Abstract Reliable operation in space–frequency block coding (SFBC) multiple‐input multiple‐output orthogonal frequency‐division multiplexing (MIMO‐OFDM) systems requires accurate channel estimation, which is challenging in high‐mobility scenarios owing to rapid channel variations. Traditional pilot‐assisted estimators, such as least‐squares (LS) and linear minimum mean‐square error (LMMSE), suffer severe performance loss under these conditions. Long short‐term memory (LSTM) networks and other deep‐learning‐based methods are more accurate but computationally expensive. This study proposes a low‐complexity gated recurrent unit (GRU)‐based channel estimator that reduces computational overhead while maintaining high performance. Simulation results over tapped‐delay‐line‐D (TDL‐D) high‐mobility channels demonstrate that the proposed GRU‐ and conventional LSTM‐based estimators outperform LS and LMMSE over the primary evaluated carrier‐to‐noise ratio (CNR) range of 0–20 dB in terms of mean‐square error and bit error rate. Whereas LSTM slightly outperforms the proposed GRU at extremely low CNRs, the proposed GRU achieves superior overall performance, particularly at high CNRs, where LSTM may saturate.
Abstract In this paper, we present a downlink non‐orthogonal multiple access (NOMA) system incorporating fluid antenna systems (FAS) at the receiver terminal. The proposed system is motivated by the fact that a large number of users can be provided with higher diversity in a smaller space through integration of the NOMA scheme with FAS. The proposed system is analyzed in terms of outage probability and average bit error rate performance. In addition, the effects of imperfect channel state information, hardware impairments, and imperfect successive interference cancellation are incorporated into the system model to provide a more practical performance analysis. A mathematical framework is derived and verified using Monte Carlo simulations. The results are presented for various combinations of system parameters to demonstrate their effects on system performance and reliability. Furthermore, the effectiveness of the proposed system compared with a conventional single‐antenna system is illustrated in terms of error performance.
Driver monitoring systems (DMS) are critical for safe autonomous driving, which requires accurate behavior recognition and reliable simulation environments for validation. This study proposes a robust two-phase framework that combines a classification model and a prototype selection procedure to automatically generate realistic motion baselines from the acquired 3D skeleton data. Phase 1 uses a spatial temporal graph convolutional network to classify driver behaviors, and Phase 2 leverages class-wise mean trajectories to interpret motion prototypes and select the closest real sequence, creating a verifiable motion trajectory library for simulation-based safety testing. Our approach addresses DMS challenges through prototype visualization, robustness via discriminative embeddings, and standardized simulation scenarios, making it suitable for human–AI interactions in automotive safety systems. This framework produces a motion library of a real recorded sequence that can be directly used for simulation scenario generation and demonstrated through Metahuman retargeting and visualization in Unreal Engine.
Abstract Sparse‐reward tasks with piecewise‐stationary topology shifts challenge reinforcement learning. Continuous spectral shaping biases agents toward geometric extrema and can delay adaptation when bottlenecks move. We propose adaptive edge‐difference shaping (AEDS), a spectral reward‐shaping method that focuses exploration on structural bottlenecks. AEDS triggers a direction‐agnostic intrinsic reward only when the agent crosses the sign‐flip boundary of the dynamically updated Fiedler vector. An episodic gating mechanism limits rewarded crossings and bounds the cumulative intrinsic return. Within each stationary phase, AEDS induces an augmented Markov decision process to which the standard tabular Q‐learning convergence theorem applies. We evaluate AEDS on grid environments with shifting bottlenecks and geometric traps. Across the evaluation, AEDS performs strongly in several bottleneck‐oriented settings, while count‐based exploration or well‐oriented dense spectral shaping can be preferable in other regimes. These results support a focused scope for AEDS in bottleneck‐oriented sparse‐reward grid tasks.
