Andere Kunden interessierten sich auch für
![Design of Heat Exchanger for Computing Clusters]( "Design of Heat Exchanger for Computing Clusters")
Design of Heat Exchanger for Computing Clusters23,99 €![Process Safety and Big Data]( "Process Safety and Big Data")
Process Safety and Big Data105,99 €![Data mining approach in Security Information & Event Management]( "Data mining approach in Security Information & Event Management")
Data mining approach in Security Information & Event Management32,99 €![Blind separation of fetal ECG from single mixture using SVD and ICA]( "Blind separation of fetal ECG from single mixture using SVD and ICA")
Blind separation of fetal ECG from single mixture using SVD and ICA23,99 €![Predicting Telecommunication Customer Churn Using Data Mining]( "Predicting Telecommunication Customer Churn Using Data Mining")
Predicting Telecommunication Customer Churn Using Data Mining32,99 €![Machine Learning: Theory & Applications]( "Machine Learning: Theory & Applications")
Machine Learning: Theory & Applications26,99 €![Integration of Data Mining Techniques for Improving Efficiency of KDD]( "Integration of Data Mining Techniques for Improving Efficiency of KDD")
Integration of Data Mining Techniques for Improving Efficiency of KDD46,99 €
Traditional clustering and feature selection methods consider the data matrix as static. However, the data matrices evolve smoothly over time in many applications. A simple approach to learn from these time-evolving data matrices is to analyze them separately. Such strategy ignores the time-dependent nature of the underlying data. We propose two formulations for evolutionary co-clustering and feature selection based on the fused Lasso regularization. The evolutionary co-clustering formulation is able to identify smoothly varying hidden block structures embedded into the matrices along the temporal dimension. Our formulation is very flexible and allows for imposing smoothness constraints over only one dimension of the data matrices. The evolutionary feature selection formulation can uncover shared features in clustering from time-evolving data matrices. We show that the optimization problems involved are non-convex, non-smooth and non-separable. To compute the solutions efficiently, we develop a two-step procedure that optimizes the objective function iteratively.