7 December 2024 in Neurocomputing
6 July 2023 in IEEE Transactions on Neural Networks and Learning Systems
Recent developments in multiagent consensus problems have heightened the role of network topology when the agent number increases largely. The existing works assume that the convergence evolution typically proceeds over a peer-to-peer architecture where agents are treated equally and communicate directly with perceived one-hop neighbors, thus resulting in slower convergence speed. In this article, we first extract the backbone network topology to provide a hierarchical organization over the original multiagent system (MAS). Second, we introduce a geometric convergence method based on the constraint set (CS) under periodically extracted switching-backbone topologies. Finally, we derive a fully decentralized framework named hierarchical switching-backbone MAS (HSBMAS) that is designed to conduct agents converge to a common stable equilibrium. Provable connectivity and convergence guarantees of the framework are provided when the initial topology is connected. Extensive simulation results on different-type and varying-density topologies have shown the superiority of the proposed framework.
26 August 2024 in IEEE Transactions on Knowledge and Data Engineering
With the rapid development of wireless communication and localization technologies, the easier collection of trajectory data can bring potential data-driven value. Recently, there has been an increasing interest in how to publish trajectory dataset without revealing personal information. However, since the large-scale and real-world sequential trajectory dataset presents a heterogeneous regional distribution, the existing study ignores the relationship between privacy budget allocation and spatial characteristics, resulting in unreasonable continuity and mapping distortion, and thus lowering the utility of the synthetic dataset. To address this problem, we propose a probability distribution model named Adaptive grid-based Weighted Differential Privacy (AWDP). First, trajectories are adaptively discretized into the multi-resolution grid structures to make trajectories more uniformly distributed and less disturbed by the noise. Second, we allocate different weighted budgets for different grids according to density-based regional characteristics. Third, a spatio-temporal continuity maintenance method is designed to solve unrealistic direction- and density-based continuity deviations of synthetic trajectories. An application system is developed for demonstration purposes which is available online at http://qgailab.com/awdp/ . The extensive experiments on three datasets demonstrate that AWDP performs significantly better than the state-of-the-art model in preserving the density distribution of the original trajectories with differential privacy guarantee and high utility.
2 December 2024 in IEEE Transactions on Mobile Computing
Modern intelligent vehicles (IVs) are equipped with a variety of sensors and communication modules, empowering Advanced Driver Assistance Systems (ADAS) and enabling inter-vehicle connectivity. This paper focuses on multi-vehicle cooperative perception, with a primary objective of achieving low latency. The task involves nearby cooperative vehicles sending their camera data to an edge server, which then merges the local views to create a global traffic view. While multi-camera perception has been actively researched, existing solutions often rely on deep learning models, resulting in excessive processing latency. In contrast, we propose leveraging the state estimation technique from the robotics field for this task. We explicitly model and solve for the system state, addressing additional challenges brought by object mobility and vision obstruction. Furthermore, we introduce a progressive state estimation pipeline to further accelerate system state notifications, supported by a motion prediction method that optimizes position accuracy and perception smoothness. Experimental results demonstrate the superiority of our approach over the deep learning method, with 12.0 × to 27.4 × reductions in server processing delay, while maintaining mean absolute errors below 1 m.
2 July 2022 in Applied Intelligence
25 December 2024 in IEEE Transactions on Circuits and Systems for Video Technology
The task of live video analytics relies on real-time object tracking that typically involves computationally expensive deep neural network (DNN) models. In practice, it has become essential to process video data on edge devices deployed near the cameras. However, these edge devices often have very limited computing resources and thus suffer from poor tracking accuracy. Through a measurement study, we identify three major factors contributing to the performance issue: outdated detection results, tracking error accumulation, and ignorance of new objects. We introduce a novel approach, called Predict & Correct based Tracking , or PCTrack, to systematically address these problems. Our design incorporates three innovative components: (1) a Predictive Detection Propagator that rapidly updates outdated object bounding boxes to match the current frame through a lightweight prediction model; (2) a Frame Difference Corrector that refines the object bounding boxes based on frame difference information; and (3) a New Object Detector that efficiently discovers newly appearing objects during tracking. Experimental results show that our approach achieves remarkable accuracy improvements, ranging from 19.4% to 34.7%, across diverse traffic scenarios, compared to state of the art methods.