Zhaojun Wang

Mr. Zhaojun Wang

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 April 2021 in Animals
Verified
Journal Article
Open access
PDF file
ZWZhaojun Wang
Zhaojun Wang
JWJiangning Wang
Jiangning Wang
CLCongtian Lin
Congtian Lin
YHYan Han
Yan Han
Zhaosheng WangZhaosheng Wang
Zhaosheng Wang
LJLiqiang Ji
Liqiang Ji
With the rapid development of digital technology, bird images have become an important part of ornithology research data. However, due to the rapid growth of bird image data, it has become a major challenge to effectively process such a large amount of data. In recent years, deep convolutional neural networks (DCNNs) have shown great potential and effectiveness in a variety of tasks regarding the automatic processing of bird images. However, no research has been conducted on the recognition of habitat elements in bird images, which is of great help when extracting habitat information from bird images. Here, we demonstrate the recognition of habitat elements using four DCNN models trained end-to-end directly based on images. To carry out this research, an image database called Habitat Elements of Bird Images (HEOBs-10) and composed of 10 categories of habitat elements was built, making future benchmarks and evaluations possible. Experiments showed that good results can be obtained by all the tested models. ResNet-152-based models yielded the best test accuracy rate (95.52%); the AlexNet-based model yielded the lowest test accuracy rate (89.48%). We conclude that DCNNs could be efficient and useful for automatically identifying habitat elements from bird images, and we believe that the practical application of this technology will be helpful for studying the relationships between birds and habitat elements.

13 June 2019 in Biodiversity Information Science and Standards
Verified
Journal Article
Open access
PDF file
JWJiangning Wang
Jiangning Wang
CLCongtian Lin
Congtian Lin
YHYan Han
Yan Han
XHXiongwei Huang
Xiongwei Huang
TXTianYu Xi
TianYu Xi
LJLiqiang Ji
Liqiang Ji
Extracting and formulating an animal trait ontology is the basis of building a trait database. The character selection from existing traditional biodiversity databases is limited and biased by the information already in a collection. With the increasing amount of character data and the advance of character information acquisition projects, the success of making animal trait ontologies or specifications of terms is imminent. According to the general workflow of our ontology project, after investigating a large number of biodiversity databases, we extracted relatively complete character terms from dictionaries, training handbooks, journals and classical textbooks, and then constructed relationships according to some rules to form a preliminary animal trait ontology. When formulating the domain ontology/specification, our process is as follows: Select the group and related materials; select the "specification" as the starting point of work; and then supplement with the teaching materials, journal citations and dictionaries of the relevant group for reference; Extract terms from multiple sources, so only a few additions and modifications are needed after the second time; Make structural adjustments to all terms according to the specification of description sequence; Invite experts to examine and approve the project and repeat steps 2 and 3 (sometimes beginning from step 1) according to their opinions until they are approved. Select the group and related materials; select the "specification" as the starting point of work; and then supplement with the teaching materials, journal citations and dictionaries of the relevant group for reference; Extract terms from multiple sources, so only a few additions and modifications are needed after the second time; Make structural adjustments to all terms according to the specification of description sequence; Invite experts to examine and approve the project and repeat steps 2 and 3 (sometimes beginning from step 1) according to their opinions until they are approved. At present, we have completed the construction of terms and their relationships for a morphological description of feature ontologies in birds, mammals, insects (only Lepidoptera), amphibians and reptiles. While constructing such morphology / taxonomy-based ontologies, we also formulated their attributes, which are supplemented by ontologies in various fields. All these terms are undergoing the second review by domain experts. Although the existing work is only one small tip of the iceberg of the whole zoological trait ontology project, it is of great public interest. Compared with existing ontologies such as OBA (ontology of biological attributes, for development researchers) and UBERON (for surgeons), our ontologies are more suitable for taxonomists and biodiversity researchers.