Measurement: Sensors (Jun 2023)
IOT-BASED professional crop recommendation system using a weight-based long-term memory approach
Abstract
For the vast majority of Indians, agriculture is their main source of income, and it plays a vital role in the country's economy. The most prevalent issue Indian farmers have is that they do not choose their crops based on the requirements of the soil, which has a significant negative impact on their productivity. Precision agriculture can help solve this problem. This method considers three parameters: soil characteristics, soil types, and crop yield data collection. A suitable crop to cultivate is suggested to the farmer based on these parameters. However, India must develop and civilizes the agro industry's technological engagement and usability. Due to the inability to select acceptable features, the existing system's accuracy is low, and it takes longer to process the given climate dataset. This paper proposes a method based on IDCSO (Improved Distribution-based Chicken Swarm Optimization) with WLSTM (Weight-based Long Short-Term Memory) for crop predictions and recommendations in order to address the aforementioned issues with the help of the Internet of Things (IoT). The primary phases are pre-processing, attribute selection using the IDCSO algorithm, and crop prediction using the WLSTM method. First, climate data are collected, then crop production data. For this study, the climate data includes a number of variables responsible for the rainfall at a given location and the agricultural yield in that region. Then, pre-processing is performed to enhance the quality of the input. To provide precise prediction results with shorter execution times, the IDCSO algorithm is utilized to choose the most helpful features. The most pertinent features from the provided dataset are chosen using the optimal fitness values. The required crop predictions are then performed using the WLSTM approach. Farmers can get instant crop recommendations by entering their preferred climate and crop attributes. The experimental findings show that in terms of precision, recall, and execution time, the suggested IDCSO-WLSTM technique performs better than its forerunner.
