Comparison of Long Short-Term Memory and Alexnet model for predicting pest in agriculture land.

The purpose of this study was to enhance the ability to predict agricultural pests. In this section, we will outline the materials and methods used in the study. In the realm of agricultural pest prediction, the utilization of Long Short-Term Memory (LSTM) and Alexnet models has been employed, employing a diverse range of training and testing splits. Approximately 85% ofthe Gpower test is employed, with a significance level of 0.07 and a power of 0.75. The obtained results indicate that the LSTM model demonstrates superior performance in object identification compared to Logistic Regression. This conclusion is supported by a significance value of 0.461 (Two tailed, p>0.07), with LSTM achieving an accuracy of 93.4050% compared to Logistic Regression's accuracy of 80.7621% (p<0.05). When conducting a comparison between LSTM and Alexnet, it becomes evident that LSTM yields more accurate outcomes. [ABSTRACT FROM AUTHOR]