The transition to smart grids has served to transform traditional power systems into data-driven power systems. The purpose of this transition is to enable effective energy management and system reliability through an analysis that is centered on energy information. However, energy theft caused by vulnerabilities in the data collected from smart meters is emerging as a primary threat to the stability and profitability of power systems. Therefore, various methodologies have been proposed for energy theft detection (ETD), but many of them are challenging to use effectively due to the limitations of energy theft datasets. This paper provides a comprehensive review of ETD methods, highlighting the limitations of current datasets and technical approaches to improve training datasets and the ETD in smart grids. Furthermore, future research directions and open issues from the perspective of generative AI-based ETD are discussed, and the potential of generative AI in addressing dataset limitations and enhancing ETD robustness is emphasized.

The implementation of accurate positioning methods in both line-of-sight (LOS) and non-line-of-sight (NLOS) environments has been emphasized for seamless 6G application services. In LOS environments with unobstructed paths between the transmitter and receiver, accurate tracking essential for seamless 6G services is achievable. However, accurate three-dimensional (3D) outdoor positioning has been challenging to achieve in NLOS environments where positioning accuracy may be severely degraded. In this paper, a novel 3D outdoor positioning method considering both LOS and NLOS environments is proposed. Considering the practical positioning systems, the data received from satellites often contain null values and outliers. Thus, a kernel density estimation (KDE)-based outlier removal method is used for effectively detecting the null values and outliers through temporal correlation analysis. A dilution of precision-based adaptive Kalman filter (DOP-AKF) is proposed to mitigate the effects of an NLOS environment. In the proposed method, the DOP-AKF can optimize the performance of the 3D positioning system that dynamically adapts to complex environments. Experimental results show that the proposed method can improve 3D positioning accuracy by up to 18.84% compared to conventional methods. Therefore, the proposed approach can be suggested as a promising solution for 3D outdoor positioning in 6G wireless systems.

A wide range of research has been conducted on path planning and collision avoidance to enhance the operational efficiency of unmanned aerial vehicles (UAVs). The existing works have mainly assumed an environment with static obstacles and global positioning system (GPS) signals. However, practical environments have often been involved with dynamic obstacles, dense areas with numerous obstacles in confined spaces, and blocked GPS signals. In order to consider these issues for practical implementation, a deep reinforcement learning (DRL)-based method is proposed for path planning and collision avoidance in GPS-denied and dense environments. In the proposed method, robust path planning and collision avoidance can be conducted by using the received signal strength (RSS) value with the extended Kalman filter (EKF). Additionally, the attitude of the UAV is adopted as part of the action space to enable the generation of smooth trajectories. Performance was evaluated under single- and multi-target scenarios with numerous dynamic obstacles. Simulation results demonstrated that the proposed method can generate smoother trajectories and shorter path lengths while consistently maintaining a lower collision rate compared to conventional methods.

An integrated navigation system is a promising solution to improve positioning performance by complementing estimated positioning in each sensor, such as a global positioning system (GPS), an inertial measurement unit (IMU), and an odometer sensor. However, under GPS-disabled environments, such as urban canyons or tunnels where the GPS signals are difficult to receive, the positioning performance of the integrated navigation system decreases. Therefore, deep learning-based integrated navigation systems have been proposed to ensure seamless localization under various positioning conditions. Nevertheless, the conventional deep learning-based systems are applied with a lack of consideration of context features on surface condition, wheel slip, and movement pattern, which are factors causing positioning performance. In this paper, a context-aware integrated navigation system (CAINS) is proposed to ensure seamless localization, especially under GPS-disabled conditions. In the proposed CAINS, two deep learning layers are designed with context-aware and state estimation layers. The context-aware layer extracts vehicle context features from IMU data, while the state estimation layer predicts the GPS position increments by modeling the relationship between context features, velocity, attitude, and position increments. From simulation results, it is confirmed that the positioning accuracy can be significantly improved based on the proposed CAINS when compared with conventional navigation systems.

The orthogonal frequency-division multiplexing (OFDM) transmission technique is well known to be efficient for data transmission but is susceptible to performance degradation due to factors such as high-order modulation schemes, multipath fading, and noise. In this paper, an approach for reconstructing images received by the OFDM transmission technique is proposed based on generative AI. The approach exploits a conditional diffusion model (CDM) that incorporates conditional factors reflecting the degree of distortion in the received images by the OFDM technique. Additionally, it employs a method to learn the variance in the reverse process during training, considering the level of distortion associated with various modulation schemes. Through this adaptability, the proposed model is experimentally demonstrated to optimize image reconstruction performance under various modulation schemes in low-SNR environments. The proposed conditional diffusion model can enhance the PSNR of OFDM-based received images by up to 8 dB in low-SNR conditions with various modulation schemes.

With the recent advancement of virtual try-on (VTO) technology, it is being applied to various fields. Although advancements in VTO technology have enabled not only 2D but also 3D visualization, applying style transfer to hyper-local regions remains challenging due to the complex surface curvature and ambiguous boundaries of 3D objects. To address these challenges, we propose an immersive 3D style transfer framework based on 3D Gaussian splatting. A segmentation model is employed to accurately segment target regions, and a large-scale specialized dataset is constructed to capture the morphological diversity of human hands. Furthermore, neural style transfer is integrated with the 3D representation to enable precise style application to hyper-local regions. The proposed framework achieves a mean intersection of union (mIoU) of 0.806 in segmentation and high-fidelity stylization with learned perceptual image patch similarity (LPIPS) and reference-based LPIPS (Ref-LPIPS) scores of 0.1472 and 0.0196, respectively. These results indicate that the proposed framework can provide the quality requirements and immersive VTO experience.