This paper introduces a novel methodology for wireless channel estimation in millimeter-wave (mmWave) bands, with a primary focus on addressing diverse physical (PHY)-layer impairments, including phase noise (PN), in-phase and quadrature-phase imbalance (IQI), carrier frequency offset (CFO), and power amplifier non-linearity (PAN). The key contribution centers around the innovative approach of training a convolutional neural network (CNN) using a synthetic and labeled dataset that encompasses a wide range of wireless channel conditions. The methodology involves the synthetic generation of labeled datasets, representing various types of wireless channels and PHY-layer impairments, which are subsequently employed in the CNN training stage. The resulting model-based trained CNN demonstrates exceptional adaptability to diverse operational scenarios, showcasing its capability to operate effectively under various channel conditions. To validate the efficacy of the proposed methodology, the trained CNN is deployed in a practical wireless testbed. Experimental results underscore the superiority of the proposed channel estimation methodology across different signal-to-noise ratio (SNR) regions and delay spread channel types. The trained CNN exhibits robust performance, confirming its effectiveness in mitigating the impact of PHY-layer impairments in real-world mmWave communication environments. This research not only advances reliable channel estimation techniques for mmWave systems but also provides valuable practical assessment results, with potential applications in next-generation wireless communication networks.

Millimeter-Wave (mmWave) bands are receiving enormous attention in 5G mobile communications, due to the capability to provide a multi-gigabit transmission rate. In this paper, a two-hop architecture for 5G communications with the capacity to support high end-to-end performance due to the use of Relay Nodes (RNs) in mmWave-bands is presented. One of the novelties of the paper is the implementation of Amplify-and-Forward (A&F) and Decode-and-Forward (D&F) RNs along with a mmWave-band transceiver chain (Tx/Rx). In addition, two approaches for channel estimation were implemented at the D&F RN for decoding the backhaul link. One of them assumes complete knowledge of the channel (PCE), and the other one performs the channel estimation through Least Square (LS) estimator. A large number of simulations, using MATLAB${}^{\mathbf{TM}}$ and Simulink${}^{\mathbf{TM}}$ software, were performed to verify the potential benefits of the proposal two-hop 5G architecture in an outdoor-to-indoor scenario. The main novelty in performing these simulations is the use of signals with 5G features, as DL-SCH transport channel coding, PDSCH generation, and SS Burst generation, which is another of the main contributions of the paper. On the other hand, mmWave transmitter and receiver chains were designed and implemented with off-the shelf components. The simulations show that the two-hop network substantially improves the Key Performance Indicators (KPIs), Bit Error Rate (BER), and Throughput, in the communications between the logical 5G Radio Node (gNodeB), and the New Radio User Equipment (NR-UE). For example, a throughput improvement of 22 Mbps is obtained when a 4 × 4 × 2 MIMO D&F with LS architecture is used versus a SISO D&F with PCE architecture for Signal-to-Noise Ratio (SNR) = 20 dB and 64-QAM signal. This improvement reaches 96 Mbps if a 256-QAM signal is considered. The improvement in BER is 11 dB and 10.5 dB, respectively, for both cases. This work also shows that the obtained results with D&F RNs are better than with A&F RNs. For example, an improvement of 17 Mbps in the use of SISO D&F with LS vs. SISO A&F, for the 64-QAM signal is obtained. Besides, this paper constitutes a first step to the implementation of a mmWave MIMO 5G cooperative network platform.

Rail transport is central to achieving sustainable and energy-efficient mobility, and its digitalization is accelerating the adoption of condition-based maintenance (CBM) strategies. However, existing maintenance practices remain largely reactive or rely on limited rule-based diagnostics, which constrain safety, interoperability, and lifecycle optimization. This survey provides a comprehensive and structured review of Artificial Intelligence techniques applied to the preventive, predictive, and prescriptive maintenance of railway infrastructure. We analyze and compare machine learning and deep learning approaches—including neural networks, support vector machines, random forests, genetic algorithms, and end-to-end deep models—applied to parameters such as track geometry, vibration-based monitoring, and imaging-based inspection. The survey highlights the dominant data sources and feature engineering techniques, evaluates the model performance across subsystems, and identifies research gaps related to data quality, cross-network generalization, model robustness, and integration with real-time asset management platforms. We further discuss emerging research directions, including Digital Twins, edge AI, and Cyber–Physical predictive systems, which position AI as an enabler of autonomous infrastructure management. This survey defines the key challenges and opportunities to guide future research and standardization in intelligent railway maintenance ecosystems.

In this paper, the uplink in a two-hop 5G new radio co-operative system using Relay Nodes (RNs) in millimeter bands has been simulated and studied. We focus on an uplink Amplify-and-Forward Relay Node (A&F RN) and Decode-and-Forward Relay Node (D&F RN) with an mmWave-band transceiver chain (Tx/Rx). We study two uplink mmWave MIMO D&F relaying protocols assuming, firstly, the complete knowledge of the uplink channel and, secondly, the uplink channel estimation through a Least Square (LS) algorithm. To verify the benefits of the proposed uplink mmWave MIMO co-operative network, a link-level co-operative simulator has been developed using Matlab${}^{\mathrm{TM}}$ and Simulink${}^{\mathrm{TM}}$ software, where an indoor-to-outdoor scenario and mmWave transceiver with off-the shelf components are considered. The main novelty of this link-level co-operative simulator and the implemented relay nodes is the usage of signals with 5G NR features, such as UL-SCH transport channel coding and PUSCH generation, which are the other main contributions of this article. Based on the numerical results in terms of the achievable Bit Error Rate (BER) and throughput, we show that the two-hop uplink co-operative network substantially improves the performance in the communications between the NR-User Equipment (NR-UE) and the logical 5G Radio Node (gNodeB). For example, the results from using uplink mmWave NR-D&F protocols far exceed those achieved with the uplink mmWave NR-A&F algorithm; in the case of the 64-QAM modulation scheme for the SISO technique, an improvement of 6.5 Mbps was achieved using the D&F PCE protocol, taking into account that the 256-QAM constellation is higher by 4.05 Mbps. On the other hand, an average throughput enhancement of 28.77 Mbps was achieved when an uplink mmWave (2 × 4 × 4) D&F PCE strategy was used versus an uplink mmWave SISO D&F LS protocol for a Signal-to-Noise Ratio (SNR) = 20 dB and 64-QAM signal. However, an improvement of 56.42 Mbps was reached when a 256-QAM modulation scheme was employed. Furthermore, this paper introduces the first study to develop an uplink mmWave MIMO 5G co-operative network platform through a Software Defined Radio (SDR) from a practical implementation point of view.

Relay Nodes (RNs) have received special attention as a radio access technology which can overcome channel fading and improve the channel capacity in high-speed and dense vehicle environments. RNs have been the object of standardization by the 3GPP; however, this process has not been accompanied by the development of hardware that allows for evaluation of the advantages of RNs. Software Defined Radio (SDR) has emerged as a promising technology to implement the concept of RNs at low cost. In this paper, a detailed study of the MIMO wireless channel between an evolved Node-B (eNB) and an RN is carried out. The developed algorithms are implemented in an SDR platform for Decode-and-Forward (D&F) relay node evaluation, resulting in significant improvements of its capabilities on the MIMO channel. A pilot symbol-assisted channel estimation algorithm based on combinations of the Least-Squares (LS) technique and Bi-Cubic (BCI), Bi-Linear (BLI), and Bi-Nearest Neighbors (BNNI) interpolation methods is considered. Furthermore, the Minimum Mean Square Error (MMSE) and Zero-Forcing (ZF) equalization schemes are studied. In the tests conducted, Line-of-Sight (LOS) and Non-Line-of-Sight (NLOS) scenarios are considered, demonstrating the capabilities of the developed platform. The performance measurements using different modulation schemes are compared under the same conditions. The simulation results show that the LS technique together with the BCI and MMSE methods performed the best among all evaluated channel estimation and equalization algorithms, in terms of the Error Vector Magnitude (EVM) performance of the received Resource Grid (RG). Furthermore, we show that the Bit Error Rate (BER) and throughput of the core network increase when using the 2 × 2 MIMO technique.

The relaying technologies in co-operative systems are considered a core element in actual and future wireless communications, assisting the network by enhancing its reliability and improving its capability through exploiting co-operativity. In this paper, a co-operative system testbed based on Software Defined Radio (SDR) through Universal Software Radio Peripherals (USRPs) and the Matlab${}^{\mathrm{TM}}$ software is presented. The main novelty in this development of the platform is the implementation of 4G signal features, such as Physical Downlink Shared Channel (PDSCH) and Downlink Shared Channel (DL-SCH) for transport channel coding, which is one of the main contribution of the paper. The developed Multi-Input and Multi-Output (MIMO) SDR co-operative platform is capable of developing prototypes for the Relay Nodes. More specifically, the Amplify-&-Forward (A&F)—with or without Zero Forcing (ZF) and Minimum Mean Square Error (MMSE) Pre-Equalization—and Decode-&-Forward (D&F) protocols were implemented. Both Single-Input and Single-Output (SISO) and MIMO modes are supported by our testbed. The developed A&F and D&F MIMO co-operative systems in this paper utilize Orthogonal Space-Frequency Block Codes (OSFBCs) for the transmission of data symbols from the source to the destination. Our results show that relay nodes can substantially improve the Bit Error Rate (BER) and throughput in communications between the eNodeB (eNB) and User Equipment (UE). In particular, the maximum throughput achieved by conventional MIMO A&F is $9.3\mathrm{Mbps}$ at $\mathrm{SNR}=16\mathrm{dB}$, which is $4\mathrm{Mbps}$ higher than throughput of MIMO Non-Co-operative. It also shows the capacity improvement when considering the pre-equalization in the A&F schemes, compared to the conventional A&F Relay Node. For example, with MIMO A&F-MMSE pattern, a value of 11.8 Mbps is achieved for $\mathrm{SNR}=16\mathrm{dB}$, which is 84.8 % of the maximum system throughput (13.95 Mbps). On the other hand, the obtained results with D&F schemes far exceed those obtained with A&F strategies, achieving the maximum performance with the 2 × 2 MIMO D&F protocol from $\mathrm{SNR}=8\mathrm{dB}$. Furthermore, this work constitutes a first stage to the implementation of a 5G New-Radio Co-operative System platform.