A Noise Suppression of LSTM algorithm combined with Kalman filter for Agriculture Automation

An immense volume of data is produced by sensor devices in the fields of aquaponics, hydroponics, and soil-based food production, where these devices track various environmental factors. Data stream mining is the method of retrieving data from fast-sampled data sources that are constantly streaming. The accuracy of data obtained through data stream mining is largely determined by the algorithm utilized to filter out noise. For threshold-based automation, an actuator can be activated when the value of sensor data is above a permissible threshold. Noise from sensors may activate the actuator. Several statistical and machine learning-based noise-suppression algorithms have been proposed in the literature. They have been evaluated based on the mean squared error metric (MSE). The Long Short-Term Memory - LSTM filter (MSE: 0.000999943) performs better noise suppression than other traditional filters Kalman (MSE: 0.0015982). We propose a new noise suppression filter - LSTM combined with Kalman (LSTM-KF). In LSTM-KF, the Kalman filter acts as an encoder and the LSTM becomes the decoder, resulting in a significantly lower MSE - 0.000080789592. The LSTM-KF is installed in our threshold-based aquaponics automation to maximize sustainable food production at minimum cost.