Research Article
Classifying shoulder implants in X-ray images using Big data techniques
@INPROCEEDINGS{10.4108/eai.7-6-2021.2308636, author={M. Sivachandran and Dr.T. Krishnakumar}, title={Classifying shoulder implants in X-ray images using Big data techniques}, proceedings={Proceedings of the First International Conference on Computing, Communication and Control System, I3CAC 2021, 7-8 June 2021, Bharath University, Chennai, India}, publisher={EAI}, proceedings_a={I3CAC}, year={2021}, month={6}, keywords={knn instance based classifier lazy classifier tsa uw}, doi={10.4108/eai.7-6-2021.2308636} }- M. Sivachandran
Dr.T. Krishnakumar
Year: 2021
Classifying shoulder implants in X-ray images using Big data techniques
I3CAC
EAI
DOI: 10.4108/eai.7-6-2021.2308636
Abstract
This research work focuses on optimal solution for the image detection and segmentation. The prosthesis may – a few or numerous years after it was embedded – come needing fix or substitution. In a portion of these cases, the maker and the model of the prosthesis might be obscure to the patients and their essential consideration specialists, for instance when the medical procedure was led in another nation where the patient has presently no admittance to the records. The highest accuracy value is 81.68% which is while applying the=7k=6 and the lowest accuracy value is 65.6% when apply the k=7. The highest precision value is 81.68% while applying the k=1 and very lowest precision value is 73.69% lies on k=2 and k=9.The highest recall value is 83.69% which is produced by while applying the parameter k=6, the lowest recall value is 65.76% while applying the parameter k=9. The K=10 model takes more time to build the model is while applying the k=10 and very low time consumption model is k=8. Another conceivable instance of not knowing the specific producer and model could be expected uncertainty in clinical records or clinical images.
