Machine learning techniques for time series classification / Michael Botsch.

Format:

Book

Author/Creator:

Botsch, Michael, author.

Series:

Künstliche Intelligenz & Digitalisierung

Künstliche Intelligenz & Digitalisierung ; v.2

Language:

English

Subjects (All):

Engineering.

Physical Description:

1 online resource (217 pages)

Edition:

Second edition.

Place of Publication:

Göttingen, Germany : Cuvillier Verlag, [2023]

Summary:

Classification of time series is an important task in various fields, e.g., medicine, finance, and industrial applications. This work discusses strong temporal classification using machine learning techniques. Here, two problems must be solved: the detection of those time instances when the class labels change and the correct assignment of the labels. For this purpose the scenario-based random forest algorithm and a segment and label approach are introduced. The latter is realized with either the augmented dynamic time warping similarity measure or with interpretable generalized radial basis function classifiers.The main application presented in this work is the detection and 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 instances when the best-possible protection of passengers is assured.

Contents:

Intro

Contents

1. Introduction

2. Machine Learning

3. Interpretable Generalized Radial Basis Function Classifiers Based on the Random Forest Kernel

4. Classification of Temporal Data

5. Classification in Car Safety Systems

6. Scenario-Based Random Forest for On-Line Time Series Classification

7. Segmentation and Labeling for On-Line Time Series Classification

8. Conclusions

Appendices

Bibliography.

Notes:

Includes bibliographical references.

Description based on print version record.

Other Format:

Print version: Botsch, Michael Machine Learning Techniques for Time Series Classification

ISBN:

9783736968134

3736968132