Machine Learning Based Precision Agriculture using Ensemble Classification with TPE Model
Open Access
- 5 January 2024
- journal article
- research article
- Published by Anapub Publications in Journal of Machine and Computing
- p. 261-268
Abstract
Many tasks are part of smart farming, including predicting crop yields, analysing soil fertility, making crop recommendations, managing water, and many more. In order to execute smart agricultural tasks, researchers are constantly creating several Machine Learning (ML) models. In this work, we integrate ML with the Internet of Things. Either the UCI dataset or the Kaggle dataset was used to gather the data. Effective data pretreatment approaches, such as the Imputation and Outlier (IO) methods, are necessary to manage the intricacies and guarantee proper analysis when dealing with data that exhibits irregular patterns or contains little changes that can have a substantial influence on analysis and decision making. The goal of this research is to provide a more meaningful dataset by investigating data preparation approaches that are particular to processing data. Following the completion of preprocessing, the data is classified using an average approach based on the Ensemble of Adaptive Neuro-Fuzzy Inference System (ANFIS), Random Neural Network (PNN), and Clustering-Based Decision Tree (CBDT) techniques. The next step in optimising the hyperparameter tuning of the proposed ensemble classifier is to employ a new Tree-Structured Parzen Estimator (TPE). Applying the suggested TPE based Ensemble classification method resulted in a 99.4 percent boost in accuracyKeywords
This publication has 23 references indexed in Scilit:
- Viable smart sensors and their application in data driven agricultureComputers and Electronics in Agriculture, 2022
- Classification and yield prediction in smart agriculture system using IoTJournal of Ambient Intelligence and Humanized Computing, 2022
- 3D convolutional neural networks-based multiclass classification of Alzheimer’s and Parkinson’s diseases using PET and SPECT neuroimaging modalitiesBrain Informatics, 2021
- Cropland Suitability Assessment Using Satellite-Based Biophysical Vegetation Properties and Machine LearningAgronomy, 2021
- From Conventional to Precision Fertilization: A Case Study on the Transition for a Small-Medium FarmAgriengineering, 2021
- Towards Paddy Rice Smart Farming: A Review on Big Data, Machine Learning, and Rice Production TasksIEEE Access, 2021
- Internet of Things for the Future of Smart Agriculture: A Comprehensive Survey of Emerging TechnologiesIEEE/CAA Journal of Automatica Sinica, 2021
- A Review of the Applications of the Internet of Things (IoT) for Agricultural AutomationJournal of Biosystems Engineering, 2020
- Wireless Sensor Network Synchronization for Precision Agriculture ApplicationsAgriculture, 2020
- Sensors Driven AI-Based Agriculture Recommendation Model for Assessing Land SuitabilitySensors, 2019