İbrahim Hökelek

Sefa Kayraklik, Ali Fuat Sahin, Onur Salan et al.

The vision of a smart wireless factory (SWF) demands highly flexible, low-latency, and reliable connectivity that goes beyond conventional wireless solutions. Reconfigurable intelligent surface (RIS)-empowered communications, when integrated with the open radio access network (O-RAN) architectures, have emerged as a promising enabler to meet these challenging requirements. This article introduces the methodology for the orchestration of RIS with xApps (ORIX), bringing the RIS technology into the O-RAN ecosystem through xApp-based control for SWF environments. ORIX features three key components: an O-RAN-compliant RIS service model for dynamic configuration, an RIS channel simulator that supports 3GPP indoor factory models with multiple industrial scenarios, and practical RIS optimization strategies with finite-resolution control. Together, these elements provide a realistic end-to-end emulation platform for evaluating RIS placement, control, and performance in SWF environments prior to deployment. The presented case study demonstrates how ORIX enables the evaluation of achievable performance gains, exploration of trade-offs among key RIS design parameters, and identification of deployment strategies that balance system performance with practical implementation constraints. By bridging theoretical advances with industrial feasibility, ORIX lays the groundwork for RIS-assisted O-RAN networks to power next-generation wireless communication in industrial scenarios.

Erhan Karakoca, Hüseyin Çevik, İbrahim Hökelek et al.

Neural receivers have recently become a popular topic, where the received signals can be directly decoded by data driven mechanisms such as machine learning and deep learning. In this paper, we propose two novel neural network based orthogonal frequency division multiplexing (OFDM) receivers performing channel estimation and equalization tasks and directly predicting log likelihood ratios (LLRs) from the received in phase and quadrature phase (IQ) signals. The first network, the Dual Attention Transformer (DAT), employs a state of the art (SOTA) transformer architecture with an attention mechanism. The second network, the Residual Dual Non Local Attention Network (RDNLA), utilizes a parallel residual architecture with a non local attention block. The bit error rate (BER) and block error rate (BLER) performance of various SOTA neural receiver architectures is compared with our proposed methods across different signal to noise ratio (SNR) levels. The simulation results show that DAT and RDNLA outperform both traditional communication systems and existing neural receiver models.

Sefa Kayraklik, Ibrahim Yildirim, Ertugrul Basar et al.

This paper presents reconfigurable intelligent surface (RIS)-aided deep learning (DL)-based spectrum sensing for next-generation cognitive radios. To that end, the secondary user (SU) monitors the primary transmitter (PT) signal, where the RIS plays a pivotal role in increasing the strength of the PT signal at the SU. The spectrograms of the synthesized dataset, including the 4G LTE and 5G NR signals, are mapped to images utilized for training the state-of-art object detection approaches, namely Detectron2 and YOLOv7. By conducting extensive experiments using a real RIS prototype, we demonstrate that the RIS can consistently and significantly improve the performance of the DL detectors to identify the PT signal type along with its time and frequency utilization. This study also paves the way for optimizing spectrum utilization through RIS-assisted CR application in next-generation wireless communication systems.