Title :
A new viewpoint and order selection criteria for AR model
Author_Institution :
Sch. of Electr. & Mech. Eng., East China Jiaotong Univ., Nanchang, China
Abstract :
In this paper a new concept based on signal periodicity for AR model is presented, many problems which are difficult to be resolved in classical viewpoint such as order selection, characteristic frequency and pseudo frequency recognizing, relation determining between coefficient and signal amplitude, and other problems are investigated profoundly according to this new viewpoint, in the end, a sample signal is analyzed, the computation result testifies that periodicity is more effective than statistical concept for AR model of signal.
Keywords :
signal processing; statistical analysis; AR model; characteristic frequency; order selection; order selection criteria; pseudo frequency recognition; signal amplitude; signal periodicity; statistical concept; AR model; order selection; signal processing; signal spectrum;
Conference_Titel :
Software Engineering and Service Science (ICSESS), 2014 5th IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4799-3278-8
DOI :
10.1109/ICSESS.2014.6933609
