Communities in DSpace
Select a community to browse its collections.
- Publications by researchers, faculty members, staff, and students of DMMMSU.
- A "lakasa" (storage) for the information materials related to La Union, Ilokano, and Iloko.
Recent Submissions
Image-based classification and segmentation of healthy and defective mangoes
(SPIE - The International Society for Optical Engineering, 2019) Baculo, Maria Jeseca C.; Ruiz, Conrado
The use of image processing and classification for agricultural applications has been widely studied and has led to work such as the automatic grading of fruit and vegetables, yield approximation and defect detection. Image segmentation is one of the first steps to identify the region of interest within an image. This paper presents an approach to automatic segmentation and classification of healthy and defective Carabao mangoes. K-means, range filtering and color-channel segmentation were utilized so that the varying texture and color of mangoes due to the surface defects can be considered. Results show that the proposed technique performs better than the classical K-means segmentation. The performance of segmentation step has a considerable influence on the precision of the classification model. Segmented and not segmented images were trained using KNN, SVM, MLP and CNN. The experiments showed that the models performed better when trained with segmented images.
Morphological characterization and geographical mapping of mango (Mangifera indica L.) accessions
(Association of Agricultural Technology in Southeast Asia, 2024) Calimpang, I. A.; Gentallan Jr., R. P.; Borromeo, T. H.
A total of eighty mango accessions located in the orchard were mapped using ArcGIS software. However, only seventy-two of these are analyzed by the Shannon-Weaver Diversity Index due to some accessions being cut down or dead. The remaining mango accessions were characterized using the International Plant Genetic Resources Institute's (IPGRI) descriptor list, with a total of seventeen morphological traits, twelve of which are qualitative traits and five of which are quantitative traits. According to the Shannon-Weaver Diversity Index (H'), the general mean of mango characters has a diversity index of 0.73. For qualitative traits, the diversity index was 0.62, while the mean average for quantitative traits was 0.84. The majority of mango accessions had higher diversity in qualitative traits such as leaf texture (H’= 0.99), mature tree height (H’= 0.96), foliage density (H’= 0.81), and leaf fragrance (H’= 0.78). Meanwhile, all quantitative traits, such as trunk circumference (H’= 0.80), crown diameter (H’= 0.87), leaf blade length (H’ = 0.86), leaf blade width (H' =0.88), and petiole length (H’= 0.80), showed greater diversity. This higher level of diversity of mango accessions located in the orchard should be maintained by using the map for easier monitoring, inventory, and access of a breeder or curators, particularly during varietal improvement. © 2024 Association of Agricultural Technology in Southeast Asia. All rights reserved.
Deep learning-assisted milkfish fingerling counting:
(Association for Computing Machinery, 2024) Sibayan, Christian Jose; Abando, Benjie R.; Acosta, Justin P.; Madrelijos, Johnico D.; Marzan, Charlie S.
The manual counting of milkfish fingerlings within the fish industry in the Philippines poses significant challenges due to its time-consuming nature, labor intensiveness, and susceptibility to errors. To address these issues, this study presents a deep learning approach for the real-time counting of milkfish fingerlings to enhance both the speed and accuracy of fingerling counts. The dataset was meticulously curated from six milkfish fingerlings farms, with gathered videos converted into image frames and subjected to polygon annotation. Furthermore, various augmentation techniques were applied to these images to enhance training efficacy before integration into a deep neural network. Notably, implementing the YOLOv8n-seg object detector with segmentation and counting yielded a remarkable accuracy rate of up to 90.64% and 93.34%, respectively. This innovative methodology promises significant advancements in the automation and efficiency of milkfish fingerling counting processes within the fish industry, paving the way for improved productivity and accuracy in fishery management practices. © 2024 ACM.
Towards a 21st century mathematics classroom:
(Asia-Pacific Social Science Review, 2020) Albay, Eduard M.
The development of 21st-century skills that are deemed necessary for learners to excel in a knowledge-based and highly globalized society is at the core of today’s education system. Towards this end, classroom practices focus on the delivery of instruction using various innovative instructional methodologies. One of the strategies used in Mathematics is the problem-solving approach. The problem-solving approach emphasizes that important mathematics concepts and procedures can be best taught through problem-solving tasks or activities, which engage students in thinking about the important mathematical concepts and skills they need to learn. This study utilized the problem-solving approach as supported by various collaborative strategies as an instructional intervention in teaching mathematics to first year college students and investigated its effects on the enhancement of their performance in and attitude towards College Algebra. The pretest-posttest control group design using two matched groups of respondents based on their intelligence quotient scores and mathematics test scores in the University Admission Test was utilized. Ten problem-solving tasks involving routine, non-routine, and real problems were developed and provided to the experimental group. On the other hand, the conventional approach in teaching and learning was employed in the control group. Necessary data to fulfill the objectives of the study were gathered through the attitude scale questionnaire and the researcher-made test and were analyzed using appropriate statistical tools. The results showed that the experimental group outperformed the control group on the bases of their posttest and mean gain scores. The experimental group also posted significant enhancement of their attitude towards college Algebra. Thus, the problem-solving approach, when applied to classroom instruction, can significantly improve students’ cognitive and affective attributes in mathematics, hence indicating the effectiveness of the approach in teaching mathematics.
Performance task assessment supported by the design thinking process:
(Elsevier Ltd, 2021) Albay, Eduard M.; Eisma, Delia V.
Providing students with a responsive classroom and relevant learning activities are vital in developing among them the 21st century skills and competences. Because schools are viewed as a compulsory place to hone these, undergraduate students must be provided with tasks and assessment that equip them with skills to facilitate a 21st century classroom. This posttest-only true experimental research study was conducted to analyze the performance of the respondents in a performance task assessment as supported by the principles of the design thinking process. Particularly, it examined and compared the performances of the experimental group and the control group in demonstration teaching. The results showed that the experimental group posted remarkably higher mean scores in the performance task and they significantly outperformed the control group. The study concluded that the implementation of the design thinking process can facilitate teachers in creating a creative, interactive, engaging and learner-centered classroom. © 2021 The Authors