BiLSTM-Based Power Spectral Density Prediction in Low Sub-Band Wire Environments

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F25%3A00384700" target="_blank" >RIV/68407700:21230/25:00384700 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1109/HPCC67675.2025.00172" target="_blank" >https://doi.org/10.1109/HPCC67675.2025.00172</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/HPCC67675.2025.00172" target="_blank" >10.1109/HPCC67675.2025.00172</a>

Result language
angličtina
Original language name
BiLSTM-Based Power Spectral Density Prediction in Low Sub-Band Wire Environments
Original language description
This work proposes the bidirectional long short-term memory (BiLSTM) algorithm to predict the PSD state in low sub-band frequencies on wire environments. A two-stream direction, forward and backward, on the BiLSTM algorithm is considered to reduce the loss of information in the analyzed data. This work appears to be the first to process PSD values analyzed using this algorithm during predictive model building. The proposed algorithm improves the accuracy of the predictive model better than the conventional long short-term memory (LSTM) and the convolutional neural network (CNN). These results show that the proposed BiLSTM algorithm can potentially be a promising solution for solving the challenge of PSD values prediction in low sub-band frequencies in wire environments.
Czech name
—
Czech description
—

Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
2025 IEEE International Conference on High Performance Computing and Communications (HPCC)
ISBN
979-8-3315-6874-0
ISSN
—
e-ISSN
—
Number of pages
7
Pages from-to
1210-1216
Publisher name
IEEE
Place of publication
Piscataway
Event location
Exeter
Event date
Aug 13, 2025
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)