Access Restriction

Author Computing, With Parallel ♦ Higuchi, Tomoyuki
Source CiteSeerX
Content type Text
File Format PDF
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Different System Observation Model ♦ Generalized State Space Model ♦ System Observation Model ♦ Appropriate System Observation Model ♦ Self-organizing State Space Model ♦ Machine Learning Approach ♦ Partial Nongaussian State Space Model ♦ Evolutionary Time Series Model ♦ Time Series Model ♦ Havewell-organized Knowledge ♦ Time Series ♦ Switching Structure ♦ Computational Point ♦ Convenient Form ♦ State Vector
Description In this study,we consider a time series model which combines the partial nonGaussian state space model and self-organizing state space model (SOSSM), where the SOSSM has been proposed to an extension of the generalized state space model. The competing different system/observation models for the state vector can be simultaneously dealt in this model as introducing a switching structure, and appropriate system/observation models among them is automatically determined as a function of time. As a result, we are free from a procedure of selecting models among competing models. Of course, this model allows us to consider an inclusion of two system/observation models which conflicts each other in some sense. Namely,we need not havewell-organized knowledge about modeling of the time series. We therefore call this model the evolutionary time series model. We regard the approach based on the evolutionary time series model as one of the machine learning approaches. The evolutionary time series model can be formulated within a framework of an extension of SOSSM whichtakes a convenient form from a computational point of view.
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Learning Resource Type Article
Publisher Date 2001-01-01
Publisher Institution In Proc. 3rd JapanUS Seminar on Statistical Time Series Analysis