GLORIA

GEOMAR Library Ocean Research Information Access

X

Your email was sent successfully. Check your inbox.

An error occurred while sending the email. Please try again.

Proceed reservation?

Export
Filter
  • Liu, Jiping  (7)
  • Wang, Yong  (7)
  • 1
    Online Resource
    Online Resource
    Enhanced semantic representation model for multisource point of interest attribute alignment
    Elsevier BV ; 2023
    In:  Information Fusion Vol. 98 ( 2023-10), p. 101852-
    Details
    In: Information Fusion, Elsevier BV, Vol. 98 ( 2023-10), p. 101852-
    Type of Medium: Online Resource
    ISSN: 1566-2535
    URL: Article
    DOI: 10.1016/j.inffus.2023.101852
    Language: English
    Publisher: Elsevier BV
    Publication Date: 2023
    detail.hit.zdb_id: 2025632-2
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 2
    Online Resource
    Online Resource
    Comparison of RetinaNet-Based Single-Target Cascading and Multi-Target Detection Models for Administrative Regions in Network Map Pictures
    MDPI AG ; 2022
    In:  Sensors Vol. 22, No. 19 ( 2022-10-07), p. 7594-
    Details
    In: Sensors, MDPI AG, Vol. 22, No. 19 ( 2022-10-07), p. 7594-
    Abstract: There is a critical need for detection of administrative regions through network map pictures in map censorship tasks, which can be implemented by target detection technology. However, on map images there tend to be numerous administrative regions overlaying map annotations and symbols, thus making it difficult to accurately detect each region. Using a RetinaNet-based target detection model integrating ResNet50 and a feature pyramid network (FPN), this study built a multi-target model and a single-target cascading model from three single-target models by taking Taiwan, Tibet, and the Chinese mainland as target examples. Two models were evaluated both in classification and localization accuracy to investigate their administrative region detection performance. The results show that the single-target cascading model was able to detect more administrative regions, with a higher f1_score of 0.86 and mAP of 0.85 compared to the multi-target model (0.56 and 0.52, respectively). Furthermore, location box size distribution from the single-target cascading model looks more similar to that of manually annotated box sizes, which signifies that the proposed cascading model is superior to the multi-target model. This study is promising in providing support for computer map reading and intelligent map censorship.
    Type of Medium: Online Resource
    ISSN: 1424-8220
    URL: Article
    DOI: 10.3390/s22197594
    Language: English
    Publisher: MDPI AG
    Publication Date: 2022
    detail.hit.zdb_id: 2052857-7
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 3
    Online Resource
    Online Resource
    Spatial Mismatch between the Supply and Demand of Urban Leisure Services with Multisource Open Data
    MDPI AG ; 2020
    In:  ISPRS International Journal of Geo-Information Vol. 9, No. 8 ( 2020-07-22), p. 466-
    Details
    In: ISPRS International Journal of Geo-Information, MDPI AG, Vol. 9, No. 8 ( 2020-07-22), p. 466-
    Abstract: Understanding the balance between the supply and demand of leisure services (LSs) in urban areas can benefit urban spatial planning and improve the quality of life of residents. In cities in developing countries, the pursuit of rapid economic growth has ignored residents’ demand for LSs, thereby leading to a high demand for and short supply of these services. However, due to the lack of relevant research data, few studies have focused on the spatial mismatch in the supply and demand of LSs in urban areas. As typical representatives of multisource geographic data, social sensing data are readily available at various temporal and spatial scales, thus making social sensing data ideal for quantitative urban research. The objectives of this study are to use openly accessible datasets to explore the spatial pattern of the supply and demand of LSs in urban areas and then to depict the relationship between the supply and demand by using correlation analysis. Therefore, taking Beijing, China, as an example, the LS supply index (SI) and societal needs index (SNI) are proposed based on open data to reflect the supply and demand of LSs. The results show that the spatial distribution of the LS supply and demand in Beijing varies with a concentric pattern from the urban center to suburban areas. There is a strong correlation between the supply and demand of commercial and multifunctional services in Chaoyang, Fengtai, Haidian and Shijingshan, but there is no obvious correlation between the supply and demand of ecological and cultural services in Beijing. Especially in Dongcheng and Xicheng, there is no obvious correlation between the supply and demand of all services. The proposed approach provides an effective urban LS supply and demand evaluation method. In addition, the research results can provide a reference for the construction of “happy cities” in China.
    Type of Medium: Online Resource
    ISSN: 2220-9964
    URL: Article
    DOI: 10.3390/ijgi9080466
    Language: English
    Publisher: MDPI AG
    Publication Date: 2020
    detail.hit.zdb_id: 2655790-3
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 4
    Online Resource
    Online Resource
    Bidirectional Gated Recurrent Unit Neural Network for Chinese Address Element Segmentation
    MDPI AG ; 2020
    In:  ISPRS International Journal of Geo-Information Vol. 9, No. 11 ( 2020-10-26), p. 635-
    Details
    In: ISPRS International Journal of Geo-Information, MDPI AG, Vol. 9, No. 11 ( 2020-10-26), p. 635-
    Abstract: Chinese address element segmentation is a basic and key step in geocoding technology, and the segmentation results directly affect the accuracy and certainty of geocoding. However, due to the lack of obvious word boundaries in Chinese text, the grammatical and semantic features of Chinese text are complicated. Coupled with the diversity and complexity in Chinese address expressions, the segmentation of Chinese address elements is a substantial challenge. Therefore, this paper proposes a method of Chinese address element segmentation based on a bidirectional gated recurrent unit (Bi-GRU) neural network. This method uses the Bi-GRU neural network to generate tag features based on Chinese word segmentation and then uses the Viterbi algorithm to perform tag inference to achieve the segmentation of Chinese address elements. The neural network model is trained and verified based on the point of interest (POI) address data and partial directory data from the Baidu map of Beijing. The results show that the method is superior to previous neural network models in terms of segmentation performance and efficiency.
    Type of Medium: Online Resource
    ISSN: 2220-9964
    URL: Article
    DOI: 10.3390/ijgi9110635
    Language: English
    Publisher: MDPI AG
    Publication Date: 2020
    detail.hit.zdb_id: 2655790-3
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 5
    Online Resource
    Online Resource
    Research on Deep Web POI Acquisition based on Retrieving Word Optimization and Spatial Adaption
    Copernicus GmbH ; 2019
    In:  Proceedings of the ICA Vol. 2 ( 2019-07-10), p. 1-6
    Details
    In: Proceedings of the ICA, Copernicus GmbH, Vol. 2 ( 2019-07-10), p. 1-6
    Abstract: Abstract. POI data is a geographical information resource that is the most closely related to the public life, and has been successfully applied in various fields such as urban planning, urban logistics, and car navigation. With the development of technologies such as mobile networks and Internet of Things, the network contains a large number of high-value POI information resources. How to effectively acquire and utilize data resources has become a research hotspot in the field of spatial information. In this paper, a deep-web POI information search method based on independent coverage ranking and spatial adaptive partition is proposed to solve the problems of difficult construction of retrieval word base and limited data request. By constructing candidate search terms, searching greedily, optimizing dimensionality reduction of search terms, and crawling spatially adaptive partitioning, the maximum coverage optimal solution of POI search is approached step by step, and the full POI information of deep web is obtained. It is of great significance to improve the recall rate and collection efficiency of POI data for enriching geographic information resources and improving the ability of spatial information service and content management.
    Type of Medium: Online Resource
    ISSN: 2570-2092
    URL: Article
    DOI: 10.5194/ica-proc-2-142-2019
    Language: English
    Publisher: Copernicus GmbH
    Publication Date: 2019
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 6
    Online Resource
    Online Resource
    Deep learning method for Chinese multisource point of interest matching
    Elsevier BV ; 2022
    In:  Computers, Environment and Urban Systems Vol. 96 ( 2022-09), p. 101821-
    Details
    In: Computers, Environment and Urban Systems, Elsevier BV, Vol. 96 ( 2022-09), p. 101821-
    Type of Medium: Online Resource
    ISSN: 0198-9715
    URL: Article
    DOI: 10.1016/j.compenvurbsys.2022.101821
    Language: English
    Publisher: Elsevier BV
    Publication Date: 2022
    detail.hit.zdb_id: 2017202-3
    SSG: 3,6
    SSG: 3,7
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 7
    Online Resource
    Online Resource
    Chinese address standardisation of POIs based on GRU and spatial correlation and applied in multi-source emergency events fusion
    Informa UK Limited ; 2021
    In:  International Journal of Image and Data Fusion Vol. 12, No. 4 ( 2021-10-02), p. 319-334
    Details
    In: International Journal of Image and Data Fusion, Informa UK Limited, Vol. 12, No. 4 ( 2021-10-02), p. 319-334
    Type of Medium: Online Resource
    ISSN: 1947-9832 , 1947-9824
    URL: Article
    DOI: 10.1080/19479832.2021.1961314
    Language: English
    Publisher: Informa UK Limited
    Publication Date: 2021
    detail.hit.zdb_id: 2553695-3
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
Close ⊗
This website uses cookies and the analysis tool Matomo. More information can be found here...