Comparison of Statistical and Non-statistical Classifiers for Thumb Motion Clasification

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F08%3A03144957" target="_blank" >RIV/68407700:21230/08:03144957 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

čeština

Original language name

Comparison of Statistical and Non-statistical Classifiers for Thumb Motion Clasification

Original language description

This paper deals with a comparison of statistical and non-statistical classifiers for thumb motion classification. Presented work is a part of research of relation between brain and muscle activity. The thumb motion is represented by trajectory coordinates of special mark placed on the thumb. Motions are classified using k-Means classifier (non-statistical classification, no prior information is needed) and Bayes classifier (statistical models of classes are needed, classifier training is necessary). The efficiency of classifiers is evaluated using the standard HTK parameters. Real testing data includes more than 900 stationary states which are used for classifier testing. The classification results are compared for both methods.

Czech name

Comparison of Statistical and Non-statistical Classifiers for Thumb Motion Clasification

Czech description

This paper deals with a comparison of statistical and non-statistical classifiers for thumb motion classification. Presented work is a part of research of relation between brain and muscle activity. The thumb motion is represented by trajectory coordinates of special mark placed on the thumb. Motions are classified using k-Means classifier (non-statistical classification, no prior information is needed) and Bayes classifier (statistical models of classes are needed, classifier training is necessary). The efficiency of classifiers is evaluated using the standard HTK parameters. Real testing data includes more than 900 stationary states which are used for classifier testing. The classification results are compared for both methods.

Type

J_x - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)

CEP classification

JA - Electronics and optoelectronics

OECD FORD branch

—

Project

—

Continuities

Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year

2008

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Lékař a technika

ISSN

0301-5491

e-ISSN

—

Volume of the periodical

38

Issue of the periodical within the volume

2

Country of publishing house

CZ - CZECH REPUBLIC

Number of pages

3

Pages from-to

—

UT code for WoS article

—

EID of the result in the Scopus database

—