東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Fundamental Data Mining Techniques f...

Grohmann, Nico,

FindBook

Google Book

Amazon

博客來

Fundamental Data Mining Techniques for Declarative Process Mining /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Fundamental Data Mining Techniques for Declarative Process Mining // Nico Grohmann.
作者:	Grohmann, Nico,
面頁冊數:	1 electronic resource (251 pages)
附註:	Source: Dissertations Abstracts International, Volume: 84-02, Section: B.
Contained By:	Dissertations Abstracts International84-02B.
標題:	Purchase orders. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29262632
ISBN:	9798841563051

Fundamental Data Mining Techniques for Declarative Process Mining /
Grohmann, Nico,

Fundamental Data Mining Techniques for Declarative Process Mining /Nico Grohmann. - 1 electronic resource (251 pages)

Source: Dissertations Abstracts International, Volume: 84-02, Section: B.

Process mining has been a hot topic for the last 10 years. It originated from the work of Wil van der Aalst and has quickly picked up attention in both industry and academia. Indeed, industry has developed so much interest in the topic, its applications, and its potential benefts that several start-ups focusing on process mining could successfully established, one of which has even reached unicorn status.Process mining is based on the idea of generating process models from event logs. In other words, it is a total deviation from process modeling, which has been popular for the last 25 years, since the interest is no longer to model a process before it is enacted and deployed, but afterwards. An event log as produced by almost every modern IT system is a protocol of all events which have occurred in a system up to a certain point in time; hence it shows both what has been executed (which software) and the order in which execution events have occurred. Obviously, process mining thus cannot capture many details which could easily be refected in a process model (e.g., the human actors, roles or re-sources involved in the execution of a process, the data model underlying the events which are executed, or a relevant risk or SWOT model). On the other hand, various applications seem satisfed with the results that process mining can produce.Several users as well as researchers see process mining as a special form of data mining. This analogy is valid, since an event log can be considered as a dataset from which a model (the process model) is learned, and then compared to the intention or purpose that is underling the execution of the respective process (and for which a model may or may not yet exist). Due to this analogy, it makes sense to study whether and which established data mining techniques can be used in this context.Nico Grohmann's thesis has two main research questions it wants to answer: How to develop an implementation which applies association rule and sequential pattern mining to event data in the form of event logs for use in practice, and how can resulting rules and patterns be translated into declarative model elements in a way that they can be exploited for process improvement. The reader's attention is particularly directed to Chapter 5, one of the main contributions, where he applies pattern and rule mining to event log data, and shows in detail how algorithms Apriori/FP-Growth and GSP can be applied by using the commercial RapidMiner tool. It is also shown how the resulting rules or sequential patterns can be translated into Declare statements. He then evaluates the approach on three vastly realistic examples, and delivers the insight that sequential mining can yield considerably better results than just rule mining.The core of the thesis is a demonstration that process mining in the declarative direction can more or less easily be done using a commercially available tool without extraordinary eforts, which makes it an interesting read especially for the practitioner.

English

ISBN: 9798841563051Subjects--Topical Terms:

3690124
Purchase orders.

Fundamental Data Mining Techniques for Declarative Process Mining /
LDR:05447nmm a22003973i 4500 001 2437631
005 20251124054949.5
006 m o d
007 cr|nu||||||||
008 261011s2021 miu||||||m |||||||eng d
020 $a 9798841563051
035 $a (MiAaPQD)AAI29262632
035 $a (MiAaPQD)WilhelmsUnivMuenster437b4f04-3cb8-4af5-9d6c-139ca3f3653a
035 $a AAI29262632
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Grohmann, Nico, $e author. $3 3828686
245 1 0 $a Fundamental Data Mining Techniques for Declarative Process Mining / $c Nico Grohmann.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 1 electronic resource (251 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 84-02, Section: B.
500 $a Advisors: Vossen, Gottfried; Becker, H. C. Jorg.
502 $b Ph.D. $c Westfaelische Wilhelms-Universitaet Muenster (Germany) $d 2021.
520 $a Process mining has been a hot topic for the last 10 years. It originated from the work of Wil van der Aalst and has quickly picked up attention in both industry and academia. Indeed, industry has developed so much interest in the topic, its applications, and its potential benefts that several start-ups focusing on process mining could successfully established, one of which has even reached unicorn status.Process mining is based on the idea of generating process models from event logs. In other words, it is a total deviation from process modeling, which has been popular for the last 25 years, since the interest is no longer to model a process before it is enacted and deployed, but afterwards. An event log as produced by almost every modern IT system is a protocol of all events which have occurred in a system up to a certain point in time; hence it shows both what has been executed (which software) and the order in which execution events have occurred. Obviously, process mining thus cannot capture many details which could easily be refected in a process model (e.g., the human actors, roles or re-sources involved in the execution of a process, the data model underlying the events which are executed, or a relevant risk or SWOT model). On the other hand, various applications seem satisfed with the results that process mining can produce.Several users as well as researchers see process mining as a special form of data mining. This analogy is valid, since an event log can be considered as a dataset from which a model (the process model) is learned, and then compared to the intention or purpose that is underling the execution of the respective process (and for which a model may or may not yet exist). Due to this analogy, it makes sense to study whether and which established data mining techniques can be used in this context.Nico Grohmann's thesis has two main research questions it wants to answer: How to develop an implementation which applies association rule and sequential pattern mining to event data in the form of event logs for use in practice, and how can resulting rules and patterns be translated into declarative model elements in a way that they can be exploited for process improvement. The reader's attention is particularly directed to Chapter 5, one of the main contributions, where he applies pattern and rule mining to event log data, and shows in detail how algorithms Apriori/FP-Growth and GSP can be applied by using the commercial RapidMiner tool. It is also shown how the resulting rules or sequential patterns can be translated into Declare statements. He then evaluates the approach on three vastly realistic examples, and delivers the insight that sequential mining can yield considerably better results than just rule mining.The core of the thesis is a demonstration that process mining in the declarative direction can more or less easily be done using a commercially available tool without extraordinary eforts, which makes it an interesting read especially for the practitioner.
520 $a Process Mining ist eine Technik des Geschaftsprozessmanagements, die Ausfuhrungsdaten von Geschaftsprozessen zur Analyse verwendet. Durch eine Bereitstellung der Daten in sogenannten Event-Logs generieren Process Mining-Tools Prozessmodelle, die die Ausfuhrungen moglichst prazise beschreiben. Dies kann entweder in graph-basierte Notationen wie Petri-Netze oder BPMN oder deklarative Notationen wie Declare resultieren. Eine Hypothese der Arbeit ist, dass deklarative Constraints die Verstandlichkeit der Modelle erhohen kann wenn Process Mining grose, unubersichtliche "Spaghetti-Diagramme" produziert. Diese Arbeit prasentiert einen Ansatz inklusive prototypischer Implementierung um Assoziations- und Sequenzmusteranalyse auf Event-Logs anzuwenden, mit dem Ziel, deklarative Prozessmodelle zu erzeugen. Auf Preprocessing-Schritte und die Ubersetzung der Regeln und Muster zu Declare-Constraints wird explizit eingegangen. Dadurch erhalten Analysten transparente Einblicke in die Basis des gesamten deklarativen Modells.
546 $a English
590 $a School code: 0583
650 4 $a Purchase orders. $3 3690124
650 4 $a Keyboards. $3 3681868
650 4 $a Computer science. $3 523869
650 4 $a Information technology. $3 532993
650 4 $a Digital technology. $3 3561497
690 $a 0984
690 $a 0489
710 2 $a Westfaelische Wilhelms-Universitaet Muenster (Germany). $e degree granting institution. $3 3827696
720 1 $a Vossen, Gottfried $e degree supervisor.
720 1 $a Becker, H. C. Jorg $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 84-02B.
790 $a 0583
791 $a Ph.D.
792 $a 2021
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29262632