In a general computational context for biomedical data analysis, DNA sequence classification is a crucial challenge. Several machine learning techniques have used to complete this task in recent years successfully. Identification and classification of viruses are essential to avoid an outbreak like COVID-19. Regardless, the feature selection process remains the most challenging aspect of the issue. The most commonly used representations worsen the case of high dimensionality, and sequences lack explicit features. It also helps in detecting the effect of viruses and drug design. In recent days, deep learning (DL) models can automatically extract the features from the input. In this work, we employed CNN, CNN-LSTM, and CNN-Bidirectional LSTM architectures using Label and K -mer encoding for DNA sequence classification. The models are evaluated on different classification metrics. From the experimental results, the CNN and CNN-Bidirectional LSTM with K -mer encoding offers high accuracy with 93.16% and 93.13%, respectively, on testing data.
This paper presents an ensemble of pre-trained models for the accurate classification of endoscopic images associated with Gastrointestinal (GI) diseases and illnesses. In this paper, we propose a weighted average ensemble model called GIT-NET to classify GI-tract diseases. We evaluated the model on a KVASIR v2 dataset with eight classes. When individual models are used for classification, they are often prone to misclassification since they may not be able to learn the characteristics of all the classes adequately. This is due to the fact that each model may learn the characteristics of specific classes more efficiently than the other classes. We propose an ensemble model that leverages the predictions of three pre-trained models, DenseNet201, InceptionV3, and ResNet50 with accuracies of 94.54%, 88.38%, and 90.58%, respectively. The predictions of the base learners are combined using two methods: model averaging and weighted averaging. The performances of the models are evaluated, and the model averaging ensemble has an accuracy of 92.96% whereas the weighted average ensemble has an accuracy of 95.00%. The weighted average ensemble outperforms the model average ensemble and all individual models. The results from the evaluation demonstrate that utilizing an ensemble of base learners can successfully classify features that were incorrectly learned by individual base learners.
Most of the countries around the world are locked down due to the pandemic. Every country has imposed strict travel restrictions and has stopped all types of visas and tourist activities. This created a major impact on the aviation sector and the tourist sector. Even the people not effected from Covid-19 and in real emergence are not able to travel from one place to another. Some countries have laid down quarantine rules, which will be a major hindrance to emergency travelers and tourists. All passengers traveling are tested for COVID-19 using RT-PCR, which can take between 48 to 72 hours to produce the result. But in some cases, people who are tested negative even after 3 or 4 RT-PCR tests show typical pneumonia in the CT Scan or a chest X-ray. If the aviation sector relies only on the RT-PCR test, many patients may be missed. To reduce the risk to some extent and prevent a high-risk patient from traveling, the passenger can be asked to upload his / her chest X-ray before travel. Using an X-ray of the chest, we can predict the possibility of Covid-19 cases before the patients are physically examined. This technique cannot replace the RT-PCR test but can be a stand-by tool to help detect Covid-19 before the RT-PCR test. It would also help to identify patients who are highly prone to the infection. In this paper, we developed a CNN from scratch to identify a patient infected with COVID from a chest X-ray image. The model was trained with the chest X-ray of normal and COVID patients. Later the model was tested on two datasets, one publicly available in GitHub, and the other dataset was compiled from the Italian Society of Medical and Interventional Radiology website using web scrapping. The model produced an accuracy of 96.48 percent with the training dataset. To further improve accuracy, we used the same dataset on a pre-trained network (VGG16) and achieved an accuracy of around 99 percent.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.