AJOU Central Library Repository: Applying Transfer Learning on Wireless Interference Identification to Improve Classification Accuracy

Graduate School of Ajou University Department of Computer Engineering 3. Theses(Master)

Applying Transfer Learning on Wireless Interference Identification to Improve Classification Accuracy

Alternative Title: Applying Transfer Learning on Wireless Interference Identification to Improve Classification Accuracy

Keyword: 2.4 GHz band; Bluetooth; CNN; WiFi; Wireless Interference Identification; and Transfer Learning

Alternative Abstract: 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)

qrcode

STATISTICS: Total Visit :3,720,960; Total Download :1,818; Today View :4,163

AJOU Central Library Repository는 국립중앙도서관 OAK 보급사업으로 구축되었습니다.