Mesa, A.R.; Chiang, J.Y. Multi-Input Deep Learning Model with RGB and Hyperspectral Imaging for Banana Grading. Agriculture 2021, 11, 687. https://doi.org/10.3390/agriculture11080687
Embedded Files
Abstract
Grading is a vital process during the postharvest of horticultural products as it dramatically affects consumer preference and satisfaction when goods reach the market. Manual grading is time-consuming, uneconomical, and potentially destructive. A non-invasive automated system for export-quality banana tiers was developed, which utilized RGB, hyperspectral imaging, and deep learning techniques. A real dataset of pre-classified banana tiers based on quality and size (Class 1 for export quality bananas, Class 2 for the local market, and Class 3 for defective fruits) was utilized using international standards. The multi-input model achieved an excellent overall accuracy of 98.45% using only a minimal number of samples compared to other methods in the literature. The model was able to incorporate both external and internal properties of the fruit. The size of the banana was used as a feature for grade classification as well as other morphological features using RGB imaging, while reflectance values that offer valuable information and have shown a high correlation with the internal features of fruits were obtained through hyperspectral imaging. This study highlighted the combined strengths of RGB and hyperspectral imaging in grading bananas, and this can serve as a paradigm for grading other horticultural crops. The fast-processing time of the multi-input model developed can be advantageous when it comes to actual farm postharvest processes.
2021 | Non-invasive Grading System for Banana Tiers using RGB Imaging and Deep Learning
Mesa, A.R.; Chiang, J.Y. 2021. Non-invasive Grading System for Banana Tiers using RGB Imaging and Deep Learning. In 2021 7th International Conference on Computing and Artificial Intelligence (ICCAI 2021). Association for Computing Machinery, New York, NY, USA, 113–118. DOI:https://doi.org/10.1145/3467707.3467723
Abstract
Food losses transpire at postharvest and processing operations in developing countries, commonly caused by inaccurate manual classification of horticultural crops. The modernization of agricultural facilities and emerging technologies in agriculture has provided solutions for such losses and even increased productivity in a short duration and with higher precision. A non-invasive classification of bananas is presented in this paper, which grades banana tiers into different categories using digital images of bananas applied with deep learning techniques. The main objective of this paper is to develop a tier-based grading system for clustered fruits such as bananas and classify them in terms of quality (export class, middle class, and reject class), maturity (green, turning yellow, yellow, and overripe), and size (small, medium, and large). The classification models for the different grading parameters are developed using
2017 | Design and Development of an Online Repository System for Thesis and Special Problem Manuscripts
Mesa A. (2017). Design and Development of an Online Repository System for Thesis and Special Problem Manuscripts. IJODeL, Vol. 3, No. 1.
Abstract
It is vital to keep track of all the scholarly works undertaken by the students in research universities. As a premier research university, The University of the Philippines (UP) Mindanao has produced several scholarly works made by its students, such as thesis or special problem manuscripts. Similar to typical residential universities in the Philippines, UP Mindanao students submit both hardbound and digital copies of their thesis and special problem manuscripts to their respective departments. Problems such as duplication of work and missing manuscripts are rampant with the current method. This is because printed and electronic copies stored in optical discs can easily be misplaced and are difficult to track when borrowed. This paper describes the development of the UP Mindanao Manuscript e-library and Repository System (UPMERS), which is a web-based information system that provides administrators a tool to monitor and manage records of manuscripts by graduates of the University. This paper also describes the system’s user acceptance using the Technology Acceptance Model (TAM). Furthermore, the study also discusses the result of the System Usability Scale survey.
2017 | Cuckoo search via Levy flights applied to uncapacitated facility location problem
Mesa A, Castromayor K, Garillos-Manliguez C, Calag V. (2017). Cuckoo search via Levy flights applied to uncapacitated facility location problem. Journal of Industrial Engineering International, 1-8 (SCOPUS Indexed)
Abstract
Facility location problem (FLP) is a mathematical way to optimally locate facilities within a set of candidates to satisfy the requirements of a given set of clients. This study addressed the uncapacitated FLP as it assures that the capacity of every selected facility is finite. Thus, even if the demand is not known, which often is the case, in reality, organizations may still be able to take strategic decisions such as locating the facilities. There are different approaches relevant to the uncapacitated FLP. Here, the cuckoo search via Lévy flight (CS-LF) was used to solve the problem. Though hybrid methods produce better results, this study employed CS-LF to determine first its potential in finding solutions for the problem, particularly when applied to a real-world problem. The method was applied to the data set obtained from a department store in Davao City, Philippines. Results showed that applying CS-LF yielded better …
2016 | Web-Based System for Marine Fishes Mapping and Assessment
Mesa A, Largo SM, Nañola C, Agrazamendez M, Novero A. (2016). Web-Based System for Marine Fishes Mapping and Assessment, UP Mindanao, Asian Conference on Remote Sensing 2016
Abstract
Estimating the abundance of fishes through underwater visual census (UVC) using the transect method contributes to the development of coastal resources management in the Philippines. The manual method of performing data administration and management of numerous marine fishes is time-consuming and arduous to researchers. Aside from that, it is also likely to human errors and may result in data inconsistency and redundancy if not done properly. Thus, a Web-based System for Marine Fishes Mapping and Assessment is developed using the Yii 2.0 Framework and Rapid Application Development to present a solution to those difficulties encountered. The system was implemented using MySQL for manipulating data, functions and queries were written using the PHP Hypertext Processor programming language, the user interface was designed and enhanced using Hypertext Markup Language (HTML), Cascading Style Sheets (CSS), and Bootstrap Materialize, while the mapping feature was accomplished using Google Maps API. Furthermore, the system allows the administrator to manage fish species information, transect locations, and make an inventory of marine fish species. The administrator could also filter data using the search bars provided and could export data into files such as text CSV, PDF, and HTML. With this system, the data gathered can be visualized geographically through an interactive map. Moreover, map markers shown on the map could also be refined by the name of species, marine site, and environment using the filters provided. The system was populated and tested with data collected by the researcher. The system was also evaluated using System Usability Scale (SUS). The results show above average scores suggesting that users are satisfied with the system. Hence, with this system, marine fishes data can be handled by marine researchers effectively. The system is also a GIS-assisted resource mapping tool that is a fast and reliable technique for decision-making and data assessment.
2008 | Particle Swarm Optimization – Tabu Search Approach to Constrained Engineering Optimization Problems
Gamot R, Mesa A. (2008). Particle Swarm Optimization – Tabu Search Approach to Constrained Engineering Optimization Problems, WSEAS (The World Scientific and Engineering Academy and Society) Transactions on Mathematics, Issue 11, Volume 7.
Abstract
Constraint handling is one of the most difficult parts encountered in practical engineering design optimizations. Different kinds of methods were proposed for handling constraints namely, genetic algorithm, self-adaptive penalty approach and other evolutionary algorithms. Particle Swarm Optimization (PSO) efficiently solved most nonlinear optimization problems with inequity constraints. This study hybridizes PSO with a meta-heuristic algorithm called Tabu Search (TS) to solve the same engineering design problems. The algorithm starts with a population of particles or solution generated randomly and is updated using the update equations of PSO. The updated particles are then subjected to Tabu Search for further refinement. The PSO algorithm handles the global search for the solution while TS facilitates the local search. With embedded hyrbridization, this study which we call PSO-TS, showed better results compared to algorithms reported in Hu et al's study as applied to four benchmark engineering problems. Specifically, this study beat the results of Coello, Deb and Hu.
Page updated
Report abuse