Eastern Visayas State University

The Complete Blood Count (CBC) is an essential diagnostic procedure widely employed in clinical laboratories to evaluate overall health and detect conditions such as infections, anemia, and hematologic malignancies. Traditional CBC methods, including manual counting with a hemocytometer and automated analyzers, are either labor-intensive or cost-prohibitive for low-resource settings. This study presents a MATLAB-based diagnostic application designed to detect and classify red blood cells (RBCs) and white blood cells (WBCs), including WBC subtypes, from blood smear images. The system utilizes pre-annotated bounding boxes for cell localization, eliminating the need for complex image segmentation. A user-friendly graphical user interface (GUI) was developed using MATLAB App Designer, allowing real-time display of cell counts and classifications. Clinical validation with licensed medical technologists ensured the morphological accuracy of WBC subtype labels. The system achieved a WBC classification accuracy of 76.92%, an RBC count accuracy of 23.08% (38.46% within a +/- 2 tolerance), and 100% accuracy in WBC counting. The results demonstrate the tool's effectiveness and practicality for hematological diagnostics in academic and low-resource healthcare environments. Future work includes integrating deep learning techniques for automated classification and batch processing.

The increasing number of applicants for the ICT Proficiency Examination has created significant challenges for the Department of Information and Communications Technology (DICT) Region VIII, particularly in the manual verification of examination requirements. Traditional validation procedures are often time-consuming, prone to data-entry mistakes, and susceptible to inconsistencies in decision-making. To address these concerns, this study developed an ICT Exam Validation System that automates the verification and assessment of applicant documents. The system was developed using the Agile System Development Life Cycle, which involved iterative phases of planning, design, development, testing, deployment, and evaluation. It features dedicated portals for applicants and administrators, secure user authentication, automated document validation, and real-time notification capabilities. To determine its effectiveness, the system underwent functional and technical evaluations based on reliability measures and the ISO/IEC 25059:2023 quality model, focusing on key attributes such as adaptability, reliability, transparency, and operational efficiency. The evaluation results indicate that the system provides a dependable and practical solution for streamlining the validation of ICT Proficiency Examination requirements. By reducing manual intervention and improving the consistency of validation decisions, the system enhances the overall efficiency of examination administration. Moreover, the project contributes to the advancement of digital governance initiatives by supporting innovation in public service delivery and promoting the modernization of government processes. The study also aligns with Sustainable Development Goals (SDGs) 9 and 16 by encouraging the adoption of intelligent technologies that strengthen institutional effectiveness, improve service accessibility, and foster sustainable digital transformation in the public sector.

Eastern Visayas State University were sampled using a stratified random sampling technique. A 24-item questionnaire was used to gather information on participants' demographics and satisfaction with online learning. Frequency counts, percentages, means, and standard deviations were used in descriptive statistics, while inferential tests used t-tests and ANOVA. The results showed that although students were satisfied with their instructors (M = 3.63) and the technology provided (M = 3.56), they rated interaction the lowest (M = 3.39). This lack of association was accompanied by a decline in overall satisfaction (M = 3.22), although some students reported being quite satisfied with their experience. Also, the students' major was the greatest predictor of their satisfaction level. Hands-on programs like Engineering and Education struggled significantly more online compared to computer-based majors like Business and Industrial Technology. The data also showed that older students were more satisfied overall, likely due to better time-management habits, whereas prior online class experience did not have a statistically significant effect. The study concludes that the presence of functioning technologies and quality teachers alone cannot ensure success in online education. To be successful in the long run, institutions of higher learning should go beyond mere content uploads and focus on developing interactive, field-oriented hybrid courses.

Efficient energy management has become a critical concern across all sectors due to rising costs and sustainability imperatives. In universities, electricity expenditure represents a substantial share of operational budgets, prompting the need for accurate forecasting models to support financial planning and sustainability initiatives. This study proposed a hybrid forecasting model integrating Simple Exponential Smoothing (SES) and Long Short-Term Memory (LSTM) networks to predict monthly electricity expenditure in a university setting. SES acts as a linear smoothing operator, emphasizing recent trends, while LSTM serves as a nonlinear sequence learner capable of modeling long-term dependencies. The hybrid formulation embeds SES forecasts as auxiliary input features to LSTM, thereby balancing interpretability with predictive power. A dataset of 60 monthly electricity expenditure observations (2019–2023) from Eastern Visayas State University–Tanauan Campus was analyzed. The proposed model was compared against classical (SES, ARIMA) and deep learning (LSTM, FB Prophet) approaches. Results show that the hybrid model achieved superior performance (RMSE = 33760.68, MAPE = 32.32%, MAE = 24580.12), with statistical validation through the Diebold-Mariano test, which confirmed significant improvements. Residual and uncertainty analyses demonstrated the model's robustness and practical applicability. The proposed model positioned it as a valuable decision-support tool for energy cost forecasting and risk-aware planning in universities.