Rate Adaptation by Binary Regression Trees in Underwater Acoustic Channels
conference paper
We analyze the rate adaptation problem for uncoded communications in underwater acoustic channels. We study two regression tree-based rate adaptation schemes. The first scheme is based on the standard CART algorithm, whereas the second utilizes Pearson's chi-squared test of independence to determine the locally optimal splits. We compare their performance in terms of the symbol error rate predictions and the spectral efficiency estimations. The results indicate that both schemes exhibit nearly identical performance with the latter achieving comparable results at significantly reduced complexity. © 2024 IEEE
TNO Identifier
1006637
Publisher
IEEE
Source title
2024 7th Underwater Communications and Networking Conference, UComms 2024
Files
To receive the publication files, please send an e-mail request to TNO Repository.