https://repository.umindanao.edu.ph/handle/123456789/2297 2026-05-20T09:46:59Z 2026-05-20T09:46:59Z Ardepolla, Johannie Ave P. Cortez, Mike Jhon Reymar Escorpion, Abigail L. Adtoon, Jetron J. https://repository.umindanao.edu.ph/handle/123456789/2316 2026-05-06T19:00:48Z 2019-01-01T00:00:00Z

Identification and classification of export quality carabao mangoes using image processing Ardepolla, Johannie Ave P.; Cortez, Mike Jhon Reymar; Escorpion, Abigail L.; Adtoon, Jetron J. The Carabao mango is the most prevalent and most exported mango variety in the Philippines due to its exotic taste and sweetness, which puts the nation on the global map. As practiced, the quality of mango is assessed by its physical look and weight. Currently, the evaluation of mango is done through manual checking. The utilization of scientific strategy for quality evaluation of mango in this study is done through image processing, which is a more efficient, non-destructive, and cost-effective grading method. Classified sample carabao mangoes from a mango export company were analyzed and become the data sets of the device then undergo image processing procedure through the Support Vector Machine (SVM) algorithm. Carabao Mangoes in the study are classified to be Export Quality, Reject Quality, and Unknown. In this paper, the proposed methodology is divided into three parts, namely: (i) identifying the color of the mangoes through RGB color recognition, (ii) grading of mango based on its weight, (iii) determining the size of the mango by its length and width. The functionality test and statistical analysis revealed 90 percent overall accuracy of the device. © 2019 ACM. This study develops an image processing and Support Vector Machine (SVM)-based system to classify Carabao mango quality using color, weight, and size for more efficient and accurate grading.

2019-01-01T00:00:00Z Arcayena, Robert D. Jr. Ballarta, Alessis D. Claros, Kendall N. Pangantihon, Rodrigo S. Jr. https://repository.umindanao.edu.ph/handle/123456789/2311 2026-05-06T19:00:28Z 2019-01-01T00:00:00Z

Development of Arduino microcontroller-based safety monitoring prototype in the hard hat Arcayena, Robert D. Jr.; Ballarta, Alessis D.; Claros, Kendall N.; Pangantihon, Rodrigo S. Jr. Construction, being one of the most dangerous sectors in the industry, comes with fortuitous or inevitable accidents. Occupational injuries like falling from heights, being hit by falling or moving objects, fatigue related complications, and heat induced illnesses cause construction losses. Despite common safety protocols, construction workers still have a chance of 1-in-200 of dying on the job within the span of a 45- year career making safety an issue of paramount importance for construction contractors to monitor and manage. The main objective of this study is to ergonomically design a hard hat with biometric sensors, an accelerometer, a GPS module, transceivers, a fingerprint scanner, and an emergency button, all connected to Arduino Uno Microcontroller. It monitors the biometrics of the worker, detect external impact forces, know the location, and send distress alert signals during emergencies. By creating a software that presents the wearer's profile with the gathered data, information generated are verified through secondary equipment for necessary calibrations. The prototype was ergonomically designed with a reliable overall performance. Pulse and temperature monitoring acquired overall accuracies of 95.62% and 99.36%, distress alerting with 95%), impact detection, location identification, and fingerprint scanning got 100% through performance analysis. © 2019 ACM. This study develops an Arduino-based smart hard hat for construction with biometric sensors, GPS, and emergency alert features to monitor construction workers’ safety, detect hazards, and improve accident response with high system accuracy.

2019-01-01T00:00:00Z Lim, Tito C. Jr. Torregosa, Jaedy O. Pescadero, Aubrey Rose A. Pangantihon, Rodrigo S. Jr. https://repository.umindanao.edu.ph/handle/123456789/2308 2026-05-06T19:00:24Z 2019-01-01T00:00:00Z

De-husked coconut quality evaluation using image processing and machine learning techniques Lim, Tito C. Jr.; Torregosa, Jaedy O.; Pescadero, Aubrey Rose A.; Pangantihon, Rodrigo S. Jr. Qualitative evaluation provides the basis for determining if the quality of products meets the target specifications. Manual evaluation of de-husked coconuts is still being performed by coconut farmers, however, it is time consuming and costly. Ergo this study aiming to replace the manual inspection, a prototype was developed for objective and automated quality evaluation of de-husked coconuts through the application of computer vision and machine learning, identifying good-quality de-husked coconuts from defective ones with respect to its RGB color space. JavaFX platform was utilized to create the system performing K-Nearest Neighbor and Arduino technology played a significant role in the hardware control of the device. The image samples were captured by a CMOS camera in an imaging chamber with invariant illumination on top of a conveyor belt. Image processing is done to get the required features of the sample and by comparing the average RGB value from the custom dataset, then the maturity level of the coconut is determined. With the accuracy of 86.67%, the system is able to evaluate de-husked coconuts which are good for further processing used in export and premature coconuts that are to be rejected. © 2019 ACM. This study develops an automated computer vision and machine learning system using K-Nearest Neighbor and Arduino technology to evaluate and classify the quality of de-husked coconuts with high accuracy.

2019-01-01T00:00:00Z Barcelon, Menkent S. Orilla, Alvin A. Mahilum, Jessabelle A. https://repository.umindanao.edu.ph/handle/123456789/2303 2026-05-06T19:00:45Z 2019-01-01T00:00:00Z

Automated vermiculture monitoring and compost segregating system using microcontrollers Barcelon, Menkent S.; Orilla, Alvin A.; Mahilum, Jessabelle A. Composting of organic waste is an efficient technology to convert organic wastes into useful composts used as biofertilizers for sustainable agriculture. Vermicomposting allows the process of breaking down biodegradable matter with the help of earthworms that transforms the nutrients of the organic matter to vermicast. This study aimed to provide an automated system for vermicast production that may improve the whole concept of organic farming. Developing a system that automatically examines a worm bin, which is used to produce vermicast or supports the process of vermicomposting. Worms and substrate are used for the preparation of the worm bin, making the sensors applicable afterward. Two Arduino microcontrollers and Raspberry Pi capture the data readings from the sensors. The second Arduino microcontroller controls the maintenance of the worm environment and switches for the activation/deactivation of the system, and the data gathered are stored in Raspberry Pi. By the span of fourteen, sixteen, and nineteen days only, the conducted experiment still produces an adequate nutrient and compost quality for a fertilizer. Sensor readings with water sprinkler system combinations do maintain the right environment for the living conditions of the worm. Through the use of the microcontrollers, Arduino and Raspberry Pi, human intervention would reduce, and the system would expedite if the process of vermicomposting would be automated rather than going manual. © 2019 ACM. This study develops an automated vermicomposting system using Arduino and Raspberry Pi to monitor and maintain optimal conditions for efficient, reduced-labor vermicast production.

2019-01-01T00:00:00Z