A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Early Malignant Mesothelioma Detection Using Ensemble of Naive Bayes Under Decorate Ensemble Framework
https://orcid.org/http://orcid.org/0000-0003-2759-3224
The growing role of machine learning in early malignant mesothelioma highlights the significance of this study. This study analyzes and suggests an ensemble approach using the Decorate ensemble where the famous Naïve Bayes algorithm has been used as the base learner for precisely distinguishing between control subjects and individuals afflicted with mesothelioma. By utilizing the ensemble approach of the Decorate (Naïve Bayes) algorithm, precision sensitivity and other critical aspects have been emphasized for accurate disease detection. The Decorate (Naive Bayes) draws strength from a diverse dataset encompassing control subjects and mesothelioma cases, ensuring a robust evaluation of the algorithm’s performance. The dataset suffers from a class imbalance issue, thus posing as a real-world diagnostic environment. Considering the challenges posed by class imbalance, the Decorate (Naïve Bayes) ensemble framework for mesothelioma detection underwent thorough evaluation using both tenfold cross-validation and leave-one-subject-out (LOSO) cross-validation techniques. In the context of tenfold cross-validation, the Decorate (Naïve Bayes) ensemble achieved an accuracy rate of 96.60%, with sensitivity and specificity reaching 98.25% and 92.71%, respectively. Likewise, during LOSO validation, the Decorate (Naïve Bayes) ensemble demonstrated impressive performance, attaining an accuracy of 97.84%, accompanied by a noteworthy sensitivity of 99.12% and a specificity of 94.79%. Overall, the results affirm the adeptness of the Decorate (Naïve Bayes) algorithm in classifying both control subjects and mesothelioma cases, highlighting how machine learning-driven approaches can reshape disease detection, particularly in challenging medical scenarios like mesothelioma.
Early Malignant Mesothelioma Detection Using Ensemble of Naive Bayes Under Decorate Ensemble Framework
https://orcid.org/http://orcid.org/0000-0003-2759-3224
The growing role of machine learning in early malignant mesothelioma highlights the significance of this study. This study analyzes and suggests an ensemble approach using the Decorate ensemble where the famous Naïve Bayes algorithm has been used as the base learner for precisely distinguishing between control subjects and individuals afflicted with mesothelioma. By utilizing the ensemble approach of the Decorate (Naïve Bayes) algorithm, precision sensitivity and other critical aspects have been emphasized for accurate disease detection. The Decorate (Naive Bayes) draws strength from a diverse dataset encompassing control subjects and mesothelioma cases, ensuring a robust evaluation of the algorithm’s performance. The dataset suffers from a class imbalance issue, thus posing as a real-world diagnostic environment. Considering the challenges posed by class imbalance, the Decorate (Naïve Bayes) ensemble framework for mesothelioma detection underwent thorough evaluation using both tenfold cross-validation and leave-one-subject-out (LOSO) cross-validation techniques. In the context of tenfold cross-validation, the Decorate (Naïve Bayes) ensemble achieved an accuracy rate of 96.60%, with sensitivity and specificity reaching 98.25% and 92.71%, respectively. Likewise, during LOSO validation, the Decorate (Naïve Bayes) ensemble demonstrated impressive performance, attaining an accuracy of 97.84%, accompanied by a noteworthy sensitivity of 99.12% and a specificity of 94.79%. Overall, the results affirm the adeptness of the Decorate (Naïve Bayes) algorithm in classifying both control subjects and mesothelioma cases, highlighting how machine learning-driven approaches can reshape disease detection, particularly in challenging medical scenarios like mesothelioma.
Early Malignant Mesothelioma Detection Using Ensemble of Naive Bayes Under Decorate Ensemble Framework
https://orcid.org/http://orcid.org/0000-0003-2759-3224
The growing role of machine learning in early malignant mesothelioma highlights the significance of this study. This study analyzes and suggests an ensemble approach using the Decorate ensemble where the famous Naïve Bayes algorithm has been used as the base learner for precisely distinguishing between control subjects and individuals afflicted with mesothelioma. By utilizing the ensemble approach of the Decorate (Naïve Bayes) algorithm, precision sensitivity and other critical aspects have been emphasized for accurate disease detection. The Decorate (Naive Bayes) draws strength from a diverse dataset encompassing control subjects and mesothelioma cases, ensuring a robust evaluation of the algorithm’s performance. The dataset suffers from a class imbalance issue, thus posing as a real-world diagnostic environment. Considering the challenges posed by class imbalance, the Decorate (Naïve Bayes) ensemble framework for mesothelioma detection underwent thorough evaluation using both tenfold cross-validation and leave-one-subject-out (LOSO) cross-validation techniques. In the context of tenfold cross-validation, the Decorate (Naïve Bayes) ensemble achieved an accuracy rate of 96.60%, with sensitivity and specificity reaching 98.25% and 92.71%, respectively. Likewise, during LOSO validation, the Decorate (Naïve Bayes) ensemble demonstrated impressive performance, attaining an accuracy of 97.84%, accompanied by a noteworthy sensitivity of 99.12% and a specificity of 94.79%. Overall, the results affirm the adeptness of the Decorate (Naïve Bayes) algorithm in classifying both control subjects and mesothelioma cases, highlighting how machine learning-driven approaches can reshape disease detection, particularly in challenging medical scenarios like mesothelioma.
Early Malignant Mesothelioma Detection Using Ensemble of Naive Bayes Under Decorate Ensemble Framework
J. Inst. Eng. India Ser. B
Moirangthem, Akash (author) / Lepcha, Olive Simick (author) / Panigrahi, Ranjit (author) / Brahma, Biswajit (author) / Bhoi, Akash Kumar (author)
Journal of The Institution of Engineers (India): Series B ; 105 ; 251-264
2024-04-01
14 pages
Article (Journal)
Electronic Resource
English
Instance Cloning Local Naive Bayes
| British Library Conference Proceedings | 2005
Prediction of Slope Stability using Naive Bayes Classifier
| Online Contents | 2018
Prediction of Slope Stability using Naive Bayes Classifier
| Springer Verlag | 2018