Baofu Wu

In the field of multivariate time series analysis, data completeness plays a crucial role in ensuring the accuracy and reliability of downstream tasks. However, in practical applications, factors such as measurement errors and equipment failures often lead to partial missing values in the data. Therefore, this paper introduces a novel model, focusing on how to efficiently handle missing values in multivariate time series and mitigate the potential negative impact of data incompleteness on subsequent tasks. In previous studies, researchers often adopted a single-perspective approach, separately considering the influence of the temporal dimension and the feature dimension, thereby overlooking the potential of dual-perspective fusion. This paper proposes TFITS, an innovative method for predicting missing values in multivariate time series data. TFITS approaches the problem from both the temporal and feature perspectives of time series data, leveraging the UNetFuse module to fuse feature maps generated from these two perspectives, thereby providing a more comprehensive solution to the missing value problem. Through this approach, TFITS can more effectively address missing values in multivariate time series data. Experimental results demonstrate that the TFITS model not only achieves excellent imputation performance but also exhibits superior and stable performance under different missing rate conditions.

Multivehicle collaborative perception is fundamental for realizing Level 4+ autonomous driving by enabling connected vehicles to share and integrate sensor data for enhanced situational awareness. Under emerging Internet of Things (IoT) architectures, fleets of vehicles form dynamic, decentralized networks. In practice, however, deployment is hampered by three core challenges: 1) transmission latency in vehicle-to-vehicle (V2V) links; 2) data transmission constrained by limited communication bandwidth; and 3) the complexity of fusing asynchronous, multisource data streams. To overcome these obstacles, this article presents STCo, a spatiotemporal context-aware and communication-efficient framework for multivehicle collaborative perception. First, a spatiotemporal context modeling mechanism is devised to enhance perceptual continuity and mitigate communication asynchrony in IoT environments. Second, a cross-vehicle sensor perspective disparity mining algorithm leverages distributed observations to extract high-value complementary information. Third, a multisource data fusion paradigm unifies diverse perception inputs into a unified representation from the ego vehicle’s perspective, thereby strengthening feature correlations. This article validates STCo on both the real-world V2V4Real dataset and the large-scale simulated OPV2V benchmark. Experimental results demonstrate that STCo outperforms state-of-the-art (SOTA) methods in detection accuracy while substantially reducing communication overhead, highlighting its efficacy and practicality for IoT-enabled autonomous driving systems.

In the era of big data, intelligent transportation systems are crucial for the development of smart cities, significantly impacting urban economic growth and planning. The integration of 6G networks and digital twin technology presents unprecedented opportunities to enhance urban traffic management through real-time data synchronization and high-fidelity simulations. Accurate traffic flow prediction is vital for congestion control, intelligent route planning, and effective urban traffic management. However, existing deep learning models often struggle to capture the complex spatio-temporal dependencies and dynamic spatial relationships inherent in urban traffic data, particularly in data-scarce environments. Given the spatial heterogeneity of urban data, where dense and sparse regions coexist, improving prediction accuracy in sparse areas is critical to ensuring overall forecasting performance. To address these challenges, we propose a novel framework called 6G-Enabled Digital Twin Collaborative Traffic Flow Prediction (DT-CTFP), which integrates advanced deep learning models within a 6G-supported digital twin environment. The framework leverages real-time data processing capabilities and ultra-low latency of 6G networks to capture complex traffic features and dynamic spatial dependencies. In data-rich regions, the Dynamic Graph Multi-Attention (DGMA) model is used to learn fine-grained spatio-temporal patterns, while for data-scarce regions, the Cross-Area Transfer Prediction (CATP) model utilizes meta-learning techniques to transfer knowledge from data-rich urban areas, improving prediction accuracy in areas with limited data. Experimental results demonstrate the superiority of the DT-CTFP framework, achieving up to 6% reductions in RMSE and 4% reductions in MAE across multiple datasets, highlighting its enhanced prediction accuracy and efficiency. These results emphasize the framework’s capacity to improve traffic management and vehicle-road cooperation within a digital twin smart city.

Intelligent vehicles, including autonomous vehicles and vehicles equipped with ADAS systems, are single-agent systems that navigate solely on the information collected by themselves. However, despite rapid advancements in hardware and algorithms, many accidents still occur due to the limited sensing coverage from a single-agent perception angle. These tragedies raise a critical question of whether single-agent autonomous driving is safe. Preliminary investigations on this safety issue led us to create a C-V2X-enabled collaborative autonomous driving framework (CCAD) to observe the driving circumstance from multiple perception angles. Our framework uses C-V2X technology to connect infrastructure with vehicles and vehicles with vehicles to transmit safety-critical information and to add safety redundancies. By enabling these communication channels, we connect previously independent single-agent vehicles and existing infrastructure. This paper presents a prototype of our CCAD framework with RSU and OBU as communication devices and an edge-computing device for data processing. We also present a case study of successfully implementing an infrastructure-based collaborative lane-keeping with the CCAD framework. Our case study evaluations demonstrate that the CCAD framework can transmit, in real-time, personalized lane-keeping guidance information when the vehicle cannot find the lanes. The evaluations also indicate that the CCAD framework can drastically improve the safety of single-agent intelligent vehicles and open the doors to many more collaborative autonomous driving applications.

Autonomous Driving (AD) has entered a period of rapid development in recent years. With the amount of sensors and control logics installed increasing tremendously to guarantee robustness, a big challenge is posed for AD middleware. Both the academia and the industry are eager for an investigation of the performance of middlewares in Autonomous Driving Vehicles (AVs). To fill this gap, we summarize typical communication scenarios of AVs and evaluate different communication mechanisms of three popular open-source middlewares comprehensively. Besides, we construct a benchmark pack named ComP which consists of a perception communication scenario and a group of real AD applications for researchers to assess middleware performance. Our findings provide useful guidelines for researchers and insightful optimization advice for designing middlewares.