University of Antique

Ensuring access to safe drinking water remains a major challenge in many low- and middle-income countries, especially in decentralized rural settings. This study examined water quality variations across four remote barangays in Barbaza, Antique, Philippines, and investigated contributing geographic and demographic factors. A total of 232 tap, drinking, and well water samples were analyzed for temperature, pH, total dissolved solids (TDS), electrical conductivity (EC), and the presence of Escherichia coli and coliform. Significant differences in EC and TDS (p < 0.01) were observed, with Binangbang Centro, a barangay relying primarily on groundwater, showing the highest median values. E. coli was detected in 23.1% of well water samples, while coliform exceeded standards (<1 colony/100 mL) in up to 100% of tap and drinking water samples. Despite widespread reliance on refilling stations, over 70% of drinking water samples contained coliform, possibly associated with post-purchase handling and storage conditions. Gua, the most densely populated barangay, recorded the highest coliform levels in drinking water (median: 102 CFU/mL). The findings highlight the need for barangay-specific strategies combining infrastructure improvements, decentralized monitoring, and hygiene education. This study supports context-sensitive policies to enhance rural water safety and community resilience under decentralized governance.

Access to safe and stable water sources is a key indicator of Sustainable Development Goal (SDG) 6. However, in the Philippines, water scarcity and water quality deterioration remain serious challenges. Using a cross-sectional field assessment, this study investigated domestic water quality and microbial contamination of household utensils in barangays within the densely populated Sampaloc District of Manila. A total of 28 households were surveyed, and tap water and drinking water samples were collected. Physicochemical parameters (water temperature, pH, electrical conductivity, and total dissolved solids) and biological indicators (Escherichia coli and total coliforms) were measured. In addition, E. coli and total coliform contamination on household utensil surfaces was assessed using swab tests. The results showed that tap and drinking water generally maintained acceptable water quality prior to use, whereas high levels of microbial contamination were detected on utensils during water handling. Furthermore, frequent water supply interruptions were reported in some households, raising concerns about the reliability of the water supply. These findings suggest that, in addition to improving water supply infrastructure, enhancing community awareness and education on water, sanitation, and hygiene (WASH) is essential to ensuring safe water use at the household level.

Poor vermibed conditions are one of the contributors to the degradation of vermicompost which includes nutrition imbalance, where the essential nutrients are not distributed evenly, like nitrogen, phosphorus, and potassium, which contribute to the healthy growth of plants. It is essential to monitor the environmental conditions of the vermibed to maintain high-quality vermicompost. However, lack of expertise, geographical limitations, and the complexity of environmental factors are a few of the challenges and burdens in manual vermibed assessment. This study explores the development of expert system-based assessment for vermicomposting to address these challenges by automating data analysis, reducing manual assessment burdens, and minimizing human error that can help our farmers to vermicompost successfully. By considering key environmental parameters such as temperature, moisture content, and pH level, this ensures that they can have consistent and objective evaluations, real-time insights for adjustments to the bed, and enhanced accessibility to expert-level assessments regardless of their location or resources.

This research fills a critical void in the empirical literature on intercultural education in Philippine HEIs by attending to the lived experiences of faculty, staff, and students immersed in intercultural learning spaces. Although there is an extant literature focused on the value and struggles of intercultural education, very little of this work examines the intersubjective realities of the people within the institutions. A significant portion of the existing literature adopts a top-down approach, focusing on institutional policies and programmatic evaluations without giving voice to the experiences of the individuals who are most directly impacted by these programs. This lacuna was addressed through the use of a qualitative research design employing the mixed-methods of data gathering to tap the richness and complexity of what intercultural education means in Philippine HEIs and to provide us with more holistic insights into the nature of its transformative promise. Since the Philippine context is also marked by the presence of diverse ethical and linguistic groups, more studies are needed to understand the particular issues involved in engendering intercultural understanding within such a context. It is also critical to comprehend the attitudes held by international academic staff members regarding institutional practices and structures for campus internationalization.

Environmental sound recognition is an active area of research within the broader field of machine listening, yet most existing studies have primarily focused on speech and music domains. This paper proposes a framework for a home-based machine listening system capable of detecting and classifying non-speech environmental sound events using deep learning techniques. The system leverages a Convolutional Neural Network (CNN) architecture alongside Mel Frequency Cepstral Coefficients (MFCC) for feature extraction, enabling a robust representation of audio signals captured in typical household environments. A dataset composed of 2,000 five-second audio samples, spanning 50 different sound classes commonly found in home settings, was used to train and evaluate the model. These classes include a diverse range of domestic, animal, and other external sounds. The CNN was implemented with a sequential model incorporating convolutional, pooling, and dropout layers to improve generalization and reduce overfitting. The model achieved an average accuracy of 73% using five-fold cross-validation, demonstrating promising performance in classifying real-world environmental audio. The proposed framework has potential applications in intelligent home monitoring, particularly for safety, security, and emergency scenarios where visual systems alone may be insufficient. Additionally, a graphical user interface (GUI) was developed to support live recognition, and monitoring of sound events in real time. Future work will explore multi-audio input, real-time system deployment, and enhanced classification using additional acoustic features.

This work introduces a new method for quantifying and sizing Brassica Oleracea instances via the use of unmanned aerial vehicle (UAV) imagery for instance segmentation. The goal of the project is to create a deep learning-based model that can recognize and classify Brassica Oleracea occurrences in images taken by unmanned aerial vehicles. The study uses the Mask R-CNN architecture and transfer learning strategies to train the model using a dataset of COCO-formatted annotated data and images of cabbage that was obtained from Mendeley Data. To improve resilience and variability, augmentation methods are used in dataset preparation. Evaluation criteria including mean Average Precision (mAP), precision, recall, and confidence levels are used to assess the model's performance. Findings show that the model performed very well, obtaining a remarkable mAP value of 98.6%. Moreover, inferencing test data shows how reliable the model is in identifying Brassica Oleracea occurrences in a variety of settings. The model continuously obtains high identification rates despite obstacles such as item incompleteness and illumination fluctuations, demonstrating its dependability and applicability for practical use in agricultural settings. The suggested strategy has the potential to advance crop management techniques and precision agriculture methods, enhancing agricultural sustainability and production.

This study explores the development and evaluation of a web-based enrollment appraisal system utilizing a rule-based decision support system for universities and colleges. Designed for the context of Antique, Philippines, the system leverages a two-tier architecture for efficient processing and secure data management. A user-friendly interface guides applicants through the enrollment process, while a secure server and rule-based engine analyze data against pre-defined eligibility criteria. The Rapid Application Development (RAD) methodology ensured a user-centered design with iterative development cycles incorporating user feedback. Evaluations using McCall's Software Quality Standard and the International Organization for Standardization and International Electrotechnical Commission (ISO/IEC) 25010 standard revealed the system's strengths in technical aspects (security, usability) and overall functionality. User feedback highlighted areas for improvement in interface design, clarity, and user perceptions of data security. The study concludes that the system offers a promising approach for more efficient and transparent enrollment processes. By addressing the feedback received, the system can be further enhanced to improve the user experience and build trust among applicants.