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.
- «
- 1 (current)
- 2
- 3
- »
Recent Submissions
Using big data analysis to retain customers for tele comindustry
(ACM Digital Library, 2019-04-19) Gu, Yuanhu; Malicdem, Alvin R.; Dela Cruz, Josephine S.; Palaoag, Thelma Domingo
Nowadays, telecommunication markets are becoming more and more competitive, and customer churn is becoming more and more serious. In the tough competitive mobile market, Customer Churn Management is becoming more and more critical. In developing countries, most customers switch service providers because of good promotional incentives and lower monthly costs offered by competitive service providers. How to predict customer churn quickly and accurately becomes very important. In this paper, the researchers successfully analyzed the customer churn using big data feature analysis and multi-feature analysis. User data were modeled by XGBoost algorithm. The model is optimized repeatedly with GridSearchCV as a parameter tool. The accuracy of the model on the test set is 85.1%. The researchers predicted about 11000 customer lists per month that may be about to churn. Using K-means clustering method, 11000 churn target customers per month were classified into three categories and telecom companies are suggested to take some solutions which are found by feature analysis to retain customers. This big data analysis can be used to retain customers for the telecom industry.
Deep residual U-Net based lung image segmentation for lung disease detection
(IOP Conference Series: Materials Science and Engineering, 2020) Mique, Eusebio L., Jr.; Malicdem, Alvin R.
The World Health Organization (WHO) estimated that by the year 2030, lung disorders such as Chronic Obstructive Pulmonary Disease (COPD) would be one of the leading cause of death all over the world. Consequently, accurate and timely detection of lung diseases may prevent further death. It is therefore vital that the early detection may lead to treatment and prevention of mortality among patients. However, there are only a minimum number of experts or well-trained radiologists reading Chest X-Ray (CXR) that delays the timely diagnosis of lung diseases. In order to aid the radiologist in reading CXR images, a computer-aided tool is proposed. Before the processing of images, it needs to be segmented to make it easier for the machine to understand. This study is focused on developing a model that will segment the lung from CXR images. Using Residual U-Net (ResUnet) architecture based semantic segmentation, the researchers were able to develop and train a model using a set of 562 CXR images and lung mask images, 70% of the images were used as training data and 30% as test data. The model was trained with 40 epochs and a batch size of 16. Dice coefficient was used to assess the similarity of the segmented result and the ground truth mask. The developed model has achieved a Dice coefficient of 0.9860. The developed model can then be used in classifying lung diseases by focusing on the segmented image rather than focusing on the entire CXR image.
Crime rate visualization with predictive analytics
(Don Mariano Marcos Memorial State University - Mid La Union Campus, 2024-05) Buncab, Lorenzo Manuel P.; Sandoval, Jean Steven F.; Ocampo, Jan Lander T.; Almodovar, Averry Dennisson A.; Pimentel, Emmalou B.; Mique Jr., Eusebio L.; Gallardo, Bernabe P.; Ledda, Mark Kristian C.
This research utilized advanced machine learning models and artificial intelligence neural networks to develop and integrate a system for predicting and visualizing crime rate data in specific areas. Partnering with a government organization, the researchers carefully selected respondents to ensure comprehensive data collection. The development process presented numerous challenges, providing valuable learning experiences. Geographic Information System (GIS) graphs and heatmaps enhanced the system's efficacy and reliability. The study achieved the following objectives: identifying crime prediction indicators, training machine learning models, developing the crime prediction system using CRISP-DM methodology, and testing the system with the User Acceptance Test (UAT) and System Usability Scale (SUS) with six police personnel and four IT experts from DMMMSU MLUC. Significant findings included the identification of dataset indicators from San Juan Police Station data, the high accuracy of regression models, successful integration using the Flask API framework, and a 100% acceptability rate from UAT and 95% from SUS
Coping strategies of college students in DMMMSU Mid La Union Campus during Covid-19 pandemic
(Don Mariano Marcos Memorial State University – Mid La Union Campus, 2022-09) Tangalin, Marjorie A.; Campos, Mark Ryan Kieth M.; Carreon, Darlyne Krishna M.; Tangalin, Junelle Xenia G.; Valdez, Aldrin Ace C.; Legaspi, Annaliza B.; Pajimola, Allan Hil B.; Siong, Venus D.; Novencido, Rosa M.; Quinitip, Tiffany Ruth R.
College students are not exempted to the stress caused by the COVID-19 pandemic. Students are frequently confronted with numerous pressures which add to their stress. This study identified the coping strategies of college students of DMMMSU MLUC, during the COVID-19 pandemic. It was a descriptive correlational survey method. A survey questionnaire was used to collect datafrom371 college students of the colleges/institute in DMMMSU MLUC, which were analyzed using frequency, percentage, rating, median, and chi-square. Finding reveals that they experienced academic and non-academic stressors. The college students sometimes experience the effects of stress and sometimes they used different stress coping strategies. The findings also revealed that the biological, psychological and social effects of stress and coping strategies has significant relationship. This means college students employ various types and methods of coping strategies to manage and lessen their stresses.
Crashlytics:
(Don Mariano Marcos Memorial State University – Mid La Union Campus, 2024-12) Madayag, Maveric B.; Asejo, Reendhel John P.; Bucsit, James V.; Gameng, Klarence Jhay G.; Mique, Jr., Eusebio L.; Sapuay-Guillen, Sheena I.; Ledda, Mark Kristian C.; Malicdem, Alvin R.
This study aimed to analyze accident-prone areas in San Fernando City, La Union, Philippines, using a web-based system developed with Association Rule Mining. It provides valuable insights to inform interventions and policies to reduce vehicular accidents in the region. The research follows the CRISP-DM methodology, which includes six phases: business understanding, data understanding, data preparation, modeling, evaluation, and deployment. System development was based on the Rapid Application Development (RAD) model, which enabled iterative prototyping with user feedback. The system integrated the FP-Growth algorithm for Association Rule Mining to identify accident patterns and was coupled with an interactive map for enhanced visualization and decision-making. Usability testing revealed an average System Usability Scale (SUS) score of 87.14, indicating "Best Imaginable" usability and high user satisfaction.