Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{184863,
        author = {SHAIK FIAZA TAZEEN and D.MURALI},
        title = {ADVANCED NEURAL NETWORKS FOR ANTICIPATING PLANT DEVELOPMENT AND HARVEST QUANTITY IN CONTROLLED GREENHOUSE CONDITIONS},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {4},
        pages = {3222-3227},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=184863},
        abstract = {In the realm of controlled greenhouse agriculture, precise anticipation of plant development stages and harvest quantities is indispensable for maximizing productivity. This paper introduces an ADVANCED NEURAL NETWORK (ANN)-based approach for this purpose, contrasting its performance with the existing system utilizing the Random Forest algorithm. Our proposed neural network model harnesses the capabilities of recurrent neural networks to capture temporal and spatial dependencies within greenhouse data. By integrating diverse inputs such as environmental parameters (e.g., temperature, humidity, light intensity), soil conditions, and plant physiological data, the model adeptly learns intricate patterns associated with plant growth stages and yield outcomes. Moreover, attention mechanisms are embedded within the neural network architecture, facilitating dynamic feature selection and enhancing prediction accuracy. Through comprehensive experimentation and validation on authentic greenhouse datasets, we demonstrate the superior performance of our neural network model compared to the incumbent Random Forest(RF)-based system. The findings underscore the efficiency of ANN in accurately forecasting plant development stages and estimating harvest quantities, surpassing the predictive capabilities of RF.},
        keywords = {credit card fraud, online transactions, machine learning, Random Forest, data preprocessing, fraud detection, GridSearchCV, real- time prediction, transaction behavior, model performance, hyperparameter tuning, interactive interface, financial losses, fraud trends, visualizations, accuracy, computational efficiency.},
        month = {September},
        }