| 000 | 00000nam c2200205 c 4500 | |
| 001 | 000045932647 | |
| 005 | 20230530103936 | |
| 007 | ta | |
| 008 | 171226s2018 ulkad bmAC 000c eng | |
| 040 | ▼a 211009 ▼c 211009 ▼d 211009 | |
| 085 | 0 | ▼a 0510 ▼2 KDCP |
| 090 | ▼a 0510 ▼b 6D36 ▼c 1074 | |
| 100 | 1 | ▼a 김충겸 ▼g 金忠謙 |
| 245 | 1 0 | ▼a Deep neural models for pre-detecting anomalies from multivariate streaming data / ▼d Chunggyeom Kim |
| 246 | 1 1 | ▼a 다변량 스트리밍 데이터에서 사전 이상 탐지를 위한 심층 신경 모델 |
| 260 | ▼a Seoul : ▼b Graduate School, Korea University, ▼c 2018 | |
| 300 | ▼a iv, 25장 : ▼b 삽화, 도표 ; ▼c 26 cm | |
| 500 | ▼a 지도교수: 강재우 | |
| 502 | 0 | ▼a 학위논문(석사)-- ▼b 고려대학교 대학원, ▼c 컴퓨터·전파통신공학과, ▼d 2018. 2 |
| 504 | ▼a 참고문헌: 장 22-25 | |
| 530 | ▼a PDF 파일로도 이용가능; ▼c Requires PDF file reader(application/pdf) | |
| 653 | ▼a Anomaly detection | |
| 776 | 0 | ▼t Deep neural models for pre-detecting anomalies from multivariate streaming data ▼w (DCOLL211009)000000079346 |
| 900 | 1 0 | ▼a Kim, Chung Gyeom, ▼e 저 |
| 900 | 1 0 | ▼a 강재우, ▼g 姜在雨, ▼d 1969-, ▼e 지도교수 ▼0 AUTH(211009)151698 |
| 945 | ▼a KLPA |
Electronic Information
| No. | Title | Service |
|---|---|---|
| 1 | Deep neural models for pre-detecting anomalies from multivariate streaming data (51회 열람) |
View PDF Abstract Table of Contents |
Holdings Information
| No. | Location | Call Number | Accession No. | Availability | Due Date | Make a Reservation | Service |
|---|---|---|---|---|---|---|---|
| No. 1 | Location Science & Engineering Library/Stacks(Thesis)/ | Call Number 0510 6D36 1074 | Accession No. 123058301 | Availability Available | Due Date | Make a Reservation | Service |
| No. 2 | Location Science & Engineering Library/Stacks(Thesis)/ | Call Number 0510 6D36 1074 | Accession No. 123058302 | Availability Available | Due Date | Make a Reservation | Service |
Contents information
Abstract
Anomaly detection in an industrial process is a crucial task for preventing unexpected economic loss. Among various signals, multivariate time series data has been one of the most difficult signals to analyze for detecting anomalies. Moreover, labels for anomalous signals are often unavailable in many fields. To tackle this problem, we present DeepNAP which is a deep neural anomaly pre-detection model based on recurrent neural networks. Without any annotated data, DeepNAP successfully learns to detect anomalies using partial reconstruction. Detecting anomalies in advance is essential for preventing catastrophic events. While previous studies focused mainly on capturing anomalies after they have occurred, DeepNAP is able to pre-detect anomalies. We evaluate DeepNAP and other baseline models on a real multivariate dataset generated from a semiconductor manufacturing fab. Compared with other baseline models, DeepNAP achieves the best performances with earlier anomaly detection.
Table of Contents
Abstract Contents i List of Figures iii List of Tables iv 1 Introduction 1 2 Related Works 3 2.1 Time Series Anomaly Detection . . . . . . . . . . . . . . . . . . . . . . . . 3 2.2 Anomaly Detection Using Neural Networks . . . . . . . . . . . . . . . . . 4 2.3 Anomaly Detection on Semiconductor Manufacturing Process . . . . . . . 5 3 Preliminary 6 3.1 Long Short-Term Memory . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 3.2 Sequence to Sequence . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 4 Model Description 9 4.1 Prediction Module . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 4.2 Detection Module . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 4.3 Deep Neural Anomaly Pre-detection Model . . . . . . . . . . . . . . . . . 13 5 Experiments 14 5.1 Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 5.2 Baselines & Proposed Models . . . . . . . . . . . . . . . . . . . . . . . . . 14 5.3 Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 5.4 Analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 6 Conclusion 21 Bibliography 22
