{"title":"Random Forest, DT And SVM Machine Learning Classifiers for Seed with Advanced WSN Sensor Node","authors":"S. D. Shingade, R. Mudhalwadkar, K. M. Masal","doi":"10.1109/ICACRS55517.2022.10029310","DOIUrl":null,"url":null,"abstract":"Random Forest- RF, Support Vector Machine - SVM and Decision Tree - DT Machine learning classifiers proposed and implemented to develop seed prediction model in Visual Studio code environment using python along with advanced Wireless Sensor Network’s raino-meter sensor node. Wireless sensor network's infrastructure consists of sensors and nodes. Use of a wireless system has the potential for significant savings of workforce, resources and time. By adding Soil pH, Temperature, Humidity and Rainfall sensor in the network one can predict the crop seed to be cultivated in the current time by analyzing the environmental conditions in the farm. Aim of this work is to develop model using data analytics and machine learning techniques. Prediction model is trained on historic environmental data of crops. Based on the history and current environmental data crop recommendation is proposed. Basic data collection nodes with the sensor network provides the required information about environmental parameters. Random Forest- RF, Support Vector Machine - SVM and Decision Tree - DT Machine learning classifiers implemented and results shows Random Forest is the best with 95.12 % accuracy, 94.94 % precision, 94.85 % recall and 95.12 % F1 score. This system helps to provide the correct advice at the correct time.","PeriodicalId":407202,"journal":{"name":"2022 International Conference on Automation, Computing and Renewable Systems (ICACRS)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 International Conference on Automation, Computing and Renewable Systems (ICACRS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICACRS55517.2022.10029310","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
Random Forest- RF, Support Vector Machine - SVM and Decision Tree - DT Machine learning classifiers proposed and implemented to develop seed prediction model in Visual Studio code environment using python along with advanced Wireless Sensor Network’s raino-meter sensor node. Wireless sensor network's infrastructure consists of sensors and nodes. Use of a wireless system has the potential for significant savings of workforce, resources and time. By adding Soil pH, Temperature, Humidity and Rainfall sensor in the network one can predict the crop seed to be cultivated in the current time by analyzing the environmental conditions in the farm. Aim of this work is to develop model using data analytics and machine learning techniques. Prediction model is trained on historic environmental data of crops. Based on the history and current environmental data crop recommendation is proposed. Basic data collection nodes with the sensor network provides the required information about environmental parameters. Random Forest- RF, Support Vector Machine - SVM and Decision Tree - DT Machine learning classifiers implemented and results shows Random Forest is the best with 95.12 % accuracy, 94.94 % precision, 94.85 % recall and 95.12 % F1 score. This system helps to provide the correct advice at the correct time.