Leveraging sequential deep learning models for detecting multitude of human action categories

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2023.

Bibliografiske detaljer
Main Authors:	Pranta, Kazi Al Refat, Islam, Fahad Mohammad Rejwanul, Ahmed, Khandakar Fahim, Saha, Prince, Rahman, Naimur
Andre forfattere:	Reza, Tanzim
Format:	Thesis
Sprog:	English
Udgivet:	Brac University 2024
Fag:	Human action recognition Intelligent decision-making Recurrent neural network (RNN) Machine learning Convolutional long short-term memory Deep learning (Machine learning) Neural networks (Computer science) Cognitive learning theory (Deep learning)
Online adgang:	http://hdl.handle.net/10361/22890

id	10361-22890
record_format	dspace
spelling	10361-228902024-05-20T21:04:21Z Leveraging sequential deep learning models for detecting multitude of human action categories Pranta, Kazi Al Refat Islam, Fahad Mohammad Rejwanul Ahmed, Khandakar Fahim Saha, Prince Rahman, Naimur Reza, Tanzim Rahman, Rafeed Department of Computer Science and Engineering, Brac University Human action recognition Intelligent decision-making Recurrent neural network (RNN) Machine learning Convolutional long short-term memory Deep learning (Machine learning) Neural networks (Computer science) Cognitive learning theory (Deep learning) This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2023. Cataloged from PDF version of thesis. Includes bibliographical references (pages 38-40). In today’s world, where science and technology are constantly evolving day by day, people are drawn to tangible experiences and visual representations. There’s a growing effort to teach machines about human movements and postures to enable smart decision-making. This has led to increased interest in the field of human action recognition (HAR) among researchers globally. Our research focuses on implementing advanced technologies to address criminal activities, specifically emphasizing Human Activity Recognition (HAR). Moreover, our dataset includes 1275 videos, covering 20 different actions involving both violent and non-violent behaviors. In addition, we have developed a pipeline that utilizes YOLO-v8 to extract background, followed by models for accurate video classification. two models,conv-lstm and lrcn, were incorporated into our deep learning pipeline. Through our observations, we found that the LRCN model outperformed the other model, achieving an accuracy of 62% and an F1 score of 60% for the 20 classes, for 17 classes an accuracy of 63% and an F1 score of 66%. for binary classification LRCN got accuracy of 88% and an F1 score of 87%Our research focusses the potential of advanced technologies to significantly improve Human Activity Recognition (HAR) in addressing various aspects of criminal activities in real-time scenario. This marks a substantial step forward in intelligent decision-making and public safety. Kazi Al Refat Pranta Fahad Mohammad Rejwanul Isalm Khandakar Fahim Ahmed Prince Saha Naimur Rahman B.Sc in Computer Science 2024-05-20T08:57:10Z 2024-05-20T08:57:10Z ©2023 2023-09 Thesis ID: 23341120 ID: 20101443 ID: 23241110 ID: 19301212 ID: 20101484 http://hdl.handle.net/10361/22890 en Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 45 pages application/pdf Brac University
institution	Brac University
collection	Institutional Repository
language	English
topic	Human action recognition Intelligent decision-making Recurrent neural network (RNN) Machine learning Convolutional long short-term memory Deep learning (Machine learning) Neural networks (Computer science) Cognitive learning theory (Deep learning)
spellingShingle	Human action recognition Intelligent decision-making Recurrent neural network (RNN) Machine learning Convolutional long short-term memory Deep learning (Machine learning) Neural networks (Computer science) Cognitive learning theory (Deep learning) Pranta, Kazi Al Refat Islam, Fahad Mohammad Rejwanul Ahmed, Khandakar Fahim Saha, Prince Rahman, Naimur Leveraging sequential deep learning models for detecting multitude of human action categories
description	This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2023.
author2	Reza, Tanzim
author_facet	Reza, Tanzim Pranta, Kazi Al Refat Islam, Fahad Mohammad Rejwanul Ahmed, Khandakar Fahim Saha, Prince Rahman, Naimur
format	Thesis
author	Pranta, Kazi Al Refat Islam, Fahad Mohammad Rejwanul Ahmed, Khandakar Fahim Saha, Prince Rahman, Naimur
author_sort	Pranta, Kazi Al Refat
title	Leveraging sequential deep learning models for detecting multitude of human action categories
title_short	Leveraging sequential deep learning models for detecting multitude of human action categories
title_full	Leveraging sequential deep learning models for detecting multitude of human action categories
title_fullStr	Leveraging sequential deep learning models for detecting multitude of human action categories
title_full_unstemmed	Leveraging sequential deep learning models for detecting multitude of human action categories
title_sort	leveraging sequential deep learning models for detecting multitude of human action categories
publisher	Brac University
publishDate	2024
url	http://hdl.handle.net/10361/22890
work_keys_str_mv	AT prantakazialrefat leveragingsequentialdeeplearningmodelsfordetectingmultitudeofhumanactioncategories AT islamfahadmohammadrejwanul leveragingsequentialdeeplearningmodelsfordetectingmultitudeofhumanactioncategories AT ahmedkhandakarfahim leveragingsequentialdeeplearningmodelsfordetectingmultitudeofhumanactioncategories AT sahaprince leveragingsequentialdeeplearningmodelsfordetectingmultitudeofhumanactioncategories AT rahmannaimur leveragingsequentialdeeplearningmodelsfordetectingmultitudeofhumanactioncategories
_version_	1814309451118673920

Leveraging sequential deep learning models for detecting multitude of human action categories

Lignende værker