A Deep Learning Approach for Real-Time Analysis of Attendees’ Engagement in Public Events

Smart city analytics requires the harnessing and analysis of emotions and sentiments conveyed by images and video footage. In recent years, facial sentiment analysis attracted significant attention for different application areas, including marketing, gaming, political analytics, healthcare, and hum...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Samuel Mathew, Sujith (author)
مؤلفون آخرون: Alkhatib, Manar (author), El Barachi , May (author)
منشور في: 2021
الموضوعات:
الوصول للمادة أونلاين:https://bspace.buid.ac.ae/handle/1234/3075
https://doi.org/10.24138/jcomss-2021-0072.
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1862980615032274944
author Samuel Mathew, Sujith
author2 Alkhatib, Manar
El Barachi , May
author2_role author
author
author_facet Samuel Mathew, Sujith
Alkhatib, Manar
El Barachi , May
author_role author
dc.creator.none.fl_str_mv Samuel Mathew, Sujith
Alkhatib, Manar
El Barachi , May
dc.date.none.fl_str_mv 2021-06-02
2025-05-15T11:19:16Z
2025-05-15T11:19:16Z
dc.identifier.none.fl_str_mv Sujith Samuel Mathew, Manar AlKhatib and May El Barachi (2021) “A Deep Learning Approach for Real-Time Analysis of Attendees’ Engagement in Public Events,” Journal of Communications Software and Systems, 17(2), pp. 106–115.
1845-6421, 1846-6079
https://bspace.buid.ac.ae/handle/1234/3075
https://doi.org/10.24138/jcomss-2021-0072.
dc.language.none.fl_str_mv en_US
dc.publisher.none.fl_str_mv CCIS
dc.relation.none.fl_str_mv Journal of Communications Software and Systemsv17 n2 (20210601): 106-115
dc.subject.none.fl_str_mv smart cities, sentiment analysis, facial recognition, convolutional neural networks, deep learning
dc.title.none.fl_str_mv A Deep Learning Approach for Real-Time Analysis of Attendees’ Engagement in Public Events
dc.type.none.fl_str_mv Article
description Smart city analytics requires the harnessing and analysis of emotions and sentiments conveyed by images and video footage. In recent years, facial sentiment analysis attracted significant attention for different application areas, including marketing, gaming, political analytics, healthcare, and human computer interaction. Aiming at contributing to this area, we propose a deep learning model enabling the accurate emotion analysis of crowded scenes containing complete and partially occluded faces, with different angles, various distances from the camera, and varying resolutions. Our model consists of a sophisticated convolutional neural network (CNN) that is combined with pooling, densifying, flattening, and Softmax layers to achieve accurate sentiment and emotion analysis of facial images. The proposed model was successfully tested using 3,750 images containing 22,563 faces, collected from a large consumer electronics trade show. The model was able to correctly classify the test images which contained faces with different angles, distances, occlusion areas, facial orientation and resolutions. It achieved an average accuracy of 90.6% when distinguishing between seven emotions (Happiness, smiling, laughter, neutral, sadness, anger, and surprise) in complete faces, and 86.16% accuracy in partially occluded faces. Such model can be leveraged for the automatic analysis of attendees’ engagement level in events. Furthermore, it can open the door for many useful applications in smart cities, such as measuring employees’ satisfaction and citizens’ happiness.
id budr_901caec5b05e1b709decd27a204eb57c
identifier_str_mv Sujith Samuel Mathew, Manar AlKhatib and May El Barachi (2021) “A Deep Learning Approach for Real-Time Analysis of Attendees’ Engagement in Public Events,” Journal of Communications Software and Systems, 17(2), pp. 106–115.
1845-6421, 1846-6079
language_invalid_str_mv en_US
network_acronym_str budr
network_name_str The British University in Dubai repository
oai_identifier_str oai:bspace.buid.ac.ae:1234/3075
publishDate 2021
publisher.none.fl_str_mv CCIS
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling A Deep Learning Approach for Real-Time Analysis of Attendees’ Engagement in Public EventsSamuel Mathew, SujithAlkhatib, ManarEl Barachi , Maysmart cities, sentiment analysis, facial recognition, convolutional neural networks, deep learningSmart city analytics requires the harnessing and analysis of emotions and sentiments conveyed by images and video footage. In recent years, facial sentiment analysis attracted significant attention for different application areas, including marketing, gaming, political analytics, healthcare, and human computer interaction. Aiming at contributing to this area, we propose a deep learning model enabling the accurate emotion analysis of crowded scenes containing complete and partially occluded faces, with different angles, various distances from the camera, and varying resolutions. Our model consists of a sophisticated convolutional neural network (CNN) that is combined with pooling, densifying, flattening, and Softmax layers to achieve accurate sentiment and emotion analysis of facial images. The proposed model was successfully tested using 3,750 images containing 22,563 faces, collected from a large consumer electronics trade show. The model was able to correctly classify the test images which contained faces with different angles, distances, occlusion areas, facial orientation and resolutions. It achieved an average accuracy of 90.6% when distinguishing between seven emotions (Happiness, smiling, laughter, neutral, sadness, anger, and surprise) in complete faces, and 86.16% accuracy in partially occluded faces. Such model can be leveraged for the automatic analysis of attendees’ engagement level in events. Furthermore, it can open the door for many useful applications in smart cities, such as measuring employees’ satisfaction and citizens’ happiness.CCIS2025-05-15T11:19:16Z2025-05-15T11:19:16Z2021-06-02ArticleSujith Samuel Mathew, Manar AlKhatib and May El Barachi (2021) “A Deep Learning Approach for Real-Time Analysis of Attendees’ Engagement in Public Events,” Journal of Communications Software and Systems, 17(2), pp. 106–115.1845-6421, 1846-6079https://bspace.buid.ac.ae/handle/1234/3075https://doi.org/10.24138/jcomss-2021-0072.en_USJournal of Communications Software and Systemsv17 n2 (20210601): 106-115oai:bspace.buid.ac.ae:1234/30752026-01-29T16:51:44Z
spellingShingle A Deep Learning Approach for Real-Time Analysis of Attendees’ Engagement in Public Events
Samuel Mathew, Sujith
smart cities, sentiment analysis, facial recognition, convolutional neural networks, deep learning
title A Deep Learning Approach for Real-Time Analysis of Attendees’ Engagement in Public Events
title_full A Deep Learning Approach for Real-Time Analysis of Attendees’ Engagement in Public Events
title_fullStr A Deep Learning Approach for Real-Time Analysis of Attendees’ Engagement in Public Events
title_full_unstemmed A Deep Learning Approach for Real-Time Analysis of Attendees’ Engagement in Public Events
title_short A Deep Learning Approach for Real-Time Analysis of Attendees’ Engagement in Public Events
title_sort A Deep Learning Approach for Real-Time Analysis of Attendees’ Engagement in Public Events
topic smart cities, sentiment analysis, facial recognition, convolutional neural networks, deep learning
url https://bspace.buid.ac.ae/handle/1234/3075
https://doi.org/10.24138/jcomss-2021-0072.