mailto:uumlib@uum.edu.my 24x7 Service; AnyTime; AnyWhere

Multimodal deep learning architecture to evaluate emotion recognition in tea packing

Xue, Yang and Ismail, Adzrool Idzwan (2024) Multimodal deep learning architecture to evaluate emotion recognition in tea packing. International Journal of Intelligent Systems and Applications in Engineering, 6 (12). pp. 521-532. ISSN 21476799

[thumbnail of IJISAE 06 12 2024 521-532.pdf]
Preview
PDF - Published Version
Available under License ["licenses_description_cc4_by_sa" not defined].

Download (525kB) | Preview

Abstract

The packaging of consumer goods, including tea, is increasingly evolving beyond its conventional role as a mere container. Virtual reality (VR) has found innovative applications in the field of packaging, transforming the way products are designed, marketed, and experienced. This research paper proposed a novel tea packaging by integrating virtual reality (VR), emotion recognition technology, and a novel Multimodal Fusion Deep LSTM (MFD-LSTM) model, creating a dynamic and interactive tea packaging experience that engages all the senses. The core contribution of this study revolves around the fusion of VR technology, emotion recognition, and the MFD-LSTM model. This synergy enables tea packaging to become a dynamic medium for conveying brand narratives and invoking emotional responses in consumers. The MFD-LSTM model, capable of processing multiple sensory inputs simultaneously, offers real-time recognition of consumer emotions, which, in turn, influences the unfolding VR experience. It is his research advocates for the widespread adoption of the interactive tea packaging experience model, which harnesses VR, emotion recognition, and the MFD-LSTM model to create a multisensory and emotionally resonant connection between tea brands and consumers. The proposed MFD-LSTM model effectively evaluates the emotions and increases the performance towards packing. Through analysis, it is concluded that the proposed MFD-LSTM model is effective in the packing scenario.

Item Type: Article
Uncontrolled Keywords: Multi Modal, LSTM, Deep Learning, Emotion Recognition, Virtual Reality, Tea Packing
Subjects: Q Science > QA Mathematics > QA76 Computer software
T Technology > TS Manufactures
Divisions: School of Creative Industry Management and Performing Arts
Depositing User: Mr. Izhar Hj. Hashim
Date Deposited: 16 Nov 2026 11:05
Last Modified: 16 Nov 2026 11:05
URI: https://repo.uum.edu.my/id/eprint/35454

Actions (login required)

View Item View Item