Enhanced hybrid classification model algorithm for medical dataset analysis

International Journal of Computational and Experimental Science and Engineering, Год журнала: 2025, Номер 11(1)

Опубликована: Фев. 26, 2025

The medical industry generates a significant volume of data that requires effective machine learning models to make accurate predictions for public healthcare. Current Machine Learning (ML) techniques have limitations in feature extraction and classifier accuracy. In this paper using diabetes dataset classification, address these issues, propose novel algorithm enhances Hybrid Classification Model approach by integrating advanced methods tailored high-dimensional data. To handle Missing Values (MV) outliers, hybrid imputation combines K-Nearest Neighbor (KNN) Multivariate Imputation Chained Equations (MICE) is initially used preprocess the datasets. Feature (FE) performed Deep Extraction techniques, including Convolutional Neural Networks (CNNs) Autoencoders, followed Fusion create comprehensive set. For Selection (FS), introduce an Advanced Ensemble method employing Genetic Algorithm-Based (GAFS), Multi-Objective Evolutionary Algorithm (MOEA), Relief-Based Methods identify most relevant features. Finally, classification achieved through incorporating Classifier with Stacked Generalization (Stacking), Boosting, Bagging Network (NN) Enhancements attention mechanisms (AM) Transfer (TL). This integrated robustness accuracy classification. Comparing suggested current methods, experimental outcomes show considerable improvement (A), sensitivity (S), specificity (SP), reduced execution time (ET).

Язык: Английский

Enhancing Breast Cancer Detection: A Hybrid Approach Integrating Local Binary Pattern Features and Deep Learning Insights from Mammogram Images

International Journal of Computational and Experimental Science and Engineering, Год журнала: 2025, Номер 11(2)

Опубликована: Апрель 13, 2025

Early identification of breast cancer improves treatment outcomes and lowers mortality rates. Mammogram images are useful for diagnosis, but their interpretation can be difficult time-consuming. The current study analyzes the feasibility promoting handmade deep learning features to enhance accuracy using mammography pictures. Previously, manual feature extraction has been labor-intensive inconsistent. Furthermore, systems frequently suffer from limited data architectural inefficiencies. To overcome these problems, we provide a novel strategy that makes use both local binary pattern (LBP) automatic seven models. concatenated LBP97.5%, SVM KNN classifiers trained on hybrid beat existing state-of-the-art Our findings indicate usefulness this technique. This work demonstrates potential suggested in improving classifier performance images. technique shows promise early more accurate contributing better patient fight against

Язык: Английский