JP2730910B

PURPOSE:To simplify a data processing, and also, to obtain the result of waveform analysis having high reliability by using an ambiguous automaton and analyzing a waveform to be analyzed in accordance with whether a feature of a reference waveform pattern determined in advance exists in the waveform...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
1. Verfasser:	OOMORI KENJI
Format:	Patent
Sprache:	eng
Schlagworte:	ACOUSTICS CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING DIAGNOSIS ELECTRIC COMMUNICATION TECHNIQUE ELECTRIC DIGITAL DATA PROCESSING ELECTRICITY HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA HUMAN NECESSITIES HYGIENE IDENTIFICATION INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS MEDICAL OR VETERINARY SCIENCE MUSICAL INSTRUMENTS PHYSICS SPEECH ANALYSIS OR SYNTHESIS SPEECH OR AUDIO CODING OR DECODING SPEECH OR VOICE PROCESSING SPEECH RECOGNITION SURGERY TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	PURPOSE:To simplify a data processing, and also, to obtain the result of waveform analysis having high reliability by using an ambiguous automaton and analyzing a waveform to be analyzed in accordance with whether a feature of a reference waveform pattern determined in advance exists in the waveform to be analyzed or not. CONSTITUTION:Fuzzy data is generated by classifying a waveform to be analyzed into gradients of plural stages determined in advance, at every prescribed small section, and its fuzzy data is processed successively by using an ambiguous automaton which is provided with plural kinds of states determined in advance, and also, in which the range of a transition condition extending from some state to other state is determined, based on gradients of plural stages. Subsequently, based on the confidence degree of a state of the ambiguous automaton at the time point when the input of the fuzzy data is ended, whether the feature of a reference waveform pattern exists in the waveform to be analyzed or not is decided. In such a way, the data processing can be executed comparatively simply, and also, the result of waveform analysis having high reliability is obtained.