Edge-Intelligent Biosensing Systems with Dual Optimization of Signal Processing and Energy Management

This work presents a conceptual approach to applying bio-inspired optimization at the sensor-node level within edge-intelligent architectures for monitoring biological objects and systems. The proposed method integrates two complementary algorithms, namely the Invasive Weed-Based Model (IWBM), which performs adaptive preprocessing of sensor data to improve signal quality and the stability of extracted features, and the Hybrid Metabolic Optimization (HMO), which manages energy efficiency by adjusting sampling intervals, computational load and data transmission according to environmental conditions. Implementing these optimization mechanisms directly at the sensor node enables localized decision-making, greater autonomy and reduced dependence on cloud infrastructures. Theoretical analysis and preliminary modeling suggest that bio-inspired optimization provides a promising foundation for developing energy-efficient and adaptive sensor networks intended for future bio-cybernetic monitoring.