Show simple item record

AuthorArje J.
AuthorRaitoharju J.
AuthorIosifidis A.
AuthorTirronen V.
AuthorMeissner K.
AuthorGabbouj M.
AuthorKiranyaz, Mustafa Serkan
AuthorKarkkainen S.
Available date2022-04-26T12:31:20Z
Publication Date2020
Publication NameSignal Processing: Image Communication
ResourceScopus
Identifierhttp://dx.doi.org/10.1016/j.image.2020.115917
URIhttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85086801575&doi=10.1016%2fj.image.2020.115917&partnerID=40&md5=2f2cbf5e5af9ce6cd082dc90bd65f3e0
URIhttp://hdl.handle.net/10576/30605
AbstractThe step of expert taxa recognition currently slows down the response time of many bioassessments. Shifting to quicker and cheaper state-of-the-art machine learning approaches is still met with expert scepticism towards the ability and logic of machines. In our study, we investigate both the differences in accuracy and in the identification logic of taxonomic experts and machines. We propose a systematic approach utilizing deep Convolutional Neural Nets and extensively evaluate it over a multi-pose taxonomic dataset with hierarchical labels specifically created for this comparison. We also study the prediction accuracy on different ranks of taxonomic hierarchy in detail. We compare the results of Convolutional Neural Networks to human experts and support vector machines. Our results revealed that human experts using actual specimens yield the lowest classification error (CE?=6.1%). However, a much faster, automated approach using deep Convolutional Neural Nets comes close to human accuracy (CE?=11.4%) when a typical flat classification approach is used. Contrary to previous findings in the literature, we find that for machines following a typical flat classification approach commonly used in machine learning performs better than forcing machines to adopt a hierarchical, local per parent node approach used by human taxonomic experts (CE?=13.8%). Finally, we publicly share our unique dataset to serve as a public benchmark dataset in this field.
Languageen
PublisherElsevier B.V.
SubjectClassification (of information)
Computer circuits
Convolution
Convolutional neural networks
Deep neural networks
Support vector machines
Automated approach
Benchmark datasets
Classification approach
Classification errors
Machine learning approaches
Prediction accuracy
State of the art
Taxonomic hierarchy
Learning systems
TitleHuman experts vs. machines in taxa recognition
TypeArticle
Volume Number87
dc.accessType Abstract Only


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record