UPLB ICS Peak One

Children's media content consumption poses both educational opportunities as well as risks of exposure to TV violence and negative messages. And with the absence of access to parental control systems or TV parental guidelines, parents face difficulties in guiding their children in the digital environment. With the aim of addressing this problem, we present an information system that will display reviews of television programs specifically for Filipino children, from an official agency - the National Council for Children’s Television (NCCT). This system is also designed to help the NCCT in facilitating the operation of its media monitoring function. Through this website, the agency will be able to share their TV program evaluations with their stakeholders - content creators, educators, parents, and all of those who are responsible for the care, education, and protection of Filipino children below 18 years old. It will also help the NCCT to efficiently store, update, and create summaries of their media monitoring data. The system was developed using the MERN stack and was evaluated based on its perceived usability. The average SUS scores from the responses of the test participants from NCCT was 75.83, while the average SUS scores from the responses of select NCCT stakeholders was 92.5. This resulted in an overall mean SUS score of 87.5, indicating excellent perceived usability of the developed information system

BanCov Tarlac is an android mobile application that was developed to inform users about the current state of the Covid-19 pandemic in the province of Tarlac. The mobile application would display the daily Covid-19 New Cases, New Recoveries, New Deaths, Active Cases, and Cumulative Covid- 19 Cases in the province. Along with the mobile application, a BanCov Tarlac Website was also developed for the input of Daily Covid-19 related data by administrators of the application. The mobile app was tested by 25 users from the Tarlac province and garnered a SUS score of 92.9/100, while the web app was evaluated by 6 admins from the Provincial Governor’s Office and garnered a SUS score of 90/100.

COVID-19 non-severe patients were advised to stay at home for self-quarantine, which increased the use of pulse oximeters that can detect “silent hypoxemia” early on. In line with this, remote monitoring becomes essential as it lessens the risk of household transmissions. This study developed a Rasp- berry Pi-based system that measures the temperature and oxygen saturation level of the patient and sends the data to a dedicated web application. If the resulting status of the measurement is not normal, it will send alerts to the patient’s relatives through SMS, with the suggestion of the nearest healthcare facility.

The COVID-19 pandemic has introduced the im- portance of digital contact tracing. In digital contact tracing, the use of Quick Response (QR) codes is widely used due to its privacy. This study has developed a digital contact tracing system for residents of the City of Gapan, Nueva Ecija. The system utilizes QR codes to log users that enter the premises of an establishment. The system also supports an admin-reporting feature where administrators are responsible for classifying individuals as positive or as close contacts.

An ensemble model composed of Decision Trees, AdaBoost and Gradient Boosting was created in order to tackle the issues of using an imbalanced dataset, and using non-English datasets. The ensemble model was trained on both English and Filipino Yelp datasets and was compared to other models. The results showed that the ensemble model achieved an f-1 score of 0.6822 and an AUC score of 0.7600 using the English Yelp dataset. In addition, it also achieved an f-1 score of 0.6859 and an AUC score of 0.7441. The findings suggest that the ensemble model can reliably classify fake reviews.