Massive Multiple-Input Multiple-Output (MIMO) communication systems are being investigated intensively for positioning services. Enhancing the accuracy on these services in terms of accurate positioning of users is an important goal to improve related applications in the future. Convolutional Neural Networks (CNNs) has been proposed to infer the position of a user from Channel State Information (CSI) of a massive MIMO system. This paper investigates different architectures of CNNs to enhance the accuracy of a fingerprint-based positionina system. Three new CNNs has been proposed in which the Convolutional Layer (CL) and the Fully Connected (FC) layer are re-dimensioned. Batch Normalization (BN) layer is introduced to the layer structure of the newly proposed CNNs. The CNNs were trained, and accordingly mean error is measured. The first re-constructed CNN composed of 13 CLs, 7 BNs, and 3 FC layers has achieved the best accuracy out of the three models. It managed to achieve a mean error of 10.09 mm, that outperforms a similar work by 82 % in terms of positioning accuracy. Pruning was added to the layer structure of the newly proposed CNN s. It reduced the model size significantly, approximately by 65 % compared to a similar model of previous work.

This paper presents the exploration of GPU-accelerated block-wise decompositions for zero-forcing (ZF) based QR and Cholesky methods applied to massive multiple-input multiple-output (MIMO) uplink detection algorithms. Three algorithms are evaluated: ZF with block Cholesky decomposition, ZF with block QR decomposition (QRD), and minimum mean square error (MMSE) with block Cholesky decomposition. The latter was the only one previously explored, but it used standard Cholesky decomposition. Our approach achieves an 11% improvement over the previous GPU-accelerated MMSE study.

Through performance analysis, we observe a trade-off between precision and execution time. Reducing precision from FP64 to FP32 improves execution time but increases bit error rate (BER), with ZF-based QRD reducing execution time from 2.04 μs to 1.24 μs for a 128 × 8 MIMO size. The study also highlights that larger MIMO sizes, particularly 2048 × 32, require GPUs to fully utilize their computational and memory capabilities, especially under FP64 precision. In contrast, smaller matrices are compute-bound.

Our results recommend GPUs for larger MIMO sizes, as they offer the parallelism and memory resources necessary to efficiently handle the computational demands of next-generation networks. This work paves the way forscalable, GPU-based massive MIMO uplink detection systems. © 2025 The Authors. Published by Elsevier B.V.