P. Brady, Martin Hill, Joseph Connell, John Barrett, B. Fennessy, P. O'sullivan, D. O'Hare
{"title":"The effects of drilling parameters on the acoustic drilling signature of the squamous temporal bone: A categorical multivariate regressive analysis","authors":"P. Brady, Martin Hill, Joseph Connell, John Barrett, B. Fennessy, P. O'sullivan, D. O'Hare","doi":"10.1109/ISABEL.2010.5702894","DOIUrl":null,"url":null,"abstract":"This paper investigates the effects of drill speed, burr type, burr style, and stroke speed on the acoustics that are generated from a surgical drill when dissecting the squamous temporal bone region. Multivariate regression is used to analyse and predict the Mel frequency cepstrum of the audio that is generated during the procedure. It is seen that each of drilling parameters along with their higher order interaction terms has a significant affect on the acoustic drilling signature of the squamous temporal bone. Furthermore, it was established, for the first time, that a categorical multivariate regressive model could consistently predict the Mel frequency cepstrum of the squamous temporal bone with accuracy of 97.78% with only 2 seconds of audio training data. This represents a significant advance on previously reported work.","PeriodicalId":165367,"journal":{"name":"2010 3rd International Symposium on Applied Sciences in Biomedical and Communication Technologies (ISABEL 2010)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 3rd International Symposium on Applied Sciences in Biomedical and Communication Technologies (ISABEL 2010)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISABEL.2010.5702894","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
This paper investigates the effects of drill speed, burr type, burr style, and stroke speed on the acoustics that are generated from a surgical drill when dissecting the squamous temporal bone region. Multivariate regression is used to analyse and predict the Mel frequency cepstrum of the audio that is generated during the procedure. It is seen that each of drilling parameters along with their higher order interaction terms has a significant affect on the acoustic drilling signature of the squamous temporal bone. Furthermore, it was established, for the first time, that a categorical multivariate regressive model could consistently predict the Mel frequency cepstrum of the squamous temporal bone with accuracy of 97.78% with only 2 seconds of audio training data. This represents a significant advance on previously reported work.