HActivityNet: A Deep Convolutional Neural Network for Human Activity Recognition

Simple item page
dc.contributor.authorKhaliluzzaman, Md.
dc.contributor.authorSayem, Abu Bakar Siddiq
dc.contributor.authorMisbah, Lutful Kader
dc.date.accessioned2022-07-03T09:46:48Z
dc.date.available2022-07-03T09:46:48Z
dc.date.issued2021-12
dc.descriptionVol. 9, No. 2, December 2021, pp. 357~376en_US
dc.description.abstractHuman Activity Recognition (HAR), a vast area of a computer vision research, has gained standings in recent years due to its applications in various fields. As human activity has diversification in action, interaction, and it embraces a large amount of data and powerful computational resources, it is very difficult to recognize human activities from an image. In order to solve the computational cost and vanishing gradient problem, in this work, we have proposed a revised simple convolutional neural network (CNN) model named Human Activity Recognition Network (HActivityNet) that is automatically extract and learn features and recognize activities in a rapid, precise and consistent manner. To solve the problem of imbalanced positive and negative data, we have created two datasets, one is HARDataset1 dataset which is created by extracted image frames from KTH dataset, and another one is HARDataset2 dataset prepared from activity video frames performed by us. The comprehensive experiment shows that our model performs better with respect to the present state of the art models. The proposed model attains an accuracy of 99.5% on HARDatase1 and almost 100% on HARDataset2 dataset. The proposed model also performed well on real data.en_US
dc.identifier.citationDOI : 10.24003/emitter.v9i2.642,en_US
dc.identifier.issn2335-391X
dc.identifier.issn24431168
dc.identifier.urihttp://dspace.iiuc.ac.bd:8080/xmlui/handle/123456789/3395
dc.language.isoenen_US
dc.publisherEMITTER International Journal of Engineering Technology ‐ Published by EEPISen_US
dc.subjectHuman activity recognition (HAR)en_US
dc.subjectconvolutional neural network (CNN)en_US
dc.subjectKTH dataseten_US
dc.subjectComputer visionen_US
dc.subjectVanishing gradient problemen_US
dc.titleHActivityNet: A Deep Convolutional Neural Network for Human Activity Recognitionen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
HActivityNet A Deep Convolutional Neural Network for Human Activity Recognition.pdf
Size:
830.74 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Department of Computer Science and Engineering