Brijesh Shah
Brijesh Shah has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- AnupKumar Pandey
Research & Development, Jio Platforms Limited, TC-22, 5th Floor, A Wing, Reliance Corporate Park, Thane Belapur Road, Ghansoli, Navi Mumbai 400701, Maharashtra, India
3 shared publications - Spiros Louvros
Technological Educational Institute of Messolonghi
3 shared publications - Yashesh Buch
Research & Development, Jio Platforms Limited, TC-22, 5th Floor, A Wing, Reliance Corporate Park, Thane Belapur Road, Ghansoli, Navi Mumbai 400701, Maharashtra, India
2 shared publications
Latest Publications
- Open Access
- 18 September 2026
- Published by IntechOpen
Massive MIMO CSI Type-I Codebook Design – Performance Analysis in 5G Deployments
In 5G New Radio (NR), the efficiency of massive Multiple Input Multiple Output (MIMO) beamforming heavily depends on accurate channel state information (CSI) feedback mechanisms standardized by 3GPP. CSI Type-I, first introduced in 3GPP Release 15 and further enhanced in subsequent releases up to Release 18, provides a structured codebook-based representation of the preferred precoding matrix, enabling scalable multiantenna operation. The Type-I codebook maps the estimated channel onto a discrete set of precoding matrix indicators (PMIs), in which the UE reports the proper PMI index that maximizes the effective received SINR. This allows the gNB to select a beamforming codebook vector that approximates channel conjugation while balancing overhead and complexity. Compared to higher-order CSI feedback schemes, Type-I offers reduced feedback overhead but with limited spatial resolution, making it particularly useful for 5G or 6G single-user MIMO, 5G nonterrestrial applications (5G NTN), or moderate-rank transmission scenarios. With ongoing 5G-Advanced (Release 18 +) enhancements, CSI Type-I remains a cornerstone for practical deployment, striking a balance between feedback efficiency and link-level spectral performance. This book chapter provides a deep description, presentation, and performance evaluation analysis of CSI Type-I functionality in the presence of realistic radio channel inconsistencies.
- 18 September 2026
- Published by IntechOpen
Open AccessMassive MIMO CSI Type-I Codebook Design – Performance Analysis in 5G Deployments
In 5G New Radio (NR), the efficiency of massive Multiple Input Multiple Output (MIMO) beamforming heavily depends on accurate channel state information (CSI) feedback mechanisms standardized by 3GPP. CSI Type-I, first introduced in 3GPP Release 15 and further enhanced in subsequent releases up to Release 18, provides a structured codebook-based representation of the preferred precoding matrix, enabling scalable multiantenna operation. The Type-I codebook maps the estimated channel onto a discrete set of precoding matrix indicators (PMIs), in which the UE reports the proper PMI index that maximizes the effective received SINR. This allows the gNB to select a beamforming codebook vector that approximates channel conjugation while balancing overhead and complexity. Compared to higher-order CSI feedback schemes, Type-I offers reduced feedback overhead but with limited spatial resolution, making it particularly useful for 5G or 6G single-user MIMO, 5G nonterrestrial applications (5G NTN), or moderate-rank transmission scenarios. With ongoing 5G-Advanced (Release 18 +) enhancements, CSI Type-I remains a cornerstone for practical deployment, striking a balance between feedback efficiency and link-level spectral performance. This book chapter provides a deep description, presentation, and performance evaluation analysis of CSI Type-I functionality in the presence of realistic radio channel inconsistencies.
- Open Access
- 30 January 2026
- Published by MDPI AG in Future Internet
- Vol. 18 (2) , 71
Cross Layer Optimization Using AI/ML-Assisted Federated Edge Learning in 6G Networks
This paper introduces a novel methodology that integrates 6G wireless Federated Edge Learning (FEEL) frameworks with MAC to PHY cross layer optimization strategies. In the context of mobile edge computing, typically ensuring robust channel estimation within the 6G network use cases presents critical challenges, particularly in managing data retransmissions. Inaccurate updates from distributed 6G devices can undermine the reliability of federated learning, affecting its overall performance. To address this, rather than relying on direct evaluations of the objective function, we propose an AI/ML-assisted algorithm for global optimization based on radial basis functions (RBFs) decision-making process to assess learned preference options.
- 30 January 2026
- Published by MDPI AG in Future Internet
- Vol. 18 (2) , 71
Open AccessCross Layer Optimization Using AI/ML-Assisted Federated Edge Learning in 6G Networks
This paper introduces a novel methodology that integrates 6G wireless Federated Edge Learning (FEEL) frameworks with MAC to PHY cross layer optimization strategies. In the context of mobile edge computing, typically ensuring robust channel estimation within the 6G network use cases presents critical challenges, particularly in managing data retransmissions. Inaccurate updates from distributed 6G devices can undermine the reliability of federated learning, affecting its overall performance. To address this, rather than relying on direct evaluations of the objective function, we propose an AI/ML-assisted algorithm for global optimization based on radial basis functions (RBFs) decision-making process to assess learned preference options.
- Open Access
- 11 November 2025
- Published by MDPI AG in Preprints.org
Cross Layer Optimization Using AI/ML Assisted Federated Edge Learning in 6G Networks
This paper introduces a novel methodology that integrates 6G wireless Federated Edge Learning (FEEL) frameworks with optimization strategies spanning from the MAC layer to the Physical layer. In the context of mobile edge computing, ensuring robust channel estimation within the 6G network slicing paradigm presents critical challenges, particularly in managing data retransmissions. Inaccurate updates from distributed 6G devices can undermine the reliability of Federated Learning (FL), affecting its overall performance. To address this, we propose an AI/ML assisted algorithm for global optimization in FL-based 6G networks, where the decision-making process leverages radial basis functions (RBF) to assess options based on learned preferences rather than relying on direct evaluations of the objective function.
- 11 November 2025
- Published by MDPI AG in Preprints.org
Open AccessCross Layer Optimization Using AI/ML Assisted Federated Edge Learning in 6G Networks
This paper introduces a novel methodology that integrates 6G wireless Federated Edge Learning (FEEL) frameworks with optimization strategies spanning from the MAC layer to the Physical layer. In the context of mobile edge computing, ensuring robust channel estimation within the 6G network slicing paradigm presents critical challenges, particularly in managing data retransmissions. Inaccurate updates from distributed 6G devices can undermine the reliability of Federated Learning (FL), affecting its overall performance. To address this, we propose an AI/ML assisted algorithm for global optimization in FL-based 6G networks, where the decision-making process leverages radial basis functions (RBF) to assess options based on learned preferences rather than relying on direct evaluations of the objective function.