Human Detection With Plant Bioelectric Signal

This research aims to utilize the bioelectric potential of plants as a tool to detect human presence in the surrounding area. The potential bioelectric signals of plants are recorded using a data logger and analyzed with the help of a computer for identification. Previous methods used time series models and Z-value tests, but challenges in achieving accurate estimates remain. We use Recurrent Neural Networks (RNN) to handle the processing of large datasets in this study. The experimental results show that the RNN model is very effective and achieves a high level of accuracy, with a perfect accuracy of 1.00 from the total duration of each class is 62030 seconds (379610 samples).303688 data samples are used as train datasets, while the others (75922 samples) are used as validation datasets This shows that RNN has great potential in processing plant bioelectric data to detect human presence with very high accuracy.