Lightweight CNN-Based Deep Neural Networks Application in Safety Measurement

Wilbur Kai Heng Lua; Peter Chunyu Yau; Chee Kiat Seow; Dennis Wong

doi:10.1109/PRAI55851.2022.9904161

Lightweight CNN-Based Deep Neural Networks Application in Safety Measurement

Wilbur Kai Heng Lua
, Peter Chunyu Yau
, Chee Kiat Seow
, Dennis Wong

Faculty of Applied Sciences

University of Glasgow

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

4 Citations (Scopus)

Abstract

Inspired by the face covering period in the past two years, COVID-19 pandemic has resulted in the mandate of public safety measures such as face mask-wearing in many countries. This paper provides a preliminary feasibility planning on how Artificial Intelligence (AI), Computer Vision (CV) and the Internet of Things (IoT) can work together to implement a face-mask detection system as a public health safety solution. This paper reviews how edge computing can overcome traditional cloud computing issues. This work also examines the current state of computer vision, convolutional neural networks and their potential application in the health and safety domain. This writing serves as an interim report on how the lightweight CNNs and single-shot detectors such as YOLOv5 variants with SSD to train and deploy an object detection system.

Original language	English
Title of host publication	2022 5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	455-459
Number of pages	5
ISBN (Electronic)	9781665499163
DOIs	https://doi.org/10.1109/PRAI55851.2022.9904161
Publication status	Published - 2022
Event	5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022 - Chengdu, China Duration: 19 Aug 2022 → 21 Aug 2022

Publication series

Name	2022 5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022

Conference

Conference	5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022
Country/Territory	China
City	Chengdu
Period	19/08/22 → 21/08/22

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

AI
CNNs
COVID-19
IoT
artificial intelligence
computer vision
deep learning
edge computing
health
internet-of-things
mask
neural network
safety

Access to Document

10.1109/PRAI55851.2022.9904161

Cite this

Kai Heng Lua, W., Chunyu Yau, P., Kiat Seow, C., & Wong, D. (2022). Lightweight CNN-Based Deep Neural Networks Application in Safety Measurement. In 2022 5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022 (pp. 455-459). (2022 5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PRAI55851.2022.9904161

Kai Heng Lua, Wilbur ; Chunyu Yau, Peter ; Kiat Seow, Chee et al. / Lightweight CNN-Based Deep Neural Networks Application in Safety Measurement. 2022 5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 455-459 (2022 5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022).

@inproceedings{c1de01836ca74ab3973c1f48d9d16032,

title = "Lightweight CNN-Based Deep Neural Networks Application in Safety Measurement",

abstract = "Inspired by the face covering period in the past two years, COVID-19 pandemic has resulted in the mandate of public safety measures such as face mask-wearing in many countries. This paper provides a preliminary feasibility planning on how Artificial Intelligence (AI), Computer Vision (CV) and the Internet of Things (IoT) can work together to implement a face-mask detection system as a public health safety solution. This paper reviews how edge computing can overcome traditional cloud computing issues. This work also examines the current state of computer vision, convolutional neural networks and their potential application in the health and safety domain. This writing serves as an interim report on how the lightweight CNNs and single-shot detectors such as YOLOv5 variants with SSD to train and deploy an object detection system.",

keywords = "AI, CNNs, COVID-19, IoT, artificial intelligence, computer vision, deep learning, edge computing, health, internet-of-things, mask, neural network, safety",

author = "\{Kai Heng Lua\}, Wilbur and \{Chunyu Yau\}, Peter and \{Kiat Seow\}, Chee and Dennis Wong",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022 ; Conference date: 19-08-2022 Through 21-08-2022",

year = "2022",

doi = "10.1109/PRAI55851.2022.9904161",

language = "English",

series = "2022 5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022",

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

pages = "455--459",

booktitle = "2022 5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022",

address = "United States",

}

Kai Heng Lua, W, Chunyu Yau, P, Kiat Seow, C & Wong, D 2022, Lightweight CNN-Based Deep Neural Networks Application in Safety Measurement. in 2022 5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022. 2022 5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022, Institute of Electrical and Electronics Engineers Inc., pp. 455-459, 5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022, Chengdu, China, 19/08/22. https://doi.org/10.1109/PRAI55851.2022.9904161

Lightweight CNN-Based Deep Neural Networks Application in Safety Measurement. / Kai Heng Lua, Wilbur; Chunyu Yau, Peter; Kiat Seow, Chee et al.
2022 5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 455-459 (2022 5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022).

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

TY - GEN

T1 - Lightweight CNN-Based Deep Neural Networks Application in Safety Measurement

AU - Kai Heng Lua, Wilbur

AU - Chunyu Yau, Peter

AU - Kiat Seow, Chee

AU - Wong, Dennis

PY - 2022

Y1 - 2022

N2 - Inspired by the face covering period in the past two years, COVID-19 pandemic has resulted in the mandate of public safety measures such as face mask-wearing in many countries. This paper provides a preliminary feasibility planning on how Artificial Intelligence (AI), Computer Vision (CV) and the Internet of Things (IoT) can work together to implement a face-mask detection system as a public health safety solution. This paper reviews how edge computing can overcome traditional cloud computing issues. This work also examines the current state of computer vision, convolutional neural networks and their potential application in the health and safety domain. This writing serves as an interim report on how the lightweight CNNs and single-shot detectors such as YOLOv5 variants with SSD to train and deploy an object detection system.

AB - Inspired by the face covering period in the past two years, COVID-19 pandemic has resulted in the mandate of public safety measures such as face mask-wearing in many countries. This paper provides a preliminary feasibility planning on how Artificial Intelligence (AI), Computer Vision (CV) and the Internet of Things (IoT) can work together to implement a face-mask detection system as a public health safety solution. This paper reviews how edge computing can overcome traditional cloud computing issues. This work also examines the current state of computer vision, convolutional neural networks and their potential application in the health and safety domain. This writing serves as an interim report on how the lightweight CNNs and single-shot detectors such as YOLOv5 variants with SSD to train and deploy an object detection system.

KW - AI

KW - CNNs

KW - COVID-19

KW - IoT

KW - artificial intelligence

KW - computer vision

KW - deep learning

KW - edge computing

KW - health

KW - internet-of-things

KW - mask

KW - neural network

KW - safety

UR - https://www.scopus.com/pages/publications/85141171477

U2 - 10.1109/PRAI55851.2022.9904161

DO - 10.1109/PRAI55851.2022.9904161

M3 - Conference contribution

AN - SCOPUS:85141171477

T3 - 2022 5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022

SP - 455

EP - 459

BT - 2022 5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022

Y2 - 19 August 2022 through 21 August 2022

ER -

Kai Heng Lua W, Chunyu Yau P, Kiat Seow C, Wong D. Lightweight CNN-Based Deep Neural Networks Application in Safety Measurement. In 2022 5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 455-459. (2022 5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022). doi: 10.1109/PRAI55851.2022.9904161

Lightweight CNN-Based Deep Neural Networks Application in Safety Measurement

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this