Wei Wang

Bio: Wei Wang is an academic researcher. The author has contributed to research in topics: GNSS applications & Recurrent neural network. The author has co-authored 2 publications.

Environment Classification for Global Navigation Satellite Systems Using Attention-Based Recurrent Neural Networks

Abstract: In this paper, an environment classification method for Global Navigation Satellite System (GNSS) is presented. The goal of the study is to characterize the statistical properties of the historical GNSS data in certain typical environments, so that appropriate localization or navigation algorithms can be chosen to achieve better performances once any environments are recognized in real practice. We extract Dilute of Precision (DOP) value, Carrier-to-Noise Ratio (C/N) and Number of Satellite in View from NMEA-0183 data collected in three real typical environments to characterize the environments. Further, an attention-based Recurrent Neural Network (RNN) is constructed; the historical characteristics extracted above are fed into the RNN. Attention values are then calculated using real-time characteristics and the RNN output in each time steps. High dimensional features are then constructed by soft attention and are used as the input of a fully connected network for classification. The performance of proposed method on the classification task of three typical environments has significantly improvement compared to recurrent neural networks without attention mechanism, and achieves an average accuracy of 94% on the testing set.

Transmission Line Tower Fault Identification Based on Image Processing Technology

Abstract: At present, the safety of transmission lines has attracted much attention from the power sector. In order to solve the problem of bird’s nest identification and insulator failure on transmission line towers, this paper studies a monitoring system using video image processing technology. Firstly, the image is gray-scaled, and then the edge of the image is extracted based on the Canny algorithm. Finally, a detection method based on the histogram of orientation gradient (HOG) and support vector machine (SVM) is proposed. This method improves the utilization efficiency of the online monitoring system and has important practical significance.

GNSS-based environmental context detection for navigation

Abstract: Environmental context detection is a topic of interest for the navigation community since it enables to build a context-adaptive solution. Indeed if the type of environment is known it is then possible to choose the proper data processing algorithm or to select the sensors to be used to dynamically adapt the navigation solution design itself. This paper proposes to build a supervised machine learning model which can robustly classify multiple contexts such as urban canyons, urban, trees and open-sky areas using GNSS data only. A training and test database have been built with four datasets acquired at different times in order to prove the relevance of the solution. These datasets are made available to the community for research purpose. The choices of features and classifier are also discussed and compared to others papers. Our solution achieved an average 82.40% of classification accuracy.

Vision-enhanced GNSS-based environmental context detection for autonomous vehicle navigation

Abstract: Context-adaptive navigation is currently considered as one of the potential solutions to achieve a more precise and robust positioning. The goal would be to adapt the sensor parameters and the navigation filter structure so that it takes into account the context-dependant sensor performance, notably GNSS signal degradations. For that, a reliable context detection is essential. This paper proposes a GNSS-based environmental context detector which classifies the environment surrounding a vehicle into four classes: canyon, open-sky, trees and urban. A support-vector machine classifier is trained on our database collected around Toulouse. We first show the classification results of a model based on GNSS data only, revealing its limitation to distinguish trees and urban contexts. For addressing this issue, this paper proposes the vision-enhanced model by adding satellite visibility information from sky segmentation on fisheye camera images. Compared to the GNSS-only model, the proposed vision-enhanced model significantly improved the classification performance and raised an average F1-score from 78% to 86%.

Information monitoring system of transmission line operation based on data analysis

Abstract: As an important part of the power transmission in the power system, the safety and stability of the transmission line directly affect the availability of the power system. With the continuous development of various industries, people's demand for energy is increasing, and the requirements for power supply reliability are also getting higher and higher. Transmission lines are an important part of the power system. Once a major power outage occurs, it will cause huge losses and inconvenience to the national economy. Therefore, the equipment and operation of transmission lines need a practical and effective management system to manage. Clearly, big data analytics has great advantages in this regard.