.png){kind=icon}
.png){kind=icon}
Return
Artificial Intelligence-Driven Ensemble Models for Virtual Reality Immersive User Experience Analysis in Human-Computer Interaction Systems
.png){kind=icon}
PRE
AI
DOI：10.1002/cav.70110.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Virtual and augmented reality (VR/AR) provides rapid access to fast-flowing information based on suitable temporal and spatial architecture. User-friendly AR interfaces enable effective interaction through efficient collaboration models integrated with human-computer interaction (HCI) methods. User experience (UX) in AR is essential for creating engaging and immersive environments and represents a subjective perception of a technological product or service. Recent design practices focus on ensuring satisfactory UX. Artificial intelligence (AI) techniques have shown remarkable progress and are increasingly adopted across industries, making AI-AR integration a promising research direction. This manuscript proposes an Ensemble of Artificial Intelligence and Optimization Algorithms for User Virtual Reality Experience (EAIOA-UVRE) in HCI to enhance UX in AR environments. Min-max normalization is applied for data pre-processing. Ensemble models, including bidirectional gated recurrent unit (BiGRU), Elman neural network (ENN), and temporal convolutional network (TCN), are employed for immersive UX classification. Enhanced hunger game search (EHGS) optimally tunes hyperparameters. Experimental evaluation on an AR experiences dataset demonstrates superior performance, achieving 98.23% accuracy, outperforming existing models.
Keywords:
artificial intelligence
enhanced hunger game search
ensemble models
human-computer interaction
user virtual reality experience
Journal
C
IF:
1.7
Papers:
45
Citations:
0
View more organizations