no code implementations • 19 Feb 2024 • Sujin Kook, Won-Yong Shin, Seong-Lyun Kim, Seung-Woo Ko
The vision of pervasive artificial intelligence (AI) services can be realized by training an AI model on time using real-time data collected by internet of things (IoT) devices.
no code implementations • 14 Nov 2023 • Kyuwon Han, Seung Min Yu, Seong-Lyun Kim, Seung-Woo Ko
A smartphone-based user mobility tracking could be effective in finding his/her location, while the unpredictable error therein due to low specification of built-in inertial measurement units (IMUs) rejects its standalone usage but demands the integration to another positioning technique like WiFi positioning.
no code implementations • 14 Oct 2023 • Jihong Park, Seung-Woo Ko, Jinho Choi, Seong-Lyun Kim, Mehdi Bennis
neural network-oriented symbolic protocols developed by converting Level 1 MAC outputs into explicit symbols; and Level 3 MAC.
no code implementations • 13 Oct 2023 • Jinhyuk Choi, Jihong Park, Seung-Woo Ko, Jinho Choi, Mehdi Bennis, Seong-Lyun Kim
In this method, referred to as SL with layer freezing (SLF), each encoder downloads a misaligned decoder, and locally fine-tunes a fraction of these encoder-decoder NN layers.
no code implementations • 15 Nov 2022 • Jinhyuk Choi, Seong-Lyun Kim, Seung-Woo Ko
Specifically, feature network is designed based on feature hierarchy, a one-directional feature dependency with a different scale.
no code implementations • 8 Jul 2022 • Sejin Seo, Jihong Park, Seung-Woo Ko, Jinho Choi, Mehdi Bennis, Seong-Lyun Kim
Classical medium access control (MAC) protocols are interpretable, yet their task-agnostic control signaling messages (CMs) are ill-suited for emerging mission-critical applications.
no code implementations • 26 Apr 2021 • Sejin Seo, Seung-Woo Ko, Jihong Park, Seong-Lyun Kim, Mehdi Bennis
The lottery ticket hypothesis (LTH) claims that a deep neural network (i. e., ground network) contains a number of subnetworks (i. e., winning tickets), each of which exhibiting identically accurate inference capability as that of the ground network.
no code implementations • 1 Jun 2020 • Sejin Seo, Sang Won Choi, Sujin Kook, Seong-Lyun Kim, Seung-Woo Ko
Due to the edge's position between the cloud and the users, and the recent surge of deep neural network (DNN) applications, edge computing brings about uncertainties that must be understood separately.
Information Theory Networking and Internet Architecture Information Theory