Audio-visual emotion recognition (AVER) is central to affective computing systems that require reliable, real-time interpretation of human emotions. However, many existing multimodal models treat feature learning and deployment efficiency separately, limiting their ability to preserve hierarchical facial relationships, capture long-range speech dynamics, and operate with low latency in distributed settings. This study proposes a latency-aware hybrid Transformer–capsule network for audio-visual emotion recognition in a simulated edge–fog–cloud environment. The visual stream employs a CNN–Capsule branch to retain spatial hierarchies in facial expressions, while the audio stream uses a CNN–Transformer branch to learn local spectral patterns and long-range temporal dependencies from speech. A cross-modal Transformer fusion module integrates complementary emotional cues, and a latency-aware task-allocation mechanism allocates preprocessing, inference, and training-related operations across edge, fog, and cloud layers according to workload, node capacity, and communication delay. Unlike approaches that optimize multimodal representation learning and distributed deployment as separate problems, the proposed framework adopts a deployment-aware co-design in which spatial visual representation, temporal acoustic modeling, multimodal interaction, and deterministic latency-aware task allocation are coordinated within a unified processing pipeline. The framework is evaluated on RAVDESS, CREMA-D, and SAVEE using a subject-independent protocol. Experimental results show an average accuracy of 91.5%, an F1-score of 90.7%, an MCC of 0.894, and an AUC of 0.950. The framework further incorporates a deterministic latency-aware task-allocation mechanism for coordinating operations across edge, fog, and cloud resources. Physical-device deployment and comprehensive resource profiling remain subjects for future validation.
The evolution of modern enterprise architecture has been strongly influenced by distributed web services, especially protocol-based standards such as Simple Object Access Protocol (SOAP) and resource-oriented architectural styles such as Representational State Transfer (REST). Cloud-native ecosystems, microservice architectures, and public API management commonly favor the lightweight, JSON-compatible, and horizontally scalable characteristics of RESTful services, whereas legacy configurations and highly regulated environments continue to use SOAP because of its formal contracts and compatibility with WS-* specifications for message-level security, reliable messaging, and transaction coordination. This paper presents a structured literature review that evaluates the architectural trade-offs, performance patterns, security boundaries, reliability considerations, and enterprise use cases of REST and SOAP. The review follows PRISMA-informed reporting practices and software-engineering review guidance, but it is not presented as an exhaustive systematic review because the original search strategy required REST and SOAP terms to appear together. IEEE Xplore, ACM Digital Library, ScienceDirect, and Scopus were searched for studies published between 2021 and 2026, resulting in 32 selected studies. The selected literature contains different evidence roles, including direct REST-SOAP empirical comparisons, REST-only and SOAP-only empirical studies, implementation studies, analytical papers, surveys, reviews, and contextual technical sources. The synthesis therefore separates direct empirical evidence from contextual and secondary evidence. The findings indicate that RESTful APIs generally show lower latency, smaller payloads, simpler parsing, and better horizontal scalability in the reported benchmark and web-facing settings, while SOAP remains relevant where formal service contracts, message-level protection, reliable messaging patterns, and transaction coordination are required. The paper identifies gaps in production-representative stress testing, empirical security comparison, reference-level traceability, and independent validation of hybrid REST-SOAP decision models. The resulting decision framework is presented as a provisional evidence-informed decision aid, not as an empirically validated tool.
Puganeswaran Kannan, Wei-Yen Chong, Mohd Fareez Said Rahman et al.· Future Internet· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
