Agriculture is the backbone of India's economy, as it is the most important factor in the country's socio-economic development. Because of the rapid expansion in human population, the "Green Revolution" introduced high yield variety (HYV) seeds, which increased crop productivity but degraded crop and soil quality. This is due to the use of excessive amounts of chemical fertilizers in HYV seeds, as well as the irrigation system utilized to grow these seeds. This stunts the growth of the crops, resulting in financial and productivity losses. Because of field surveys, traditional ways to crop production prediction will take longer, and contemporary agriculture will face certain obstacles. As a result, a comprehensive review of various crop key factors such as climatic factors, soil nutrients, production factors, and environmental factors is conducted using a variety of machine learning approaches such as Support Vector Machine, bayes classifier, decision tree, random forest, linear regression and Extreme Learning Machines. The accuracy measures such as root mean square error, coefficient of determination and mean absolute error are used for comparing the performance of the system. Based on the findings of the reviews, an intelligent and robust machine learning technique provides the optimum option for achieving (i) soil fertility, (ii) crop prediction, and (iii) yield prediction. The importance of soil variables and the amount of nutrients available in the soil for growing crops has been found, according to an examination of 51 peer-reviewed studies, to create qualitative yield prediction. Furthermore, the investigations will yield recommendations for future fertilizer research.
Background
Soil nutrients play an important role in soil fertility and other environmental factors. Soil testing is an effective tool for evaluating soil nutrient levels and calculating the appropriate quantitative of soil nutrients based on fertility and crop requirements. Because traditional soil nutrient testing models are impractical for real-time applications, efficient soil nutrient and potential hydrogen (pH) prediction models are required to improve overall crop productivity. Soil testing is an effective method to evaluate the presence of nutrient status of soil and assists in determining appropriate nutrient quantity.
Methods
Various machine learning (ML) models proposed, predict the soil nutrients, soil type, and soil moisture. To assess the significant soil nutrient content, this study develops an enhanced reptile search optimization with convolutional autoencoder (ERSOCAE-SNC) model for classifying and predicting the fertility indices. The model majorly focuses on the soil test reports. For classification, CAE model is applied which accurately determines the nutrient levels such as phosphorus (P), available potassium (K), organic carbon (OC), boron (B) and soil pH level. Since the trial-and-error method for hyperparameter tuning of CAE model is a tedious and erroneous process, the ERSO algorithm has been utilized which in turn enhances the classification performance. Besides, the ERSO algorithm is derived by incorporating the chaotic concepts into the RSO algorithm.
Results
Finally, the influence of the ERSOCAE-SNC model is examined using a series of simulations. The ERSOCAE-SNC model reported best results over other approaches and produces an accuracy of 98.99% for soil nutrients and 99.12% for soil pH. The model developed for the ML decision systems will help the Tamil Nadu government to manage the problems in soil nutrient deficiency and improve the soil health and environmental quality. Also reduces the input expenditures of fertilizers and saves time of soil experts.
The proliferation of technologies based on web services in the past few years has driven the exponential growth of the number of services available to the user. Due to the large number of candidates, it is difficult for a user to select the service best suited to their needs. Thus it is of paramount importance to devise a strategy to recommend the appropriate service to a given user. Collaborative Filtering (CF) is a widely employed technique to filter relevant data in Web Service Recommendations (WSRs). Although several CF based WSR techniques have been proposed over the past few years, their performance still requires significant improvement.In this paper, we propose a CF approach that leverages the location of the users for the filtering process. This ensures a greater measure of similarity between users to aid in making recommendations. Moreover, we also consider the history of the user and the web service to produce accurate recommendations. This is done by assigning weights to a candidate based on the user or service history to produce a similarity measure allowing the system to accurately determine the preferences of a user and make recommendations accordingly. The results of our proposed method are simulated through a set of comprehensive experiments performed on a real world Web Service dataset that is used to determine its performance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.