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.
  Citation Number 2
 Views 19
 Downloands 2
KÇ3B-ESA: Hiperspektral Görüntü Sınıflandırması için Yeni 3B Evrişimli Sinir Ağı ve Uzaktan Algılama Uygulaması
2020
Journal:  
Avrupa Bilim ve Teknoloji Dergisi
Author:  
Abstract:

Hiperspektral Görüntüleme (HSG) uzamsal ve spektral bilgiyi içeren yüzlerce banttan oluşur. HSG verileri sınıflandırılırken uzamsal özelliklerin yanında spektral özelliklerinde elde edilmesi büyük önem taşır. Bu çalışmada hem uzamsal hem de spektral bilgilerin elde edilmesi için yeni bir derin öğrenme modeli önerilmiştir. Öncelikle, HSG verilerinin boyutlarının büyük olmasından dolayı tüm verilere Temel Bileşen Analizi (TBA) uygulanarak uzamsal boyut değişmeyecek şekilde spektral boyut küçültülmüştür. Daha sonra yeni bir yöntem olan, HSG verilerinin sınıflandırıldığı çalışmalarda yer alan, Komşuluk Çıkarımı (KÇ) yöntemi kullanılmıştır. Bu yöntem ile tüm pikselleri tarayacak şekilde mini küpler oluşturularak örnek sayısı artırılmıştır. Son olarak oluşturulan bu küpler 3B konvolüsyon katmanlarının bulunduğu 3B-Evrişimli Sinir Ağı (3B-ESA) modeli ile eğitilmiştir. Bu sayede daha anlamlı özelliklerin elde edilmesi sağlanmıştır. Önerilen modeli test etmek için Indian Pines (IP), Salinas Scene (SA) ve Pavia University (PU) uzaktan algılama veri setleri kullanılarak HSG sınıflandırma deneyleri yürütülmüştür. Yürütülen bu deneyler sonucunda tüm veri setleri için genel doğruluk (GD), kappa katsayısı (KC) ve ortalama doğruluk (OD) değerleri hesaplanarak sınıflandırma performansı değerlendirilmiştir. Sınıflandırma işlemi sonucunda IP veri seti için %99.10 GD, %98.97 KC, %96.23 OD; SA veri seti için %100 GD, %100 KC, %100 OD; ve son olarak PU veri seti için %99.90 GD, %99.87 KC, %99.67 OD doğruluk oranları elde edilmiştir. Daha sonra bu sonuçlar gelişmiş derin öğrenme tabanlı metotlarla karşılaştırılarak, önerilen KÇ3B-ESA modelinin çok daha iyi bir performans gösterdiği kanıtlanmıştır.

Keywords:

KC3B-ESA: New 3B Evolutionary Neural Network and Remote Detection Application for Hyperspectral Image Classification
2020
Author:  
Abstract:

Hyperspectral Imaging (HSG) consists of hundreds of bands containing spatial and spectral information. HSG data is very important to be obtained in spectral characteristics in addition to spatial characteristics when classified. In this study, a new deep learning model was proposed to obtain both spatial and spectral knowledge. First of all, due to the size of the HSG data, the spectral size has been reduced in such a way that the spatial size does not change by applying the Basic Component Analysis (TBA) to all data. Then a new method, HSG data classified in the studies, the Neighbourhood Output (KC) method was used. This method has increased the number of samples by creating mini-cubs to scan all pixels. The newly created cubes are trained with the 3B-Evolutive Neural Network (3B-ESA) model, which contains 3B convergence layers. This makes it possible to obtain more meaningful characteristics. HSG classification experiments were conducted using the Indian Pines (IP), Salinas Scene (SA) and Pavia University (PU) remote detection data sets to test the proposed model. The results of these experiments were classification performance assessed by calculating the values of general accuracy (GD), cover ratio (KC) and average accuracy (OD) for all data sets. The classification process resulted in 99.10% GD, 98.97% KC, 96.23% OD for the IP data set; 100% GD, 100% KC, 100% OD for the SA data set; and finally 99.90% GD, 99.87% KC, 99.67% OD for the PU data set. Later, these findings compared with advanced deep learning-based methods, it has been proven that the recommended KC3B-ESA model has shown much better performance.

Keywords:

Ne3d-cnn: A New 3d Convolutional Neural Network For Hyperspectral Image Classification and Remote Sensing Application
2020
Author:  
Abstract:

Hyperspectral Imaging (HSI) consists of hundreds of bands containing spatial and spectral information. When classifying HSI data, it is of great importance to obtain spectral features as well as spatial features. In this study, a new deep learning model is proposed to obtain both spatial and spectral information. First of all, due to the large size of HSI data, Principal Component Analysis (PCA) was applied to all data and the spectral size was reduced so that the spatial dimension would not change. Then, Neighbourhood Extraction (NE) method, which is a new method used in studies in which HSI data were classified, was used. With the method, the number of samples was increased by creating mini cubes to scan all pixels. Finally, the cubes were trained with the 3D-Convolutional Neural Network (3D-CNN) model, which has 3D convolution layers. In this way, more meaningful features were obtained. HSI classification experiments were conducted using Indian Pines (IP), Salinas Scene (SA) and Pavia University (PU) remote sensing datasets to test the proposed model. As a result of the experiments, the classification performance was evaluated by calculating the overall accuracy (OA), kappa coefficient (KC) and average accuracy (AA) values for all data sets. At the end of the classification process, accuracy rates of 99.10% OA, 98.97% KC, 96.23% AA for the IP data set, 100% OA, 100% KC, 100% AA for SA data set, and finally 99.90% OA, 99.87% KC, 99.67% AA for the PU data set were obtained. Later, by comparing the results with state-of-the-art deep learning-based methods, it has been proven that the proposed NE3D-CNN model gives a much better performance.

Keywords:

Citation Owners
Attention!
To view citations of publications, you must access Sobiad from a Member University Network. You can contact the Library and Documentation Department for our institution to become a member of Sobiad.
Off-Campus Access
If you are affiliated with a Sobiad Subscriber organization, you can use Login Panel for external access. You can easily sign up and log in with your corporate e-mail address.
Similar Articles




Avrupa Bilim ve Teknoloji Dergisi

Field :   Fen Bilimleri ve Matematik; Mühendislik

Journal Type :   Uluslararası

Metrics
Article : 3.175
Cite : 5.553
2023 Impact : 0.178
Avrupa Bilim ve Teknoloji Dergisi