Exploring Novel Mathematical Models and Efficient Algorithms to Discover Periodic Spatial Patterns in Irregular Spatiotemporal Big Data
Project/Area Number |
21K12034
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Review Section |
Basic Section 61030:Intelligent informatics-related
|
Research Institution | The University of Aizu |
Principal Investigator |
Rage Uday・Kiran 会津大学, コンピュータ理工学部, 准教授 (20874324)
|
Co-Investigator(Kenkyū-buntansha) |
是津 耕司 国立研究開発法人情報通信研究機構, ユニバーサルコミュニケーション研究所統合ビッグデータ研究センター, 研究センター長 (40415857)
|
Project Period (FY) |
2021-04-01 – 2025-03-31
|
Project Status |
Granted (Fiscal Year 2022)
|
Budget Amount *help |
¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2024: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2023: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2022: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2021: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
Keywords | Big data / high utility patterns / spatial information / data mining / Pattern mining / Air pollution analytics |
Outline of Research at the Start |
“Mining time series data” is one of the top-10 challenges in data mining. This research aims to tackle this challenging problem of great importance by proposing a mathematical model to uncover periodic spatial patterns in irregular spatiotemporal big data. We will deliver a mathematical model and software programs to uncover interesting patterns in spatiotemporal big data. Our deliverables will be “open-sourced” to foster R&D on data mining.
|
Outline of Annual Research Achievements |
High utility itemset mining is an important knowledge discovery in data mining. Exicisting studies ignored the spatial information of the items in the database and tried to find hidden patterns. We have observed that ignoring the spatial information results either in missing useful information or generating suprious information that is not useful to the experts. In this year, we have tested our cliam, which is important to capture the spatial information of the items to find patterns that have high value. The work was published in Applied Intelligence Journal.
|
Current Status of Research Progress |
Current Status of Research Progress
2: Research has progressed on the whole more than it was originally planned.
Reason
We were successful in downloading the air pollution data of various sensors in Japan, USA, and other countries. We were able to test the distribution of characteritics of the data. We found that existing high utility itemset mining algorithms were inadequate to find spatially interesting patterns as they ignored the spatial information. We proposed a new model and an efficient algorithm to discover spatially interesting patterns having high value. Our work also published in Applied Intelligence journal.
|
Strategy for Future Research Activity |
1. This year we will model the air pollution has uncertain data generated by the sensors and study the current limitations. Next, we will analyze the results and make claim, followed by introducing a new model and algorithm to find spatially interesting patterns in uncertain data.
2. We will also study how to model air pollution as fuzzy dataset to extract useful information
|
Report
(2 results)
Research Products
(7 results)