Karotis Arter Intima-Medya Kalınlığı Ultrason Görüntülerinde Derin Öğrenme Modellerinin Karşılaştırılması: CAIMTUSNet

Topaloğlu, Nurettin; Kazci, Omer; Koşar, Pınar Nercis

doi:10.17671/gazibtd.804617

Cited by 12 publications

(9 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Bir CNN (Convolutional Neural Network), evrişim katmanları, havuzlama katmanları ve tamamen bağlı katmanlardan oluşan çoklu katmanlardan oluşur [44]. Evrişimli bir katmanda, her nöron bir önceki katmanın alt alanından girdi alırve bir önceki katmanın alt alanına "alıcı alan" adı verilir.…”

Section: E Evrişimli Sinir Ağları (Cnn)unclassified

“…Derin öğrenme alanında en çok kullanılan yöntemlerden biri olan evrişimli sinir ağları, birçok alanda, özellikle öznitelik çıkarımının oldukça zor olduğu problemlerde son derece faydalıdır [44]. Bir çok problem çeşidinde, özellikle görüntü işleme problemlerinde [44], [47]- [49] öznitelik çıkarma aşamasının zor olması sebebi ile tercih edilen bu yöntem, zaman serisi analizinde de oldukça sık kullanılmaktadır. Tıp alanında tümör sınıflandırma gibi problemlerde de faydalı olan bir sınıflandırıcıdır [50].…”

Section: 𝑆(𝑖 𝑗) = (𝐼 * 𝐾)(𝑖 𝑗) = ∑ ∑ 𝐼(𝑚 𝑛)𝐾(𝑖 − 𝑚 𝑗 − 𝑚)unclassified

See 1 more Smart Citation

A General Review of the Methods Used Financial Time Series Forecasting

YURDUSEVEN

Müngen

2022

Bilecik Şeyh Edebali Üniversitesi Fen Bilimleri Dergisi

View full text Add to dashboard Cite

As in the past, it is very important for investors to be able to predict the trend of financial data and to create a financial strategy using this information. However, nowadays, rapid access to financial data with fast Internet connections, developments in informatics, and cloud systems, the use of artificial intelligence algorithms for financial forecasting increase competition in this field. The share of artificial intelligence applications in areas such as portfolio management in Fintech is increasing. The aim of this study is to compile previous academic studies to predict financial time series data, to explain artificial intelligence algorithms used to predict time series, and to examine some predicted financial data types and their dependencies. At the end of the study, inferences were made such as the adequacy of the techniques used in the articles examined and which method could yield more successful results for which data type.

show abstract

Section: E Evrişimli Sinir Ağları (Cnn)unclassified

Section: 𝑆(𝑖 𝑗) = (𝐼 * 𝐾)(𝑖 𝑗) = ∑ ∑ 𝐼(𝑚 𝑛)𝐾(𝑖 − 𝑚 𝑗 − 𝑚)unclassified

A General Review of the Methods Used Financial Time Series Forecasting

YURDUSEVEN

Müngen

2022

Bilecik Şeyh Edebali Üniversitesi Fen Bilimleri Dergisi

View full text Add to dashboard Cite

show abstract

“…Every year, stroke affects around 16 million people globally and has significant economic repercussions. In recent years, machine learning (ML) has rapidly expanded and changed across a number of applications in several different health care systems (Merino, 2014;Savaş et al, 2019Savaş et al, , 2022. The most recent estimates for global health from 2000 to 2016 are shown in Figure 1 (Sirsat et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Transfer Learning-Based Classification Comparison of Stroke

ALHATEMİ¹

2022

BBD

Self Cite

View full text Add to dashboard Cite

One type of brain disease that significantly harms people's lives and health is stroke. The diagnosis and management of strokes both heavily rely on the quantitative analysis of brain Magnetic Resonance (MR) images. The early diagnosis process is of great importance for the prevention of stroke cases. Stroke prediction is made possible by deep neural networks with the capacity for enormous data learning. Therefore, in thus study, several deep neural network models, including DenseNet121, ResNet50, Xception, MobileNet, VGG16, and EfficientNetB2 are proposed for transfer learning to classify MR images into two categories (stroke and non-stroke) in order to study the characteristics of the stroke lesions and achieve full intelligent automatic detection. The study dataset comprises of 1901 training images, 475 validation images, and 250 testing images. On the training and validation sets, data augmentation was used to increase the number of images to improve the models’ learning. The experimental results outperform all the state of arts that were used the same dataset. The overall accuracy of the best model is 98.8% and the same value for precision, recall, and f1-score using the EfficientNetB2 model for transfer learning.

show abstract

“…DNNs are effective for classifying medical images, but they need a lot of training data. High-performance GPUs are used to train a network of DNNs using largescale datasets (Savaş et al, 2019(Savaş et al, , 2022. DL systems enabled by GPUs have shown superior skin cancer detection than people (Nugroho et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

Classification of Skin Cancer with Deep Transfer Learning Method

AL-SAEDİ¹

2022

BBD

Self Cite

View full text Add to dashboard Cite

Skin cancer is a serious health hazard for human society. This disease is developed when the pigments that produce skin color become cancerous. Dermatologists face difficulties in diagnosing skin cancer since many skin cancer colors seem identical. As a result, early diagnosis of lesions (the foundation of skin cancer) is very crucial and beneficial in totally curing skin cancer patients. Significant progress has been made in creating automated methods with the development of artificial intelligence (AI) technologies to aid dermatologists in the identification of skin cancer. The widespread acceptance of AI-powered technologies has enabled the use of a massive collection of photos of lesions and benign sores authorized by histology. This research compares six alternative transfer learning networks (deep networks) for skin cancer classification using the International Skin Imaging Collaboration (ISIC) dataset. DenseNet, Xception, InceptionResNetV2, ResNet50, and MobileNet were the transfer learning networks employed in the investigation which were successful in different studies recently. To compensate for the imbalance in the ISIC dataset, the photos of classes with low frequencies are augmented. The results show that augmentation is appropriate for the classification success, with high classification accuracies and F-scores with decreased false negatives. With an accuracy rate of 98.35%, modified DenseNet121 was the most successful model against the rest of the transfer learning nets utilized in the study.

show abstract

Karotis Arter Intima-Medya Kalınlığı Ultrason Görüntülerinde Derin Öğrenme Modellerinin Karşılaştırılması: CAIMTUSNet

Cited by 12 publications

References 47 publications

A General Review of the Methods Used Financial Time Series Forecasting

A General Review of the Methods Used Financial Time Series Forecasting

Transfer Learning-Based Classification Comparison of Stroke

Classification of Skin Cancer with Deep Transfer Learning Method

Contact Info

Product

Resources

About