Y
Yizhou Yang
Researcher at Australian National University
Publications - 8
Citations - 37
Yizhou Yang is an academic researcher from Australian National University. The author has contributed to research in topics: Transmitter power output & Wireless. The author has an hindex of 2, co-authored 4 publications receiving 16 citations.
Papers
More filters
Proceedings ArticleDOI
Deep Learning Channel Prediction for Transmit Power Control in Wireless Body Area Networks
TL;DR: An LSTM-based RNN channel prediction framework providing long-term channel prediction up to 2s with low error is proposed, which reduces circuit power consumption significantly while improving communications reliability.
Journal ArticleDOI
Power Control for Body Area Networks: Accurate Channel Prediction by Lightweight Deep Learning
TL;DR: In this paper, the authors proposed a LSTM-based neural network (NN) prediction method that provides long-term accurate channel gain prediction of up to 2 s over nonstationary BAN on-body channels.
Journal Article
Behaviour-Diverse Automatic Penetration Testing: A Curiosity-Driven Multi-Objective Deep Reinforcement Learning Approach
Yizhou Yang,Xin Liu +1 more
TL;DR: This work forms the automatic penetration testing in the Multi-Objective Reinforcement Learning (MORL) framework and proposes a Chebyshev decomposition critic to find diverse adversary strategies that balance different objectives in the penetration test.
Posted Content
Robust Wireless Body Area Networks Coexistence: A Game Theoretic Approach to Time-Division MAC
Yizhou Yang,David R. Smith +1 more
TL;DR: A TDMA based MAC layer Scheme, with a back-off mechanism that reduces packet collision probability; and estimate performance using a Markov chain model, based on the MAC layer scheme, a novel non-cooperative game is proposed to jointly adjust sensor node's transmit power and rate.
Proceedings ArticleDOI
Wireless body area networks: Energy-efficient, provably socially-efficient, transmit power control
Yizhou Yang,David Smith +1 more
TL;DR: Using a realistic channel model, the game is shown to be very energy-efficient, significantly reducing power consumption and improving packet delivery ratio (PDR) with respect to other potential schemes, consuming 67% less circuit power than transmitting constantly at 0 dBm.