Solar energy is a renewable energy used for urban power generation, contributing to sustainable cities. In solar energy generation, it is important to inspect the health of photovoltaic (PV) cells for safety and power transformation efficiency. Defects in PV cells are usually irregular with different scales, challenging automated defect detection for PV cells. Therefore, this article presents a channel and coordinate aware-based YOLO (CCA-YOLO) for efficient PV cell defect detection. Specifically, to provide accurate backbone features from the complex background defect images, the residual coordinate convolution-based ECA (RCC-ECA) enhances the backbone feature representation by learning from channel and coordinate information. To learn the intraclass/interclass variations and interclass similarity and convey coordinate information among different scales, the multiscale defect feature localization module (MDFLM) incorporates a larger backbone feature to improve the robustness of multiscale defects. The RCC-Up/Down optimizes the sampled features to minimize the inaccurate representation of the features caused by the sampling process. In addition, RCC-Up/Down conveys the coordinate information during the up/down sampling process to maintain coordinate awareness, which allows the network to learn from the coordinate information efficiently. Furthermore, the residual feature fusion with coordinate convolution-based CBAM (RFC-CBAM) is introduced to maintain the channel and coordinate awareness for efficient learning from fused features. The proposed CCA-YOLO outperforms state-of-the-art (SOTA) methods in PVEL-AD on precision (71.71%), recall (76.91%), F1-Scores (74.19%), mAP50 (98.57%), $\text {AP}_{S}$ (26.80%), $\text {AP}_{M}$ (64.78%), and $\text {AP}_{L}$ (74.93%).

Cognitive Radio (CR) is a practical technique for overcoming spectrum inefficiencies by sensing and utilizing spectrum holes over a wide spectrum. In particular, cooperative spectrum sensing (CSS) determines the state of primary users (PUs) by cooperating with multiple secondary users (SUs) distributed around a Cognitive Radio Network (CRN), further overcoming various noise and fading issues in the radio environment. But it’s still challenging to balance energy efficiency and good sensing performances in the existing CSS system, especially when the CRN consists of battery-limited sensors. This article investigates the application of machine learning technologies for cooperative spectrum sensing, especially through solving a multi-dimensional optimization that cannot be readily addressed by traditional approaches. Specifically, we develop a neural network, which involves parameters that are integral to the CSS performance, including a device sleeping rate for each sensor and thresholds used in the energy detection method, and a customized loss function based on the energy consumption of the CSS system and multiple penalty terms reflecting the system requirements. Using this formulation, energy consumption is to be minimized with the guarantee of reaching a certain probability of false alarm and detection in the CSS system. With the proposed method, comparison studies under different hard fusion rules (‘OR’ and ‘AND’) demonstrate its effectiveness in improving the CSS system performances, as well as its robustness in the face of changing global requirements. This paper also suggests the combination of the traditional and the proposed scheme to circumvent the respective inherent pitfalls of neural networks and the traditional semi-analytic methods.

Security and privacy are vital challenges in Industrial Internet of Things (IIoT) systems due to the inherent broadcast property of industrial wireless communication. Therefore, how to improve the security of smart devices in IIoT systems has attracted widespread attention. In this article, a novel security optimization scheme for space shift keying (SSK)-based IIoT systems is proposed by applying secrecy enhancing techniques in the physical layer. Specifically, two methods are adopted in the proposed optimization scheme. First, the sender transmits artificial noise (AN) to interfere with the eavesdropper, while the legitimate receiver can eliminate AN. Second, the sender can select optimal antennas based on the proposed minmax criteria to transmit AN and information, which further promotes the security of industrial wireless communication. The optimal antenna selection pattern increases the difference of the average mutual information between the legitimate receiver and the eavesdropper. In addition, the proposed minmax antenna selection approach only requires the channel state information of the legitimate receiver, which satisfies the application scenario of unknown eavesdropper attacks in IIoT. Finally, we adopt a deep learning-based maximum likelihood (ML) detection algorithm to detect the optimal antenna index and analyze the bit error rate (BER) and secrecy rate (SR) of the proposed optimization scheme. Simulation results show that the proposed scheme can achieve similar SR improvements and superior BER performance compared with the state-of-the-art scheme, namely the signal-leakage-to-noise ratio (SLNR) scheme. The BER performance of the proposed scheme achieves a maximum of 100 times superior to that of the SLNR scheme when the signal-to-noise ratio (SNR) is 27 dB. Moreover, the proposed scheme outperforms the traditional antenna selection scheme (random selection) in terms of BER and SR.

In the next generation wireless Internet of Things (IoT) networks empowered by modern communication technology, non-orthogonal multiple access (NOMA) and faster-than-Nyquist (FTN) signaling are purportedly two enabling technologies that enhance spectral efficiency (SE) without requiring additional spectrum resources. In addition, simultaneous wireless information and power transfer (SWIPT) technology enables IoT sensors and devices to harvest energy from radio frequency (RF) signals, effectively mitigating power supply limitations. This article proposes and investigates a novel SWIPT-NOMA system based on FTN technology, referred to as FTN-assisted SWIPT-NOMA, for IoT relay networks over Rayleigh fading channels. We provide a comprehensive analysis of the ergodic capacity and achievable rate of the FTN-assisted SWIPT-NOMA system applied in IoT relay networks. Specifically, we explore two distinct relaying architectures geared towards augmenting SE and energy utilization, i.e., power-splitting (PS) and time-switching (TS). We derive approximated expressions for the ergodic capacity and analyze high SNR slopes for sensor users in both architectures. Simulation results show that the ergodic capacity of the proposed system surpasses that of the conventional Nyquist-SWIPT-NOMA system, with greater capacity improvements as the FTN acceleration factor τ decreases. This highlights the substantial potential of FTN-assisted SWIPT-NOMA systems in enhancing the performance of IoT relay networks, particularly with respect to SE.

To enable highly reliable and spectrum-efficient vehicle-to-everything (V2X) communications under conditions with severe Doppler effects and rapidly time-varying channels, we propose a novel faster-than-Nyquist orthogonal time frequency space (FTN-OTFS) modulation scheme. In this scheme, FTN signaling is integrated with spectrally efficient frequency division multiplexing (SEFDM) within the OTFS framework, enabling a higher symbol-transmission density within a fixed time–frequency resource block and thus enhancing spectral efficiency without increasing the occupied bandwidth. An analytical input–output model is derived in both the delay–Doppler and time–frequency domains. To further enhance numerical stability, an improved detection algorithm called adaptive damping log-domain message-passing (ADL-MP) is developed for the proposed scheme. Simulation results demonstrate that the proposed scheme achieves robust and reliable performance in high-mobility scenarios and that the proposed algorithm consistently outperforms conventional methods in terms of bit error rate (BER) under both the extended vehicular A (EVA) model and the high-speed train (HST) scenario, confirming its effectiveness and superiority for V2X communications.

Intelligent Reflective Surface (IRS)-aided Multiple-Input Multiple-Output (MIMO) systems have emerged as a promising solution to enhance spectral and energy efficiency in future wireless communications. However, accurate channel estimation remains a key challenge due to the passive nature and high dimensionality of IRS channels. This paper proposes a lightweight hybrid framework for cascaded channel estimation by combining a physics-based Bilinear Alternating Least Squares (BALS) algorithm with a deep neural network named ConvTrans-ResNet. The network integrates convolutional embeddings and Transformer modules within a residual learning architecture to exploit both local and global spatial features effectively while ensuring training stability. A series of ablation studies is conducted to optimize architectural components, resulting in a compact configuration with low parameter count and computational complexity. Extensive simulations demonstrate that the proposed method significantly outperforms state-of-the-art neural models such as HA02, ReEsNet, and InterpResNet across a wide range of SNR levels and IRS element sizes in terms of the Normalized Mean Squared Error (NMSE). Compared to existing solutions, our method achieves better estimation accuracy with improved efficiency, making it suitable for practical deployment in IRS-aided systems.