Normal view MARC view ISBD view

Development of a machine learning based dried cacao beans sorter / by John Lloyd Daguimol and Jerome Gerald U. Tena.

By:

Daguimol, John Lloyd [author]

Contributor(s):

Material type: Text

TextLanguage: English Publication details: Indang, Cavite : Cavite State University- Main Campus, 2022.Description: xvi, 80 pages : illustrations ; 28 cmContent type:

text

Media type:

unmediated

Carrier type:

volume

Subject(s):

DDC classification:

633.74 D13 2022

Online resources:

Click here to view the Abstract and Table of Contents

Production credits:

College of Engineering and Information Technology (CEIT).

Abstract: TENA, JEROME U. and DAGUIMOL, JOHN LLOYD. DEVELOPMENT OF A MACHINE LEARNING BASED DRIED CACAO BEANS SORTER. Undergraduate Thesis. Bachelor of Science in Computer Engineering. Cavite State University, Indang, Cavite. June 2022. Adviser: Andy A. Dizon A study was conducted to develop a system that automates the sorting of cacao beans. It was conducted to help lighten the burden of cacao processing by automating the longest phase of the process, which is the bean sorting. This process is commonly done by manually picking the best possible beans within the set of beans to be processed. This resulted to a very time-consuming and physically exhausting task. The general objective of this study was to develop a machine that would help laborers in the cacao processing industry by lessening the burden of manually sort pre- roasted beans. Specifically, the study aimed to design and fabricate the machine's frame and physicality; construct the needed circuits for the system; develop the software program capable of detecting the beans to be sorted; test and evaluate the system for its accuracy and performance; and conduct a cost computation. The system implemented used two (2) Raspberry Pi 4 2GB RAM, two (2) power supplies for each RPi 4, two (2) 64GB Micro SD Card for RPi, one (1) servo motor, two (2) SriCam 2MP Cameras, two (2) Conveyors, LED Lights, miscellaneous electronic components, and the overall framework. The system initiates the detection process after a bean has dropped from the initial conveyor, which aims to file the beans into a linear manner, to the second conveyor underneath. Two (2) cameras were used for the detection process to cover detections for the bean's top and one of its sides. The sorter was considered accurate as it can distinguished good and bad beans with an accuracy of 97 percent. Overall, the development of the machine was computed to be 19,384.75 pesos.

Average rating: 0.0 (0 votes)

Holdings ( 1 )
Title notes ( 5 )

Holdings
Item type	Current library	Collection	Call number	Materials specified	URL	Status	Notes	Date due	Barcode
Theses / Manuscripts	Ladislao N. Diwa Memorial Library Theses Section	Non-fiction	633.74 D13 2022 (Browse shelf(Opens below))		Link to resource	Room use only	T-9189		00083566

Thesis (Bachelor of Science in Computer Engineering) Cavite State University.

Includes bibliographical references.

College of Engineering and Information Technology (CEIT).

TENA, JEROME U. and DAGUIMOL, JOHN LLOYD. DEVELOPMENT OF A MACHINE LEARNING BASED DRIED CACAO BEANS SORTER. Undergraduate Thesis. Bachelor of Science in Computer Engineering. Cavite State University, Indang, Cavite. June 2022. Adviser: Andy A. Dizon

A study was conducted to develop a system that automates the sorting of cacao beans. It was conducted to help lighten the burden of cacao processing by automating the longest phase of the process, which is the bean sorting. This process is commonly done by manually picking the best possible beans within the set of beans to be processed. This resulted to a very time-consuming and physically exhausting task. The general objective of this study was to develop a machine that would help laborers in the cacao processing industry by lessening the burden of manually sort pre- roasted beans. Specifically, the study aimed to design and fabricate the machine's frame and physicality; construct the needed circuits for the system; develop the software program capable of detecting the beans to be sorted; test and evaluate the system for its accuracy and performance; and conduct a cost computation. The system implemented used two (2) Raspberry Pi 4 2GB RAM, two (2) power supplies for each RPi 4, two (2) 64GB Micro SD Card for RPi, one (1) servo motor, two (2) SriCam 2MP Cameras, two (2) Conveyors, LED Lights, miscellaneous electronic components, and the overall framework. The system initiates the detection process after a bean has dropped from the initial conveyor, which aims to file the beans into a linear manner, to the second conveyor underneath. Two (2) cameras were used for the detection process to cover detections for the bean's top and one of its sides. The sorter was considered accurate as it can distinguished good and bad beans with an accuracy of 97 percent. Overall, the development of the machine was computed to be 19,384.75 pesos.

Submitted copy to the University Library. 06/29/2022 T-9189