Authors:
S. Sujitha, B. Venkatesh, S. Gopikha, M. Arunadevi Thirumalraj, Jouma Ali Al-Mohamad
Addresses:
Department of Electrical and Electronics Engineering, New Horizon College of Engineering, Bengaluru, Karnataka, India. Department of Electrical and Electronics Engineering, B.M.S College of Engineering, Bengaluru, Karnataka, India. Department of Information Technology, St. Joseph's College of Engineering, Chennai, Tamil Nadu, India. Department of Computer Science and Engineering, Karunya Institute of Technology and Sciences, Coimbatore, Tamil Nadu, India. Department of Computer Science and Business Management, Saranathan College of Engineering, Tiruchirappalli, Tamil Nadu, India. Department of Computer and Mobile Communications Engineering, Faculty of Information Engineering, Al-Shahbaa Private University, Aleppo, Aleppo Governorate, Syria.
Abstract:
Internet of Things (IoT) advancements have brought about noticeable lifestyle shifts. In many nations, agriculture plays a crucial role; this industry needs to evolve towards the "Smart" economy. The key conclusion is a lack of soil expertise. Soil comes in a wide variety, each with its own set of properties. An in-depth understanding of soil conditions provides a wealth of data to improve harvests. In agriculture, machine learning is a cutting-edge tool for improving precision and addressing issues in crop productivity. New possibilities for relaxing, measuring, and understanding data are paired with massive data growth and improved computing power. An improved version of the sparrow search algorithm (ISSA) is presented in this study for picking out useful soil data. Based on the sparrow search algorithm (SSA), the ISSA adds a nonlinear weighting element to enhance its global search capabilities. This study presented a new extreme gradient boosting (XGBoost) model optimised using the Reptile Search optimisation strategy. Specifically, the impact of dataset size on model accuracy was investigated. Good agreement with experimental results is demonstrated by the findings that the prediction accuracy of the projected model declines with reduced dataset size, yet total (IoT) advancements have brought about noticeable lifestyle shifts.
Keywords: Soil Expertise; Good Agreement; Lifestyle Shifts; Reptile Search Optimisation; Crop Yield Problem; Sparrow Search Algorithm; Gradient Boosting; Optimised XGBoost Model.
Received: 17/11/2024, Revised: 01/03/2025, Accepted: 25/04/2025, Published: 09/09/2025
DOI: 10.64091/ATICS.2025.000199
AVE Trends in Intelligent Computing Systems, 2025 Vol. 2 No. 3 , Pages: 155-173