This study aims to evaluate the developed predictive dropout risk model in the Alternative Learning System (ALS) by analyzing various demographic, socio-economic, academic, and behavioral factors. The early identification of students who are at risks in dropping out is crucial in order to provide necessary academic intervention programs. The researcher used Knowledge Discovery in Databases (KDD) as methodology in the evaluation of the predictive models. Using Gradient Boosting Decision Trees (GBDT) for predictive modeling. Key findings highlighted that with both classes achieving an F1-score of 93% which demonstrate a balanced performance between precision and recall for both positive and negative classes. In summary, the overall evaluation of the system is 3.59 which indicates that they system can be used for deployment and maybe further be improved.

URBANIHAN is a capstone project made by Digital Dino wherein the project is a 2D animated informative video and website that is made to inform the youth into the practice of urban gardening benefits and projects and programs made from the said practice. The project consists of five episodes with each story highlighting the benefits of urban gardening as well as showcasing the projects and programs implemented by the client, Agricultural Training Institute (ATI). The study aims to inform and increase the youth enthusiasm on urban gardening. The objective of the study is to inform the youth regarding the practice of urban gardening and how it benefits the people mentally, financially, economically, and socially, and education. Additionally, a website is designed using a web builder that serves as additional information about urban gardening using the supplementary materials and information provided by ATI and their urban gardening programs and projects for the community. The target audience of the study are the youth ages 15 to 30. The methodology used for the study is a combination of qualitative and quantitative approach to gather the necessary data through interviews for subject experts and surveys for the target audience of the study. As per the findings, a weighted mean of 4.51 has been acquired post-assessment, which is a significant improvement on the mean of 3.82 from the pre-assessment; indicating the effectiveness of the project corresponding to its objective. In conclusion, the videos produced provide sufficient information about urban gardening and its benefits, as well as the client. The website is also able to provide additional information about urban gardening through the supplementary materials and the previous projects mentioned in the animated videos.

According to the Philippines Commission on Higher Education (CHED) Circular Memorandum Order (CMO) 101 series of 2017, one of the allowed Elective Courses for the Electronics Engineering (ECE) Program is Instrumentation and Control which includes Advanced Instrumentation and Control Systems and Robotics. With these elective courses, there will be a need to have designated laboratory facilities and equipment which includes Mechatronics and Automation Equipment. This study aims to bridge the academe-industry gap by integrating a project based learning approach. The students of Jose Rizal University designed and developed a project-based four-story elevator trainer that became a platform for the real-world model of an actual elevator. Basic and Advanced Programmable Logic Controller (PLC) and Human Machine Interface (HMI) programming skills of the students were enhanced as they developed twenty comprehensive laboratory experiments on the elevator trainer. A 94.2% usability result indicates substantial effectiveness in learning mechatronics. T-tests for means and equal variance were used to analyze the significance of the elevator trainer in comparing the pre-test and post-test scores of ECE students. An alpha (p-value of 0.00000000013) for the accumulated test scores of each ECE student and (p
-value of 0.0000291) for the comparison of average mean score on the six areas: PLC, HMI, Variable Frequency Drive (VFD), pneumatics, electropneumatics, and motor control were found to be both smaller than the alpha of 0.05 for the target 95% confidence level. The study showed that the effectiveness of the elevator trainer was statistically significant in the learning of the ECE students in a project-based approach. The study highlights the need for a more hands-on project in each laboratory course to increase the quality of produced electronics engineering students in the Philippines by allowing them to be well-trained, globally competitive, and equipped with the necessary skills to become industry-ready.

Climate change is intensifying maritime risks, including sea level rise, stronger storms, and disrupted ocean currents—posing threats to coastal infrastructure, navigation, and security. Traditional monitoring systems lack the predictive capabilities and coverage to address these evolving challenges. This paper explores the integration of Artificial Intelligence (AI) and satellite-based Earth observation as a next-generation early warning system (EWS) for maritime security. We assess observed and projected hazard trends, propose an AI-enhanced system architecture, and evaluate readiness in climate-vulnerable geographies. The findings highlight actionable strategies to improve forecasting, risk detection, and climate resilience in coastal and maritime domains.

Blue carbon ecosystems (mangroves, saltmarshes, seagrasses) are globally significant carbon sinks, absorbing an estimated 50% of oceanic carbon despite covering only 2% of the ocean surface. However, these important habitats face rapid degradation, with 25% to 50% loss over the past 50–70 years, transforming them into carbon sources. This paper presents a climate-smart communication and sensing framework for real-time monitoring of these critical marine ecosystems. It integrates Artificial Intelligence (AI) with advanced sensing technologies, including satellite, Uncrewed Aerial Vehicles (UAVs), LiDAR, and in-situ sensors, for comprehensive data acquisition and analysis. The framework evaluates energy-efficient and secure underwater (acoustic, optical) and overwater (satellite, cellular, LoRaWAN) communication strategies to ensure continuous data flow. AI algorithms enhance data processing, pattern recognition, predictive modeling, and autonomous operations of platforms like Autonomous Underwater Vehicles (AUVs). This integrated approach not only supports accurate carbon accounting but also yields substantial co-benefits for climate change mitigation and adaptation, biodiversity conservation, and maritime security by deterring illegal activities and pollution. The framework provides a transformative pathway for sustainable blue economy and resilient coastal communities.

This study proposes a Blockchain-Integrated Circular Economy Framework to improve lifecycle tracking and emissions reporting for maritime ICT and energy materials. The system combines Digital Product Passports, IoT telemetry, and smart contracts on a permissioned blockchain to record operational data and end-of-life events for batteries, photovoltaic modules, and navigation equipment. A parametric algorithm calculates emissions by combining production impacts, usage profiles, and recycling credits, while automated incentives promote material recovery. Synthetic data simulations illustrate the framework's ability to monitor degradation, quantify emissions, and enforce circularity incentives. Results indicate that production emissions dominate lifecycle impacts, highlighting the value of integrated tracking and verified recovery to support low-carbon maritime operations.

This study assesses the potential of advanced materials, specifically graphene, perovskites, and nanostructured ceramics to enhance the energy efficiency, durability, and environmental resilience of 5G and 6G communication systems deployed in harsh environments. A comparative evaluation was conducted based on electrical conductivity, thermal stability, mechanical strength, optical performance, and corrosion resistance, drawing on recent experimental data and life-cycle analyses. Graphene demonstrates electrical conductivity near 10^8 S/m and thermal conductivity up to 5000 W/m-K, enabling transistors with 200 times higher speeds and coatings reducing corrosion by over 90%. Perovskite-based devices achieve solar cell efficiencies up to 34% and optical modulators operating at 170 Gbps. Nanostructured ceramics offer low dielectric loss and stability above 1000°C, supporting high-frequency operation in challenging conditions. Integrating these materials is projected to extend device lifespans by up to 40% and reduce energy and cooling demands by 30%. These findings indicate that adopting advanced materials can significantly improve the performance and sustainability of next-generation communication infrastructure.

Accurate resource yield prediction is critical for military logistics, planning, and operational readiness, yet remains challenging due to numerous influencing factors such as environmental conditions, resource quality, and logistical constraints. This study examines the effectiveness of quantile-based data binning on classical machine learning algorithms in predicting resource yields pertinent to military applications. Furthermore, the effectiveness of Backpropagation Artificial Neural Networks (BP-ANN) and Naive Bayes classifiers with regression models such as K-Nearest Neighbors (KNN), Linear Regression, and Multi-Layer Perceptron Regressors (MLPRegressor) are compared using a robust dataset representative of global resource metrics. The results indicate that binning continuous data into quartiles substantially enhances model accuracy, precision, recall, and computational efficiency. In particular, the binned data enables the BP-ANN to achieve an accuracy of approximately 90.4%, with regression models such as KNN and MLPRegressor outperforming this benchmark by attaining accuracies exceeding 93%. Additionally, binning drastically reduced hyperparameter tuning duration from around 149 minutes to less than 10 minutes, underscoring its computational efficiency advantage. Overall, this research demonstrates that quantile-based data binning is a valuable preprocessing technique that improves predictive accuracy, reduces computational cost, and enhances the reliability of classical machine learning models for military resource forecasting.

In military and expeditionary (maritime) health care environments where isolation, safety, limited personnel, and resource constraints can threaten the delivery of frontline health care, access to timely and knowledgeable medical assistance can be extremely valuable. The purpose of this paper is to investigate the use of large language models (LLMs) in military and maritime health care environments by creating an AI-powered, Over-the-Counter (OTC) Medication Assistance Bot using the Mistral-7B model. The bot is intended to be deployed within tactical, or even shipboard systems, and it would empower autonomous, in-the-moment recommendations of medications for specific symptoms, while mitigating the risks associated with deploying personnel self-medicating through potential non-fundamental use errors. For this work, we employed Low-Rank Adaptation (LoRA) to fine-tune the system, and the bot was trained on a specific dataset derived from material on pharmacological sources, contextualized for medical practices in the Philippines. Based on evaluation the model achieved an average F1-score of 0.7296, which is above the 0.60-0.70 expected levels of performance for medical dialogue systems. The research shows promise for the model as it enhances combat and maritime healthcare readiness by providing consistent, low-bandwidth, and local medical assistance when connected medical supervision may not be immediately available.

This study aimed to develop models for predicting trip frequency in San Jose City, Province of Nueva Ecija, Philippines incorporating socio-demographic factors (SDF) and attitudinal factors (AF) through the use of artificial neural network (ANN). Socio-demographic factors in the model include age, sex, civil status (CS), number of children (NOC), barangay, number of household members (NHM), educational attainment (EA), employment status (ES), household income (HI), number of driver license holder (DLH), number of personal vehicles owned (PVO), and number of vehicles owned by the household (VOH) while the attitudinal factors in the model include car dependency (CD), convenience, speed, privacy and safety (PS), health and environment (HE), cost, and comfort. The collected data were processed to develop ANN model in different pandemic stages with 19-19-1 (input-hidden-output) network structure used for these models. The sensitivity analysis (SA) results indicate that in the pre-pandemic period, employment status is the most influential parameter (MIP) to the trip frequency in the study area, while the educational attainment is the MIP during the pandemic period and in the post-pandemic period. The findings of the study signify the effectiveness of ANN in forecasting trip frequency as evident to the low mean absolute percentage error (MAPE) values obtained for the three models. The results can be used by policymakers in making informed strategies in further improving the travel experience of the population in the study area.