FEATURE SELECTION AND CLASSIFICATION OF LEUKEMIC CELLS USING IOT AND MACHINE LEARNING

Machine learning and the Internet of Things (IoT) have affected every step of the leukemia process, from diagnosis to understanding to therapy. Consequently, this study delves into the planning of an innovative system that employs IoT and machine learning techniques to precisely differentiate leukemic cells. Depending on the patient's samples, the system uses different ways to feature selection and cell classification. To pick the most informative collection of features that enables stable and accurate cell categorization into suitable categories, the offered research relies on strong machine-learning approaches for feature selection. Next, a classification model is used to classify cells based on their properties using the attributes that have been chosen. There is evidence that the suggested approach can classify leukemic cells with an identification rate of up to 99%, which is greater than the current methods. As a novel strategy for managing massive volumes of biological and medical samples, the suggested method will be an invaluable tool for doctors treating leukemia patients. The system's ability to process data from various Internet of Things (IoT) sources should aid its ability to learn and adapt to real-world clinical settings. With the results of this study in hand, we may be able to detect leukemia sooner, with greater precision, and maybe use more tailored treatments for each patient, leading to better results while reducing healthcare expenditures.