Similarity Measurement of Metadata of Geospatial Data: An Artificial Neural Network Approach
To help users discover the most relevant spatial datasets in the ever-growing global spatial data infrastructures (SDIs), a number of similarity measures of geospatial data based on metadata have been proposed. Researchers have assessed the similarity of geospatial data according to one or more char...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-03-01
|
Series: | ISPRS International Journal of Geo-Information |
Subjects: | |
Online Access: | http://www.mdpi.com/2220-9964/7/3/90 |
id |
doaj-efab059ee6f44975b79ae2a9bc3ae18e |
---|---|
record_format |
Article |
spelling |
doaj-efab059ee6f44975b79ae2a9bc3ae18e2020-11-24T22:12:54ZengMDPI AGISPRS International Journal of Geo-Information2220-99642018-03-01739010.3390/ijgi7030090ijgi7030090Similarity Measurement of Metadata of Geospatial Data: An Artificial Neural Network ApproachZugang Chen0Jia Song1Yaping Yang2State Key Laboratory of Resources and Environmental Information System, Beijing 100101, ChinaState Key Laboratory of Resources and Environmental Information System, Beijing 100101, ChinaState Key Laboratory of Resources and Environmental Information System, Beijing 100101, ChinaTo help users discover the most relevant spatial datasets in the ever-growing global spatial data infrastructures (SDIs), a number of similarity measures of geospatial data based on metadata have been proposed. Researchers have assessed the similarity of geospatial data according to one or more characteristics of the geospatial data. They created different similarity algorithms for each of the selected characteristics and then combined these elementary similarities to the overall similarity of the geospatial data. The existing combination methods are mainly linear and may not be the most accurate. This paper reports our experiences in attempting to learn the optimal non-linear similarity integration functions, from the knowledge of experts, using an artificial neural network. First, a multiple-layer feed forward neural network (MLFFN) was created. Then, the intrinsic characteristics were used to represent the metadata of geospatial data and the similarity algorithms for each of the intrinsic characteristics were built. The training and evaluation data of MLFFN were derived from the knowledge of domain experts. Finally, the MLFFN was trained, evaluated, and compared with traditional linear combination methods, which was mainly a weighted sum. The results show that our method outperformed the existing methods in terms of precision. Moreover, we found that the combination of elementary similarities of experts to the overall similarity of geospatial data was not linear.http://www.mdpi.com/2220-9964/7/3/90artificial neural networksgeospatial datasimilaritymetadataintrinsic characteristicscombination |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zugang Chen Jia Song Yaping Yang |
spellingShingle |
Zugang Chen Jia Song Yaping Yang Similarity Measurement of Metadata of Geospatial Data: An Artificial Neural Network Approach ISPRS International Journal of Geo-Information artificial neural networks geospatial data similarity metadata intrinsic characteristics combination |
author_facet |
Zugang Chen Jia Song Yaping Yang |
author_sort |
Zugang Chen |
title |
Similarity Measurement of Metadata of Geospatial Data: An Artificial Neural Network Approach |
title_short |
Similarity Measurement of Metadata of Geospatial Data: An Artificial Neural Network Approach |
title_full |
Similarity Measurement of Metadata of Geospatial Data: An Artificial Neural Network Approach |
title_fullStr |
Similarity Measurement of Metadata of Geospatial Data: An Artificial Neural Network Approach |
title_full_unstemmed |
Similarity Measurement of Metadata of Geospatial Data: An Artificial Neural Network Approach |
title_sort |
similarity measurement of metadata of geospatial data: an artificial neural network approach |
publisher |
MDPI AG |
series |
ISPRS International Journal of Geo-Information |
issn |
2220-9964 |
publishDate |
2018-03-01 |
description |
To help users discover the most relevant spatial datasets in the ever-growing global spatial data infrastructures (SDIs), a number of similarity measures of geospatial data based on metadata have been proposed. Researchers have assessed the similarity of geospatial data according to one or more characteristics of the geospatial data. They created different similarity algorithms for each of the selected characteristics and then combined these elementary similarities to the overall similarity of the geospatial data. The existing combination methods are mainly linear and may not be the most accurate. This paper reports our experiences in attempting to learn the optimal non-linear similarity integration functions, from the knowledge of experts, using an artificial neural network. First, a multiple-layer feed forward neural network (MLFFN) was created. Then, the intrinsic characteristics were used to represent the metadata of geospatial data and the similarity algorithms for each of the intrinsic characteristics were built. The training and evaluation data of MLFFN were derived from the knowledge of domain experts. Finally, the MLFFN was trained, evaluated, and compared with traditional linear combination methods, which was mainly a weighted sum. The results show that our method outperformed the existing methods in terms of precision. Moreover, we found that the combination of elementary similarities of experts to the overall similarity of geospatial data was not linear. |
topic |
artificial neural networks geospatial data similarity metadata intrinsic characteristics combination |
url |
http://www.mdpi.com/2220-9964/7/3/90 |
work_keys_str_mv |
AT zugangchen similaritymeasurementofmetadataofgeospatialdataanartificialneuralnetworkapproach AT jiasong similaritymeasurementofmetadataofgeospatialdataanartificialneuralnetworkapproach AT yapingyang similaritymeasurementofmetadataofgeospatialdataanartificialneuralnetworkapproach |
_version_ |
1725801942495526912 |