titoli, abstracts, parole chiave >>>
Knowledge discovery in databases of biomechanical variables: application to the sit to stand motor task

Vannozzi, Giuseppe and Della Croce, Ugo and Starita, Antonina and Benvenuti, Francesco and Cappozzo, Aurelio (2004) Knowledge discovery in databases of biomechanical variables: application to the sit to stand motor task. Journal of NeuroEngineering and Rehabilitation, Vol. 1 (7), p. 1-10. ISSN 1743-0003. Article.

Full text disponibile come PDF Richiede visualizzatore di PDF come GSview, Xpdf o Adobe Acrobat Reader
Available under License Creative Commons Attribution.


DOI: 10.1186/1743-0003-1-7


Background: The interpretation of data obtained in a movement analysis laboratory is a crucial issue in clinical contexts. Collection of such data in large databases might encourage the use of modern techniques of data mining to discover additional knowledge with automated methods. In order to maximise the size of the database, simple and low-cost experimental set-ups are preferable. The aim of this study was to extract knowledge inherent in the sit-to-stand task as performed by healthy adults, by searching relationships among measured and estimated biomechanical quantities. An automated method was applied to a large amount of data stored in a database. The sit-to-stand motor task was already shown to be adequate for determining the level of individual motor ability. Methods: The technique of search for association rules was chosen to discover patterns as part of a Knowledge Discovery in Databases (KDD) process applied to a sit-to-stand motor task observed with a simple experimental set-up and analysed by means of a minimum measured input model. Selected parameters and variables of a database containing data from 110 healthy adults, of both genders and of a large range of age, performing the task were considered in the analysis. Results: A set of rules and definitions were found characterising the patterns shared by the investigated subjects. Time events of the task turned out to be highly interdependent at least in their average values, showing a high level of repeatability of the timing of the performance of the task. Conclusions: The distinctive patterns of the sit-to-stand task found in this study, associated to those that could be found in similar studies focusing on subjects with pathologies, could be used as a reference for the functional evaluation of specific subjects performing the sit-to-stand motor task.

Item Type:Article
ID Code:106
Uncontrolled Keywords:Knowledge discovery, data mining, association rules, human movement, sit to stand
Subjects:Area 09 - Ingegneria industriale e dell'informazione > ING-INF/06 Bioingegneria elettronica e informatica
Divisions:001 Università di Sassari > 01 Dipartimenti > Scienze biomediche
Publisher:BioMed Central
Deposited On:18 Aug 2009 10:01

I documenti depositati in UnissResearch sono protetti dalle leggi che regolano il diritto d'autore

Repository Staff Only: item control page