The optimization of reconfigured real-time datasets for improving classification performance of machine learning algorithms

Sudhakar Sengan; P. Vidya Sagar; R. Ramesh; Osamah Ibrahim Khalaf; R. Dhanapal

Sudhakar Sengan Department of Computer Science and Engineering, PSN College of Engineering and Technology, Tirunelveli â€“ 627152, Tamil Nadu, India.
P. Vidya Sagar Department of Computer Science {\&} Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, A.P, India
R. Ramesh Department of Science and Humanities, Sri Krishna College of Engineering and Technology, Coimbatore-641008
Osamah Ibrahim Khalaf Al-Nahrain University-Baghdad, Iraq, AlNahrain Nanorenewable Energy Research Centre.
R. Dhanapal Department of Computer Science and Engineering, Karpagam Academy of Higher Education, Coimbatore

Abstract

Machine Learning (ML) is one of the modern techniques with promising outcomes in classification and prediction domains. In order to improve demand projections, historical data can be analyzed with different methods, such as ML techniques, time series analysis, and deep learning models. A knowledgeable demand visualization system is developed in this work. This enhanced model is based on the study investigations and interpretation of statistical data using various prediction methods, including traditional time series techniques, support~vector machines, and deep learning algorithms. Therefore, we are aiming to analyze the effectiveness of different model classification for ML to prevent the use of personalized log
data. We offer classification pre-processing steps to improve the performance results and speed of the eXtended Machine Learning (X-ML) algorithm in the training data sets. We also proved~the classification speed improvement on several real datasets via this automated system. The improvement is significantly greater and coherent, with the accuracy dropped in only a few case scenarios.