Machine Learning for Smart Soil Monitoring  

作　　者：Khaoula Ben Abdellafou Kamel Zidi Ahamed Aljuhani Okba Taouali Mohamed Faouzi Harkat 

机构地区：[1]Faculty of Computers and Information Technology,University of Tabuk,Tabuk,71491,SaudiArabia [2]Applied College,University of Tabuk,Tabuk,71491,SaudiArabia [3]Department of Electronics,Faculty of Engineering Annaba,Badji Mokhtar BP.12,Annaba,23000,Algeria

出　　处：《Computers, Materials & Continua》2025年第5期3007-3023,共17页计算机、材料和连续体(英文)

基　　金：supported by the Deputyship for Research and Innovation,Ministry of Education in Saudi Arabia for funding this research work through the project number(0226-1443-S).

摘　　要：Environmental protection requires identifying,investigating,and raising awareness about safeguarding nature from the harmful effects of both anthropogenic and natural events.This process of environmental protection is essential for maintaining human well-being.In this context,it is critical to monitor and safeguard the personal environment,which includes maintaining a healthy diet and ensuring plant safety.Living in a balanced environment and ensuring the safety of plants for green spaces and a healthy diet require controlling the nature and quality of the soil in our environment.To ensure soil quality,it is imperative to monitor and assess the levels of various soil parameters.Therefore,an Optimized Reduced Kernel Partial Least Squares(ORKPLS)method is proposed to monitor and control soil parameters.This approach is designed to detect increases or deviations in soil parameter quantities.A Tabu search approach was used to select the appropriate kernel parameter.Subsequently,soil analyses were conducted to evaluate the performance of the developed techniques.The simulation results were analyzed and compared.Through this study,deficiencies or exceedances in soil parameter quantities can be identified.The proposed method involves determining whether each soil parameter falls within a normal range.This allows for the assessment of soil parameter conditions based on the principle of fault detection.

关 键 词：Systems security soil analyses kernel partial least squares(KPLS) optimized reduced kernel partial least squares(ORKPLS) tabu search process monitoring machine learning fault detection(FD) 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]