UPLB ICS Peak One

The study addresses the challenge of finding com- patible roommates among college students around University of the Philippines Los Baños, presenting a solution in the form of ”BunkUP,” a Flutter and Firebase-based mobile application for roommate-finding. Leveraging features adapted from existing matchmaking applications, the application aims to streamline the process of locating an ideal roommate based on individual preferences and lifestyle. The methodology involves content- based filtering to generate roommate suggestions. Evaluating the application on University of the Philippines Los Baños students using the System Usability Scale yielded a high score of 92.05, indicating strong usability and user-friendliness. Feedback further confirmed the application’s effectiveness in simplifying roommate selection. The successful integration of Flutter and Firebase contributed to enhanced functionality and user experience, emphasizing the potential of this approach in addressing the roommate-finding challenges faced by college students.

Closed-circuit television (CCTV) cameras have been widely used for security purposes, to ensure the safety of the public. Quickly assessing the interaction between two people as either hostile or non-hostile could help prevent a life-and- death situation through intervention from authorities. This paper discussed the use of pose estimation to detect actions as hostile or non-hostile, hostile actions being choking, hold-up, hostage, punching, and kicking, and non-hostile actions being cheek-to- cheek, dancing, handshaking, hugging, and talking. The training dataset, taken from recorded videos, contains 5000 images, with each class having 500 images. YOLOv4 was used as the machine learning model. The overall accuracy of the model in classifying them as either Hostile or Non-Hostile is 71.83%, while the overall accuracy of the model in detecting each action correctly and classifying them as either Hostile or Non-Hostile is 43.58%. It can be concluded that the model had some difficulty in differentiating actions but it can identify if the action is Hostile or Non-Hostile.

Music induces basic to complex emotions such as happiness, sadness, and nostalgia. These emotions can be classified into categories like positive or negative using sentiment analysis. Existing studies on mood classification mostly focus on the audio features of a song while the lyric features are ignored. A few studies on lyrics mood classification, on the other hand, pointed out the need to explore other classifiers like Naı̈ve Bayes and improve its performance, using a larger dataset. In this study, a Naı̈ve Bayes classifier model was created to identify whether a song is positive or negative based on its lyrics. The model which produced exceptional results with 95.02% accuracy and 94.42% precision was trained and tested using a dataset containing 1,810 song lyrics. Feature extraction techniques such as N-grams (trigrams) and TF-IDF were applied after preprocessing the data.

Traditional Meter Reading where a meter man does an ocular visit to each household to log the water consumption indicated in the water meters is very time-consuming and inefficient. This study proposes a new system that revolves around a mounted meter reading device with Wi-Fi connectivity as its main way to communicate with the server. This comes along with a new information system that has features based on the existing application used by the Client. To showcase automation, a digit recognition script was used to identify the digits indicated in the water meter through Neural Network. The client, Molino Homes Water Management, evaluated the proposed system, its features and plausibility of the system to replace their current system through a Client Satisfaction Survey. The results were non-satisfactory as the system was deemed to be average and currently cannot be deployed. Nonetheless, the clients are still interested for the system once it is industry grade and scalable to the whole subdivision.

The rise of social media has led to the widespread use of online posts as valuable data for machine learning studies. However, these studies often encounter the challenge of dealing with metaphors embedded in the text, which can introduce inconsistencies in data processing since metaphors are known to change meaning of text. This challenge is even more prominent in high context languages such as Filipino. In response to this issue, multiple novelties were introduced in this study. These novelties are the Filipino metaphor corpus, the Filipino metaphor identifier created that utilizes an automatic definition selector, and finally a modified metaphor counting method in the evaluation.