Data mining the effects of testing conditions and specimen properties on brain biomechanics
| Autor: | Raj Prabhu, Folly Patterson, Osama Abuomar, Keith E. Tansey, Michael John Jones |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Self-organizing map
principal component analysis Computer science lcsh:Biotechnology Biomedical Engineering self-organizing maps Physical Therapy Sports Therapy and Rehabilitation computer.software_genre lcsh:Physiology Article Traumatic brain injury lcsh:TP248.13-248.65 Orthopedics and Sports Medicine Sensitivity (control systems) Cluster analysis lcsh:QP1-981 Rehabilitation Confounding Biomechanics Computer Science Applications fuzzy c-means clustering Assessment methods Principal component analysis Data mining computer Research Article |
| Zdroj: | International Biomechanics article-version (VoR) Version of Record International Biomechanics, Vol 6, Iss 1, Pp 34-46 (2019) |
| ISSN: | 2333-5432 |
| Popis: | Traumatic brain injury is highly prevalent in the United States. However, despite its frequency and significance, there is little understanding of how the brain responds during injurious loading. A confounding problem is that because testing conditions vary between assessment methods, brain biomechanics cannot be fully understood. Data mining techniques, which are commonly used to determine patterns in large datasets, were applied to discover how changes in testing conditions affect the mechanical response of the brain. Data at various strain rates were collected from published literature and sorted into datasets based on strain rate and tension vs. compression. Self-organizing maps were used to conduct a sensitivity analysis to rank the testing condition parameters by importance. Fuzzy C-means clustering was applied to determine if there were any patterns in the data. The parameter rankings and clustering for each dataset varied, indicating that the strain rate and type of deformation influence the role of these parameters in the datasets. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|