From Multidimensional Mixture Data Analysis to Spatio-temporal Multidimensional Collective Data Analysis
Futoshi Naya, Hiroshi Sawada · NTT technical review · 2016
This article introduces a multidimensional mixture data analysis technique that can efficiently extract significant features that transect different types of data with multiple attributes such as application logs available on the Web and sensor data collected from IoT (Internet of Things) sensors.The basic algorithm and an example of an application to review site data analysis are described.Spatio-temporal data modeling and an extension of a spatio-temporal multidimensional collective data analysis technique for predicting the time and place of near-future events are also explained.