click here to download the project abstract of smlt
click here to download the base paper of smlt
ABSTRACT
Agriculture is responsible for the majority of the nation’s economic contribution across the world. However, due to a lack of ecosystem control methods, the majority of agricultural lands are still underdeveloped. Crop output is not improving as a result of these issues, which has an impact on the farm economy. As a result, a rise in agricultural output is aided by the forecast of plant yields. To avoid this issue, agricultural industries must use machine learning algorithms to estimate the harvest from a given dataset. The supervised machine learning method (SMLT) analyses a to capture a dataset several pieces of information, such as variable identification, Missing value treatments, univariate analysis, bivariate and multivariate analysis, and so on. A comparison of machine learning algorithms was
performed to see which one was more accurate in forecasting the best crop. When entropy calculation, and are evaluated, precision, recall, F1 Score, sensitivity, specificity, & entropy come out ahead. the data show that the recommended machine learning algorithm technique has the highest accuracy
INTRODUCTION
Agriculture research has boosted the world economy and offers enormous benefits to society as a whole. Crop evaluation in agriculture remains challenging, despite recent improvements that involve the use of a wide range the availability of technical resources techniques,as well as techniques Precision farming and agritechnology sometimes referred to as virtual farming, are current research areasthat boosts the usage of data-intensive approaches agricultural productivity while lowering environmental impact.Accurate crop detection focuses on ecological and soil Agricultural production is dependent on a number of factors,
one of which has been identified. the subject of decades of research.. The majority of existing algorithms for crop yield estimate involve machine learning (ML), but very little was done to forecast territory crops solely on soil and climate data as well as the environment Crop cultivation is influenced by a variety of factors, Soil texture, nutrients (N2, P, and K), micronutrients (Fe, B, and Mn), temp, and rainfall are all factors to consider.l. Because the characteristics vary by zone, resulting in a large order to ensure the sustainability data set, it is necessary to pick key aspects that aid in the diagnosis of acceptable crops for certain land regions. Feature selection (FS) approaches are used to carry out the procedure. Prediction relies heavily on machine learning methods. FS approaches are utilized to reduce fitting problems and identify important characteristics for the prediction procedure, from the data set resulting in improved ML performance. Filters , wrap , and embed are the three types of the FS approach. Filter techniques are unaffected by the classifier’s performance, Wrapper approaches, on the other hand, pick features depending on the success of the classifier. Because it combines both filter and wrapper approaches, the embedded approach is analogous to the latter. This investigation focuses on wrapper FS approaches. To anticipate an appropriate crop and measure the efficacy of the FS process, the chosen attributes are fed into the k-nearest neighbor (kNN), Naïve Bayes ( NB) , decision tree (DT), support vector machine (SVM), and random forest (RF). The purpose of this research is just to improve the crops underlying model by selecting key data points
