Show simple item record

dc.contributor.advisorZhang, Xiangliang
dc.contributor.authorWang, Su
dc.date.accessioned2016-05-23T13:06:11Z
dc.date.available2017-05-23T00:00:00Z
dc.date.issued2016-05-23
dc.identifier.citationWang, S. (2016). Exploring Ocean Animal Trajectory Pattern via Deep Learning. KAUST Research Repository. https://doi.org/10.25781/KAUST-29M51
dc.identifier.doi10.25781/KAUST-29M51
dc.identifier.urihttp://hdl.handle.net/10754/610580
dc.description.abstractWe trained a combined deep convolutional neural network to predict seals’ age (3 categories) and gender (2 categories). The entire dataset contains 110 seals with around 489 thousand location records. Most records are continuous and measured in a certain step. We created five convolutional layers for feature representation and established two fully connected structure as age’s and gender’s classifier, respectively. Each classifier consists of three fully connected layers. Treating seals’ latitude and longitude as input, entire deep learning network, which includes 780,000 neurons and 2,097,000 parameters, can reach to 70.72% accuracy rate for predicting seals’ age and simultaneously achieve 79.95% for gender estimation.
dc.language.isoen
dc.subjectdeep learning
dc.subjectanimal trajectory
dc.subjectconvolutional neural network
dc.subjectfeature representation
dc.titleExploring Ocean Animal Trajectory Pattern via Deep Learning
dc.typeThesis
dc.contributor.departmentComputer, Electrical and Mathematical Science and Engineering (CEMSE) Division
dc.rights.embargodate2017-05-23
thesis.degree.grantorKing Abdullah University of Science and Technology
dc.contributor.committeememberGao, Xin
dc.contributor.committeememberMoshkov, Mikhail
thesis.degree.disciplineComputer Science
thesis.degree.nameMaster of Science
dc.rights.accessrightsAt the time of archiving, the student author of this thesis opted to temporarily restrict access to it. The full text of this thesis became available to the public after the expiration of the embargo on 2017-05-23.
refterms.dateFOA2017-05-23T00:00:00Z


Files in this item

Thumbnail
Name:
Thesis.pdf
Size:
4.405Mb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record