Cross-individual electrophysiological signal recognition in Clivia biosensors via domain adaptation

This study explores the use of Clivia plants as biosensors for environmental monitoring and ecological protection, focusing on the analysis of electrophysiological signals generated under various stress conditions. Plants’ ability to produce real-time electrophysiological signals in response to stressors such as salinity, drought, and pest infestations presents a promising method for precision agriculture and ecological surveillance. However, a key challenge is the significant variability in plant responses and signal distributions across individual plants, which limits the generalizability of models trained on specific plant samples.To address this, we introduce DA-PlantNet, a novel model that leverages domain adaptation techniques to enhance the model's adaptability and transferability across different plant individuals. By minimizing discrepancies in feature distribution between plants, DA-PlantNet effectively differentiates and classifies electrophysiological signals from various Clivia individuals, enabling robust cross-individual classification. We collected signals from Clivia plants under varying soil moisture conditions and analyzed them using DA-PlantNet. Experimental results demonstrate that DA-PlantNet significantly outperforms traditional methods, achieving an accuracy of 95.336 %, precision of 93.853 %, recall of 95.467 %, and an F1-score of 94.047 %, underscoring its robustness and generalization capability.This research introduces a novel approach to enhancing the adaptability and transferability of plant-based biosensor models, paving the way for scalable and reliable applications in precision agriculture and environmental monitoring. DA-PlantNet offers a valuable tool for ecological protection and sustainable agricultural practices, advancing the engineering of plant-based biosensors for real-world applications.