Enhancing face pose normalization with deep learning

Çelik, Anıl; Arıca, Nafiz

doi:10.3906/elk-1810-192

Cited by 7 publications

(5 citation statements)

References 26 publications

(64 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…With this modeling, the learning and adaptation ability is gained. Deep learning includes the artificial neural network architecture on each layer [21][22][23]. Unlike machine learning algorithms, the deep learning method makes feature selections by itself.…”

Section: Deep Learningmentioning

confidence: 99%

Shoulder Implant Manufacturer Detection by Using Deep Learning: Proposed Channel Selection Layer

Yilmaz

2021

Coatings

View full text Add to dashboard Cite

Total Shoulder Arthroplasty (TSA) is the process of replacing the damaged ball and socket joint in the shoulder with a prosthesis made with polyethylene and metal components. After this procedure, intervention may be required as a result of damage to the prosthesis, except for the need for an examination regarding the prosthesis at certain periods. If the patient does not have information about the model and manufacturer of the prosthesis, the treatment process is delayed. Artificial intelligence-assisted systems can speed up the treatment process by classifying the manufacturer and model of the prosthesis. In this study, artificial intelligence methods were applied to classify shoulder implants using X-Ray images. The model and manufacturer of the prosthesis is detected by using the proposed deep learning method. Besides, the most commonly used machine learning classifiers were applied for the same problem to compare the results and show the effectiveness of the proposed method. In addition, the accuracy and precision analysis and measurements of the processing times for the applied methods were performed to reveal the performance, accuracy, and efficiency of the study. In order to measure the performance of the proposed method, it was compared with studies on the same problem in the literature. As a result of the comparison, it was found that the proposed method, with an accuracy rate of 97.2%, performed better than the other studies. In the study, the implant manufacturer and model are classified in order to carry out the implant surgery process in the best way with the proposed deep learning model. With the success of the proposed system, the applicability of this model in similar prosthesis classifications has been shown. Differently from the studies in the literature, the channel selection formula is presented in the proposed deep learning method recommended for selecting the most distinctive feature filters.

show abstract

Section: Deep Learningmentioning

confidence: 99%

Shoulder Implant Manufacturer Detection by Using Deep Learning: Proposed Channel Selection Layer

Yilmaz

2021

Coatings

View full text Add to dashboard Cite

show abstract

“…Convolutional Neural Networks (CNNs), in contrast to the artificial neural networks, are a deep learning approach that has a layer, which allows the extraction of features [ 18,19,20,21,22]. CNNs that produce good values for performance results in image processing [23,24].…”

Section: Convolutional Neural Network (Cnns)mentioning

confidence: 99%

Risk Assessment for Cardiac Arrest : A Deep Learning Approach

Yilmaz¹

2021

Preprint

View full text Add to dashboard Cite

Background:Risk of developing cardiovascular diseases, in the world, is increasing day by day. Accordingly, the number of deaths due to heart attacks is quite remarkable. Early risk assessment and diagnosis of heart disease are vital to prevent heart attacks by providing effective treatment planning and evaluation of outcomes. When a patient with high risk of heart attack is not treated correctly, chances of survival may reduce dramatically. Methods: In this study, individuals who has heart attack risks are predicted by using a CNN method. A set of medical data from patients with heart attacks and healthy individuals are provided from the UCI database. Reinforced deep learning and ANFIS architectures are also applied to the same problem in order to compare the results and put forth the efficiency of applied method. In addition, ROC analysis and measurements of processing times for the applied methods were performed to reveal the performance, accuracy and efficiency of the study. Results: The applied CNN method and other methods are tested and evaluated. The accuracy performance of the methods were 94.34% for the applied CNN method, 91.58% for the ANFIS, and 92.66% for the deep multilayer neural network. Highest accuracy has been obtained by using the applied CNN method, which is 94.34%. The reasons why the applied CNN method is better than other methods is the number of convolution and pooling layers, the filter size used in these layers, and the functions used in the loss and activation layers. Conclusions: In the study, the applicability of proposed CNN method with images obtained from numerical data has been demonstrated. With the early prediction system proposed, it is now possible to take precautionary measures against possible cardiac arrest. In this study; a new method based on CNN is proposed for early detection of possible heart attack, which is a great risk for human life. Different from studies in the literature, it was used in the applied CNN method by converting all numerical data from dataset into 2D images. Afterwards, to show whether this the proposed method is applicable or not, the dataset which is numerical form was applied to other methods and compared.

show abstract

“…Evrişimli Sinir Ağları (CNN), yapay sinir ağlarının aksine, özniteliklerin çıkarılmasına izin veren katmanlara sahip derin öğrenme yaklaşımıdır [26][27][28]. Görüntü işlemede performans sonuçları için iyi değerler üreten CNN'ler, çok katmanlı yapay sinir ağı tabanlıdır ve özelleştirilmiş derin öğrenme mimarisi yapısına sahiptir [29,30].…”

Section: Evrişimli Sinir Ağları (Convolutional Neural Network)unclassified

Çok kanallı CNN mimarisi ile X-Ray görüntülerinden COVID-19 tanısı

Yilmaz

2021

Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi

View full text Add to dashboard Cite

Proposed multi-channel CNN deep learning architecture with channel selection formula  A new method for diagnosing Covid-19  High performance valuesDeep learning has been widely used in a variety of applications to solve a scope of complex problems that require extremely high accuracy and precision, especially in the medical field. In this study, the Covid-19 is diagnosed automatically using a proposed multichannel CNN method. Patients and healthy individuals' Lung X-Ray images data sets were obtained from three separate online databases. Simple recurrent networks (SRN) architecture was also applied for the same problem to compare the results and demonstrate the efficiency of the proposed method. The study proposes a new CNN-based method for early detection of Covid-19, which is a major risk to human life worldwide. Differently from the studies in the literature, the multi-channel CNN architecture with five convolution channels is proposed and the channel selection formulas are presented. It is used for selecting the most distinctive feature filters among the results produced by these channels. The architecture consists of the following components (Figure A). Figure A. Proposed model architecturePurpose: This study aims to diagnose the Covid-19 with deep learning methods to design an assistive technology system that can be used by doctors and health employee Theory and Methods: The proposed multi-channel CNN, and simple recurrent networks (SRN) models were trained on the three different dataset, which was obtained from the Kaggle data repository. The first dataset has 50 images, the second dataset has 1125 images and the third dataset has 5856 images. Their performances were compared with each other. Results:It was observed that the proposed multi-channel CNN model is better than other models in diagnosing Covid-19 with %99,41-%97,75-%96,74 accuracy, %99,554-%98,221-%96,923 F1-score and 0,89-1,13-1,92 RMSE values. The training process took 981546 seconds and the proposed model can also be used in real-time systems. Conclusion:In this study; A new method based on CNN is proposed for the early detection of Covid-19 from lung X-Ray images, which is a major risk to human life worldwide. Differently the studies in the literature, the multichannel CNN architecture with five convolution channels is proposed and the channel selection formulas is presented which are used for selecting the most distinctive feature filters among the results produced by these channels.

show abstract

Enhancing face pose normalization with deep learning

Cited by 7 publications

References 26 publications

Shoulder Implant Manufacturer Detection by Using Deep Learning: Proposed Channel Selection Layer

Shoulder Implant Manufacturer Detection by Using Deep Learning: Proposed Channel Selection Layer

Risk Assessment for Cardiac Arrest : A Deep Learning Approach

Çok kanallı CNN mimarisi ile X-Ray görüntülerinden COVID-19 tanısı

Contact Info

Product

Resources

About