developed day by day, for solving problems at many sectors like finance, health, defense, and education, applied to data mining for many social, economic, and scientific issues. In the education area, where both number of instructors and students always increase, for enhancing system performance, it is needed to observe and evaluate the performance of students and instructors and such situation causes to reveal a new concept Educational Data Mining. Research in this area generally focuses on student performance. Thus, there is a need for research in instructor performance. Research using machine learning combined with attribute selection in the field of educational data mining have focused on student performance in general, but few studies have focused on instructor performance. In this paper, it was discussed how the performance of the instructor can be determined by educational data mining methods. A Likert type questionnaire dataset on opinions of the Gazi University’s student regarding their instructor’s teaching performance is used in this research and different feature reduction, and machine learning algorithms are used for evaluating the data set and performances of instructors. According to the obtained results, it has been revealed that the feature selection with genetic algorithm gives the best result for the used data set compared to the other methods and 19 attributes can be used instead of 33 attributes. Utilizing genetic algorithm and deep learning as a machine learning method has achieved a predictive accuracy performance of 97.70 %, which is higher than the value that can be achieved by using all the attributes. This study differs from the others in that it combines the reduced number of attributes and machine learning, as well as the ordering of instructor performances in concrete terms.
- Published
- 2018
30. A reduced probabilistic neural network for the classification of large databases
- Author
-
Abdelkader Benyettou and Abdelhadi Lotfi
- Subjects
General Computer Science ,Artificial neural network ,Database ,Biometrics ,Basis (linear algebra) ,business.industry ,Computer science ,Time delay neural network ,Computer Science::Neural and Evolutionary Computation ,Retraining ,Neocognitron ,Pattern recognition ,Machine learning ,computer.software_genre ,Probabilistic neural network ,ComputingMethodologies_PATTERNRECOGNITION ,Computer Science::Computer Vision and Pattern Recognition ,Classification,pattern recognition,reduced probabilistic neural network,handwritten digit recognition,optimization ,Pattern recognition (psychology) ,Artificial intelligence ,Electrical and Electronic Engineering ,business ,computer - Abstract
The probabilistic neural network (PNN) is a special type of radial basis neural network used mainly for classification problems. Due to the size of the network after training, this type of network is usually used for problems with a small-sized training dataset. In this paper, a new training algorithm is presented for use with large training databases. Application to the handwritten digit database shows that the reduced PNN performs better than the standard PNN for all of the studied cases with a big gain in size and processing speed. This new type of neural network can be used easily for problems with large training databases like biometrics and data mining applications. An extension of the network is possible for new training samples and/or classes without retraining.
- Published
- 2015
31. RULE LEARNING WITH MACHINE LEARNING ALGORITHMS AND ARTIFICIAL NEURAL NETWORKS
- Author
-
Uzun, Yusuf, Tezel, Gülay, and Selçuk Üniversitesi
- Subjects
Machine Learning ,Quantitative Biology::Neurons and Cognition ,Neural Networks ,Learning Rules ,Computer Science::Neural and Evolutionary Computation ,Classification - Abstract
Machine learning, a branch of artificial intelligence, is a scientific discipline that is concerned with the design and development of algorithms that allow computers to evolve behaviors based on empirical data, such as from sensor data or databases. Artificial neural networks are composed of interconnecting artificial neurons (programming constructs that mimic the properties of biological neurons). Artificial neural networks may either be used to gain an understanding of biological neural networks, or for solving artificial intelligence problems without necessarily creating a model of a real biological system. In this paper, we made analysis with machine learning algorithms and artificial neural networks classification from instances in data set. Furthermore, machine learning algorithms and artificial neural networks with constituted rules.
- Published
- 2012
32. A simulational comparison of intelligent control algorithms on a direct drive manipulator
- Author
-
E. Murat Esin, Ertuğrul Akbaş, Maltepe Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Akbaş, Ertuğrul, and Esin, Murat
- Subjects
Direct inverse modeling architecture ,Computational complexity theory ,Computer science ,General Mathematics ,Robot manipulator ,Machine learning ,computer.software_genre ,Fuzzy logic ,Feedback error learning architecture ,Control theory ,Manipulator ,Artificial neural network ,business.industry ,Gaussian neuro-fuzzy variable structure ,Payload (computing) ,Robotics ,Neural network ,Computer Science Applications ,Nonlinear system ,Control and Systems Engineering ,Trajectory ,Artificial intelligence ,business ,Intelligent control ,computer ,Software ,DIMA - Abstract
This paper investigates the control of nonlinear systems by neural networks and fuzzy logic. As the control methods, Gaussian neuro-fuzzy variable structure (GNFVS), feedback error learning architecture (FELA) and direct inverse modeling architecture (DIMA) are studied, and their performances are comparatively evaluated on a two degrees of freedom direct drive robotic manipulator with respect to trajectory tracking performance, computational complexity, design complexity, RMS errors, necessary training time in learning phase and payload variations.
- Published
- 2004
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.