Machine Learning Methods for Computational Sustainability Public Deposited

http://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/sn00b2317

Descriptions

Attribute NameValues
Creator
Abstract or Summary
  • Maintaining the sustainability of the earth’s ecosystems has attracted much attention as these ecosystems are facing more and more pressure from human activities. Machine learning can play an important role in promoting sustainability as a large amount of data is being collected from ecosystems. There are at least three important and representative issues in the study of sustainability: detecting the presence of species, modeling the distribution of species, and protecting endangered species. For these three issues, this thesis selects three typical problems as the main focus and studies these problems with different machine learning techniques. Specifically, this thesis investigates the problem of detecting bird species from bird song recordings, the problem of modeling migrating birds at the population level, and the problem of designing a conservation area for an endangered species. First, this thesis models the problem of bird song classification as a weakly-supervised learning problem and develops a probabilistic classification model for the learning problem. The thesis also analyzes the learnability of the superset label learning problem to determine conditions under which one can learn a good classifier from the training data. Second, the thesis models bird migration with a probabilistic graphical model at the population level using a Collective Graphical Model (CGM). The thesis proposes a Gaussian approximation to significantly improve the inference efficiency of the model. Theoretical results show that the proposed Gaussian approximation is correct and can be calculated efficiently. Third, the thesis studies a typical reserve design problem with a novel formulation of transductive classification. Then the thesis solves the formulation with two optimization algorithms. The learning techniques in this thesis are general and can also be applied to many other machine learning problems.
Resource Type
Date Available
Date Copyright
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Non-Academic Affiliation
Keyword
Subject
Rights Statement
Peer Reviewed
Language
Replaces
Additional Information
  • description.provenance : Submitted by Liping Liu (liuli@oregonstate.edu) on 2016-06-10T23:25:30Z No. of bitstreams: 2 license_rdf: 1379 bytes, checksum: da3654ba11642cda39be2b66af335aae (MD5) LiuLiping2016.pdf: 746665 bytes, checksum: 0962c2e02d03a94853ccd4571c6be385 (MD5)
  • description.provenance : Made available in DSpace on 2016-06-14T20:54:41Z (GMT). No. of bitstreams: 2 license_rdf: 1379 bytes, checksum: da3654ba11642cda39be2b66af335aae (MD5) LiuLiping2016.pdf: 746665 bytes, checksum: 0962c2e02d03a94853ccd4571c6be385 (MD5) Previous issue date: 2016-06-10
  • description.provenance : Approved for entry into archive by Laura Wilson(laura.wilson@oregonstate.edu) on 2016-06-14T20:54:41Z (GMT) No. of bitstreams: 2 license_rdf: 1379 bytes, checksum: da3654ba11642cda39be2b66af335aae (MD5) LiuLiping2016.pdf: 746665 bytes, checksum: 0962c2e02d03a94853ccd4571c6be385 (MD5)
  • description.provenance : Approved for entry into archive by Julie Kurtz(julie.kurtz@oregonstate.edu) on 2016-06-14T18:16:49Z (GMT) No. of bitstreams: 2 license_rdf: 1379 bytes, checksum: da3654ba11642cda39be2b66af335aae (MD5) LiuLiping2016.pdf: 746665 bytes, checksum: 0962c2e02d03a94853ccd4571c6be385 (MD5)

Relationships

Parents:

This work has no parents.

Last modified

Downloadable Content

Download PDF

Items