Atrial Fibrillation Detection Using Weight-Pruned, Log-Quantised Convolutional Neural Networks
Deep neural networks (DNN) are a promising tool in medical applications. However, the implementation of complex DNNs on battery-powered devices is challenging due to high energy costs for communication. In this work, a convolutional neural network model is developed for detecting atrial fibrillation...
Saved in:
Main Authors | , , , , , , , , |
---|---|
Format | Journal Article |
Language | English |
Published |
14.06.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Deep neural networks (DNN) are a promising tool in medical applications.
However, the implementation of complex DNNs on battery-powered devices is
challenging due to high energy costs for communication. In this work, a
convolutional neural network model is developed for detecting atrial
fibrillation from electrocardiogram (ECG) signals. The model demonstrates high
performance despite being trained on limited, variable-length input data.
Weight pruning and logarithmic quantisation are combined to introduce sparsity
and reduce model size, which can be exploited for reduced data movement and
lower computational complexity. The final model achieved a 91.1% model
compression ratio while maintaining high model accuracy of 91.7% and less than
1% loss. |
---|---|
AbstractList | Deep neural networks (DNN) are a promising tool in medical applications.
However, the implementation of complex DNNs on battery-powered devices is
challenging due to high energy costs for communication. In this work, a
convolutional neural network model is developed for detecting atrial
fibrillation from electrocardiogram (ECG) signals. The model demonstrates high
performance despite being trained on limited, variable-length input data.
Weight pruning and logarithmic quantisation are combined to introduce sparsity
and reduce model size, which can be exploited for reduced data movement and
lower computational complexity. The final model achieved a 91.1% model
compression ratio while maintaining high model accuracy of 91.7% and less than
1% loss. |
Author | Panicker, Rajesh C Choong, Benjamin Chen Ming John, Deepu Wang, Shuhui Chang, Xiu Qi Han, Rui Chew, Ann Feng Xiaolin, Li He, Wang |
Author_xml | – sequence: 1 givenname: Xiu Qi surname: Chang fullname: Chang, Xiu Qi – sequence: 2 givenname: Ann Feng surname: Chew fullname: Chew, Ann Feng – sequence: 3 givenname: Benjamin Chen Ming surname: Choong fullname: Choong, Benjamin Chen Ming – sequence: 4 givenname: Shuhui surname: Wang fullname: Wang, Shuhui – sequence: 5 givenname: Rui surname: Han fullname: Han, Rui – sequence: 6 givenname: Wang surname: He fullname: He, Wang – sequence: 7 givenname: Li surname: Xiaolin fullname: Xiaolin, Li – sequence: 8 givenname: Rajesh C surname: Panicker fullname: Panicker, Rajesh C – sequence: 9 givenname: Deepu surname: John fullname: John, Deepu |
BackLink | https://doi.org/10.48550/arXiv.2206.07649$$DView paper in arXiv |
BookMark | eNotj8tOhDAYRrvQhY7zAK7kAQR7oReWE3QcE-Jo1LiTFPqDjdiaUkZ9ex10db7Fl5OcY3TgvAOETgnOcsU5vtDhy-4ySrHIsBR5cYReVjFYPSRr2wQ7DDpa75JLiNDO62m0rk-ewfavMb0LkwNznlS-T-8n7aIdwSSldzs_TPv7r-cWpjAjfvrwNp6gw04PIyz_uUAP66vHcpNW2-ubclWlWsgi1UZgTlqVg5Kcd0KBkNAaKppcScKMLDrKFKdES6NJzjFrlWJNQRWlrDVsgc7-rHNf_RHsuw7f9b6znjvZD8GWT94 |
ContentType | Journal Article |
Copyright | http://arxiv.org/licenses/nonexclusive-distrib/1.0 |
Copyright_xml | – notice: http://arxiv.org/licenses/nonexclusive-distrib/1.0 |
DBID | AKY GOX |
DOI | 10.48550/arxiv.2206.07649 |
DatabaseName | arXiv Computer Science arXiv.org |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: GOX name: arXiv.org url: http://arxiv.org/find sourceTypes: Open Access Repository |
DeliveryMethod | fulltext_linktorsrc |
ExternalDocumentID | 2206_07649 |
GroupedDBID | AKY GOX |
ID | FETCH-LOGICAL-a679-ad6051c84e8755f68e67ecd26b48713d79f238521a7da14503c883b928223cd3 |
IEDL.DBID | GOX |
IngestDate | Mon Jan 08 05:49:44 EST 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-a679-ad6051c84e8755f68e67ecd26b48713d79f238521a7da14503c883b928223cd3 |
OpenAccessLink | https://arxiv.org/abs/2206.07649 |
ParticipantIDs | arxiv_primary_2206_07649 |
PublicationCentury | 2000 |
PublicationDate | 2022-06-14 |
PublicationDateYYYYMMDD | 2022-06-14 |
PublicationDate_xml | – month: 06 year: 2022 text: 2022-06-14 day: 14 |
PublicationDecade | 2020 |
PublicationYear | 2022 |
Score | 1.847219 |
SecondaryResourceType | preprint |
Snippet | Deep neural networks (DNN) are a promising tool in medical applications.
However, the implementation of complex DNNs on battery-powered devices is
challenging... |
SourceID | arxiv |
SourceType | Open Access Repository |
SubjectTerms | Computer Science - Learning |
Title | Atrial Fibrillation Detection Using Weight-Pruned, Log-Quantised Convolutional Neural Networks |
URI | https://arxiv.org/abs/2206.07649 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwdV1NS8QwFHzs7smLKCrrJzl4NNimadoel9V1ET9RcU8uL00qC9LKfuHP9_W1ohdPhTYUOk0ymWY6D-DUGJuRroiloZlQ6jA0ElGjNIhY2CxXluuQ3d6Z8Yu-nsSTDoiff2Fw_jVbN_nAdnGuFGdrGp11oatUbdm6up80m5McxdW2_21Ha0w-9YckRluw2a7uxKB5HdvQ8eUOvA24NIYY1e76j8Z7Ji78kk1QpeBNe_HKnyjlw3xF896ZuKne5eOKnnq28E4Mq3LddhG6T52nwQc2cC924Wl0-Twcy7asgUSTZBIdKYgwT7UnqRAXJvUm8blTxpJ2CCOXZAXRKLEqJg5DHQdRnqYRIUpUHuUu2oNeWZW-DyIJ0BsMfJwSvKkukAYoiczcW6fQJ8E-9BmL6WcTXDGtYZoyTAf_XzqEDVVb_Ov6PPoIesv5yh8T8S7tCaP_DSRDg9U |
link.rule.ids | 228,230,780,885 |
linkProvider | Cornell University |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Atrial+Fibrillation+Detection+Using+Weight-Pruned%2C+Log-Quantised+Convolutional+Neural+Networks&rft.au=Chang%2C+Xiu+Qi&rft.au=Chew%2C+Ann+Feng&rft.au=Choong%2C+Benjamin+Chen+Ming&rft.au=Wang%2C+Shuhui&rft.date=2022-06-14&rft_id=info:doi/10.48550%2Farxiv.2206.07649&rft.externalDocID=2206_07649 |