In order to meet the demands of autonomy and control optimization in solar greenhouse control systems, this paper developed an intelligent temperature and humidity control system for greenhouses based on the Single Neuron Proportional Integral Derivative (SNPID) algorithm. The system is centered around the Huada HC32F460 Micro-Controller Unit (MCU) and the RT-Thread operating system, integrated with the SNPID control algorithm. Through comprehensive simulation, model construction, and comparative experiments, this system was thoroughly evaluated in comparison with traditional PID control systems (cPID) that rely on overseas software and hardwsbuare. Simulation results show that our new system significantly outperforms traditional PID (Proportional Integral Derivative) systems in terms of temperature control stability and accuracy. Experimental data further confirm that, while ensuring cost-effectiveness, the new system achieves a remarkable 50.2% improvement in temperature and humidity control precision compared to traditional systems. The temperature Root Mean Square Error (RMSE) in the experimental greenhouse is 0.734 compared to 1.594 in the comparison greenhouse, indicating better stable temperature control capability. The vents in the experimental greenhouse have a maximum opening of 67 cm and a minimum of 5 cm, showing a quick response property to high temperatures. In contrast, the control greenhouse has a maximum vent opening of 55 cm, remaining unchanged during the test period, which reflects its slower response to temperature fluctuations. These results demonstrate the significant advantages of the designed solar greenhouse temperature and humidity control system in terms of autonomy and control optimization, providing an efficient and economical solution for solar greenhouse environmental management. This system shows significant practical application perspective in promoting intelligent agriculture and sustainable agricultural production, highlighting its broad impact and potential significance.

Due to the distinct functionalities of various social network platforms, users often register accounts on different platforms, posing significant challenges for unified user management. However, current multi-social-network user identification algorithms heavily rely on user attributes and cannot perform user identification across multiple social networks. To address these issues, this paper proposes two identity recognition models. The first model is a cross-social-network user identification model based on bidirectional GCN. It calculates user intimacy using the Jaccard similarity coefficient and constructs an adjacency matrix to accurately represent user relationships in the social network. It then extracts cross-social-network user information to accomplish user identification tasks. The second model is the multi-network feature user identification (MNF-UI) model, which introduces the concept of network feature vectors. It effectively maps the structural features of different social networks and performs user identification based on the common features of seed nodes in the cross-network environment. Experimental results demonstrate that the bidirectional GCN model significantly outperforms baseline algorithms in cross-social-network user identification tasks. The MNF-UI (multi-network feature user identification) model can operate in situations with two or more networks with inconsistent structures, resulting in improved identification accuracy. These two user identification algorithms provide technical and theoretical support for in-depth research on social network information integration and network security maintenance.

Semantic segmentation-based Complex Waterway Scene Understanding has shown great promise in the environmental perception of Unmanned Surface Vehicles. Existing methods struggle with estimating the edges of obstacles under conditions of blurred water surfaces. To address this, we propose the Lightweight Dual-branch Mamba Network (LDMNet), which includes a CNN-based Deep Dual-branch Network for extracting image features and a Mamba-based fusion module for aggregating and integrating global information. Specifically, we improve the Deep Dual-branch Network structure by incorporating multiple Atrous branches for local fusion; we design a Convolution-based Recombine Attention Module, which serves as the gate activation condition for Mamba-2 to enhance feature interaction and global information fusion from both spatial and channel dimensions. Moreover, to tackle the directional sensitivity of image serialization and the impact of the State Space Model’s forgetting strategy on non-causal data modeling, we introduce a Hilbert curve scanning mechanism to achieve multi-scale feature serialization. By stacking feature sequences, we alleviate the local bias of Mamba-2 towards image sequence data. LDMNet integrates the Deep Dual-branch Network, Recombine Attention, and Mamba-2 blocks, effectively capturing the long-range dependencies and multi-scale global context information of Complex Waterway Scene images. The experimental results on four benchmarks show that the proposed LDMNet significantly improves obstacle edge segmentation performance and outperforms existing methods across various performance metrics.

Introduction: Identifying promising export destinations requires considering both the likelihood of establishing a bilateral trade relationship and the potential trade scale once that relationship is established. Methods: This study develops a graph-augmented dual-task forecasting framework for global information and communication technology (ICT) goods trade using GAT-XGBoost. The framework integrates BACI bilateral ICT goods trade data under the HS 2012 classification for 2012–2024 with country characteristics, gravity variables, historical trade information, and network features. A strict chronological design uses 2014–2021 for training, 2022 for validation, and 2023–2024 for out-of-period testing. Results: On the 2024 test set, the framework achieves an AUC of 0.9631 and an Average Precision of 0.9394 for trade-link prediction, while conditional log-flow prediction achieves an RMSE of 1.7711 and an R ² of 0.8344. Ablation results indicate that historical bilateral trade provides the dominant predictive signal, while observed network measures and graph-derived representations contribute complementary information. Discussion: By combining predicted trade-link probabilities with conditional trade magnitudes, the framework produces exporter-specific destination rankings and opportunity classifications. The resulting measures support systematic screening of potential ICT export markets rather than causal inference or guaranteed future trade outcomes.