Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2302.00341 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914020583276544 |
|---|---|
| author | Rizzello, Valentina Böck, Benedikt Joham, Michael Utschick, Wolfgang |
| author_facet | Rizzello, Valentina Böck, Benedikt Joham, Michael Utschick, Wolfgang |
| contents | This work aims to predict channels in wireless communication systems based on noisy observations, utilizing sequence-to-sequence models with attention (Seq2Seq-attn) and transformer models. Both models are adapted from natural language processing to tackle the complex challenge of channel prediction. Additionally, a new technique called reverse positional encoding is introduced in the transformer model to improve the robustness of the model against varying sequence lengths. Similarly, the encoder outputs of the Seq2Seq-attn model are reversed before applying attention. Simulation results demonstrate that the proposed ordering techniques allow the models to better capture the relationships between the channel snapshots within the sequence, irrespective of the sequence length, as opposed to existing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2302_00341 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Reverse Ordering Techniques for Attention-Based Channel Prediction Rizzello, Valentina Böck, Benedikt Joham, Michael Utschick, Wolfgang Machine Learning Networking and Internet Architecture Signal Processing This work aims to predict channels in wireless communication systems based on noisy observations, utilizing sequence-to-sequence models with attention (Seq2Seq-attn) and transformer models. Both models are adapted from natural language processing to tackle the complex challenge of channel prediction. Additionally, a new technique called reverse positional encoding is introduced in the transformer model to improve the robustness of the model against varying sequence lengths. Similarly, the encoder outputs of the Seq2Seq-attn model are reversed before applying attention. Simulation results demonstrate that the proposed ordering techniques allow the models to better capture the relationships between the channel snapshots within the sequence, irrespective of the sequence length, as opposed to existing methods. |
| title | Reverse Ordering Techniques for Attention-Based Channel Prediction |
| topic | Machine Learning Networking and Internet Architecture Signal Processing |
| url | https://arxiv.org/abs/2302.00341 |