Ilavsky, J. Nika: software for two-dimensional data reduction.
CMIPS faculty and staff include experts in causal inference, survival data analysis, longitudinal analysis, computing and optimization, measurement error, high-dimensional data reduction, network science, epidemiologic methods, health economics and qualitative and mixed methods.
Jeno [33] did a research on high-dimensional data reduction from the perspective of center vector and least squares.
Least squares mapping method Jeno [33] did a research on high-dimensional data reduction from the perspective of center vector and least squares.
The SOM is an unsupervised method for multi-dimensional data reduction and display [ 15].
1 While certain computationally expensive techniques 2 can construct predictive models with considerable accuracy from high-dimensional data, reduction of these data prior to modeling is a separate problem that has received recent attention.
Clearly, to deal with high-dimensional data, dimensionality reduction is an effective solution through finding meaningful low-dimensional structures hidden in their high-dimensional observations.
There are three types of clustering algorithms for high-dimensional data: attribute reduction [2], subspace clustering [3], and co-clustering [4].
Projection Pursuit Classification Model (PPC) can achieve high-dimensional data dimension reduction operation and conduct integrated evaluation for data in low-dimensional space without limitation from problem scale and data structure.
One of the most widely-used procedures for dimensionality reduction of high dimensional data is Principal Component Analysis (PCA).
PCA helps to explain the variance in data and is a common technique for dimensionality reduction in high dimensional data.
