repository
Dynamic Tucker Decomposition with Applications to Air Quality Stream Data Analysis
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | 이슬 | - |
| dc.contributor.author | 이상석 | - |
| dc.date.accessioned | 2022-11-29T03:01:16Z | - |
| dc.date.available | 2022-11-29T03:01:16Z | - |
| dc.date.issued | 2022-02 | - |
| dc.identifier.other | 31762 | - |
| dc.identifier.uri | https://dspace.ajou.ac.kr/handle/2018.oak/20956 | - |
| dc.description | 학위논문(석사)--아주대학교 일반대학원 :인공지능학과,2022. 2 | - |
| dc.description.tableofcontents | 1. Introduction 1 2. Background 2 2.1 Tensor Operation 2 2.2 Tucker Decomposition 3 2.3 Incremental SVD 3 2.4 Zoom SVD 4 3. Proposed Method 6 3.1. Storage Phase 6 3.2. Query Phase 9 3.2.1 Partial-SVD 10 3.2.2 Stiched-SVD 11 3.3. Initialization Phase 12 3.3.1 First Factor 12 3.3.2 Second Factor 12 3.3.3 Remain Factor 13 3.4. Iteration Phase 13 3.4.1 First Factor 14 3.4.2 Second Factor 14 3.4.3 Remain Factor 15 3.5. Anomaly Detection 15 3.5.1. Anomaly Score 15 3.5.2.Fixed Thresholding 16 3.6 Recontruction error 16 4. Experiment 17 4.1. Data Set 17 4.1.1 Air Pollution Data 17 4.2. Experiment Settings 18 4.3. Space Cost 18 4.4. Effect of Block Size 19 4.5. Anomaly Detection 19 4.5.1 K-means clustering setting 20 4.5.2. Fixed Threshold Setting 21 4.5.3. Decomposed Tensor Factor Analysis 21 4.6. Location Analysis 23 4.6.1. Location Vector Clustering 23 5. Conclusion 27 6. References 27 | - |
| dc.language.iso | eng | - |
| dc.publisher | The Graduate School, Ajou University | - |
| dc.rights | 아주대학교 논문은 저작권에 의해 보호받습니다. | - |
| dc.title | Dynamic Tucker Decomposition with Applications to Air Quality Stream Data Analysis | - |
| dc.type | Thesis | - |
| dc.contributor.affiliation | 아주대학교 일반대학원 | - |
| dc.contributor.department | 일반대학원 인공지능학과 | - |
| dc.date.awarded | 2022. 2 | - |
| dc.description.degree | Master | - |
| dc.identifier.localId | 1245061 | - |
| dc.identifier.uci | I804:41038-000000031762 | - |
| dc.identifier.url | https://dcoll.ajou.ac.kr/dcollection/common/orgView/000000031762 | - |
| dc.subject.keyword | real-time Dynamic Tensor Decomposition and Analysis | - |
| dc.description.alternativeAbstract | How can we efficiently store and dynamic tensor data? A large portion of real-world data composes of stream data that are in a form of time-growing tensors.For example, air quality measurements are tensor stream data that consists of several sensory data at several locations over time. Such data, accumulated over time, consumes a lot of resources. We need a way to efficiently store tensor data generated in real-time that allow us to effectively retrieve the data for monitoring abnormalities. We propose a dynamic Tucker decomposition method for efficient storage and analysis of multi-dimensional streamline data. Assuming that tensors come in unit blocks, we slice the blocks into matrices and decompose them via singular value decomposition (SVD). The SVDs of sliced matrices, instead of the raw tensor, are stored to reduce space. When data analysis is needed at a certain time interval, involved SVDs of sliced matrices are retrieved to undergo Tuckerdecomposition. The factor matrices and core tensor of the decomposed results can be then used for further data analysis. We compare our proposed method with the existing method and show that our method is more low space cost and analytical. We also apply our method to detect ad-normal air conditions using real-world airquality data. | - |
- Appears in Collections:
- Graduate School of Ajou University > Department of Artificial Intelligence > 3. Theses(Master)
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
-
- License
- STATISTICS
- Total Visit :3,547,939
- Total Download :1,795
- Today View :10,305
