Deep learning-based feature extraction coupled with multi-class SVM for COVID-19 detection in the IoT era

Özsöz, Mehmet; Mubarak, Auwalu Saleh; Said, Zubaida; Aliyu, Rabiu; Turjman, Fadi Al; Serte, Sertan

doi:10.1504/ijnt.2021.10040115

Cited by 10 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning algorithms' architecture automatically identifies patterns in data, which is perfect for data-driven sciences, such as genomics [25,26]. The usage of DL frameworks in medical imaging has been widespread [27][28][29][30][31]. To create computer models that can more accurately predict the existence of linear B-cell epitopes from an amino acid sequence for vaccine production against a pathogenic organism, in silico techniques have Processes 2023, 11, 1829 3 of 18 been frequently employed [32].…”

Section: Introductionmentioning

confidence: 99%

Accelerating SARS-CoV-2 Vaccine Development: Leveraging Novel Hybrid Deep Learning Models and Bioinformatics Analysis for Epitope Selection and Classification

Ameen¹,

Mostafa

Ozsahin

et al. 2023

Processes

View full text Add to dashboard Cite

It is essential to use highly antigenic epitope areas, since the development of peptide vaccines heavily relies on the precise design of epitope regions that can elicit a strong immune response. Choosing epitope regions experimentally for the production of the SARS-CoV-2 vaccine can be time-consuming, costly, and labor-intensive. Scientists have created in silico prediction techniques based on machine learning to find these regions, to cut down the number of candidate epitopes that might be tested in experiments, and, as a result, to lessen the time-consuming process of their mapping. However, the tools and approaches involved continue to have low accuracy. In this work, we propose a hybrid deep learning model based on a convolutional neural network (CNN) and long short-term memory (LSTM) for the classification of peptides into epitopes or non-epitopes. Numerous transfer learning strategies were utilized, and the fine-tuned method gave the best result, with an AUC of 0.979, an f1 score of 0.902, and 95.1% accuracy, which was far better than the performance of the model trained from scratch. The experimental results obtained show that this model has superior performance when compared to other methods trained on IEDB datasets. Using bioinformatics tools such as ToxinPred, VaxiJen, and AllerTop2.0, the toxicities, antigenicities, and allergenicities, respectively, of the predicted epitopes were determined. In silico cloning and codon optimization were used to successfully express the vaccine in E. coli. This work will help scientists choose the best epitope for the development of the COVID-19 vaccine, reducing cost and labor and thereby accelerating vaccine production.

show abstract

Section: Introductionmentioning

confidence: 99%

Accelerating SARS-CoV-2 Vaccine Development: Leveraging Novel Hybrid Deep Learning Models and Bioinformatics Analysis for Epitope Selection and Classification

Ameen¹,

Mostafa

Ozsahin

et al. 2023

Processes

View full text Add to dashboard Cite

show abstract

“…With its extraordinary advancement, artificial intelligence has provided new horizons for predicting, detecting, decision-making, and planning—resulting in the option for better and less costly elements of human life. Artificial intelligence can be instrumental in diagnosing diseases [ 9 , 10 , 11 , 12 , 13 , 14 ], increasing accuracy in diagnosis and decision-making, and even surpassing human capability. Due to limited human attention, changing mental conditions, and a wide range of human tasks and functions, the power of human diagnosis is limited in diagnosing complex and sensitive diseases.…”

Section: Introductionmentioning

confidence: 99%

Breast Cancer Screening Based on Supervised Learning and Multi-Criteria Decision-Making

Mustapha

Ozsahin

et al. 2022

Diagnostics

View full text Add to dashboard Cite

On average, breast cancer kills one woman per minute. However, there are more reasons for optimism than ever before. When diagnosed early, patients with breast cancer have a better chance of survival. This study aims to employ a novel approach that combines artificial intelligence and a multi-criteria decision-making method for a more robust evaluation of machine learning models. The proposed machine learning techniques comprise various supervised learning algorithms, while the multi-criteria decision-making technique implemented includes the Preference Ranking Organization Method for Enrichment Evaluations. The Support Vector Machine, having achieved a net outranking flow of 0.1022, is ranked as the most favorable model for the early detection of breast cancer. The net outranking flow is the balance between the positive and negative outranking flows. This indicates that the higher the net flow, the better the alternative. K-nearest neighbor, logistic regression, and random forest classifier ranked second, third, and fourth, with net flows of 0.0316, −0.0032, and −0.0541, respectively. The least preferred alternative is the naive Bayes classifier with a net flow of −0.0766. The results obtained in this study indicate the use of the proposed method in making a desirable decision when selecting the most appropriate machine learning model. This gives the decision-maker the option of introducing new criteria into the decision-making process.

show abstract

Densely Connected CNN-Based XAuNet1.0 for Brain Tumor Classification via MRI Images in the IoT Era

Benyamina,

Al-Turjman

2024

Advances in Science, Technology &Amp; Innovation

View full text Add to dashboard Cite

Deep learning-based feature extraction coupled with multi-class SVM for COVID-19 detection in the IoT era

Cited by 10 publications

References 0 publications

Accelerating SARS-CoV-2 Vaccine Development: Leveraging Novel Hybrid Deep Learning Models and Bioinformatics Analysis for Epitope Selection and Classification

Accelerating SARS-CoV-2 Vaccine Development: Leveraging Novel Hybrid Deep Learning Models and Bioinformatics Analysis for Epitope Selection and Classification

Breast Cancer Screening Based on Supervised Learning and Multi-Criteria Decision-Making

Densely Connected CNN-Based XAuNet1.0 for Brain Tumor Classification via MRI Images in the IoT Era

Contact Info

Product

Resources

About