Hypermeters Optimization in Recurrent Neural Networks-LSTM Approach for Human Activity Recognition

dc.contributor.authorTopbaş, Ayşenur
dc.contributor.authorHameed, Alaa Ali
dc.contributor.authorJamil, Akhtar
dc.contributor.authorTopbaş, Ayşenur
dc.date.accessioned2025-01-18T09:42:48Z
dc.date.available2025-01-18T09:42:48Z
dc.date.issued2021
dc.departmentMühendislik ve Doğa Bilimleri Fakültesi
dc.description1st International Conference on Computing and Machine Intelligence (ICMI-2021) February 19-20, 2021, Istanbul, Turkey -- Editorial Board Dr. Akhtar JAMIL Dr. Alaa Ali HAMEED -- ISBN: 9786050667578 -- Istanbul Sabahattin Zaim University Yayınları; No. 57.
dc.description.abstractHuman activity recognition (HAR) has become more popular with the increase of applications involving human-computer interaction. The problem of recognizing and classifying people's daily life activities is a very important and challenging issue in the field of artificial intelligence. In recent years, deep learning based techniques have achieved high accuracy for HAR. However, these methods require obtaining a optimal number parameters. In this study, we investigated Long Short-Term Memory (LSTM) for HAR from videos. In addition, hyperparameters of the model were obtained thourh a thorough search to optimize ther performance of the model. Specifically, we obtained optimal values for number of layers, batch size, epochs to obtained best accuracy for the model. Experiments were performed to evaluate the performance of the proposed model on WISDM dataset. The proposed model produced an overall 97.18% overall accuracy indicates that LSTM is an effective technique for HAR.
dc.identifier.endpage365
dc.identifier.startpage360
dc.identifier.urihttps://hdl.handle.net/20.500.12436/7003
dc.institutionauthorTopbaş, Ayşenur
dc.institutionauthorHameed, Alaa Ali
dc.institutionauthorJamil, Akhtar
dc.language.isoen
dc.publisherİstanbul Sabahattin Zaim Üniversitesi
dc.relation.ispartof1st International Conference on Computing and Machine Intelligence
dc.relation.publicationcategoryKonferans Öğesi - Ulusal - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectHuman Activity Recognition
dc.subjectRNN
dc.subjectLSTM Neural Networks
dc.subjectDeep Learning
dc.titleHypermeters Optimization in Recurrent Neural Networks-LSTM Approach for Human Activity Recognition
dc.typeConference Object
dspace.entity.typePublication
relation.isAuthorOfPublication070356a3-1a01-471e-b43c-6fa1abd4b1aa
relation.isAuthorOfPublication.latestForDiscovery070356a3-1a01-471e-b43c-6fa1abd4b1aa

Dosyalar

Orijinal paket

Listeleniyor 1 - 2 / 2
Yükleniyor...
Küçük Resim
İsim:
hypermeters-optimization-in-recurrent-neural-networks-lstm-approach-for-human-activity-recognition.pdf
Boyut:
947.75 KB
Biçim:
Adobe Portable Document Format
Açıklama:
Proceedings file
Yükleniyor...
Küçük Resim
İsim:
1st International Conference on Computing and Machine Intelligence.pdf
Boyut:
371.2 KB
Biçim:
Adobe Portable Document Format
Açıklama:
Contents

Lisans paketi

Listeleniyor 1 - 1 / 1
Yükleniyor...
Küçük Resim
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama: