In this paper, we present an extreme learning machine (ELM) neural network designed to perform multiple-input multiple-output (MIMO) detection for millimeter-wave (mm-wave) communications operating in the 28 GHz frequency band. The ELM strategy can perform online MIMO combining processing. This method does not require offline training like with deep neural networks. The proposed technique was compared in terms of the achievable bit error rate (BER) and spectral efficiency (SE) to the maximum ratio (MR) and minimum mean squared error (MMSE) MIMO detectors, considering an orthogonal frequency-division multiplexing (OFDM) uplink scheme based on the fifth generation (5G) New Radio standard. Numerical results show that the ELM strategy outperforms the MR and MMSE detectors since this method reduces the inter-user interference effects, specifically for low equivalent isotropic radiated power at the receiver during the uplink communication. Furthermore, the ELM method requires only 16 % of the floating-point operations required by the MMSE detector.

在本文中，我们提出了一种极限学习机 (ELM) 神经网络，旨在为在 28 GHz 频段工作的毫米波 (mm-wave) 通信执行多输入多输出 (MIMO) 检测。ELM 策略可以进行在线 MIMO 合并处理。这种方法不需要像深度神经网络那样的离线训练。考虑到正交频分复用 (OFDM)，所提出的技术在可实现的误码率 (BER) 和频谱效率 (SE) 与最大比率 (MR) 和最小均方误差 (MMSE) MIMO 检测器方面进行了比较基于第五代（5G）新无线电标准的上行链路方案。数值结果表明，ELM 策略优于 MR 和 MMSE 检测器，因为该方法减少了用户间干扰影响，专门针对上行链路通信期间接收器处的低等效各向同性辐射功率。此外，ELM 方法仅需要 MMSE 检测器所需浮点运算的 16%。