- 216 pages
- English
- PDF
- Available on iOS & Android
About this book
Classification of time series is an important task in various fields, e.g., medicine, finance, and industrial applications. This workdiscusses strong temporal classification using machine learningtechniques. Here, two problems must be solved: the detection ofthose time instances when the class labels change and the correctassignment of the labels. For this purpose the scenario-basedrandom forest algorithm and a segment and label approach areintroduced. The latter is realized with either the augmenteddynamic time warping similarity measure or with interpretablegeneralized radial basis function classifiers.The main application presented in this work is the detectionand categorization of car crashes using machine learning.Depending on the crash severity different safety systems, e.g., belt tensioners or airbags must be deployed at time instanceswhen the best-possible protection of passengers is assured.
Tools to learn more effectively
Saving Books
Keyword Search
Annotating Text
Listen to it instead