User Guide
Why can I only view 3 results?
You can also view all results when you are connected from the network of member institutions only. For non-member institutions, we are opening a 1-month free trial version if institution officials apply.
So many results that aren't mine?
References in many bibliographies are sometimes referred to as "Surname, I", so the citations of academics whose Surname and initials are the same may occasionally interfere. This problem is often the case with citation indexes all over the world.
How can I see only citations to my article?
After searching the name of your article, you can see the references to the article you selected as soon as you click on the details section.
 Views 7
 Downloands 1
Farklı Kültürlere Ait Farklı Türdeki Müziklerden Duygu Tanıma
2020
Journal:  
Çukurova Üniversitesi Mühendislik Fakültesi Dergisi
Author:  
Abstract:

Bu çalışmada, klasik makine öğrenme yöntemleri farklı kültürlere ait farklı türdeki müziklerden oluşmuş veri tabanları üzerinde duygu tanıması yapmak için kullanılmışlardır. Bu veri tabanlarında bulunan müziklerden öznitelik çıkarmak için çalışmalarda yaygın olarak kullanılan araçlar tercih edilmiştir. Çıkarılan bütün özniteliklere korelasyon tabanlı öznitelik seçme yöntemi uygulanmıştır. Makine öğrenmesi yöntemleri olarak Bayes Ağları, Sıralı Minimal Optimizasyon, Lojistik Regresyon ve Karar Ağaçları kullanılmıştır. Öznitelik seçim işlemi sonrasında kalan özniteliklere Bayes Ağları yöntemi uygulandığında, Türkçe Duygusal Müzik Veri Tabanı için %94,35, Bi-Modal Veri Tabanı için %79,62 ve Soundtrack Veri Tabanı için ise %75,45 tanıma oranı elde edilmiş ve karşılaştırılan sınıflandırıcılardan daha iyi sonuç alınmıştır. Daha sonra, araçlardan çıkarılan öznitelikler bir araya getirilmiş ve yine seçim işlemi yapılmıştır. Bu işlemden sonra ise, sırasıyla bu veritabanları için %95,96, %80,24 ve %82,72 tanıma oranları elde edilmiştir.

Keywords:

Know the emotions of different kinds of music from different cultures
2020
Author:  
Abstract:

In this study, classic machine learning methods were used to make sensational recognition on the databases consisting of different kinds of music of different cultures. The tools that are widely used in the studies are preferred to get out of the music found in these databases. The method of selection is based on the correlation of all subjects. Mechanical learning methods have been used by Bayes Networks, sequential Minimum Optimization, Logistics Regression and Decision Tree. When the Bayes Networks method is applied to the remaining properties after the selection process, 94.35% for the Turkish Emotional Music Database, 79.62% for the Bi-Modal Database, and 75.45% for the Soundtrack Database, the recognition rate has been obtained and better results have been obtained than compared classifiers. After that, the properties removed from the vehicles were gathered and the election process was again made. After this process, 95.96, 80.24 and 82.72 per cent recognition rates were obtained for these databases respectively.

Keywords:

Emotion Recognition From Different Types Of Music From Different Cultures
2020
Author:  
Abstract:

In this study, various machine learning methods were used to recognize emotions on databases of different types of music belonging to different cultures. In order to obtain features from the music in these databases, widely used toolboxes were preferred. Correlation-based feature selection method was applied to all the obtained features. BayesNet, Sequential Minimal Optimization, Logistic Regression and Decision Trees are used as machine learning methods. When BayesNet was applied to the remaining features after the feature selection process, %94,35 recognition accuracy rate was obtained for Turkish Emotional Music Database, %79,62 for Bi-Modal Database, and %75,45 for Soundtrack Database, and better results were achieved than other classifiers. Then, the features obtained from the toolboxes were combined and the selection process was made again. After this process, recognition rates of %95,96, %80,24 and %82,72 were obtained for these databases, respectively.

Keywords:

Citation Owners
Information: There is no ciation to this publication.
Similar Articles










Çukurova Üniversitesi Mühendislik Fakültesi Dergisi

Field :   Mühendislik

Journal Type :   Ulusal

Metrics
Article : 1.001
Cite : 1.738
Çukurova Üniversitesi Mühendislik Fakültesi Dergisi