Classification of Stroke and Non-Stroke Patients from Human Body Movements using Smartphone Videos and Deep Neural Networks

Zafira Binta Feliandra; Siti Khadijah; Muhammad Febrian Rachmadi; Dina Chahyati

doi:10.1109/ICACSIS56558.2022.9923501

Classification of Stroke and Non-Stroke Patients from Human Body Movements using Smartphone Videos and Deep Neural Networks

Zafira Binta Feliandra
, Siti Khadijah
, Muhammad Febrian Rachmadi
, Dina Chahyati

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Citations (Scopus)

Abstract

This study covers a pilot study on developing a tele-health system for detection and classification of stroke and non-stroke patients from human body movements using smartphone videos. Human body poses are extracted from smartphone videos which are then transformed into RGB images and classified into either stroke (positive) or non-stroke (negative) labels. We tested PoseNet, BlazePose, and MoveNet for human body pose detection and AlexN et and SqueezeN et for classification. From this pilot study, we found that MoveNet is the best human body pose detection while AlexNet is the best for classification.

Original language	English
Title of host publication	Proceedings - ICACSIS 2022
Subtitle of host publication	14th International Conference on Advanced Computer Science and Information Systems
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	187-192
Number of pages	6
ISBN (Electronic)	9781665489362
DOIs	https://doi.org/10.1109/ICACSIS56558.2022.9923501
Publication status	Published - 2022
Event	14th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2022 - Virtual, Online, Indonesia Duration: 1 Oct 2022 → 3 Oct 2022

Publication series

Name	Proceedings - ICACSIS 2022: 14th International Conference on Advanced Computer Science and Information Systems

Conference

Conference	14th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2022
Country/Territory	Indonesia
City	Virtual, Online
Period	1/10/22 → 3/10/22

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

classification
human body movements analysis
smartphone videos
stroke movements detection

Access to Document

10.1109/ICACSIS56558.2022.9923501

Cite this

Feliandra, Z. B., Khadijah, S., Rachmadi, M. F., & Chahyati, D. (2022). Classification of Stroke and Non-Stroke Patients from Human Body Movements using Smartphone Videos and Deep Neural Networks. In Proceedings - ICACSIS 2022: 14th International Conference on Advanced Computer Science and Information Systems (pp. 187-192). (Proceedings - ICACSIS 2022: 14th International Conference on Advanced Computer Science and Information Systems). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICACSIS56558.2022.9923501

Feliandra, Zafira Binta ; Khadijah, Siti ; Rachmadi, Muhammad Febrian et al. / Classification of Stroke and Non-Stroke Patients from Human Body Movements using Smartphone Videos and Deep Neural Networks. Proceedings - ICACSIS 2022: 14th International Conference on Advanced Computer Science and Information Systems. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 187-192 (Proceedings - ICACSIS 2022: 14th International Conference on Advanced Computer Science and Information Systems).

@inproceedings{9370e213043a40a4b0a4aa28482ed491,

title = "Classification of Stroke and Non-Stroke Patients from Human Body Movements using Smartphone Videos and Deep Neural Networks",

abstract = "This study covers a pilot study on developing a tele-health system for detection and classification of stroke and non-stroke patients from human body movements using smartphone videos. Human body poses are extracted from smartphone videos which are then transformed into RGB images and classified into either stroke (positive) or non-stroke (negative) labels. We tested PoseNet, BlazePose, and MoveNet for human body pose detection and AlexN et and SqueezeN et for classification. From this pilot study, we found that MoveNet is the best human body pose detection while AlexNet is the best for classification.",

keywords = "classification, human body movements analysis, smartphone videos, stroke movements detection",

author = "Feliandra, \{Zafira Binta\} and Siti Khadijah and Rachmadi, \{Muhammad Febrian\} and Dina Chahyati",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 14th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2022 ; Conference date: 01-10-2022 Through 03-10-2022",

year = "2022",

doi = "10.1109/ICACSIS56558.2022.9923501",

language = "English",

series = "Proceedings - ICACSIS 2022: 14th International Conference on Advanced Computer Science and Information Systems",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "187--192",

booktitle = "Proceedings - ICACSIS 2022",

address = "United States",

}

Feliandra, ZB, Khadijah, S, Rachmadi, MF & Chahyati, D 2022, Classification of Stroke and Non-Stroke Patients from Human Body Movements using Smartphone Videos and Deep Neural Networks. in Proceedings - ICACSIS 2022: 14th International Conference on Advanced Computer Science and Information Systems. Proceedings - ICACSIS 2022: 14th International Conference on Advanced Computer Science and Information Systems, Institute of Electrical and Electronics Engineers Inc., pp. 187-192, 14th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2022, Virtual, Online, Indonesia, 1/10/22. https://doi.org/10.1109/ICACSIS56558.2022.9923501

Classification of Stroke and Non-Stroke Patients from Human Body Movements using Smartphone Videos and Deep Neural Networks. / Feliandra, Zafira Binta; Khadijah, Siti; Rachmadi, Muhammad Febrian et al.
Proceedings - ICACSIS 2022: 14th International Conference on Advanced Computer Science and Information Systems. Institute of Electrical and Electronics Engineers Inc., 2022. p. 187-192 (Proceedings - ICACSIS 2022: 14th International Conference on Advanced Computer Science and Information Systems).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Classification of Stroke and Non-Stroke Patients from Human Body Movements using Smartphone Videos and Deep Neural Networks

AU - Feliandra, Zafira Binta

AU - Khadijah, Siti

AU - Rachmadi, Muhammad Febrian

AU - Chahyati, Dina

PY - 2022

Y1 - 2022

N2 - This study covers a pilot study on developing a tele-health system for detection and classification of stroke and non-stroke patients from human body movements using smartphone videos. Human body poses are extracted from smartphone videos which are then transformed into RGB images and classified into either stroke (positive) or non-stroke (negative) labels. We tested PoseNet, BlazePose, and MoveNet for human body pose detection and AlexN et and SqueezeN et for classification. From this pilot study, we found that MoveNet is the best human body pose detection while AlexNet is the best for classification.

AB - This study covers a pilot study on developing a tele-health system for detection and classification of stroke and non-stroke patients from human body movements using smartphone videos. Human body poses are extracted from smartphone videos which are then transformed into RGB images and classified into either stroke (positive) or non-stroke (negative) labels. We tested PoseNet, BlazePose, and MoveNet for human body pose detection and AlexN et and SqueezeN et for classification. From this pilot study, we found that MoveNet is the best human body pose detection while AlexNet is the best for classification.

KW - classification

KW - human body movements analysis

KW - smartphone videos

KW - stroke movements detection

UR - https://www.scopus.com/pages/publications/85142051449

U2 - 10.1109/ICACSIS56558.2022.9923501

DO - 10.1109/ICACSIS56558.2022.9923501

M3 - Conference contribution

AN - SCOPUS:85142051449

T3 - Proceedings - ICACSIS 2022: 14th International Conference on Advanced Computer Science and Information Systems

SP - 187

EP - 192

BT - Proceedings - ICACSIS 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 14th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2022

Y2 - 1 October 2022 through 3 October 2022

ER -

Feliandra ZB, Khadijah S, Rachmadi MF, Chahyati D. Classification of Stroke and Non-Stroke Patients from Human Body Movements using Smartphone Videos and Deep Neural Networks. In Proceedings - ICACSIS 2022: 14th International Conference on Advanced Computer Science and Information Systems. Institute of Electrical and Electronics Engineers Inc. 2022. p. 187-192. (Proceedings - ICACSIS 2022: 14th International Conference on Advanced Computer Science and Information Systems). doi: 10.1109/ICACSIS56558.2022.9923501

Classification of Stroke and Non-Stroke Patients from Human Body Movements using Smartphone Videos and Deep Neural Networks

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this