Real-Time Stress Detection and Secure Communication in Wireless IoT Networks Using the Secure Dual-Stream Edge Fusion Optimization (SDEFO) Algorithm

The rapid proliferation of Internet of Things (IoT) technologies has enabled the development of more advanced applications, such as stress detection in healthcare and occupational settings. Still, IoT networks face vulnerabilities related to privacy and latency requirements during real-time aerial data processing. This work proposes a paradigm-shifting Secure Dual Stream Edge Fusion Optimization (SDEFO) algorithm that simultaneously solves two significant challenges: (1) realtime stress monitoring and automated feedback using physiological sensor data; and (2) communication security across wireless IoT nodes. Within the proposed SDEFO framework, dualstream edge analytics bio-signal processing (e.g., GSR or heart rate variability) is emotion-aware and deregulated. At the same time, network threat levels dictate responsive routing and encryption at the node level. A multilayered fusion technique integrates biometric feature extraction with entropy-based secure transmission, strengthening reliability and privacy simultaneously. The system is tested on a real-time dataset acquired through wearable IoT sensors under various stress levels and network threat simulations. Evaluation results demonstrate enhanced accuracy in stress detection, accompanied by lower packet loss and improved resilience to denial-of-service attacks and data tampering. The model demonstrates improvement over other proposed single-stream and non-secure configurations in latency, throughput, and security index. This study has significant implications for health monitoring, innovative workplaces, and defense communication systems, where both data transmission reliability and confidentiality are crucial. This paper presents a novel, multilayered architecture that integrates affective computing with cryptographic routing to enhance the design of intelligent, secure, and adaptive IoT networks.