Nitrous oxide produced during wastewater treatment is a major greenhouse gas, and accurate prediction and control of N₂O emissions are crucial for achieving carbon neutrality. In this study, aiming to address the complex issues of N₂O emission prediction in wastewater treatment, large-scale multidimensional data from the Altenrhein wastewater treatment plant was used to build a sample database. The role of symmetry in model architecture and data analysis was discussed, and six intelligent prediction models for N₂O emissions were proposed based on deep learning technology. The results showed that the PLO-CNN-BiLSTM-Attention model achieved the best performance, with an R² of 0.99 on the test set. Engineering validation using 48 subsequent datasets confirmed the model’s strong generalization ability and robustness. Feature importance analysis based on SHAP revealed that water temperature was the most critical factor influencing N₂O emissions, while dissolved oxygen concentration and inlet flow rate also had impacts but showed a certain symmetrical change between summer and winter. This study provides efficient and reliable technical support for monitoring and predicting N₂O emissions in urban wastewater treatment plants and offers a scientific basis for developing strategies to reduce greenhouse gas emissions.

Road-surface distress poses a serious threat to traffic safety and imposes a growing burden on urban maintenance budgets. While modern detectors based on convolutional networks and Vision Transformers achieve strong frame-level performance, they often overlook an essential property of road environments—structural symmetry within road networks and damage patterns. We present Graph-MambaRoadDet (GMRD), a symmetry-aware and lightweight framework that integrates dynamic graph reasoning with state–space modeling for accurate, topology-informed, and real-time road damage detection. Specifically, GMRD employs an EfficientViM-T1 backbone and two DefMamba blocks, whose deformable scanning paths capture sub-pixel crack patterns while preserving geometric symmetry. A superpixel-based graph is constructed by projecting image regions onto OpenStreetMap road segments, encoding both spatial structure and symmetric topological layout. We introduce a Graph-Generating State–Space Model (GG-SSM) that synthesizes sparse sample-specific adjacency in $\mathcal{O}\left(M\right)$ time, further refined by a fusion module that combines detector self-attention with prior symmetry constraints. A consistency loss promotes smooth predictions across symmetric or adjacent segments. The full INT8 model contains only 1.8 M parameters and 1.5 GFLOPs, sustaining 45 FPS at 7 W on a Jetson Orin Nano—eight times lighter and 1.7× faster than YOLOv8-s. On RDD2022, TD-RD, and RoadBench-100K, GMRD surpasses strong baselines by up to +6.1 mAP_50:95 and, on the new RoadGraph-RDD benchmark, achieves +5.3 G-mAP and +0.05 consistency gain. Qualitative results demonstrate robustness under shadows, reflections, back-lighting, and occlusion. By explicitly modeling spatial and topological symmetry, GMRD offers a principled solution for city-scale road infrastructure monitoring under real-time and edge-computing constraints.

The prompt and precise detection of road damage is vital for effective infrastructure management, forming the foundation for intelligent transportation systems and cost-effective pavement maintenance. While current convolutional neural network (CNN)-based methodologies have made progress, they are fundamentally limited by treating damages as independent, isolated entities, thereby ignoring the intrinsic spatial symmetry and topological organization inherent in complex damage patterns like alligator cracking. This conceptual asymmetry in modeling leads to two major deficiencies: “context blindness,” which overlooks essential structural interrelations, and “temporal inconsistency” in video analysis, resulting in unstable, flickering predictions. To address this, we propose a Spatio-Temporal Graph Mamba You-Only-Look-Once (STG-Mamba-YOLO) network, a novel architecture that introduces a symmetry-informed, hierarchical reasoning process. Our approach explicitly models and integrates contextual dependencies across three levels to restore a holistic and consistent structural representation. First, at the pixel level, a Mamba state-space model within the YOLO backbone enhances the modeling of long-range spatial dependencies, capturing the elongated symmetry of linear cracks. Second, at the object level, an intra-frame damage Graph Network enables explicit reasoning over the topological symmetry among damage candidates, effectively reducing false positives by leveraging their relational structure. Third, at the sequence level, a Temporal Graph Mamba module tracks the evolution of this damage graph, enforcing temporal symmetry across frames to ensure stable, non-flickering results in video streams. Comprehensive evaluations on multiple public benchmarks demonstrate that our method outperforms existing state-of-the-art approaches. STG-Mamba-YOLO shows significant advantages in identifying intricate damage topologies while ensuring robust temporal stability, thereby validating the effectiveness of our symmetry-guided, multi-level contextual fusion paradigm for structural health monitoring.

As intelligent vehicle technologies evolve, reliable driver monitoring systems have become increasingly critical for ensuring the safety of human drivers and operational reliability. This paper proposes a novel visual computing framework for Driver Fatigue Monitoring Systems (DFMSs) based on hierarchical decoupling and scenario element analysis, specifically designed for intelligent transportation environments. By treating the monitoring system as an engineering-level embodied perception–decision system deployed within the vehicle, rather than a purely disembodied vision module, the framework decouples low-level algorithmic perception from application-layer decision logic, enabling a more granular evaluation of visual computing performance in real-world scenarios. We leverage Python 3.9-driven automated test case generation to simulate diverse environmental variables, improving testing efficiency by 50% over traditional manual methods. The system utilizes deep learning-based visual computing to achieve high-fidelity monitoring of eye closure (PERCLOS, EAR), yawning (MAR), and head pose dynamics, enabling real-time assessment of the driver’s state within the embodied system loop. Comparative benchmarking reveals that our framework significantly outperforms existing models in visual understanding accuracy, achieving perfect confidence scores (1.000) for eye closure and smoking behavior detection, while drastically reducing false positives in mobile phone usage detection (misidentification rate: 0.016 vs. 0.805). These results demonstrate that an embodied approach to visual perception enhances the robustness and reliability of driver monitoring systems deployed in real vehicles, providing a scalable pathway for the development of next-generation intelligent transportation safety standards.

Personalized surgical assistance requires an understanding of individual surgeon styles and preferences; however, existing methods utilize fixed models to represent these styles, which cannot account for the diverse range of techniques utilized by different surgeons. SurgeonAdaptRL, a new framework, utilizes a combination of meta-reinforcement learning and hierarchical imitation learning to model and replicate surgeon-specific operative styles based on surgical video data. This framework makes three key contributions: (1) the development of an architecture for meta-policy optimization for adapting to each surgeon’s style based on few-shot demonstrations; (2) the design of a library of skill primitives that includes temporal awareness to represent the motion patterns of a surgeon at the different stages of a procedure, and (3) a method for safely refining a policy validated through simulation. The research has been validated using the CATARACTS dataset and its related CaDIS segmentation benchmark, as well as a subset of Cataract-1K Videos with phase annotations, and results show that SurgeonAdaptRL outperforms baseline methods, as evidenced by an increase in normalized trajectory prediction accuracy of 12.7% and improved style fidelity metrics, requiring 65.6% less adaptation time than baseline methods. Further validation has been conducted by deploying the framework in a physics-based surgical simulation environment, which demonstrates that safe constraints can be satisfied. This work lays the groundwork for personalized surgical video analysis that will serve as the basis for future robotic surgical systems.