In the domain of autonomous driving systems, vehicle trajectory prediction represents a critical aspect, as it significantly contributes to the safe maneuvering of vehicles within intricate traffic environments. Nevertheless, a preponderance of extant research efforts have been chiefly centered on the spatio-temporal relationships intrinsic to the vehicle itself, thereby exhibiting deficiencies in the dynamic perception of and interaction capabilities with adjacent vehicles. In light of this limitation, we propose a vehicle trajectory prediction algorithm predicated on a hybrid prediction model. Initially, the algorithm extracts pertinent context information pertaining to the target vehicle and its neighboring vehicles through the application of a two-layer long short-term memory network. Subsequently, a fusion module is deployed to assimilate the characteristics of the temporal influence, spatial influence, and interactive influence of the surrounding vehicles, followed by the integration of these attributes. Ultimately, the prediction module is engaged to yield the predicted movement positions of the vehicles, expressed in coordinate form. The proposed algorithm was trained and validated using the publicly accessible datasets I-80 and US-101. The experimental results demonstrate that our proposed algorithm is capable of generating more precise prediction results.

An ANN model-based method is proposed to retrieve the ocean surface wind speed from Cyclone Global Navigation Satellite System (CYGNSS) L1 observation data. The proposed method is embedded with an input features and output results filtering module based on a machine learning (ML) algorithm, abbreviated as the MF-ANN method. By studying the relationship between physical observation variables from CYGNSS L1 data and the wind speed of the European Centre for Medium-Range Weather Forecast (ECMWF) reanalysis dataset and Cross-Calibrated Multiplatform (CCMP) dataset, a feature parameter selection module based on the XGBoost algorithm and Pearson correlation coefficient is designed to automatically select the optimal combination of feature parameters related to the ocean surface wind speed and input the feature parameters into the ANN model. An outlier filtering module based on the unsupervised ML algorithm is designed to identify and eliminate the outliers in the wind speed data retrieved by the ANN model, reducing the errors that cannot be eliminated by the fixed threshold of the quality flag providing in the CYGNSS L1 product. The experiments show that the RMSEs of the MF-ANN model can be reduced by 11.73% and 15.31% compared with those of a single ANN model by adding feature selection modules and quality filtering modules, respectively. The RMSE of the MF-ANN model combining these two modules can be reduced by 29.08%.

In road scenes, the collected 3D point cloud data is usually accompanied by a large amount of interference mainly composed of ground point clouds and the property of uneven density distribution, which will bring difficulties to subsequent recognition and prediction. To address these problems, this paper proposes a ground point cloud segmentation algorithm based on local density plane fitting. Firstly, for the uneven density distribution of 3D point clouds, density segmentation is used to obtain several regions with balanced density. Then, candidate sample selection and plane validity detection are carried out for each region. The modified classical DBSCAN clustering algorithm is used to obtain effective fitting planes and perform clustering according to the fitting planes. Finally, different planes are divided according to the clustering results, and abnormal inspection is performed on the obtained results to screen out the most reasonable result. This scheme can effectively improve the scalability of the algorithm, reduce training costs, and improve deployment efficiency and universality. Experimental results show that the algorithm used in this paper has advantages compared with advanced algorithms of the same category, and can greatly reduce ground interference.

Short-term photovoltaic (PV) power forecasting is pivotal for grid stability and high renewable-energy integration, yet existing hybrid deep-learning models face three unresolved challenges: they fail to balance accuracy, computational efficiency, and interpretability; cannot mitigate iTransformer’s inherent weakness in local feature capture (critical for transient events like minute-level cloud shading); and rely on linear concatenation that mismatches the nonlinear correlations between global multivariate trends and local fluctuations in PV sequences. To address these gaps, this study proposes a novel lightweight hybrid framework—DSC-Chebyshev KAN-iTransformer—for 15-min short-term PV power forecasting. The core novelty lies in the synergistic integration of Depthwise Separable Convolution (DSC) for low-redundancy local temporal pattern extraction, Chebyshev Kolmogorov–Arnold Network (Chebyshev KAN) for adaptive nonlinear fusion and global nonlinear modeling, and iTransformer for efficient capture of cross-variable global dependencies. This design not only compensates for iTransformer’s local feature deficiency but also resolves the linear fusion mismatch issue of traditional hybrid models. Experimental results on real-world PV datasets demonstrate that the proposed model achieves an $R^2$ of 0.996, with root mean square error (RMSE) and mean absolute error (MAE) reduced by 19.6–62.1% compared to state-of-the-art baselines (including iTransformer, BiLSTM, and DSC-CBAM-BiLSTM), while maintaining lightweight characteristics (2.04M parameters, 3.90 GFLOPs) for urban edge deployment. Moreover, Chebyshev polynomial weight visualization enables quantitative interpretation of variable contributions (e.g., solar irradiance dominates via low-order polynomials), enhancing model transparency for engineering applications. This research provides a lightweight, accurate, and interpretable forecasting solution, offering policymakers a data-driven tool to optimize urban PV-infrastructure integration and improve grid resilience amid the global energy transition.

Filter bank multicarrier (FBMC) is a crucial complementary waveform to orthogonal frequency-division multiplexing (OFDM) in future communication systems. However, FBMC systems also suffer from the drawback of an excessively high peak-to-average power ratio (PAPR). Moreover, PAPR reduction methods designed for OFDM systems cannot be directly applied to FBMC systems due to the overlapping nature of FBMC symbols. In this paper, we propose a novel deep learning (DL)-based PAPR reduction scheme for FBMC systems. This innovative approach employs a deep denoising autoencoder (DAE) network in the time domain to suppress the PAPR of FBMC signals and reconstruct the ideal signal. Simulation results demonstrate that the proposed DAE-PAPR scheme achieves a PAPR reduction gain of approximately 2.3 dB to 4.5 dB compared to conventional state-of-the-art methods, while maintaining excellent bit error rate (BER) performance and out-of-band energy leakage characteristics.