A Novel Front Door Security (FDS) Algorithm Using GoogleNet-BiLSTM Hybridization
Security has always been a significant concern since the dawn of human civilization. That is why we build houses to keep ourselves and our belongings safe. And we do not hesitate to spend a lot on front-door locks and install CCTV cameras to monitor security threats. This paper presents an innovativ...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10050861/ |
_version_ | 1811161991588347904 |
---|---|
author | Luiz Paulo Oliveira Paula Nuruzzaman Faruqui Imran Mahmud Md. Whaiduzzaman Eric Charles Hawkinson Sandeep Trivedi |
author_facet | Luiz Paulo Oliveira Paula Nuruzzaman Faruqui Imran Mahmud Md. Whaiduzzaman Eric Charles Hawkinson Sandeep Trivedi |
author_sort | Luiz Paulo Oliveira Paula |
collection | DOAJ |
description | Security has always been a significant concern since the dawn of human civilization. That is why we build houses to keep ourselves and our belongings safe. And we do not hesitate to spend a lot on front-door locks and install CCTV cameras to monitor security threats. This paper presents an innovative automatic Front Door Security (FDS) algorithm that uses Human Activity Recognition (HAR) to detect four different security threats at the front door from a real-time video feed with 73.18% accuracy. The activities are recognized using an innovative combination of GoogleNet-BiLSTM hybrid network. This network receives the video feed from the CCTV camera and classifies the activities. The proposed algorithm uses this classification to alert any attempts to break the door by kicking, punching, or hitting. Furthermore, the proposed FDS algorithm is effective in detecting gun violence at the front door, which further strengthens security. This Human Activity Recognition (HAR)-based novel FDS algorithm demonstrates the potential of ensuring better safety with 71.49% precision, 68.2% recall, and an F1-score of 0.65. |
first_indexed | 2024-04-10T06:22:50Z |
format | Article |
id | doaj.art-7111ee55a23e4e9d84019812c4c6248b |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-04-10T06:22:50Z |
publishDate | 2023-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-7111ee55a23e4e9d84019812c4c6248b2023-03-02T00:00:37ZengIEEEIEEE Access2169-35362023-01-0111191221913410.1109/ACCESS.2023.324850910050861A Novel Front Door Security (FDS) Algorithm Using GoogleNet-BiLSTM HybridizationLuiz Paulo Oliveira Paula0https://orcid.org/0000-0003-2514-0280Nuruzzaman Faruqui1Imran Mahmud2https://orcid.org/0000-0003-2962-8515Md. Whaiduzzaman3https://orcid.org/0000-0003-2822-0657Eric Charles Hawkinson4Sandeep Trivedi5https://orcid.org/0000-0002-1709-247XCentro Universitârio UniBTA, São Paulo, BrazilDepartment of Software Engineering, Daffodil International University, Birulia, BangladeshDepartment of Software Engineering, Daffodil International University, Birulia, BangladeshSchool of Information Systems, Queensland University of Technology, Brisbane, QLD, AustraliaDepartment of Global Tourism, Kyoto University of Foreign Studies, Kyoto, JapanDeloitte Consulting LLP, Houston, TX, USASecurity has always been a significant concern since the dawn of human civilization. That is why we build houses to keep ourselves and our belongings safe. And we do not hesitate to spend a lot on front-door locks and install CCTV cameras to monitor security threats. This paper presents an innovative automatic Front Door Security (FDS) algorithm that uses Human Activity Recognition (HAR) to detect four different security threats at the front door from a real-time video feed with 73.18% accuracy. The activities are recognized using an innovative combination of GoogleNet-BiLSTM hybrid network. This network receives the video feed from the CCTV camera and classifies the activities. The proposed algorithm uses this classification to alert any attempts to break the door by kicking, punching, or hitting. Furthermore, the proposed FDS algorithm is effective in detecting gun violence at the front door, which further strengthens security. This Human Activity Recognition (HAR)-based novel FDS algorithm demonstrates the potential of ensuring better safety with 71.49% precision, 68.2% recall, and an F1-score of 0.65.https://ieeexplore.ieee.org/document/10050861/Intelligent surveillancereal-time securitydeep learninghybrid networkssequence foldingvideo-frame feature vector |
spellingShingle | Luiz Paulo Oliveira Paula Nuruzzaman Faruqui Imran Mahmud Md. Whaiduzzaman Eric Charles Hawkinson Sandeep Trivedi A Novel Front Door Security (FDS) Algorithm Using GoogleNet-BiLSTM Hybridization IEEE Access Intelligent surveillance real-time security deep learning hybrid networks sequence folding video-frame feature vector |
title | A Novel Front Door Security (FDS) Algorithm Using GoogleNet-BiLSTM Hybridization |
title_full | A Novel Front Door Security (FDS) Algorithm Using GoogleNet-BiLSTM Hybridization |
title_fullStr | A Novel Front Door Security (FDS) Algorithm Using GoogleNet-BiLSTM Hybridization |
title_full_unstemmed | A Novel Front Door Security (FDS) Algorithm Using GoogleNet-BiLSTM Hybridization |
title_short | A Novel Front Door Security (FDS) Algorithm Using GoogleNet-BiLSTM Hybridization |
title_sort | novel front door security fds algorithm using googlenet bilstm hybridization |
topic | Intelligent surveillance real-time security deep learning hybrid networks sequence folding video-frame feature vector |
url | https://ieeexplore.ieee.org/document/10050861/ |
work_keys_str_mv | AT luizpaulooliveirapaula anovelfrontdoorsecurityfdsalgorithmusinggooglenetbilstmhybridization AT nuruzzamanfaruqui anovelfrontdoorsecurityfdsalgorithmusinggooglenetbilstmhybridization AT imranmahmud anovelfrontdoorsecurityfdsalgorithmusinggooglenetbilstmhybridization AT mdwhaiduzzaman anovelfrontdoorsecurityfdsalgorithmusinggooglenetbilstmhybridization AT ericcharleshawkinson anovelfrontdoorsecurityfdsalgorithmusinggooglenetbilstmhybridization AT sandeeptrivedi anovelfrontdoorsecurityfdsalgorithmusinggooglenetbilstmhybridization AT luizpaulooliveirapaula novelfrontdoorsecurityfdsalgorithmusinggooglenetbilstmhybridization AT nuruzzamanfaruqui novelfrontdoorsecurityfdsalgorithmusinggooglenetbilstmhybridization AT imranmahmud novelfrontdoorsecurityfdsalgorithmusinggooglenetbilstmhybridization AT mdwhaiduzzaman novelfrontdoorsecurityfdsalgorithmusinggooglenetbilstmhybridization AT ericcharleshawkinson novelfrontdoorsecurityfdsalgorithmusinggooglenetbilstmhybridization AT sandeeptrivedi novelfrontdoorsecurityfdsalgorithmusinggooglenetbilstmhybridization |