Enhancing AdaBoost Performance: Comparative Analysis of CPU Parallel Processing on Breast Cancer Classification

Abstract

The implementation of time-sharing across processes in a real-time way has the potential to increase the execution efficiency of multiprocessor systems like the one described above. The system is able to carry out tasks that make use of a large number of processors in an effective way as a result of this. The aim of this research is to design a system with two primary goals: to enhance accuracy and to minimise the amount of time necessary with processing. This will be accomplished by integrating the ADABoost model with the decision tree algorithm. Furthermore, the statistics unambiguously demonstrate that the accuracy remains the same regardless of whether or not the central processing unit (CPU) makes use of parallel processing, which suggests that there is no variation in parallelization. As a consequence of this, there is a direct connection between the amount of time that is spent and an increase in the amount of parallel processing that is carried out by the central processing unit pertaining to the breast cancer dataset that is being investigated. This research was carried out using Python, which was the programming language that was used for the coding technique that was carried out during the course of its execution.