植物能通过电波感知人类情绪，识别准确率达97%
Plant Bioelectric Early Warning Systems: A Five-Year Investigation into Human-Plant Electromagnetic Communication
- 用自研传感器与深度学习分析植物电压波动
- 识别人类情绪准确率97%，远超随机水平
- 适合对植物智能和人机交互感兴趣的读者
本文基于2020-2025年五年的系统研究，探索植物对人类存在与情绪状态的生物电响应。通过定制植物传感器与机器学习分类，发现植物会生成与人类接近、情绪状态及生理状况相关的特异性生物电信号。基于ResNet50架构的深度学习模型，在植物电压光谱图上对人类情绪分类达到97%准确率，而标签随机打乱的对照模型仅30%准确。研究整合了个体识别（66%准确率）、韵律手势检测、压力预测以及对人类语音和动作的响应等多项实验结果。我们提出这些现象可能代表进化出的反植食动物预警系统，植物通过生物电场变化在接触前感知临近动物。研究挑战了传统对植物感知能力的认知，为农业、医疗及人-植物交互研究提供新思路。
原文摘要 · Abstract (English)
We present a comprehensive investigation into plant bioelectric responses to human presence and emotional states, building on five years of systematic research. Using custom-built plant sensors and machine learning classification, we demonstrate that plants generate distinct bioelectric signals correlating with human proximity, emotional states, and physiological conditions. A deep learning model based on ResNet50 architecture achieved 97% accuracy in classifying human emotional states through plant voltage spectrograms, while control models with shuffled labels achieved only 30% accuracy. This study synthesizes findings from multiple experiments spanning 2020-2025, including individual recognition (66% accuracy), eurythmic gesture detection, stress prediction, and responses to human voice and movement. We propose that these phenomena represent evolved anti-herbivory early warning systems, where plants detect approaching animals through bioelectric field changes before physical contact. Our results challenge conventional understanding of plant sensory capabilities and suggest practical applications in agriculture, healthcare, and human-plant interaction research.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。