Wiki Contents

Classification of Bee Species

Project Description

One of the biggest challenges for pollinator ecology and conservation is the proper identification of pollinator species. Species identification is traditionally performed using captured bees under conditions, such as cleaned, pinned, labeled, and individually identified by taxonomic experts. This identification process is time-consuming for those interested in monitoring pollinator health and habitats, including bee watchers, ecologists, and conservationists. There is a critical need for accurate, predictive classification models that provide quick and ready species identification.

We have developed an online, web application, called BeeMachine. Applying convolutional neural networks, such as InceptionV3, we are currently able to identify 100 bumblebee species from around the world with an overall test accuracy of 93.7% (99.3% top-3 candidates) using over 313,000 bumblebee images. Future plans for the project include:

  • Developing a learning to score image functionality where BeeMachine may be able to determine the quality of an image submitted for classification.
  • An autocropping feature to remove environmental background noise from an image submitted for classification.

BeeMachine is funded by USDA NIFA and Kansas State University. Computer vision models were developed with data primarily from the Global Biodiversity Infrastructure Facility (GBIF), Bumble Bee Watch, Wisconsin Bumble Bee Brigade, Hanamaru Maruhana Project, and Jerry Cole.

Keywords

artificial intelligence, machine learning, deep learning, image classification, analogous learning

Methods

Discuss approaches and current open research problems that are part of this work. Cite third-party research as appropriate and put references to the background and related work below.

Current Team Members

This section should list the names (and link to the home pages) of graduate students currently working on this research.

  • Team Member 1 - Team Leader
  • Team Member 2 - Team Leader
  • Team Member 3 -
  • Team Member 4 -
  • Derek Christensen - M.S. Operations Research, Kansas State University

Examples:

  • Heath Yates - Adjunct Assistant Professor, Computer Science, Kansas State University
  • William H. Hsu - Professor, Computer Science, Kansas State University
  • Carlos A. Aguirre - Developing Scholars Program and Undergraduate Research Programmer, Computer Science, Kansas State University

Affiliates

  • Natasha Jacques - Ph.D. candidate, MIT

Alumni

OR {delete}

This section should list the names (and link to KDD wiki or LinkedIn pages) of students who worked on this research and have graduated.

Data Sets

Link to any data sets for the project here. For any federally-sponsored research project (especially NSF and NIH-sponsored projects) of the KDD Lab, there must be an open access data repository. These may be subdirectories of a Bitbucket repository, but link to them separately here anyway. For all other projects, link to sites where data produced from the project are shared - e.g., a publisher server, Kaggle landing page, NIST documentation page, etc. Link to any data sharing agreements here.

Trello Board

Every KDD Lab project must have a Trello Team and Trello Board, which must be private. Link to the Trello Board for the project here.

Source Code

Every KDD Lab project must have a Bitbucket repository, which may be public or private. Link to the repository or repositories for the project here.

References

See the Machine Learning and Probabilistic Reasoning subpages of the original KDD wiki (v1, 2001 - 2006).

KDD Lab Publications

Use APA citation format and make sure citations are synchronized with the pages listing conference papers, journal articles, book chapters, posters, and student publications.

  • De La Torre, M. F., Aguirre, C. A., Anshutz, B., & Hsu, W. (2018). MATESC: Metadata-Analytic Text Extractor and Section Classifier for Scientific Publications. Proceedings of the 10th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2018): International Conference on Knowledge Discovery and Information Retrieval (KDIR 2018), Seville, Spain, September 18-20, 2018.
  • Yates, H., Chamberlain, B., Healey, J., & Hsu, W. (2018). Binary Classification of Arousal in Built Environments using Machine Learning. Working Notes of the 2nd International Joint Conference on Artificial Intelligence (IJCAI) Workshop on Artificial Intelligence in Affective Computing, Stockholm, Sweden, July 15, 2018.

Last updated by rotclanny on Mar 22, 2024