Sensitivity analysis on effect of biomechanical factors for classifying vertebral deformities. Athertya, J. & Saravana Kumar, G. Volume 614 , 2018.
abstract   bibtex   
© Springer International Publishing AG 2018. Classification of degenerations prevalent in human population is considered to be a crucial task which is performed by a physician or the radiologist. With numerous data being generated and innumerable features getting extracted, identification of normal and pathological case becomes a daunting process. Data learning techniques provide valuable resources in automating the entire procedure easing the burden on the consultant physician. However, since the inception of various machine learning techniques, feasible solution at the cost of computational expense needs to be evaluated. Factors considered for classification play a significant role in defining the accuracy of a system. The current study aims at demonstrating the trade off achieved at the expense of accuracy amongst the number of features and instances. In this article, vertebral column dataset from UCI repository is used for training and testing. Effect of various data pre-processing techniques are presented alongside an extensive study on feature selection method. For validation, breast tissue dataset from the former repository is considered and analyzed.
@book{
 title = {Sensitivity analysis on effect of biomechanical factors for classifying vertebral deformities},
 type = {book},
 year = {2018},
 source = {Advances in Intelligent Systems and Computing},
 identifiers = {[object Object]},
 volume = {614},
 id = {c2c7ca09-87ab-3559-9259-e29c3c993184},
 created = {2018-04-26T04:49:30.962Z},
 file_attached = {false},
 profile_id = {0b583732-52d5-33b9-b059-682c26f2d83c},
 last_modified = {2018-04-26T04:49:30.962Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {false},
 hidden = {false},
 private_publication = {false},
 abstract = {© Springer International Publishing AG 2018. Classification of degenerations prevalent in human population is considered to be a crucial task which is performed by a physician or the radiologist. With numerous data being generated and innumerable features getting extracted, identification of normal and pathological case becomes a daunting process. Data learning techniques provide valuable resources in automating the entire procedure easing the burden on the consultant physician. However, since the inception of various machine learning techniques, feasible solution at the cost of computational expense needs to be evaluated. Factors considered for classification play a significant role in defining the accuracy of a system. The current study aims at demonstrating the trade off achieved at the expense of accuracy amongst the number of features and instances. In this article, vertebral column dataset from UCI repository is used for training and testing. Effect of various data pre-processing techniques are presented alongside an extensive study on feature selection method. For validation, breast tissue dataset from the former repository is considered and analyzed.},
 bibtype = {book},
 author = {Athertya, J.S. and Saravana Kumar, G.}
}

Downloads: 0