Design and development of nitrogen deficiency detector for rice plant using Convolutional Neural Network / by Joan Pearl D. Anog and Nikka Shane R. Carandang.

By: Contributor(s): Material type: TextTextLanguage: English Publication details: Indang, Cavite : Cavite State University- Main Campus, 2023Description: xviii, 77 pages : illustrations ; 28 cmContent type:
  • text
Media type:
  • unmediated
Carrier type:
  • volume
Subject(s): DDC classification:
  • 631.52306  An7 2023
Online resources: Production credits:
  • College of Engineering and Information Technology (CEIT) - Department of Computer and Electronics Engineering.
Abstract: ANOG, JOAN PEARL D., and CARANDANG, NIKKA SHANE R. Design and Development of Nitrogen Deficiency Detector for Rice Plant using Convolutional Neural Network. Undergraduate Design Project. Bachelor of Science in Electronics Engineering. Cavite State University, Indang, Cavite. December 2022. Adviser: Dr. Michael T. Costa. The general objective of the study was to develop a Nitrogen Deficiency Detector for Rice plants using Convolutional Neural Network. It was designed to be both portable and rechargeable. Through the use of the Leaf Color Chart (LCC), developed by the International Rice Research Institute (IRRI), was intended to be able to identify nitrogen deficiency in plants based on the colors of their leaves. This study was conducted to classify the amount of Nitrogen needed to achieve a healthier rice plant. The exterior of the device is 3D printed, and designed with a switch, nozzle, and handle. The interior of the device was composed of Raspberry Pi 3B+, camera module v2, 12C OLED screen display, LED, and a power bank. The interior was assembled and connected to the microcontroller which holds the processes programmed to control the device. The back-end system of the device was a trained Convolutional Neural Network Model and the front-end system was a Graphical User Interface displayed on the OLED screen display. The project was tested by the researchers at a farm in Naic, Cavite, where the device had accuracy values Of 94%, 93%, 100%, and 95%, and precision values of 88%, 87.5%, 100%, 88.24% for LCC 1, LCC 2, LCC 3, and LCC 4, respectively. The evaluation was conducted at the Engineering Science Building, Cavite State University, Indang, Cavite with the Electronics Engineer Professors. The evaluation marked the design project as operational for achieving its main objectives. The device works and performs as expected. This evaluation is considered as successful. The total cost of the construction of the system amounted to P8,288.00.
List(s) this item appears in: Theses 2024
Star ratings
    Average rating: 0.0 (0 votes)
Holdings
Item type Current library Collection Call number Materials specified URL Status Notes Date due Barcode
Theses / Manuscripts Theses / Manuscripts Ladislao N. Diwa Memorial Library Theses Section Non-fiction 631.52306 An7 2023 (Browse shelf(Opens below)) Link to resource Room use only DP-784 00084138

Design Project (Bachelor of Science in Electronics and Communications Engineering) Cavite State University.

Includes bibliographical references.

College of Engineering and Information Technology (CEIT) - Department of Computer and Electronics Engineering.

ANOG, JOAN PEARL D., and CARANDANG, NIKKA SHANE R. Design and
Development of Nitrogen Deficiency Detector for Rice Plant using Convolutional Neural Network. Undergraduate Design Project. Bachelor of Science in Electronics Engineering. Cavite State University, Indang, Cavite. December 2022. Adviser: Dr. Michael T. Costa.
The general objective of the study was to develop a Nitrogen Deficiency Detector for Rice plants using Convolutional Neural Network. It was designed to be both portable and rechargeable. Through the use of the Leaf Color Chart (LCC), developed by the International Rice Research Institute (IRRI), was intended to be able to identify nitrogen deficiency in plants based on the colors of their leaves. This study was conducted to classify the amount of Nitrogen needed to achieve a healthier rice plant.
The exterior of the device is 3D printed, and designed with a switch, nozzle, and handle. The interior of the device was composed of Raspberry Pi 3B+, camera module v2, 12C OLED screen display, LED, and a power bank. The interior was assembled and connected to the microcontroller which holds the processes programmed to control the device. The back-end system of the device was a trained Convolutional Neural Network Model and the front-end system was a Graphical User Interface displayed on the OLED screen display.
The project was tested by the researchers at a farm in Naic, Cavite, where the device had accuracy values Of 94%, 93%, 100%, and 95%, and precision values of 88%, 87.5%, 100%, 88.24% for LCC 1, LCC 2, LCC 3, and LCC 4, respectively.
The evaluation was conducted at the Engineering Science Building, Cavite State University, Indang, Cavite with the Electronics Engineer Professors. The evaluation marked the design project as operational for achieving its main objectives. The device works and performs as expected. This evaluation is considered as successful. The total cost of the construction of the system amounted to P8,288.00.

Submitted to the University Library January 30, 2023 DP-784

Copyright © 2024. Cavite State University | Koha 23.05