repository
Applying Transfer Learning on Wireless Interference Identification to Improve Classification Accuracy
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | YOUNG-JUNE CHOI | - |
| dc.contributor.author | THIDA SHWE | - |
| dc.date.accessioned | 2022-11-29T02:32:16Z | - |
| dc.date.available | 2022-11-29T02:32:16Z | - |
| dc.date.issued | 2020-08 | - |
| dc.identifier.other | 30200 | - |
| dc.identifier.uri | https://dspace.ajou.ac.kr/handle/2018.oak/19780 | - |
| dc.description | 학위논문(석사)--아주대학교 일반대학원 :컴퓨터공학과,2020. 8 | - |
| dc.description.tableofcontents | CHAPTER I. Introduction 1 A. 2.4 GHz ISM Band 1 B. WII (Wireless Interference Identification) 2 C. Motivation 4 D. Contribution and Outlines 4 CHAPTER II. Background Discussion 6 A. Related Works 6 B. Deep Learning Contribution on Classification 8 C. TL (Transfer Learning) 10 1. Method of TL 11 2. Application of TL 11 3. Denotation of TL 12 D. Fft (Fast Fourier Transforming) 13 CHAPTER III. Proposed Idea and Implementation 15 A. TL denotation of Proposed Idea 15 B. Dataset 16 C. Type and Architecture of Neural Networks 18 D. Operation: Fine tuning Pre-Trained Model 20 CHAPTER IV. Simulation Result 21 A. Environment set up and Hyper-Parameters 21 B. Result 22 CHAPTER V. Conclusion and Future Work 27 A. Conclusion 27 B. Future work 27 CHAPTER VI. References 28 | - |
| dc.language.iso | eng | - |
| dc.publisher | The Graduate School, Ajou University | - |
| dc.rights | 아주대학교 논문은 저작권에 의해 보호받습니다. | - |
| dc.title | Applying Transfer Learning on Wireless Interference Identification to Improve Classification Accuracy | - |
| dc.title.alternative | Applying Transfer Learning on Wireless Interference Identification to Improve Classification Accuracy | - |
| dc.type | Thesis | - |
| dc.contributor.affiliation | 아주대학교 일반대학원 | - |
| dc.contributor.alternativeName | THIDA SHWE | - |
| dc.contributor.department | 일반대학원 컴퓨터공학과 | - |
| dc.date.awarded | 2020. 8 | - |
| dc.description.degree | Master | - |
| dc.identifier.localId | 1151691 | - |
| dc.identifier.uci | I804:41038-000000030200 | - |
| dc.identifier.url | http://dcoll.ajou.ac.kr:9080/dcollection/common/orgView/000000030200 | - |
| dc.subject.keyword | 2.4 GHz band | - |
| dc.subject.keyword | Bluetooth | - |
| dc.subject.keyword | CNN | - |
| dc.subject.keyword | WiFi | - |
| dc.subject.keyword | Wireless Interference Identification | - |
| dc.subject.keyword | and Transfer Learning | - |
| dc.description.alternativeAbstract | This work targets to address the problem of identifying the resource of wireless interference by using a recent popular deep learning technique called Transfer Learning (TL). The Wireless Interference Identification (WII) is targeting in recognizing the type of wireless channel’s resource and trying to avoid usage of already occupied spectrum channel by another technology type in order to avoid the Wide Band Interference (WBI). As Deep learning is becoming a powerful tool in classification of materials, the adoption of DL in solving WII is becoming a trend. Among available DL technical tools, TL is one of the newest and most efficient technique in enhancing the classification accuracy. In this work, we applied TL in recognizing the interference resource type of WiFi and Bluetooth as they are the most significant ‘resident’ of the 2.4 GHz band. | - |
- Appears in Collections:
- Graduate School of Ajou University > Department of Computer Engineering > 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 :3,767,904
- Total Download :1,819
- Today View :4,405
