Sort By:
(*) denotes equal contribution
() denotes corresponding
Enhancing Parallelism in Cross-silo Federated Learning for T1-weighted MRI-Based Brain Disease Classification New
This study exclusively focuses on brain disease detection using privacy-preserving federated learning based on independent and identically distributed (IID) data dynamics. It investigates, additionally, the minimum amount of client participation required in cross-silo federated settings.
Oral Presentation
To Appear
Towards Privacy-Preserving Alzheimer’s Disease Classification: Federated Learning on T1-weighted MRI Data. New
This study aims to minimize communication costs by increasing parallelism and enhancing computation per client. Moreover, to reflect real-world scenarios, synthetic data dynamics are generated based on the original data dynamics, and experiments are conducted using them.
Predictive Modeling of Multi-class Diabetes Mellitus Using Machine Learning and Filtering Iraqi Diabetes Data Dynamics.
This study proposes a moderately imbalance dataset from an extremely imbalance diabetes mellitus dataset. Additionally, investigated the prediction of diabetes mellitus using reduced features through feature selection, and also explored hyperparameter optimization.
Performance Discrepancy Mitigation in Heart Disease Prediction for Multisensory Inter-Datasets.
This study investigates performance variations in inter-dataset heart disease prediction settings using machine learning. It proposes, moreover, an effective preprocessing pipeline to mitigate performance discrepancies in inter-dataset heart disease prediction.
Effect of Imbalance Data Handling Techniques to Improve the Accuracy of Heart Disease Prediction Using Machine Learning and Deep Learning
The aim of this analysis is to identify the effect of imbalance data handling techniques on improving classification performance using machine learning and deep learning models for prediction Cardiovascular diseases.
Acceptance Rate 68.3%Oral Presentation
