中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 植物研究所
  3. 中国科学院植物研究所
  4. 植被与环境变化国家重点实验室
ADMorph: A 3D Digital Microfossil Morphology Dataset for Deep Learning

文献类型：期刊论文

作者Hou, Yemao1,7; Cui, Xindong1,6,7; Canul-Ku, Mario; Jin, Shichao3,4,6; Hasimoto-Beltran, Rogelio; Guo, Qinghua3,6; Zhu, Min1,6,7
刊名IEEE ACCESS
出版日期2020
卷号8页码:148744-148756
关键词Three-dimensional displays Solid modeling Computational modeling Machine learning Two dimensional displays Biological system modeling Shape Archives of digital morphology data preprocessing feature extraction 3D microfossil model classification deep learning
ISSN号2169-3536
DOI10.1109/ACCESS.2020.3016267
文献子类Article
英文摘要Microfossils, tiny fossils whose study requires the use of a microscope, have been widely applied in many fields of earth, life, and environmental sciences. The abundance and high diversity of microfossils, as well as the need for rapid identification, call for automated methods to classify microfossils. In this study, we constructed an open dataset of three-dimensional (3D) microfossils and proposed a deep learning-based approach for microfossil classification. The dataset, named 'Archives of Digital Morphology' (ADMorph), currently contains more than ten thousand 3D models from five classes of 410 million-year-old fishes. The deep learning-based method includes data preprocessing, feature extraction, and 3D microfossil model classification. To assess the method performance and dataset representability, we performed extensive experiments. Compared with multiview convolutional neural networks (MVCNN) (91.54%), PointNet (64.13%), and VoxNet (78.15%), the method proposed herein had higher accuracy (97.60%) on the experimental dataset. We also verified data preprocessing (92.36%) and feature extraction (97.10%). We combined them to obtain the macroaveraging accuracy of 97.60%, the highest accuracy of 100%, and the lowest accuracy of 88.78%. We suggest that the proposed method can be applied to other 3D fossils and biomorphological research fields. The fast-accumulating 3D fossil models might become a source of information-rich datasets for deep learning.
学科主题Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
出版地PISCATAWAY
WOS关键词REPRESENTATION ; RETRIEVAL
WOS研究方向Computer Science ; Engineering ; Telecommunications
语种英语
WOS记录号WOS:000562067800001
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构Strategic Priority Research Program of the Chinese Academy of SciencesChinese Academy of Sciences [XDA19050102, XDB26000000] ; National Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [41530102] ; Key Research Program of Frontier Sciences, CAS [QYZDJ-SSW-DQC002]
源URL[http://ir.ibcas.ac.cn/handle/2S10CLM1/21616]  
专题植被与环境变化国家重点实验室
作者单位1.Chinese Acad Sci, Inst Vertebrate Paleontol & Paleoanthropol, Key Lab Vertebrate Evolut & Human Origins, Beijing 100044, Peoples R China
2.Chinese Acad Sci, Inst Bot, State Key Lab Vegetat & Environm Change, Beijing 100093, Peoples R China
3.Nanjing Agr Univ, Plant Phen Res Ctr, Nanjing 210095, Peoples R China
4.Ctr Invest Matemat CIMAT, Guanajuato 36023, Mexico
5.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
6.CAS Ctr Excellence Life & Paleoenvironm, Beijing 100044, Peoples R China
7.Xidian Univ, Sch Life Sci & Technol, Xian 710071, Peoples R China
推荐引用方式
GB/T 7714		 Hou, Yemao,Cui, Xindong,Canul-Ku, Mario,et al. ADMorph: A 3D Digital Microfossil Morphology Dataset for Deep Learning[J]. IEEE ACCESS,2020,8:148744-148756.
APA Hou, Yemao.,Cui, Xindong.,Canul-Ku, Mario.,Jin, Shichao.,Hasimoto-Beltran, Rogelio.,...&Zhu, Min.(2020).ADMorph: A 3D Digital Microfossil Morphology Dataset for Deep Learning.IEEE ACCESS,8,148744-148756.
MLA Hou, Yemao,et al."ADMorph: A 3D Digital Microfossil Morphology Dataset for Deep Learning".IEEE ACCESS 8(2020):148744-148756.

入库方式： OAI收割

来源：植物研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。