Multivariate and Big Data Modeling and Related Issues
1National University of Sciences and Technology, Islamabad, Pakistan
2King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia
3Uludag University, Uludag, Turkey
Multivariate and Big Data Modeling and Related Issues
Description
Traditional data sets are being replaced by high-dimensional data structures known as big data sets as technology advances. This has been seen in practically every field of research, including dependability, life testing, econometrics, meteorology, actuarial science, biology, chemistry, and other disciplines. On the plus side, quantitative methodologies developed in recent decades in the fields of multivariate data analysis and machine learning have paved the way for advancements in tackling current data-based concerns. They are of practical and theoretical relevance to scientists from various disciplines.
Predictive regression models, classification models, clustering, and dimension reduction techniques are among the most recent data analysis tools. The key issue is dealing with the complexity of substantial data sets, which may be solved utilising hybrid machine learning methodologies. The key difficulties include data complexity, a lack of basic knowledge of Big Data, data expansion concerns, and suitable Big Data tool selection.
This Special Issue accepts theoretical and empirical research articles that investigate the multifaceted analysis, as well as offering a venue for scholars and the big data analysis sector to share their insights and creative ways to data analysis. We welcome contributions of original research and reviews to focus on the pragmatic application of multivariate data analysis techniques and machine learning models to specific themes in big data analysis are of special relevance.
Potential topics include but are not limited to the following:
- Big data analysis
- Dimensionality issues include advanced methods of principal component analysis, factor analysis
- Multivariate linear, nonlinear, and spline regression are examples of predictive modelling
- Classification techniques include linear discriminate analysis, support vector machine, neural network, and k-nearest neighborhood classification, among others
- Clustering approaches include flat and hierarchical clustering
- Performance indicators for prediction, classification, and clustering procedures