A unified neural network model for OFDM and OTFS modulations in wireless systems.
Saved in:
| Title: | A unified neural network model for OFDM and OTFS modulations in wireless systems. |
|---|---|
| Authors: | Chennamsetty, Sneha1 (AUTHOR) sneha20peee007@mahindrauniversity.edu.in, Boddu, Subbarao1 (AUTHOR) |
| Source: | Sādhanā: Academy Proceedings in Engineering Sciences. Jun2026, Vol. 51 Issue 2, p1-10. 10p. |
| Subjects: | Orthogonal frequency division multiplexing, Artificial neural networks, Electronic modulation, 5G networks, Bit error rate, Wireless communications |
| Abstract: | Orthogonal frequency division multiplexing (OFDM) is a widely adopted modulation scheme in modern wireless communication systems, particularly in fifth-generation (5G) networks. Orthogonal time–frequency space (OTFS) is an emerging modulation technique currently under active investigation for future sixth-generation (6G) networks due to its promising performance in high-mobility, doubly dispersive channels. Despite the benefits of both approaches, using them independently may lead to less-than-ideal efficiency because there is no common processing framework. This research presents a novel neural network (NN)-based architecture that combines the processing of both modulation techniques into a single system to address this problem. This integrated framework enables the development of intelligent and flexible communication systems that can operate reliably across a wide range of operational conditions. The proposed NN model maintains minimal computing complexity while managing many signal-processing tasks concurrently. Simulation results demonstrate improved bit-error-rate (BER) performance with the integration of OTFS and NN, and comparisons with OFDM-based results highlight the advantages and reliability of the proposed unified strategy. [ABSTRACT FROM AUTHOR] |
| Copyright of Sādhanā: Academy Proceedings in Engineering Sciences is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Orthogonal frequency division multiplexing (OFDM) is a widely adopted modulation scheme in modern wireless communication systems, particularly in fifth-generation (5G) networks. Orthogonal time–frequency space (OTFS) is an emerging modulation technique currently under active investigation for future sixth-generation (6G) networks due to its promising performance in high-mobility, doubly dispersive channels. Despite the benefits of both approaches, using them independently may lead to less-than-ideal efficiency because there is no common processing framework. This research presents a novel neural network (NN)-based architecture that combines the processing of both modulation techniques into a single system to address this problem. This integrated framework enables the development of intelligent and flexible communication systems that can operate reliably across a wide range of operational conditions. The proposed NN model maintains minimal computing complexity while managing many signal-processing tasks concurrently. Simulation results demonstrate improved bit-error-rate (BER) performance with the integration of OTFS and NN, and comparisons with OFDM-based results highlight the advantages and reliability of the proposed unified strategy. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 02562499 |
| DOI: | 10.1007/s12046-026-03100-0 |
