NORMA eResearch @NCI Library

Detection of Violent activities in the Cloud Computing Environment using Gated Recurrent Unit

Gugale, Honey Rajendra (2022) Detection of Violent activities in the Cloud Computing Environment using Gated Recurrent Unit. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
Preview
PDF (Configuration manual)
Download (2MB) | Preview

Abstract

Over the years, violence has been increasing among different communities and people. The surging apprehension has demanded various approaches to counter the violence. Around the world, the authorities have implemented various approaches, from multiple rules and regulations to technologies. However, the measures implemented for decades were not enough to hinder the violence. There are multiple types of violence, such as shoving, thrashing, biting, piercing knives, shooting with a gun, etc. Therefore, in our study, we have introduced a novel approach by implementing advanced deep learning architectures—the study aimed for an optimal model to automatically detect violence through the surveillance system. Various DNN algorithms were considered, such as GRU, RNN, and LSTM. Each algorithm was implemented and assessed using specific evaluation metrics. The best-performing model was considered in the cloud interface for further implementations.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Cloud computing
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Cloud Computing
Depositing User: Tamara Malone
Date Deposited: 29 Nov 2022 15:19
Last Modified: 08 Mar 2023 14:56
URI: https://norma.ncirl.ie/id/eprint/5939

Actions (login required)

View Item View Item