arXiv subjects

Zirui Li

Publications and source records attributed to Zirui Li.

81 records · Page 5Linked to original sources

arXiv2020

Stochastic Graph Recurrent Neural Network

Representation learning over graph structure data has been widely studied due to its wide application prospects. However, previous methods mainly focus on static graphs while many real-world graphs evolve over time. Modeling such evolution is important for predicting properties of unseen networks. To resolve this challenge, we propose SGRNN, a novel neural architecture that applies stochastic latent variables to simultaneously capture the evolution in node attributes and topology. Specifically, deterministic states are separated from stochastic states in the iterative process to suppress mutual interference. With semi-implicit variational inference integrated to SGRNN, a non-Gaussian variational distribution is proposed to help further improve the performance. In addition, to alleviate KL-vanishing problem in SGRNN, a simple and interpretable structure is proposed based on the lower bound of KL-divergence. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed model. Code is available at https://github.com/StochasticGRNN/SGRNN.

stat.ML↗

arXiv2020

A Survey on Sensor Technologies for Unmanned Ground Vehicles

Unmanned ground vehicles have a huge development potential in both civilian and military fields, and have become the focus of research in various countries. In addition, high-precision, high-reliability sensors are significant for UGVs' efficient operation. This paper proposes a brief review on sensor technologies for UGVs. Firstly, characteristics of various sensors are introduced. Then the strengths and weaknesses of different sensors as well as their application scenarios are compared. Furthermore, sensor applications in some existing UGVs are summarized. Finally, the hotspots of sensor technologies are forecasted to point the development direction.

cs.CV↗

arXiv2020

Driver Behavior Modelling at the Urban Intersection via Canonical Correlation Analysis

The urban intersection is a typically dynamic and complex scenario for intelligent vehicles, which exists a variety of driving behaviors and traffic participants. Accurately modelling the driver behavior at the intersection is essential for intelligent transportation systems (ITS). Previous researches mainly focus on using attention mechanism to model the degree of correlation. In this research, a canonical correlation analysis (CCA)-based framework is proposed. The value of canonical correlation is used for feature selection. Gaussian mixture model and Gaussian process regression are applied for driver behavior modelling. Two experiments using simulated and naturalistic driving data are designed for verification. Experimental results are consistent with the driver's judgment. Comparative studies show that the proposed framework can obtain a better performance.

cs.CV↗

arXiv2019

From perception to control: an autonomous driving system for a formula student driverless car

This paper introduces the autonomous system of the "Smart Shark II" which won the Formula Student Autonomous China (FSAC) Competition in 2018. In this competition, an autonomous racecar is required to complete autonomously two laps of unknown track. In this paper, the author presents the self-driving software structure of this racecar which ensure high vehicle speed and safety. The key components ensure a stable driving of the racecar, LiDAR-based and Vision-based cone detection provide a redundant perception; the EKF-based localization offers high accuracy and high frequency state estimation; perception results are accumulated in time and space by occupancy grid map. After getting the trajectory, a model predictive control algorithm is used to optimize in both longitudinal and lateral control of the racecar. Finally, the performance of an experiment based on real-world data is shown.

cs.RO↗

arXiv2019

Choosing Transfer Languages for Cross-Lingual Learning

Cross-lingual transfer, where a high-resource transfer language is used to improve the accuracy of a low-resource task language, is now an invaluable tool for improving performance of natural language processing (NLP) on low-resource languages. However, given a particular task language, it is not clear which language to transfer from, and the standard strategy is to select languages based on ad hoc criteria, usually the intuition of the experimenter. Since a large number of features contribute to the success of cross-lingual transfer (including phylogenetic similarity, typological properties, lexical overlap, or size of available data), even the most enlightened experimenter rarely considers all these factors for the particular task at hand. In this paper, we consider this task of automatically selecting optimal transfer languages as a ranking problem, and build models that consider the aforementioned features to perform this prediction. In experiments on representative NLP tasks, we demonstrate that our model predicts good transfer languages much better than ad hoc baselines considering single features in isolation, and glean insights on what features are most informative for each different NLP tasks, which may inform future ad hoc selection even without use of our method. Code, data, and pre-trained models are available at https://github.com/neulab/langrank

cs.CL↗

arXiv2018

Towards a General-Purpose Linguistic Annotation Backend

Language documentation is inherently a time-intensive process; transcription, glossing, and corpus management consume a significant portion of documentary linguists' work. Advances in natural language processing can help to accelerate this work, using the linguists' past decisions as training material, but questions remain about how to prioritize human involvement. In this extended abstract, we describe the beginnings of a new project that will attempt to ease this language documentation process through the use of natural language processing (NLP) technology. It is based on (1) methods to adapt NLP tools to new languages, based on recent advances in massively multilingual neural networks, and (2) backend APIs and interfaces that allow linguists to upload their data. We then describe our current progress on two fronts: automatic phoneme transcription, and glossing. Finally, we briefly describe our future directions.

cs.CL↗

arXiv2018

Learning and Generalizing Motion Primitives from Driving Data for Path-Tracking Applications

Considering the driving habits which are learned from the naturalistic driving data in the path-tracking system can significantly improve the acceptance of intelligent vehicles. Therefore, the goal of this paper is to generate the prediction results of lateral commands with confidence regions according to the reference based on the learned motion primitives. We present a two-level structure for learning and generalizing motion primitives through demonstrations. The lower-level motion primitives are generated under the path segmentation and clustering layer in the upper-level. The Gaussian Mixture Model(GMM) is utilized to represent the primitives and Gaussian Mixture Regression (GMR) is selected to generalize the motion primitives. We show how the upper-level can help to improve the prediction accuracy and evaluate the influence of different time scales and the number of Gaussian components. The model is trained and validated by using the driving data collected from the Beijing Institute of Technology (BIT) intelligent vehicle platform. Experiment results show that the proposed method can extract the motion primitives from the driving data and predict the future lateral control commands with high accuracy.

cs.LG↗

arXiv2018

Theoretical Limits and Scaling Laws for Electrokinetic Molecular Concentration via Ion Concentration Polarization

We develop the first theoretical model for the analytical description of ion concentration polarization (ICP)-based electrokinetic molecular concentration, which had not been possible due to the extraordinary complexity of the system. We define the two separate limits for the enrichment factor achievable in a given system and derive the scaling laws for critical parameters, which are validated by numerical simulations and experiments. This work provides clear theoretical explanations on the diverse experimental behaviors previously observed yet unexplainable, while setting solid foundation for the engineering of ICP-based concentrators and other fluid-coupled electrokinetic systems.

physics.flu-dyn↗

arXiv2017

Accurate Multi-physics Numerical Analysis of Particle Preconcentration Based on Ion Concentration Polarization

This paper studies mechanism of preconcentration of charged particles in a straight micro-channel embedded with permselective membranes, by numerically solving coupled transport equations of ions, charged particles and solvent fluid without any simplifying assumptions. It is demonstrated that trapping and preconcentration of charged particles are determined by the interplay between drag force from the electroosmotic fluid flow and the electrophoretic force applied trough the electric field. Several insightful characteristics are revealed, including the diverse dynamics of co-ions and counter ions, replacement of co-ions by focused particles, lowered ion concentrations in particle enriched zone, and enhanced electroosmotic pumping effect etc. Conditions for particles that may be concentrated are identified in terms of charges, sizes and electrophoretic mobilities of particles and co-ions. Dependences of enrichment factor on cross-membrane voltage, initial particle concentration and buffer ion concentrations are analyzed and the underlying reasons are elaborated. Finally, post priori a condition for validity of decoupled simulation model is given based on charges carried by focused charge particles and that by buffer co-ions. These results provide important guidance in the design and optimization of nanofluidic preconcentration and other related devices.

physics.flu-dyn↗