Vakeesan Diluxshan
University of Moratuwa, SL
Abstract Title: Yield Analysis of Black Gram Under Line Sowing and Broadcasting methods: A Study Integrated with Data Analytics.
Biography: Aspiring Data Scientist with a strong academic foundation in Artificial Intelligence and Data Science, currently pursuing an MSc at the University of Moratuwa. Furthermore, Much having concern on the nature and the hygienic food habits. Additionally, Skilled in Python, TensorFlow, PyTorch, and OpenCV, with hands-on experience in real-time IoT systems, machine learning model development, and data-driven automation. Experienced in data preprocessing, model deployment, and edge computing for smart solutions. Passionate on applying AI to solve real-world problems in areas such as predictive analytics, smart environments, and human-computer interaction.
Research Interest: This research investigates the impact of line sowing and broadcasting methods on the yield and economic returns of blackgram (Vigna mungo - MI BG4). Field experiments compared plant growth, yield components, and profitability be- tween the two sowing techniques. Results demonstrated that line sowing consistently produced higher seed yields and improved harvest indices compared to broadcasting. Economic analysis further indicated that line sowing offers greater profitability for blackgram cultivation. These findings suggest that adopting line sowing can enhance productivity and farmer income in blackgram production systems. Furthermore, I have attached the IoT sensors for collecting actual values to determine the soil moisture level and the air temperature level. Index Terms—Blackgram, Vigna mungo, line sowing, broad- casting, yield, agronomy, crop management, Smart Irrigation. blackgram productivity remains rel- atively low compared to its potential, largely due to suboptimal agronomic practices. Among these, the method of sowing is a key factor influencing crop establishment, growth, and final yield. Broadcasting, the traditional method of sowing, is widely practiced because of its simplicity and minimal labor requirement. However, it often results in uneven seed distribution, poor plant population, and increased competition among plants, which can limit yield potential. Index Terms—Blackgram, Vigna mungo, line sowing, broad- casting, yield, agronomy, crop management, Smart Irrigation Recent Publications 1. V.Diluxshan*, BTGS Kumara*, Deep Neural Network and Image Processing Based Approach for Identifying Road Signs. In ITRU Symposium Conference organized by the University of Moratuwa. 2. Built a SenzAgro-based machine learning algorithm implemented to AI-driven irrigation in several crops farming, utilizing real-time soil moisture sensors and predictive analytics to achieve a 40% reduction in crop loss.