@inproceedings{ca47e3892b634bb3aaaa2f849a0f2b78,
title = "CNN-based real-time prediction of growth stage in soybeans cultivated in hydroponic set-ups",
abstract = "The purpose of this research is to create a deep learning model capable of predicting the day of harvest for soybeans growing in hydroponic conditions. The algorithm uses feature extraction to calculate the day of growth for each annotated picture fed into the model. The recorded photos in this study were tagged using the Computer Vision Annotation Tool (CVAT), which was then used to train a five-layer Convolutional Neural Network (CNN) to predict the range of cultivation days. This pre-trained model was then deployed on the backend using Flask, and for each picture provided as input to the model, a Graphical User Interface (GUI) was created to accept a taken image as input and estimate the day of cultivation for real-time application.",
keywords = "CNN, CVAT, Flask, GUI, hydroponic",
author = "Dhal, \{Sambandh Bhusan\} and Shikhadri Mahanta and Gadepally, \{Krishna Chaitanya\} and Samuel He and Mary Hughes and Janie Moore and Nowka, \{Kevin J.\} and Stavros Kalafatis",
note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE SoutheastCon, SoutheastCon 2023 ; Conference date: 01-04-2023 Through 16-04-2023",
year = "2023",
month = apr,
day = "16",
doi = "10.1109/SoutheastCon51012.2023.10115131",
language = "English",
series = "Conference Proceedings - IEEE SOUTHEASTCON",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "193--197",
booktitle = "SoutheastCon 2023",
}