scispace - formally typeset
Search or ask a question
Author

Xiongfeng Yan

Other affiliations: Wuhan University
Bio: Xiongfeng Yan is an academic researcher from Tongji University. The author has contributed to research in topics: Computer science & Artificial intelligence. The author has an hindex of 5, co-authored 11 publications receiving 90 citations. Previous affiliations of Xiongfeng Yan include Wuhan University.

Papers
More filters
Journal ArticleDOI
TL;DR: A novel graph convolution is introduced by converting it from the vertex domain into a point-wise product in the Fourier domain using the graph Fourier transform and convolution theorem, which achieves a significant improvement over existing methods.
Abstract: Machine learning methods, specifically, convolutional neural networks (CNNs), have emerged as an integral part of scientific research in many disciplines. However, these powerful methods often fail to perform pattern analysis and knowledge mining with spatial vector data because in most cases, such data are not underlying grid-like or array structures but can only be modeled as graph structures. The present study introduces a novel graph convolution by converting it from the vertex domain into a point-wise product in the Fourier domain using the graph Fourier transform and convolution theorem. In addition, the graph convolutional neural network (GCNN) architecture is proposed to analyze graph-structured spatial vector data. The focus of this study is the classical task of building pattern classification, which remains limited by the use of design rules and manually extracted features for specific patterns. The spatial vector data representing grouped buildings are modeled as graphs, and indices for the characteristics of individual buildings are investigated to collect the input variables. The pattern features of these graphs are directly extracted by training labeled data. Experiments confirmed that the GCNN produces satisfactory results in terms of identifying regular and irregular patterns, and thus achieves a significant improvement over existing methods. In summary, the GCNN has considerable potential for the analysis of graph-structured spatial vector data as well as scope for further improvement.

114 citations

Journal ArticleDOI
TL;DR: This study develops a learning strategy to combine multiple features extracted from its boundary and obtain a reasonable shape representation, and shows that the GCAE model can produce a cognitively compliant shape coding, with the ability to distinguish different shapes.
Abstract: The shape of a geospatial object is an important characteristic and a significant factor in spatial cognition. Existing shape representation methods for vector-structured objects in the map space a...

35 citations

Journal ArticleDOI
TL;DR: A template matching simplification method from the perspective of shape cognition based on the typical template characteristics of building distributions and representations that can enhance the impression of well-known landmarks and reflect the pattern in mapping areas by the symbolic template.
Abstract: This study proposes a template matching simplification method from the perspective of shape cognition based on the typical template characteristics of building distributions and representations. The method first formulates a series of templates to abstract the building shape by generalizing their polygons and analyzing their symbolic meanings, then conducts the simplification by searching and matching the most similar template that can be used later to replace the original building. On the premise of satisfying the individual geometric accuracy on a smaller scale, the proposed method can enhance the impression of well-known landmarks and reflect the pattern in mapping areas by the symbolic template. The turning function that describes shape by measuring the changes of the tangent-angle as a function of the arc-length is employed to obtain the similar distance between buildings and template polygons, and the least squares model is used to control the geometry matching of the candidate template. Experiments on real datasets are carried out to assess the usefulness of this method and compare it with two existing methods. The experiments suggest that our method can preserve the main structure of building shapes and geometric accuracy.

18 citations

Journal ArticleDOI
TL;DR: This study examines the various possible changes from different perspectives, such as the reasons for their occurrence, the forms in which they manifest, and their effects on output, and applies map algebra theory to establish a cartographic model for updating polygonal building data.

13 citations

Journal ArticleDOI
TL;DR: Wang et al. as mentioned in this paper presented an ensemble classification method that combines vector-based buildings and points-of-interest (POIs) to extract morphological features from the constituent buildings.
Abstract: The automatic classification of urban functional regions is vital for urban planning and governance. The current methods mainly rely on single remote sensing image data or social sensing data. However, these imagery-based methods have the disadvantage of capturing high-level socioeconomic features, whereas the information from social sensing data alone rarely contains the morphological features. To overcome these limitations, it is necessary to combine multisource data for sensing urban functionalities. This study presents an ensemble classification method that combines vector-based buildings and points-of-interest (POIs). For each block, we constructed an improved graph convolutional neural network (GCNN) to extract morphological features from the constituent buildings. The ‘Word2Vec’ model was used to obtain the socioeconomic characteristics of POIs. On this basis, a stacking ensemble model was designed to combine morphological and socioeconomic features for classifying the functionality of each block. The proposed method was trained and tested in Nanshan District, Shenzhen, China. The results showed a classification accuracy of 86.83%, which was 12.2%–16.1% higher than standalone applications based on single-source data. The trained models were also applied to two other districts, namely Futian and Guangming, achieving accuracies of 85.32% and 68.37%, respectively, which were 3.68%–7.79% and 3.69%–8.94% higher than those obtained using single-sourced data. Moreover, the classification accuracies of the proposed method showed improvements of 2.41%–9.76%, compared with the existing multisource data integration method in the three study areas. These results suggest that our ensemble method can effectively integrate features from different data sources and provide an alternative, higher-accuracy solution for classifying urban functional regions.

10 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: A novel graph convolution is introduced by converting it from the vertex domain into a point-wise product in the Fourier domain using the graph Fourier transform and convolution theorem, which achieves a significant improvement over existing methods.
Abstract: Machine learning methods, specifically, convolutional neural networks (CNNs), have emerged as an integral part of scientific research in many disciplines. However, these powerful methods often fail to perform pattern analysis and knowledge mining with spatial vector data because in most cases, such data are not underlying grid-like or array structures but can only be modeled as graph structures. The present study introduces a novel graph convolution by converting it from the vertex domain into a point-wise product in the Fourier domain using the graph Fourier transform and convolution theorem. In addition, the graph convolutional neural network (GCNN) architecture is proposed to analyze graph-structured spatial vector data. The focus of this study is the classical task of building pattern classification, which remains limited by the use of design rules and manually extracted features for specific patterns. The spatial vector data representing grouped buildings are modeled as graphs, and indices for the characteristics of individual buildings are investigated to collect the input variables. The pattern features of these graphs are directly extracted by training labeled data. Experiments confirmed that the GCNN produces satisfactory results in terms of identifying regular and irregular patterns, and thus achieves a significant improvement over existing methods. In summary, the GCNN has considerable potential for the analysis of graph-structured spatial vector data as well as scope for further improvement.

114 citations

Journal ArticleDOI
TL;DR: An improved graph convolutional network (IGCN) and a Dual-CNN are designed to construct GC-CNN, which can simultaneously capture stock market features and individual stock features.

108 citations

Journal ArticleDOI
TL;DR: A comprehensive survey of relevant research on machine learning applied in landslides prevention is presented, mainly focusing on landslides detection based on images, landslides susceptibility assessment, and the development of landslide warning systems.
Abstract: Landslides are one of the most critical categories of natural disasters worldwide and induce severely destructive outcomes to human life and the overall economic system To reduce its negative effects, landslides prevention has become an urgent task, which includes investigating landslide-related information and predicting potential landslides Machine learning is a state-of-the-art analytics tool that has been widely used in landslides prevention This paper presents a comprehensive survey of relevant research on machine learning applied in landslides prevention, mainly focusing on (1) landslides detection based on images, (2) landslides susceptibility assessment, and (3) the development of landslide warning systems Moreover, this paper discusses the current challenges and potential opportunities in the application of machine learning algorithms for landslides prevention

78 citations

Journal ArticleDOI
TL;DR: It is anticipated that the cooperation and training of cross-disciplinary talents may promote the standardization and sharing of ecological resource data, improve the universality and interpretability of algorithms, and enrich applications with the development of hardware.
Abstract: Ecological resources are an important material foundation for the survival, development, and self-realization of human beings. In-depth and comprehensive research and understanding of ecological resources are beneficial for the sustainable development of human society. Advances in observation technology have improved the ability to acquire long-term, cross-scale, massive, heterogeneous, and multi-source data. Ecological resource research is entering a new era driven by big data. Traditional statistical learning and machine learning algorithms have problems with saturation in dealing with big data. Deep learning is a method for automatically extracting complex high-dimensional nonlinear features, which is increasingly used for scientific and industrial data processing because of its ability to avoid saturation with big data. To promote the application of deep learning in the field of ecological resource research, here, we first introduce the relationship between deep learning theory and research on ecological resources, common tools, and datasets. Second, applications of deep learning in classification and recognition, detection and localization, semantic segmentation, instance segmentation, and graph neural network in typical spatial discrete data are presented through three cases: species classification, crop breeding, and vegetation mapping. Finally, challenges and opportunities for the application of deep learning in ecological resource research in the era of big data are summarized by considering the characteristics of ecological resource data and the development status of deep learning. It is anticipated that the cooperation and training of cross-disciplinary talents may promote the standardization and sharing of ecological resource data, improve the universality and interpretability of algorithms, and enrich applications with the development of hardware.

51 citations