Nöbet Tespitinde Derin Öğrenme Uygulamaları

Loading...
Thumbnail Image

Date

2018

Journal Title

Journal ISSN

Volume Title

Publisher

Open Access Color

OpenAIRE Downloads

OpenAIRE Views

Research Projects

Organizational Units

Organizational Unit
Software Engineering
(2005)
Department of Software Engineering was founded in 2005 as the first department in Ankara in Software Engineering. The recent developments in current technologies such as Artificial Intelligence, Machine Learning, Big Data, and Blockchains, have placed Software Engineering among the top professions of today, and the future. The academic and research activities in the department are pursued with qualified faculty at Undergraduate, Graduate and Doctorate Degree levels. Our University is one of the two universities offering a Doctorate-level program in this field. In addition to focusing on the basic phases of software (analysis, design, development, testing) and relevant methodologies in detail, our department offers education in various areas of expertise, such as Object-oriented Analysis and Design, Human-Computer Interaction, Software Quality Assurance, Software Requirement Engineering, Software Design and Architecture, Software Project Management, Software Testing and Model-Driven Software Development. The curriculum of our Department is catered to graduate individuals who are prepared to take part in any phase of software development of large-scale software in line with the requirements of the software sector. Department of Software Engineering is accredited by MÜDEK (Association for Evaluation and Accreditation of Engineering Programs) until September 30th, 2021, and has been granted the EUR-ACE label that is valid in Europe. This label provides our graduates with a vital head-start to be admitted to graduate-level programs, and into working environments in European Union countries. The Big Data and Cloud Computing Laboratory, as well as MobiLab where mobile applications are developed, SimLAB, the simulation laboratory for Medical Computing, and software education laboratories of the department are equipped with various software tools and hardware to enable our students to use state-of-the-art software technologies. Our graduates are employed in software and R&D companies (Technoparks), national/international institutions developing or utilizing software technologies (such as banks, healthcare institutions, the Information Technologies departments of private and public institutions, telecommunication companies, TÜİK, SPK, BDDK, EPDK, RK, or universities), and research institutions such TÜBİTAK.

Journal Issue

Events

Abstract

Bu tezde, Derin otomatik kodlayıcı ve güç spektral yoğunluğuna dayalı yeni bir yöntem önerilmiştir. ilk, giriş verileri, her bir veri satırı için sinyalin güç spektral yoğunluğunu ölçerek özellik çıkarımı için güç spektral yoğunluğu kullanılarak analiz edilir. Üretilen çıktı, boyutu azaltmak ve yüksek seviyeli özellikler elde etmek için ilk Otomatik kodlayıcıya girdi olur. İlk otomatik kodlayıcının çıkışı, özelliklerin sayısını azaltmak ve yüksek seviyeli özellikler elde etmek için ikinci otomatik kodlayıcıya girdi olur. Ayrıca, bu özellikler iki gruba ayrılır: SoftMax sınıflandırıcı kullanılarak normal ve anormal. Son olarak, iki otomatik kodlayıcı ve SoftMax, sınıflandırma doğruluğunu geliştirmek için geri yayılım algoritması kullanılarak yığılmış ve eğitilmiştir. Önerilen yöntem, bu dosyada sunulan ortak yöntemlerle karşılaştırıldığında tatmin edici sonuçlar verir. Burada, Otomatik kodlayıcıların sayısı verilerin yanı sıra boyutun davranışına da bağlıdır. Önerilen yöntem, epilepsi seri tespitinde yaygın olarak kullanılan veri setleri ile test edilmiş ve elde edilen sonuçlar, güçlü ve zayıf yönleri belirlemek amacıyla bu alandaki diğer ve en önemli çalışmalarla karşılaştırılmıştır.
In this thesis, a new method is proposed based on deep auto encoder and power spectral density. First, the input data is analyzed using power spectral density for feature extraction by measuring the power spectral density of the signal for each row of data. The produced output becomes input to the first Auto encoder to reduce the dimension and extracted high level features. The output of first auto-encoder become input to the second auto-encoder also to reduce number of features and extracted high level features. In addition, these features are classified into two groups: normal and abnormal by using SoftMax classifier. Finally, the two auto-encoders and SoftMax stacked and trained by using backpropagation algorithm to improve the classification accuracy. The proposed method gives satisfactory results when compared with the common methods presented in this filed .Here, the number of Auto encoders depend on the behavior of the data as well as the dimension. The proposed method is tested with commonly used datasets in the epilepsy serius detection, and the results obtained are compared with other and most prominent works in this field in order to determine the strengths and weaknesses.

Description

Keywords

Elektrik ve Elektronik Mühendisliği, Electrical and Electronics Engineering

Turkish CoHE Thesis Center URL

Fields of Science

Citation

WoS Q

Scopus Q

Source

Volume

Issue

Start Page

0

End Page

53