Search Results (657)

Urbanization and traffic congestion caused by the surge in car ownership have exacerbated energy consumption and carbon emissions, and dynamic traffic flow prediction and energy-saving route planning have become the key to solving this problem. Dynamic traffic flow prediction accurately captures the spatio-temporal changes of traffic flow through advanced algorithms and models, providing prospective information for traffic management and travel decision-making. Energy-saving route planning optimizes travel routes based on prediction results, reduces the time vehicles spend on congested road sections, thereby reducing fuel consumption and exhaust emissions. However, there are still many shortcomings in the current relevant research, and the existing research is mostly isolated and applies a single model, and there is a lack of systematic comparison of the adaptability, generalization ability and fusion potential of different models in various scenarios, and the advantages of heterogeneous graph neural networks in integrating multi-source heterogeneous data in traffic have not been brought into play. This paper systematically reviews the relevant global studies from 2020 to 2025, focuses on the integration path of dynamic traffic flow prediction methods and energy-saving route planning, and reveals the advantages of LSTM, graph neural network and other models in capturing spatiotemporal features by combing the application of statistical models, machine learning, deep learning and mixed methods in traffic forecasting, and comparing their performance with RMSE, MAPE and other indicators, and points out that the potential of heterogeneous graph neural networks in multi-source heterogeneous data integration has not been fully explored. Aiming at the problem of disconnection between traffic prediction and path planning, an integrated framework is constructed, and the real-time prediction results are integrated into path algorithms such as A* and Dijkstra through multi-objective cost functions to balance distance, time and energy consumption optimization. Finally, the challenges of data quality, algorithm efficiency, and multimodal adaptation are analyzed, and the development direction of standardized evaluation platform and open source toolkit is proposed, providing theoretical support and practical path for the sustainable development of intelligent transportation systems. Full article

Global navigation satellite systems (GNSS) can provide high-quality location information in outdoor environments. In indoor environments, GNSS cannot achieve accurate and stable location information due to the obstruction and attenuation of buildings together with the influence of multipath effects. Due to the rapid development of micro-electro-mechanical system (MEMS) sensors, today’s smartphones are equipped with various low-cost and small-volume MEMS sensors. Therefore, it is of great significance to study indoor pedestrian positioning technology based on smartphones. In order to provide pedestrians with high-precision and reliable location information in indoor environments, we propose a pedestrian dead reckoning (PDR) method based on Transformer+TCN (temporal convolutional network). Firstly, we use IMU (inertial measurement unit)/PDR pre-integration to suppress the inertial navigation divergence. Secondly, we propose a step length estimation algorithm based on Transformer+TCN. The Transformer and TCN networks are superimposed to improve the ability to capture complex dependencies and improve the generalization and reliability of step length estimation. Finally, we propose factor graph optimization (FGO) models based on sliding windows (SW-FGO) to provide accurate posture, which use accelerometer (ACC)/gyroscope/magnetometer (MAG) data to establish factors. We designed a fusion positioning estimation test and a comparison test on step length estimation algorithm. The results show that the fusion method based on SW-FGO proposed by us improves the positioning accuracy by 29.68% compared with the traditional FGO algorithm, and the absolute position error of the step length estimation algorithm based on Transformer+TCN in pocket mode is mitigated by 42.15% compared with the LSTM algorithm. The step length estimation model error of Transformer+TCN is 1.61%, and the step length estimation accuracy is improved by 24.41%. Full article

A general high-order linear consensus protocol is proposed for coupling topologies defined by directed graphs with partial relative state information and a reference model with lobal/local gains. Necessary and sufficient second-order stability bounds for the cases of relative position feedback with reference velocity and relative position and velocity feedback are then reviewed. Next, new necessary and sufficient stability bounds are obtained for third-order consensus for three cases of feedback of full and partial relative state information. The stability bounds obtained, unlike in prior studies, allow for the gains to be conveniently selected in a sequential manner and are shown to utilize those for second-order consensus. Comparisons with conservative stability bounds from previous studies are shown, and illustrative examples of the proposed consensus protocols and the obtained stability bounds are provided. Full article

Traffic violations, the primary cause of road accidents, threaten public safety by disrupting traffic flow and causing substantial casualties and economic losses. Accurate spatiotemporal prediction of violations offers critical insights for proactive traffic management. While Graph Attention Network (GAT) methods excel in spatiotemporal forecasting, their practical deployment is hindered by prohibitive computational costs when handling dynamic large-scale data. To address this issue, we propose a Lightweight Traffic Violation Prediction with Graph Attention Distillation (LTVPGA) model, transferring spatial topology comprehension from a complex GAT to an efficient multilayer perceptron (MLP) via knowledge distillation. Our core contribution lies in topology-invariant knowledge transfer, where spatial relation priors distilled from the teacher’s attention heads enable the MLP student to bypass explicit graph computation. This approach achieves significant efficiency gains for large-scale data—notably accelerated inference time and reduced memory overhead—while preserving modeling capability. We conducted a performance comparison between LTVPGA, Conv-LSTM, and GATR (teacher model). LTVPGA achieved revolutionary efficiency: consuming merely 15% memory and 0.6% training time of GATR while preserving nearly the same accuracy. This capacity enables practical deployment without sacrificing fidelity, providing a scalable solution for intelligent transportation governance. Full article

With the rapid development of socioeconomics and the continuous advancement of urbanization, water environment issues in plain river networks have become increasingly prominent. Accurate and reliable water quality (WQ) predictions are a prerequisite for water pollution warning and management. Data-driven modeling offers a promising approach for WQ prediction in plain river networks. However, existing data-driven models suffer from inadequate capture of spatiotemporal (ST) dependencies and misalignment between direct prediction strategy assumptions with actual data characteristics, limiting prediction accuracy. To address these limitations, this study proposes a spatiotemporal graph neural network (ST-GNN) that integrates four core modules. Experiments were performed within the Chengdu Plain river network, with performance comparisons against five baseline models. Results suggest that ST-GNN achieves rapid and accurate WQ prediction for both short-term and long-term, reducing prediction errors (MAE, RMSE, MAPE) by up to 46.62%, 37.68%, and 45.67%, respectively. Findings from the ablation experiments and autocorrelation analysis further confirm the positive contribution of the core modules in capturing ST dependencies and eliminating data autocorrelation. This study establishes a novel data-driven model for WQ prediction in plain river networks, supporting early warning and pollution control while providing insights for water environment research. Full article

Accurate and high-resolution spatio-temporal prediction of PM_2.5 concentrations remains a significant challenge for air pollution early warning and prevention. Advanced artificial intelligence (AI) technologies, however, offer promising solutions to this problem. A spatio-temporal prediction model is designed in this study, which is built upon a seq2seq architecture. This model employs an improved graph convolutional neural network to capture spatially dependent features, integrates time-series information through a gated recurrent unit, and incorporates an attention mechanism to achieve PM_2.5 concentration prediction. Benefiting from high-resolution satellite remote sensing data, the regional, multi-step and high-resolution prediction of PM_2.5 concentration in Beijing has been performed. To validate the model’s performance, ablation experiments are conducted, and the model is compared with other advanced prediction models. The experimental results show our proposed Spatio-Temporal Graph Convolutional Network with Attention Mechanism (STGCA) outperforms comparison models in multi-step forecasting, achieving root mean squared error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) of 4.21, 3.11 and 11.41% for the first step, respectively. For subsequent steps, the model also shows significant improvements. For subsequent steps, the model also shows significant improvements, with RMSE, MAE and MAPE values of 5.08, 3.69 and 13.34% for the second step and 6.54, 4.61 and 16.62% for the third step, respectively. Additionally, STGCA achieves the index of agreement (IA) values of 0.98, 0.97 and 0.95, as well as Theil’s inequality coefficient (TIC) values of 0.06, 0.08 and 0.10 proving its superiority. These results demonstrate that the proposed model offers an efficient technical approach for smart air pollution forecasting and warning in the future. Full article

This work investigates the solutions of fractional integro-differential equations (FIDEs) using a unique kernel operator within the Caputo framework. The problem is addressed using both analytical and numerical techniques. First, the two-step Adomian decomposition method (TSADM) is applied to obtain an exact solution (if it exists). In the second part, numerical methods are used to generate approximate solutions, complementing the analytical approach based on the Adomian decomposition method (ADM), which is further extended using the Sumudu and Shehu transform techniques in cases where TSADM fails to yield an exact solution. Additionally, we establish the existence and uniqueness of the solution via fixed-point theorems. Furthermore, the Ulam–Hyers stability of the solution is analyzed. A detailed error analysis is performed to assess the precision and performance of the developed approaches. The results are demonstrated through validated examples, supported by comparative graphs and detailed error norm tables ($L_{\infty }$, $L_2$, and $L_1$). The graphical and tabular comparisons indicate that the Sumudu-Adomian decomposition method (Sumudu-ADM) and the Shehu-Adomian decomposition method (Shehu-ADM) approaches provide highly accurate approximations, with Shehu-ADM often delivering enhanced performance due to its weighted formulation. The suggested approach is simple and effective, often producing accurate estimates in a few iterations. Compared to conventional numerical and analytical techniques, the presented methods are computationally less intensive and more adaptable to a broad class of fractional-order differential equations encountered in scientific applications. The adopted methods offer high accuracy, low computational cost, and strong adaptability, with potential for extension to variable-order fractional models. They are suitable for a wide range of complex systems exhibiting evolving memory behavior. Full article

Traditional GCN based methods capture the propagation structure between posts, but do not fully model dynamic semantic information, such as the role of specific users on the propagation path and the context of post content that changes over time, leading to a decrease in the accuracy of rumor detection. Therefore, we propose an innovative path attention graph convolution network (PAGCN) framework, which effectively solves this limitation by integrating propagation structure and semantic representation learning. PAGCN first uses the graph neural network (GNN) to model the information transmission path, focusing on the differences between rumor and fact information in communication behavior, such as the differences between depth first and breadth first dissemination modes. Then, in order to enhance the ability of semantic understanding, we design a multi head attention mechanism based on convolutional neural network (CNN), which extracts deep contextual relationships from text content. Furthermore, by introducing the comparative learning technology, PAGCN can adaptively optimize the representation of structural and semantic features, dynamically focus on the most discriminative features, and significantly improve the sensitivity to subtle patterns in rumor propagation. The experimental verification on three benchmark datasets of twitter15, twitter16, and Weibo, shows that the proposed PAGCN performs best among the 17 comparison models, and the accuracy rates on twitter15 and Weibo datasets are 90.9% and 93.9%, respectively, which confirms the effectiveness of the framework in capturing propagation structure and semantic information at the same time. Full article

Accurate prediction of effluent quality indicators is essential for ensuring stable operation and regulatory compliance in wastewater treatment plants. However, the inherent spatial distribution and temporal fluctuations of wastewater processes present significant challenges for modeling. In this study, we propose a dynamic multi-scale spatio-temporal Transformer (DMST-Transformer) with a symmetric architecture to enhance prediction accuracy in complex wastewater systems. Unlike conventional asymmetric designs, the DMST-Transformer extracts spatial and temporal features in parallel using a spatial graph convolutional network and a multi-scale self-attention mechanism coupled with a dynamic self-tuning module. The model is evaluated on a full-process dataset collected from a municipal wastewater treatment plant, with biochemical oxygen demand selected as the target indicator. Experimental results on test data show that the DMST-Transformer achieves a coefficient of determination of 0.93, root mean square error of 1.40 mg/L, and mean absolute percentage error of 6.61%, outperforming classical models such as linear regression, partial least squares, and graph convolutional networks, as well as advanced deep learning baselines including Transformer and ST-Transformer. Ablation studies confirm the complementary effectiveness of the spatial and temporal modules, and computational time comparisons demonstrate the model’s suitability for real-time applications. These results validate the practical potential of the DMST-Transformer for robust effluent quality monitoring in wastewater treatment plants. Future research will focus on scaling the model to larger and more diverse datasets, extending it to predict additional water quality indicators, and deploying it in real-time environmental monitoring systems to support intelligent water resource management. Full article

Exploring food’s rich composition and nutritional information is crucial for understanding and improving people’s dietary preferences and health habits. However, most existing food recommendation models tend to overlook the impact of food choices on health. Moreover, due to the high sparsity of food-related data, most existing methods fail to effectively leverage the multi-dimensional information of food, resulting in poorly learned node embeddings. Considering these factors, we propose a cross-view contrastive heterogeneous-graph learning method for healthy food recommendation (CGHF). Specifically, CGHF constructs feature relation graphs and heterogeneous information connection graphs by integrating user–food interaction data and multi-dimensional information about food. We then design a cross-view contrastive learning task to learn node embeddings from multiple views collaboratively. Additionally, we introduce a meta-path-based local aggregation mechanism to aggregate node information in local subgraphs, thus allowing for the efficient capturing of users’ dietary preferences. Experimental comparisons with various advanced models demonstrate the effectiveness of the proposed model. Full article

Salient object detection is a challenging task in the field of computer vision. The graph-based model has attracted lots of research attention and achieved remarkable progress in this task, which constructs graphs to formulate the intrinsic structure of any image. Nevertheless, the existing graph-based salient object detection methods still have certain limitations and face two major challenges: (1) Previous graphs are constructed by the Gaussian kernel, but they are often corrupted by original noise. (2) They fail to capture common representations and complementary diversity of multi-view features. Both of these degrade saliency performance. In this paper, we propose a novel method, called multi-scale pure graphs with multi-view subspace clustering for salient object detection. Its main contribution is a new, two-stage graph, constructed and constrained by multi-view subspace clustering with sparsity and low rank. One of the advantages is that the multi-scale pure graphs upgrade the saliency performance from the propagation of noise in the graph matrix. Another advantage is that the multi-scale pure graphs exploit consistency and complementary information among multi-view features, which can effectively boost the capability of the graphs. In addition, to verify the impact of the symmetry of the multi-scale pure graphs on the salient object detection performance, we compared the proposed two-stage graphs, which included cases considering the multi-scale pure graphs and those not considering the multi-scale pure graphs. The experimental results were derived using several RGB benchmark datasets and several state-of-the-art algorithms for comparison. The results demonstrate that the proposed method outperforms the state-of-the-art approaches in terms of multiple standard evaluation metrics. This paper reveals that multi-view subspace clustering is beneficial in promoting graph-based saliency detection tasks. Full article

Rolling bearings are prone to failure, meaning that research on intelligent fault diagnosis is crucial in relation to this key transmission component in rotating machinery. The application of deep learning (DL) has significantly advanced the development of intelligent fault diagnosis. This paper proposes a novel method for rolling bearing fault diagnosis based on the fractional constant Q non-stationary Gabor transform (FCO-NSGT) and VMamba-Conv. Firstly, a rolling bearing fault experimental platform is established and the vibration signals of rolling bearings under various working conditions are collected using an acceleration sensor. Secondly, a kurtosis-to-entropy ratio (KER) method and the rotational kernel function of the fractional Fourier transform (FRFT) are proposed and applied to the original CO-NSGT to overcome the limitations of the original CO-NSGT, such as the unsatisfactory time–frequency representation due to manual parameter setting and the energy dispersion problem of frequency-modulated signals that vary with time. A lightweight fault diagnosis model, VMamba-Conv, is proposed, which is a restructured version of VMamba. It integrates an efficient selective scanning mechanism, a state space model, and a convolutional network based on SimAX into a dual-branch architecture and uses inverted residual blocks to achieve a lightweight design while maintaining strong feature extraction capabilities. Finally, the time–frequency graph is inputted into VMamba-Conv to diagnose rolling bearing faults. This approach reduces the number of parameters, as well as the computational complexity, while ensuring high accuracy and excellent noise resistance. The results show that the proposed method has excellent fault diagnosis capabilities, with an average accuracy of 99.81%. By comparing the Adjusted Rand Index, Normalized Mutual Information, F1 Score, and accuracy, it is concluded that the proposed method outperforms other comparison methods, demonstrating its effectiveness and superiority. Full article

Accurate forecasting of tropical cyclone (TC) tracks is critical for disaster preparedness and risk mitigation. While traditional numerical weather prediction (NWP) systems have long served as the backbone of operational forecasting, they face limitations in computational cost and sensitivity to initial conditions. In recent years, deep learning (DL) has emerged as a promising alternative, offering data-driven modeling capabilities for capturing nonlinear spatiotemporal patterns. This paper presents a comprehensive review of DL-based approaches for TC track forecasting. We categorize all DL-based TC tracking models according to the architecture, including recurrent neural networks (RNNs), convolutional neural networks (CNNs), Transformers, graph neural networks (GNNs), generative models, and Fourier-based operators. To enable rigorous performance comparison, we introduce a Unified Geodesic Distance Error (UGDE) metric that standardizes evaluation across diverse studies and lead times. Based on this metric, we conduct a critical comparison of state-of-the-art models and identify key insights into their relative strengths, limitations, and suitable application scenarios. Building on this framework, we conduct a critical cross-model analysis that reveals key trends, performance disparities, and architectural tradeoffs. Our analysis also highlights several persistent challenges, such as long-term forecast degradation, limited physical integration, and generalization to extreme events, pointing toward future directions for developing more robust and operationally viable DL models for TC track forecasting. To support reproducibility and facilitate standardized evaluation, we release an open-source UGDE conversion tool on GitHub. Full article

The evaluation of large language models (LLMs) increasingly relies on other LLMs acting as automated judges. While this approach offers scalability and efficiency, it raises serious concerns regarding evaluator reliability, positional bias, and ranking stability. This paper presents a scalable framework for diagnosing positional bias and instability in LLM-based evaluation by using controlled pairwise comparisons judged by multiple independent language models. The system supports mirrored comparisons with reversed response order, prompt injection, and surface-level perturbations (e.g., paraphrasing, lexical noise), enabling fine-grained analysis of evaluator consistency and verdict robustness. Over 3600 pairwise comparisons were conducted across five instruction-tuned open-weight models using ten open-ended prompts. The top-performing model (gemma:7b-instruct) achieved a 66.5% win rate. Evaluator agreement was uniformly high, with 100% consistency across judges, yet 48.4% of verdicts reversed under mirrored response order, indicating strong positional bias. Kendall’s Tau analysis further showed that local model rankings varied substantially across prompts, suggesting that semantic context influences evaluator judgment. All evaluation traces were stored in a graph database (Neo4j), enabling structured querying and longitudinal analysis. The proposed framework provides not only a diagnostic lens for benchmarking models but also a blueprint for fairer and more interpretable LLM-based evaluation. These findings underscore the need for structure-aware, perturbation-resilient evaluation pipelines when benchmarking LLMs. The proposed framework offers a reproducible path for diagnosing evaluator bias and ranking instability in open-ended language tasks. Future work will apply this methodology to educational assessment tasks, using rubric-based scoring and graph-based traceability to evaluate student responses in technical domains. Full article

Robotic search of people in human-centered environments, including healthcare settings, is challenging, as autonomous robots need to locate people without complete or any prior knowledge of their schedules, plans, or locations. Furthermore, robots need to be able to adapt to real-time events that can influence a person’s plan in an environment. In this paper, we present MLLM-Search, a novel zero-shot person search architecture that leverages multimodal large language models (MLLM) to address the mobile robot problem of searching for a person under event-driven scenarios with varying user schedules. Our approach introduces a novel visual prompting method to provide robots with spatial understanding of the environment by generating a spatially grounded waypoint map, representing navigable waypoints using a topological graph and regions by semantic labels. This is incorporated into an MLLM with a region planner that selects the next search region based on the semantic relevance to the search scenario and a waypoint planner that generates a search path by considering the semantically relevant objects and the local spatial context through our unique spatial chain-of-thought prompting approach. Extensive 3D photorealistic experiments were conducted to validate the performance of MLLM-Search in searching for a person with a changing schedule in different environments. An ablation study was also conducted to validate the main design choices of MLLM-Search. Furthermore, a comparison study with state-of-the-art search methods demonstrated that MLLM-Search outperforms existing methods with respect to search efficiency. Real-world experiments with a mobile robot in a multi-room floor of a building showed that MLLM-Search was able to generalize to new and unseen environments. Full article