WXWeng Xiao-Xiong

Weng Xiao-Xiong

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Weng Xiao-Xiong has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Efficient and Robust Driver Fatigue Detection Framework Based on the Visual Analysis of Eye States

    by Yancheng Ling, Xiaoxiong Weng

    Fatigue detection based on vision is widely employed in vehicles due to its real-time and reliable detection results. With the coronavirus disease (COVID-19) outbreak, many proposed detection systems based on facial characteristics would be unreliable due to the face covering with the mask. In this paper, we propose a robust visual-based fatigue detection system for monitoring drivers, which is robust regarding the coverings of masks, changing illumination and head movement of drivers. Our system has three main modules: face key point alignment, fatigue feature extraction and fatigue measurement based on fused features. The innovative core techniques are described as follows: (1) a robust key point alignment algorithm by fusing global face information and regional eye information, (2) dynamic threshold methods to extract fatigue characteristics and (3) a stable fatigue measurement based on fusing percentage of eyelid closure (PERCLOS) and proportion of long closure duration blink (PLCDB). The excellent performance of our proposed algorithm and methods are verified in experiments. The experimental results show that our key point alignment algorithm is robust to different scenes, and the performance of our proposed fatigue measurement is more reliable due to the fusion of PERCLOS and PLCDB.


  • ANAS: Asymptotic NAS for large-scale proxyless search and multi-task transfer learning

    by Bangquan Xie, Zongming Yang, Liang Yang, Ruifa Luo, Jun Lu, Ailin Wei, Xiaoxiong Weng, Bing Li


  • Open Access

    Detecting Invalid Associations between Fare Machines and Metro Stations Using Smart Card Data

    by Pengfei Zhang, Zhenliang Ma, Xiaoxiong Weng

    Data quality is essential for its authentic usage in analysis and applications. The large volume of automated collection data inevidently suffers from data quality issues including data missing and invalidity. This paper deals with an invalid data problem in the automated fare collection (AFC) database caused by the erroneous association between the fare machines and metro stations, e.g., a fare machine located at Station A is wrongly associated with Station B in the AFC database. It could lead to inappropriate fare charges in a distance-based fare system and cause analysis bias for planning/operation practice. We propose a tensor decomposition and isolation forest-based approach to detect and correct the invalid associated fare machines in the system. The tensor decomposition extracts features of passenger flows and travel times passing through fare machines. The isolation forest coupled with a neural network (NN) takes these features as inputs to detect the wrongly associated fare machines and infer the correct association stations. Case studies using data from a metro system show that the proposed detection approach achieves over 90% accuracy in detecting the invalid associations for up to 35% invalid associations. The inferred association has a 90% accuracy even when the invalid association ratio reaches 40%. The proposed data-driven invalid data detection method is useful for large-scale data management in terms of data quality check and fix.


  • Open Access

    Driver Eye Location and State Estimation Based on a Robust Model and Data Augmentation

    by Yancheng Ling, Ruifa Luo, Xiaoxian Dong, Xiaoxiong Weng

    Eye state evaluation is crucial for vision-based driver fatigue detection. With the outbreak of COVID-19, many proposed models for eye location and state evaluation based on facial landmarks are unreliable due to mask coverings. In this paper, we proposed a robust facial landmark location model for eye location and state evaluation. First, we develop an existing lightweight face alignment model for eye key point locations that is robust in large poses. Then, to develop the performance of our model in a complex driving environment such as an environment with mask coverings, changing illumination, etc., we design a method to augment the training data set based on the original landmark data set without any extra cost. Finally, some facial landmarks around the eyes are extracted, and the eye aspect ratio (EAR) is introduced to evaluate the eye state based on eye key points. The experiment shows that our model achieves significantly improved landmark location performance on a driving simulation data set due to data augmentation. We tested our model on the BioID data set to measure the eye state evaluation performance, and the results showed that our model obtained satisfactory performance with an accuracy of approximately 97.7%. Further testing on the driving simulation data set shows that our model is robust in different driving scenarios with an average accuracy of approximately 93.9%.


  • A Service Oriented Urban Traffic Simulation Platform on Grid

    by Qin-Min Hong, Xiao-Xiong Weng, Yu-An Tan

    Urban traffic congestion has become a major concern for many cities throughout the world. Traffic simulation is an important approach to studying a real or proposed traffic system. As one approach of traffic simulation, microscopic traffic simulation defines the behavior of each interactive object in the traffic network, such as a vehicle and a traffic light through an individual model so that we can observe the details of traffic information in a certain scenario. Since microscopic model requires large computational power and data storage power, new simulation system architecture is needed. In this paper we propose a service-oriented urban traffic simulation platform in grid environment. The simulation platform which combines grid and HLA(High Level Architecture). With HLA, a large-scale distributed simulation can be constructed using even a huge number of geographically distributed computing nodes. With grid it realizes resource sharing and promotes computing efficiency with grid in selection of optimal travel scheme. Simultaneously, it is the demonstration of practising and applying information grid technology. It can promote further study and development of traffic simulation technology and offer better services for traffic information users.

  • Multidimensional State Estimation Rules in Urban Traffic System Based on Rough Set Theory

    by Xiao-Xiong Weng, Dan Weng, Li-Ping Ye

    Traffic flow is a complex, changeful, nonlinear, unstructured, space time-varying and random system. With the foundation and operating of the Intelligent Traffic System, it is imperative to search for a traffic state estimation model, which is suitable for mixed-traffic in China. On the basic of analysis of the multidimensional state characteristics of mixed-traffic, using the Rough Set Theory, the four-dimensional state estimation model is founded. By data discretization and attribute reduction, the two-dimensional decision table is gained, and the rules of multidimensional state estimation in urban traffic system are presented. A case is given and it indicates that this method can eliminate the redundancy information of the system effectively and improve the precision of rule mining.

  • Analysis on Economy Factors for Choosing Taxi's Types

    by Gongxiang, Weng Xiao-Xiong, Pu Yun

    This paper is concerned with a debatable policy of choosing taxi types. Now prevalent in many urban transportation management departments, such a policy strongly favors automobiles of large displacement and rejects those of small displacement. Despite the joint policy of six national ministries and commissions that all restrictions on energy-saving environment-friendly automobiles of small displacement should be cancelled, a few cities still adopt a soft "forced-out" policy against the small-displacement taxis. Sometimes justified on the thin ground of improving the city's outlook, those policy often disregarded the local development of economy and the capability of local market. In choosing the taxi type, instead of focusing solely on a city's outlook,we argue for a policy-making strategy based on analysis of the economic factors such as fuel consumption, depreciation, comfort level and exhaust emission. Grounded on a comprehensive survey of passenger trip characteristics, our strategy would be sensitive to the market condition. As a basic guideline for policy-making, we argue that energy preservation, environmental protection and improvement of the city's outlook should be considered in descending priorities.

  • OGSA-Based Traffic Information System

    by Weng Xiao-Xiong, Hong Qin-Min, Tan Yu-An

    As a complicated system, the intelligent transportation system (ITS) encounters the difficulties of resource sharing and service coordination in conventional network environment, which influences the further development of ITS. The feature, which utilizes grid technology to establish traffic grid application environment to achieve sharing and coordination, offers a new way to resolve such problem. Information grid can provide stronger computing and more resource sharing by integrating heterogeneous computers for complicated distributed traffic system. This paper analyses the relation of traffic services and presents a traffic information system based on open grid service architecture standard (OGSA-based). The OGSA-based traffic information system realizes resource sharing and promotes computing efficiency with grid in selection of optimal travel scheme. Simultaneously, it is the demonstration of practising and applying information grid technology. It can promote further study and development of information grid technology and offer better services for traffic information users

  • Analysis of Spectrum and Prediction for Short-term Traffic Flow

    by Weng Xiaoxiong, Jian Jun

    In this paper, based on analysing spectrum of short-term traffic flow by FFT transformation in limited length, we make use of neutral network to forecast the direct data and every scales data which was decomposed and reconstructed by wavelet analysis. Comparing with two results, prediction of the composing data which has been decomposed and reconstructed by wavelet has better accuracy, it can prove that wavelet analysis has value for studying in prediction of short-term traffic flow.

  • Decouple Analysis on Distributed Architecture of Urban Traffic System

    by Weng Xiao-Xiong, Du Gao-Li, Ye Li-Ping, Weng Dan

    The establishment of traffic model suitable for ITS is an important aspect to promote the rapid development of urban traffic. The paper develops an urban traffic particle model based on practical observation of traffic flow, in which intersection is regarded as elementary granular unit and there are decoupled relations among them. Then the exercise mechanism of traffic flow is introduced, and a correlative model and its decoupled method are argued between units. Finally the paper takes practical data of two adjacent intersections for example. Signal cycle, traffic flows of each phase are used to analyze stability of elementary unit as time scale, state variables. Through computer simulation and analysis, modeling distributed traffic particle flow is feasible; the model provides theories basis for distributed architecture of intelligent transport system of cities