| Project/Area Number |
22K17883
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 60060:Information network-related
|
|---|
| Research Institution | Osaka University |
|---|
Principal Investigator |
エルデーイ ヴィクトル 大阪大学, 大学院情報科学研究科, 特任助教(常勤) (40850938)
|
|---|
| Project Period (FY) |
2022-04-01 – 2026-03-31
|
| Project Status |
Granted (Fiscal Year 2023)
|
| Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2025: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2024: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2023: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2022: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | Object recognition / wireless sensing / localization / backscatter tags / object recognition / privacy / interaction tracking |
|---|
| Outline of Research at the Start |
We aim to develop technological solutions to improve our awareness of our environment, with a focus on our interactions with objects. Such information has several applications including healthcare and well-being (lifestyle analysis, navigation assistance), asset tracking, and security screening. These applications require us to recognize, identify and track objects and their interactions. In this project, we will:
(1) Build a contact-less object recognition system for plain, uninstrumented objects
(2) Develop a scalable, low-power, privacy-preserving system for tracking object interactions
|
| Outline of Annual Research Achievements |
We addressed reviewers' comments after our paper was rejected by IEEE IoT Journal. We performed additional data collection experiments in order to investigate object recognition performance when using different liquids in bottles, different bottle sizes, and different sensing distances. Clarifications were also made to the text. We plan to resubmit to the same journal as suggested by reviewers.
We proposed a low-cost backscatter tag system for localization, tackling the battery management challenge in RF-based methods using ultra-low-power backscatter tags. It estimates Angle of Arrival and Time of Flight using a receiving antenna array and MUSIC-based algorithm, without needing FPGA or ASIC (application specific circuits) in the backscatter tag. This work contributed to a master's thesis and a published workshop paper on Angle of Arrival estimation.
Building on our localization research, we proposed activity recognition using Wi-Fi CSI and backscatter tags. Backscatter tags can increase the quantity of CSI observations without extra Wi-Fi devices, enhancing accuracy and coverage. Preliminary experiments show high accuracy in distinguishing activities, and combining CSI and CSI backscatter data further improves performance. This work contributed to another master's thesis, titled "Activity Recognition Using CSI Backscatter with Commodity Wi-Fi."
|
| Current Status of Research Progress |
Current Status of Research Progress
2: Research has progressed on the whole more than it was originally planned.
Reason
Based on the details reported in the achievements section, we can say that we have made significant progress in the research. However, we note that the focus of the research has slightly shifted due to new information and results found, the development of the scientific field, and the availability of students for each topic.
|
| Strategy for Future Research Activity |
We hope to resubmit and publish our results on object recognition in the near future. Then, we may shift our focus towards extending the backscatter-based localization work. Regarding localization, potential future directions are as follows. First, we could investigate the feasibility of using Bluetooth backscatter for localization. Second, we could explore the angle of arrival feature provided by Bluetooth 5. Third, we found that it is difficult to use our current backscatter tags to communicate over longer distances (more than a few tens of centimeters). Therefore, we could investigating this issue of limited range, e.g., by monitoring the amplitude and structure of the backscatter signal (reflected by the tag). Fourth, we could explore the feasibility of using backscatter tags for real-world elderly monitoring instead of using BLE/Wi-Fi-based smart home IoT devices (depends on solving the distance issue). Finally, we could also consider a real implementation of a Wi-Fi access point with an additional feature of transmitting simple sine waves designed to aid localization (e.g., by modifying an open-source router firmware).
As we have identified several possible open-ended research directions for the localization work, we may choose to focus on these instead of engaging deeply with the "private object interaction tracking" topic of the original research proposal. Nevertheless, protecting privacy remains to be an important aspect of our research.
|
