Analysis on Deep Learning approaches in Video classification of Human Activity Recognition

Analysis on Deep Learning approaches in Video classification of Human Activity Recognition

Registration ID: IJNRD_220824

Published ID: IJNRD2406127

DOI: http://doi.one/10.1729/Journal.40091

S.A. Amutha Jeevakumari , Koushik Dey

This paper investigates two cutting-edge Deep Learning approaches: Long-term Recurrent Convolutional Networks (LRCN) and Convolutional Long Short-term Memory (ConvLSTM) networks in the video classification of Human Activity Recognition (HAR). ConvLSTM adds convolutional components to recurrent networks so that the model may efficiently collect spatial-temporal data. LRCN is a sequential neural network that confidently exhibits proficiency in processing sequential and spatial data, thereby addressing the challenge of video action classification effectively and confidently. The LRCN architecture employed in this model comprises an encoder and decoder. The encoder is composed of time-distributed convolutional layers, succeeded by an LSTM layer, which results in a reduction of spatial dimensions. The decoder encompasses a dense layer, an LSTM layer incorporating dropout, and a subsequent dense layer, designed for classification. We implement a variety of experimental configurations, encompassing distinct frame counts per video and employing learning strategies to enhance overall performance. Both models underwent training and assessment utilizing a standard action recognition dataset, UCF50. While both models demonstrate noteworthy accuracy, the LRCN model surpasses the ConvLSTM model by achieving a remarkable 96.67% accuracy with the UCF50 dataset.

Published Paper   E-Certificate

"Analysis on Deep Learning approaches in Video classification of Human Activity Recognition", IJNRD - INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT (www.IJNRD.org), ISSN:2456-4184, Vol.9, Issue 6, page no.b266-b278, June-2024, Available :https://ijnrd.org/papers/IJNRD2406127.pdf

Volume 9 Issue 6, June-2024

Pages : b266-b278

Paper Reg. ID: IJNRD_220824

Published Paper Id: IJNRD2406127

Downloads: 000121242

Research Area: Computer Science & Technology 

Country: Chennai Campus, Tamil Nadu, India

Published Paper PDF: https://ijnrd.org/papers/IJNRD2406127.pdf

Published Paper URL: https://ijnrd.org/viewpaperforall?paper=IJNRD2406127

DOI: http://doi.one/10.1729/Journal.40091

Journal Name: INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT(IJNRD)

ISSN: 2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar | ESTD YEAR: 2016

An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator

Publisher: IJNRD (IJ Publication) Janvi Wave

This work is licensed under a Creative Commons Attribution 4.0 International License and The Open Definition

Call For Paper - Volume 10 | Issue 8 | August 2025

IJNRD is Scholarly open access journals, Peer-reviewed, and Refereed Journals, High Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool), Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI) with Open-Access Publications.

INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT (IJNRD) aims to explore advances in research pertaining to applied, theoretical and experimental Technological studies. The goal is to promote scientific information interchange between researchers, developers, engineers, students, and practitioners working in and around the world. IJNRD will provide an opportunity for practitioners and educators of engineering field to exchange research evidence, models of best practice and innovative ideas.

Indexing In Google Scholar, SSRN, ResearcherID-Publons, Semantic Scholar | AI-Powered Research Tool, Microsoft Academic, Academia.edu, arXiv.org, Research Gate, CiteSeerX, ResearcherID Thomson Reuters, Mendeley : reference manager, DocStoc, ISSUU, Scribd, and many more

How to submit the paper?

Important Dates for Current issue

Paper Submission Open For: August 2025

Current Issue: Volume 10 | Issue 8

Last Date for Paper Submission: Till 31-Aug-2025

Notification of Review Result: Within 1-2 Days after Submitting paper.

Publication of Paper: Within 01-02 Days after Submititng documents.

Frequency: Monthly (12 issue Annually).

Journal Type: International Peer-reviewed, Refereed, and Open Access Journal.

Subject Category: Research Area