emotion_labels.zip

We present a systematic investigation of Purple Heart plant (Tradescantia pallida) bioelectrical signals for dual-purpose classification tasks: environmental state detection and human emotion recognition. Using an AD8232 ECG sensor at 400Hz sampling rate, we recorded 3-second bioelectrical signal segments with 1-second overlap, converting them to mel-spectrograms for ResNet18 CNN classification. For lamp on/off detection, we achieved 85.4% accuracy with balanced precision (0.85-0.86) and recall (0.84-0.86) metrics across 2,767 spectrogram samples. For human emotion classification, our system achieved optimal performance at 73% accuracy with 1-second lag, distinguishing between happy and sad emotional states across 1,619 samples. These results demonstrate the viability of plant bioelectrical signals as environmental sensors and provide preliminary evidence for emotion detection capabilities, opening new research directions in bio-informational engineering and plant-computer interfaces.