Accurate load decomposition and behavior pattern recognition are critical for efficient energy management and personalized demand response in modern smart grids. However, existing methods often struggle to capture complex temporal dependencies in electricity consumption data and rely heavily on manual feature engineering, limiting their accuracy and adaptability. To address these challenges, this paper proposes BLIP, a novel BiGRU-based framework for load decomposition and electricity consumption behavior pattern recognition. By leveraging the bidirectional temporal modeling capability of BiGRU networks, BLIP accurately decomposes aggregated load signals into distinct components, capturing both past and future dependencies. The framework further exploits the decomposed load features to recognize personalized electricity consumption patterns, enabling fine-grained differentiation of user or device behaviors. Unlike traditional approaches, BLIP performs end-to-end learning, improving robustness and generalization in complex power system environments. BLIP incorporates a unique adaptation to the BiGRU architecture, enabling better handling of irregular load fluctuations and introducing a novel attention mechanism for enhanced behavior pattern recognition. This adaptation is particularly effective in addressing challenges like inaccurate peak load forecasting and excessive energy consumption, which are common in smart grid systems. Experimental results on real-world datasets demonstrate that BLIP significantly enhances both load disaggregation accuracy and behavioral pattern identification, supporting more intelligent and efficient energy management.

Enhancing bus movements along urban arterial roads to reduce waiting times and stops at intersections is critical for improving overall bus operational efficiency. Although extensive research has investigated transit signal priority (TSP) and bus guidance to achieve these objectives, mixed traffic conditions without dedicated bus lanes remain constrained due to inefficient traffic organization and underutilized intersection lanes. To address these limitations, this study proposes a multi-strategy bus guidance approach for connected environments that maximizes intersection lane utilization through right-turn lane sharing (RTS), particularly in China where dedicated and uncontrolled right-turn lanes are common. The approach is implemented via a dual-stage hybrid Bayesian network (HBN): Stage I forecasts bus travel times and queuing states using real-time bus positions and signal states data; Stage II determines the combination of speed guidance, dwell-time management, and RTS by accounting for passenger car speed distributions and allowable dwell times at stops. We evaluated the approach in a SUMO simulation environment of a real-world urban arterial in Kunshan, China, under four demand scenarios with varying volume-to-capacity (V/C) ratios of total traffic flow. Simulation results demonstrated that the proposed approach significantly reduced bus waiting times and stops at intersections. Under low-to-moderate demand situations, the combination of three strategies outperformed other strategies, and RTS-incorporated strategies achieved the greatest benefits under high-demand conditions.

The acquisition of real-time and accurate traffic arrival information is of vital importance for proactive traffic control systems, especially in partially connected vehicle environments. License plate recognition (LPR) data that record both vehicle departures and identities are proven to be desirable in reconstructing lane-based arrival curves in previous works. Existing LPR data-based methods are predominantly designed for reconstructing historical arrival curves. For real-time reconstruction of multi-lane urban roads, it is pivotal to determine the lane choice of real-time link-based arrivals, which has not been exploited in previous studies. In this study, we propose a Bayesian deep learning approach for real-time lane-based arrival curve reconstruction, in which the lane choice patterns and uncertainties of link-based arrivals are both characterized. Specifically, the learning process is designed to effectively capture the relationship between partially observed link-based arrivals and lane-based arrivals, which can be physically interpreted as lane choice proportion. Moreover, the lane choice uncertainties are characterized using Bayesian parameter inference techniques, minimizing arrival curve reconstruction uncertainties, especially in low LPR data matching rate conditions. Real-world experiment results conducted in multiple matching rate scenarios demonstrate the superiority and necessity of lane choice modeling in reconstructing arrival curves.

Trajectory prediction is crucial for autonomous vehicle (AV) trajectory planning. The deep learning based trajectory prediction models are easily manipulated by cyber attack such as adversarial attack or confidential information tampering. Current research in adversarial attack typically relies on vehicle physical motion boundaries to conduct linear search, which limits the diversity of samples and covers up the vulnerabilities of model. Moreover, the reckless driving behaviors underlying the generated trajectory samples can be easily detected and smoothed. In this study, a dual constraint optimization framework for adversarial attack is developed. The proposed framework integrates hard constraint of physical boundary with soft constraint of driving risk map to simulate the actual vehicles interaction. Subsequently, Stochastic Gradient Descent (SGD) incorporates Hard-Soft constraint to increase the search space of local optimal solution. The high-precision vehicle trajectory data (sampling interval 0.1s) from the Next Generation Simulation (NGSIM) dataset supports microscopic traffic flow analysis and is used for validating our methods. The vulnerability of the prediction model is revealed from number of attack frames and input features. Results show that our proposed method increases the Average Displacement Errors (ADE) by 42.04% and Final Displacement Error (FDE) by 24.19% compared to the state-of-the-art method.

Accurately estimating spatiotemporal traffic states on freeways is a significant challenge due to limited sensor deployment and potential data corruption. In this study, we propose an efficient and robust low-rank model for precise spatiotemporal traffic speed state estimation (TSE) using low-penetration vehicle trajectory data. Leveraging traffic wave priors, an oblique grid-based matrix is first designed to transform the inherent dependencies of spatiotemporal traffic states into the algebraic low-rankness of a matrix. Then, with the enhanced traffic state low-rankness in the oblique matrix, a low-rank matrix completion method is tailored to explicitly capture spatiotemporal traffic propagation characteristics and precisely reconstruct traffic states. In addition, an anomaly-tolerant module based on a sparse matrix is developed to accommodate corrupted data input and thereby improve the TSE model robustness. Notably, driven by the understanding of traffic waves, the computational complexity of the proposed efficient method is only correlated with the problem size itself, not with dataset size and hyperparameter selection prevalent in existing studies. Extensive experiments demonstrate the effectiveness, robustness, and efficiency of the proposed model. The performance of the proposed method achieves up to a 12% improvement in Root Mean Squared Error (RMSE) in the TSE scenarios and an 18% improvement in RMSE in the robust TSE scenarios, and it runs more than 20 times faster than the state-of-the-art (SOTA) methods.

Rapid advancements in traffic monitoring and sensing technologies have permitted the multiplex and democratized gathering of numerous traffic data (e.g. speed, volume), depicting identical traffic dynamics from various but complementary views. Incomplete values are ubiquitous in these data, which undermines their utility in subsequent applications. In order to manage and enhance traffic data quality, most existing methods recover single traffic variable data independently based on intra-view spatiotemporal correlations, while the inter-view complementarities are ignored. In this paper, we leverage both intra-view and inter-view correlations for multiple traffic variable data simultaneous recovery. To explore the inter-view relationships, a multi-view subspace consistency learning module is developed to bridge connections and activate complementarities among multi-view traffic data. Specifically, the latent subspace features of each data view are extracted and organized as a multi-view subspace tensor with low-rank regularization. The multi-view low-rank tensor captures the consistent subspace structure across multiple data views while reserving unique features within each data view. To characterize the intra-view dependencies, a tensor-based low-rank representation is presented to explore the distinct spatiotemporal patterns within single-view traffic data. For model validation, we additionally design a nonrandom missing pattern to simulate sensor permanent failure cases in practice. Extensive experiments implemented on three real-world multi-view traffic datasets demonstrate the effectiveness and robustness of the proposed model.

Monitoring-based traffic participant detection (TPD) is a highly desirable but challenging task. So far, deep learning-based methods have attained significant improvements on the TPD task, but oftentimes fail in urban mixed traffic due to the lack of relevant datasets and suitable detectors. In this study, we propose a large and detailed dataset named SEU_PML specialized for monitoring-based TPD in urban mixed traffic. This dataset contains a total of 270,684 objects annotated with 2D bounding box and covers 13 sub-categories, having (i) high-resolution images (from$1920\times 1080$to$4096\times 2160$pixels), (ii) high-quality annotation (annotation accuracy reaches 98%), and (iii) rich traffic scenarios covering diverse traffic scenes as well as different weather and illumination conditions. The mixed traffic along with high-quality annotation bring about a variety of small objects. To further address the issue on small object detection, we propose a novel detector named YOLO SOD, which embeds a super-resolution feature extraction module and uses knowledge distillation to learn the knowledge how the detector with high-resolution inputs perceives small objects. Moreover, a novel loss function named S-IoU is designed to enable YOLO SOD to focus more on small objects. Experimental results show that (1) the YOLO SOD detector has an increased mAP of 1.58% and operates approximately four times faster when compared to a state-of-art detector; (2) the detectors trained on the SEU_PML dataset have a strong transferability and could be well applied to traffic participant detection in urban mixed traffic. Our dataset is now available athttps://github.com/vvgoder/SEU_PML_Dataset.

Link progression speed is a key characteristic of urban traffic flow and is essential to developing effective signal coordination schemes. Typically, it is empirically determined as a fixed value regardless of its stochastic nature. Previous studies have proposed both analytical and simulation models to investigate the vehicle progression delay caused by different sources (i.e., midblock traffic, pedestrian crossing, and on-street parking). However, these models need explicit modeling efforts and an intensive collection of traffic data. This paper provides a practical approach that is easy to implement and accurate enough to characterize link-specific progression speed and its uncertainty. The pure input is the low-frequency probe vehicle data which is the most widely available and large-scale data source to provide spatiotemporal traffic information. By assuming the effects of progression delay are relatively stable during the same period of a day, the instantaneous speed of probe vehicles is aggregated to calculate progression speed at different locations of a link. To describe the continuous vehicle progression process and capture realistic driving behaviors, two latent progression states (i.e., normal and cautious driving states) and their spatial correlation are encoded to each cell of a link and formulated in a Hidden Markov Model (HMM). The effectiveness of the proposed method has been validated using field data, and the concept of reliable green bandwidth is also demonstrated to discuss the application of the proposed method to enhance the reliability of signal coordination.

Accurate and reliable traffic state identification is crucial to developing responsive and proactive traffic management applications. In this study, the problem of vehicle discharge state identification at signalized intersections is investigated, which focuses on the vehicle discharge process during the green interval. Instead of using detailed vehicle trajectory data and treating the observations of vehicles independently, this study formulates the vehicle discharge process in a Hidden Markov Model (HMM) framework using sequential observations of vehicle travel time and discharge headway as inputs. Three vehicle discharge states (i.e., overflow, single stop, and free arrival) are encoded as latent states, and a restricted left-to-right state transition matrix is imposed to respect the nature of the vehicle discharge process in the real world. The standard HMM is further extended to incorporate two informative covariates to parameterize the probabilities of the initial states and state transitions. The proposed models have been validated on the Next Generation Simulation (NGSIM) dataset. Compared to a benchmark model, the proposed models show their strength in correctly inferring the vehicle discharge state and are more reliable to use in presence of random missing observations. The effectiveness of covariate incorporation is also investigated, and several extended applications of the proposed models are discussed.