Automatic detection of eardrum otoendoscopic images in patients with otitis media using <scp>hybrid‐based</scp> deep models

Eroğlu, Orkun; Yıldırım, Muhammed

doi:10.1002/ima.22683

Cited by 19 publications

(14 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different performance measurement metrics are available in AI-based models. Most of the performance measurement metrics are calculated using the confusion matrix [30]. An example of a confusion matrix is given in Figure 6.…”

Section: Application Resultsmentioning

confidence: 99%

Detection of COVID-19 Fake News in Online Social Networks with the Developed CNN-LSTM Based Hybrid Model

Yıldırım¹

2022

RCES

Self Cite

View full text Add to dashboard Cite

Technological developments have led to the emergence of different platforms. Social media platforms are one of the most used platforms recently. In this study, a text-based study was conducted on fake news sharing about COVID-19 in online social networks with Shallow Learning (SL) and Deep Learning (DL) methods. In order to classify the news in the dataset, the news in the dataset is converted into a format that can be understood by the machines in the preprocessing step. In the study, the glove method was used for word representation. The document matrix obtained using the glove method was classified with the proposed hybrid model. In the proposed hybrid model, LSTM and CNN structures are used together. In addition, different Shallow Learning methods accepted in the literature were used to compare the performances of the proposed model, and the results were obtained and these results were compared with the proposed model. Among these models, the most successful results were obtained in the proposed hybrid model. When the performance evaluation metrics obtained are examined, it is obvious that the proposed model can be used to solve many other social media and network problems related to COVID-19.

show abstract

Section: Application Resultsmentioning

confidence: 99%

Detection of COVID-19 Fake News in Online Social Networks with the Developed CNN-LSTM Based Hybrid Model

Yıldırım¹

2022

RCES

Self Cite

View full text Add to dashboard Cite

show abstract

“…During the experiments, a dataset containing 3 classes, 1 of which was normal, was used. The accuracy rate of their proposed model in classifying OME was stated as 94.27% [5].…”

Section: Related Workmentioning

confidence: 99%

“…Every year, billions of dollars are spent on healthcare in the United States for the treatment of OME, and millions of boxes of antibiotics are used [3,4]. Since this disease does not show severe symptoms, it is likely to be overlooked by experts [5]. In addition, when the disease is diagnosed, it is very important to follow up with certain periods in terms of the course of the disease.…”

Section: Introductionmentioning

confidence: 99%

Classification of OME with Eardrum Otoendoscopic Images Using Hybrid-Based Deep Models, NCA, and Gaussian Method

Bingol¹

2022

View full text Add to dashboard Cite

Otitis media with effusion (OME) is defined as a middle ear disease that occurs with the accumulation of fluid in the posterior part of the eardrum, usually without any symptoms. When OME disease is not treated, some negative consequences arise that deeply affect the education, social and cultural life of the patient. OME disease is a difficult issue to diagnose by specialists. In this article, autoendoscopic images of the eardrum have been classified using deep learning methods to help specialists in the diagnosis of OME. In this study, a hybrid deep model based on artificial intelligence is proposed. In the proposed hybrid model, feature maps were obtained using Efficientnetb0 and Densenet201 architectures from both the original dataset and the improved dataset using the gaussian method. Then, the merging process was applied to these feature maps. Unnecessary features are eliminated by applying NCA dimension reduction to the combined feature map. The most valuable features obtained at the end of the optimization process are classified in different machine learning classifiers. The proposed model reached a very competitive accuracy value of 98.20% in the SVM classifier.

show abstract

“…Thanks to the NCA dimension reduction method, unnecessary features in the feature map are eliminated. This step allows the training time of the proposed hybrid model to be completed in a shorter time [25,26].…”

Section: Spectrogram Deep Models and Ncamentioning

confidence: 99%

Automatic Diagnosis of Snoring Sounds with the Developed Artificial Intelligence-based Hybrid Model

Yıldırım

2022

Turkish Journal of Science and Technology

Self Cite

View full text Add to dashboard Cite

Sleep patterns and sleep continuity have a great impact on people's quality of life. The sound of snoring both reduces the sleep quality of the snorer and disturbs other people in the environment. Interpretation of sleep signals by experts and diagnosis of the disease is a difficult and costly process. Therefore, in the study, an artificial intelligence-based hybrid model was developed for the classification of snoring sounds. In the proposed method, first of all, audio signals were converted into images using the Mel-spectrogram method. The feature maps of the obtained images were obtained using Alexnet and Resnet101 architectures. After combining the feature maps that are different in each architecture, dimension reduction was made using the NCA dimension reduction method. The feature map optimized using the NCA method was classified in the Bilayered Neural Network. In addition, spectrogram images were classified with 8 different CNN models to compare the performance of the proposed model. Later, in order to test the performance of the proposed model, feature maps were obtained using the MFCC method and the obtained feature maps were classified in different classifiers. The accuracy value obtained in the proposed model is 99.5%

show abstract

Automatic detection of eardrum otoendoscopic images in patients with otitis media using hybrid‐based deep models

Cited by 19 publications

References 32 publications

Detection of COVID-19 Fake News in Online Social Networks with the Developed CNN-LSTM Based Hybrid Model

Detection of COVID-19 Fake News in Online Social Networks with the Developed CNN-LSTM Based Hybrid Model

Classification of OME with Eardrum Otoendoscopic Images Using Hybrid-Based Deep Models, NCA, and Gaussian Method

Automatic Diagnosis of Snoring Sounds with the Developed Artificial Intelligence-based Hybrid Model

Contact Info

Product

Resources

About