Name
Abstract | ||
|---|---|---|
Assessment of the risks associated with bone injures is nontrivial because fragility of human bones is varying with aging. Since only a limited number of experiments have been performed on the specimens from human donors, there is limited number of fracture resistance curves available in literature. This study proposes a decision support system for the assessment of bone stress intensity factor by using artificial neural networks (ANN). The procedure estimates stress intensity factor according to patient's age and diagnosed crack length. ANN was trained using the experimental data available in literature. The automated training of ANN was performed using evolutionary assembled Artificial Neural Networks. The obtained results showed good correlation with the experimental data, with potential for further improvements and applications. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1109/BIBE.2015.7367680 | IEEE International Conference on Bioinformatics and Bioengineering |
Keywords | Field | DocType |
bone stress intensity factor,bone injures,human bone fragility,fracture resistance curves,decision support system,crack length,ANN automated training,evolutionary assembled artificial neural networks | Stress intensity factor,Experimental data,Computer science,Decision support system,Correlation,Fragility,Artificial intelligence,Artificial neural network,Machine learning | Conference |
Citations | PageRank | References |
0 | 0.34 | 1 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Arso M. Vukicevic | 1 | 8 | 3.27 |
| Gordana R. Jovicic | 2 | 8 | 2.93 |
| Nebojsa Jovicic | 3 | 0 | 0.34 |
| Zarko Milosevic | 4 | 56 | 10.35 |
| Nenad Filipovic | 5 | 59 | 31.21 |