paper-with-me

홈 › Papers

A Neural Network Prediction Based Adaptive Mode Selection Scheme in Full-Duplex Cognitive Networks

2019-04-12

We propose a neural network (NN) predictor and an adaptive mode selection scheme for the purpose of both improving secondary user's (SU's) throughput and reducing collision probability to the primary user (PU) in full-duplex (FD) cognitive networks. SUs can adaptively switch between FD transmission-and-reception (TR) and transmission-and-sensing (TS) modes based on the NN prediction results for each transmission duration. The prediction performance is then analysed in terms of prediction error probability. We also compare the performance of our proposed scheme with conventional TR and TS modes in terms of SUs average throughput and collision probability, respectively. Simulation results show that our proposed scheme achieves even better SUs average throughput compared with TR mode. Meanwhile, the collision probability can be reduced close to the level of TS mode.

📄 PDF Abstract BibTeX arXiv:1904.06222

Code (0)

등록된 구현이 없습니다.

Tasks

Prediction

Similar Papers 제목 키워드 기반

Dynamic Model Selection for Prediction Under a Budget

2017-04-25 · Feng Nan, Venkatesh Saligrama

We present a dynamic model selection approach for resource-constrained prediction. Given an input instance at test-time, a gating function identifies a prediction model for the input among a collection of models. Our obj…

modelModel SelectionPrediction

Data-efficient Active Learning for Structured Prediction with Partial Annotation and Self-Training

2023-05-22 · Zhisong Zhang, Emma Strubell, Eduard Hovy

In this work we propose a pragmatic method that reduces the annotation cost for structured label spaces using active learning. Our approach leverages partial annotation, which reduces labeling costs for structured output…

Active LearningStructured Prediction

Adaptive model selection in photonic reservoir computing by reinforcement learning

2020-04-27 · Kazutaka Kanno, Makoto Naruse, Atsushi Uchida

Photonic reservoir computing is an emergent technology toward beyond-Neumann computing. Although photonic reservoir computing provides superior performance in environments whose characteristics are coincident with the tr…

Load ForecastingModel Selectionreinforcement-learningReinforcement Learning+4

Enhancement of a state-of-the-art RL-based detection algorithm for Massive MIMO radars

2021-12-05 · Francesco Lisi, Stefano Fortunati, Maria Sabrina Greco, Fulvio Gini

In the present work, a reinforcement learning (RL) based adaptive algorithm to optimise the transmit beampattern for a colocated massive MIMO radar is presented. Under the massive MIMO regime, a robust Wald type detector…

Reinforcement Learning (RL)

JEPA as a Neural Tokenizer: Learning Robust Speech Representations with Density Adaptive Attention

2025-12-08 · Georgios Ioannides, Christos Constantinou, Aman Chadha, Aaron Elkins 외 arxiv

We introduce a two-stage self-supervised framework that combines the Joint-Embedding Predictive Architecture (JEPA) with a Density Adaptive Attention Mechanism (DAAM) for learning robust speech representations. Stage~1 u…