Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Bücher
Zeitschriften
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
ATZ-Fachkongress

Chassis.tech plus 2024


4 Kongresse in einer Veranstaltung

Treffen Sie in München die Fachleute von Chassis, Lenkung, Bremsen sowie Reifen/Räder.
Erweiterte Suche
Anmelden
nach oben

2022 | Buch

Introduction Kapitel lesen Erstes Kapitel lesen

Discovery of Ill–Known Motifs in Time Series Data

verfasst von: Sahar Deppe

Verlag: Springer Berlin Heidelberg

Buchreihe : Technologien für die intelligente Automation

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten
insite
SUCHEN

Über dieses Buch

This book includes a novel motif discovery for time series, KITE (ill-Known motIf discovery in Time sEries data), to identify ill-known motifs transformed by affine mappings such as translation, uniform scaling, reflection, stretch, and squeeze mappings. Additionally, such motifs may be covered with noise or have variable lengths. Besides KITE’s contribution to motif discovery, new avenues for the signal and image processing domains are explored and created. The core of KITE is an invariant representation method called Analytic Complex Quad Tree Wavelet Packet transform (ACQTWP). This wavelet transform applies to motif discovery as well as to several signal and image processing tasks. The efficiency of KITE is demonstrated with data sets from various domains and compared with state-of-the-art algorithms, where KITE yields the best outcomes.

Inhaltsverzeichnis

Frontmatter
Chapter 1. Introduction
Abstract
The increasing importance of technology in different aspects of human life and the accessibility to the internet result in an accumulation of a huge amount of data. According to IBM [IBM20], over 2.5 quintillion bytes of data are created every single day, obtained from different fields such as economics, medicine and epidemiology, industry and telecommunications, geographical and physical science [PfL18, ElB18, CTC+19, SGO20]. These data are mainly collected from e.g. the internet or various sensors in the form of time series, which is an ordered set of numbers measured at successive and regular time intervals [Fu11].
Sahar Deppe
Chapter 2. Preliminaries
Abstract
The definitions, mathematical notations, and tools applied throughout this thesis are given in this section. First, a general introduction to time-series is included since time series constitute this dissertation’s main scope. In the context of data mining and knowledge discovery, time series analysis does not only aim to extract statistics but mainly to discover the characteristics and meaningful information from the data by employing tasks such as clustering, classification, prediction, and motif discovery [Alp10,EsA12,BLB+17,ToL17b].
Sahar Deppe
Chapter 3. General Principles of Time Series Motif Discovery
Abstract
The general approach towards motif discovery is depicted in Fig. 3.1. The first step, pre-processing, contains tasks such as normalisation or segmentation. The data representation step aims to reduce the data’s size or to approximate it without losing relevant information. In the final step, the similarity measurement step, motifs are detected by quantifying their similarity based on a given threshold [EsA12,Mue14,ToL17b].
Sahar Deppe
Chapter 4. State of the Art in Time Series Motif Discovery
Abstract
Time series are one of the most substantial parts of the world’s supply of data, according to [Fu11], and they are part of several applications from diverse areas. This topic attracts several researchers from the domain of data and knowledge discovery. Data mining and pattern recognition tasks aim to provide information derived from time series [BeR14, BLB+17, FaV17, AAJ+19, AlA20].
Sahar Deppe
Chapter 5. Distortion-Invariant Motif Discovery
Abstract
This section represents the core of this dissertation. According to the motivation given in Chapter 1, the review of the motif discovery algorithms, and the research gaps provided in Chapter 4, KITE’s approach is proposed in this section. KITE aims to overcome the limitations of the existing methods regarding detecting illknown motifs by means of its steps.
Sahar Deppe
Chapter 6. Evaluation
Abstract
In the previous sections, the theoretical methods and their properties that contributed to this dissertation have been described. In this chapter, experiments are performed in order to evaluate the performance of KITE. All the examinations are benchmarked against six state-of-the-art algorithms, as explained in Chapter 4.
Sahar Deppe
Chapter 7. Conclusion and Outlook
Abstract
After introducing the term Knowledge Discovery in Databases (KDD) by Gregory Piatetsky-Shapiro in 1989, this topic and machine learning have become an attractive area for several researchers. By increasing the power of computers to collect and compute data, the need for methods that analyse the data and extract knowledge from it is growing. This issue is addressed by tasks such as clustering, classification, query by content, anomaly detection, and motif discovery [BeR14,BLB+17,FaV17,AAJ+19,AlA20].
Sahar Deppe
Backmatter
Metadaten
Titel
Discovery of Ill–Known Motifs in Time Series Data
verfasst von
Sahar Deppe
Copyright-Jahr
2022
Verlag
Springer Berlin Heidelberg
Electronic ISBN
978-3-662-64215-3
Print ISBN
978-3-662-64214-6
DOI
https://doi.org/10.1007/978-3-662-64215-3

Premium Partner

    Bildnachweise