IoT-Driven Mushroom Farm Automation Using Neural Turing Machines (NTM)

Mushroom cultivation leads global agriculture due to its impact on worldwide trade. One of the main challenges in this area is optimal weather, especially temperature and humidity. Unfortunately, traditional farming's inability to achieve these conditions often leads to low yields. The recommended procedure involves collecting sensor data, constructing the model, and training it. Preprocessing includes spectral smoothing, normalization, and reflectance calibration. Sensors measure motion, temperature, light, and soil moisture. Photo feature extraction uses edge detection to identify objects. The model is trained using NTM. The suggested NTM-based model beats top-tier models like Random Forest (RF) and Support Vector Machine (SVM) with 92.35 percent accuracy. This increasing accuracy shows the model's mushroom production optimization. This proposed uses sensor data and current image processing techniques to improve mushroom farming conditions. NTM-based mushroom cultivation is more efficient and yields more than conventional methods.