MARC details
| 000 -LEADER |
|---|
| fixed length control field |
04357nam a22002537a 4500 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION |
|---|
| fixed length control field |
210318b2021 a|||f mb|| 00| 0 eng d |
| 040 ## - CATALOGING SOURCE |
|---|
| Original cataloging agency |
EG-CaNU |
| Transcribing agency |
EG-CaNU |
| 041 0# - Language Code |
|---|
| Language code of text |
eng |
| Language code of abstract |
eng |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER |
|---|
| Classification number |
610 |
| 100 0# - MAIN ENTRY--PERSONAL NAME |
|---|
| Personal name |
Fadi Nader Zaki Baskharon |
| 245 1# - TITLE STATEMENT |
|---|
| Title |
Predicting Remaining Cycle Time from Ongoing Cases: |
| Remainder of title |
A Survival Analysis-Based Approach / |
| Statement of responsibility, etc. |
Fadi Nader Zaki Baskharon |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. |
|---|
| Date of publication, distribution, etc. |
2021 |
| 300 ## - PHYSICAL DESCRIPTION |
|---|
| Extent |
51 p. |
| Other physical details |
ill. |
| Dimensions |
21 cm. |
| 500 ## - GENERAL NOTE |
|---|
| Materials specified |
Supervisor: Mohamed A. ElHelw |
| 502 ## - Dissertation Note |
|---|
| Dissertation type |
Thesis (M.A.)—Nile University, Egypt, 2021 . |
| 504 ## - Bibliography |
|---|
| Bibliography |
"Includes bibliographical references" |
| 505 0# - Contents |
|---|
| Formatted contents note |
Contents:<br/>1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1<br/>1.1 Problem Statement . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3<br/>1.2 Thesis Outline and Summary of Contributions . . . . . . . . . . . . . . . . . . 4<br/>2. Background . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6<br/>2.1 Preliminaries . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6<br/>2.1.1 Definitions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6<br/>2.1.2 Survival Analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7<br/>2.1.3 Weibull distribution . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13<br/>2.1.4 Recurrent Neural Networks . . . . . . . . . . . . . . . . . . . . . . . . 15<br/>2.2 Related Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19<br/>2.3 Baseline Approach . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22<br/>3. Proposed Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23<br/>3.1 Model Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23<br/>3.2 Optimization function . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27<br/>3.3 Output interpretation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28<br/>4. Evaluation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30<br/>4.1 Experiment I . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30<br/>4.2 Experiment II . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36<br/>vii<br/>5. Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39<br/>5.1 Future directions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39<br/>5.2 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40<br/>Appendices:<br/>A. cycle prediction documentation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42<br/>Bibliography . |
| 520 3# - Abstract |
|---|
| Abstract |
Abstract:<br/>in predictive process monitoring. Different approaches that learn from event logs, e.g., relying<br/>on an existing representation of the process or leveraging machine learning approaches, have<br/>been proposed in the literature to tackle this problem. Machine learning-based techniques have<br/>shown superiority over other techniques with respect to the accuracy of the prediction as well<br/>as freedom from knowledge about the underlying process models generating the logs. However,<br/>all proposed approaches only learn from complete traces. This might cause delays in starting<br/>new training cycles as usually process instances last over a long time that could even reach<br/>months or years.<br/>In this thesis, we propose a machine learning approach that can also accept and learn from<br/>incomplete (ongoing) traces. Using a time-aware survival analysis technique, we can train a<br/>neural network to predict the most likely remaining cycle time of a running case.<br/>This approach is evaluated on different real-life datasets and is compared with a state-ofthe-<br/>art baseline. Results show that our approach, in most cases, is able to outperform the<br/>baseline approach with a simple model architecture and less training time.<br/>The approach is further enhanced to learn from trace level - fixed - features as well as the<br/>events-related features. We empirically proved that trace-level features enhance the prediction<br/>power of the model using a real-life dataset. |
| 546 ## - Language Note |
|---|
| Language Note |
Text in English, abstracts in English. |
| 650 #4 - Subject |
|---|
| Subject |
Informatics |
| 655 #7 - Index Term-Genre/Form |
|---|
| Source of term |
NULIB |
| focus term |
Dissertation, Academic |
| 690 ## - Subject |
|---|
| School |
Informatics |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) |
|---|
| Source of classification or shelving scheme |
Dewey Decimal Classification |
| Koha item type |
Thesis |
| 655 #7 - Index Term-Genre/Form |
|---|
| -- |
187 |
| 690 ## - Subject |
|---|
| -- |
499 |