I am a detail-oriented and dedicated individual who is constantly striving to learn and grow in my personal and professional life. I am a recent graduate with a Bachelor of Science in Computer Science with a major in Intelligent Systems that have a strong knowledge in Machine Learning.
I have a strong foundation in computer programming, computer systems and networks, and data analytics. I am proficient in Python, Java, C++, Arduino, PHP Laravel Framework, Figma, Adobe Photoshop, Canva, Excel, SQL, and Power BI. I am also familiar with Agile project management methodologies.
Welcome to the TO-PARCU Request Management System, a web application meticulously crafted using the PHP Laravel Framework. This project serves as a vital tool for the Department of Science and Technology (DOST) CALABARZON's Technical Operations - Public Affairs, Relations, and Communications Unit (TO-PARCU). Designed to streamline the request process, this system empowers requestors within DOST CALABARZON to effortlessly submit service requests to TO-PARCU. Once a request is made, it undergoes a comprehensive tracking mechanism, providing real-time updates on its status.
Welcome to LakeMetrics, your comprehensive web application revolutionizing the analysis of Philippine lakes through satellite imagery. Developed with cutting-edge technology, this platform utilizes a YOLOv8 algorithm to classify lakes based on uploaded satellite images. Once a lake is identified, LakeMetrics dynamically retrieves its boundaries and calculates surface area measurements with precision. This enables users to track changes over time, comparing current data with historical records to assess fluctuations in lake size.
Introducing the WaterMarket Management System, a robust application built using Python's Tkinter library and SQLite3 database. This comprehensive management tool empowers businesses to efficiently track products, manage inventory, and engage with customers, all from one intuitive platform.
Key features include:
Welcome to the Casino Management System, a comprehensive software solution developed using the C# programming language. Designed to optimize casino operations, this system empowers administrators to efficiently manage player registrations, game configurations, and essential data with simple CRUD (Create, Read, Update, Delete) functionalities.
Key features include:
Welcome to the Los Baños Bbayog Senior High School Hub, a bespoke web application crafted exclusively for our school community. Developed using HTML, CSS, and Javascript, this platform serves as your comprehensive digital companion, designed to enhance communication, collaboration, and efficiency within our senior high school ecosystem.
Welcome to Lake Metrics, a groundbreaking project at the forefront of lake classification and measurement technology. Leveraging the power of the YOLOv8 algorithm, our machine learning model is tailored specifically to the unique geography of the Philippines, enabling precise classification of lakes from satellite imagery.
Market basket analysis stands as a cornerstone in data mining, especially within retail and transactional datasets. By unraveling the intricate relationships between items frequently purchased together, this analytical technique sheds light on consumer behavior, enabling businesses to drive product recommendations, optimize inventory management, and craft targeted marketing strategies.
Association learning, the underlying principle behind market basket analysis, operates in an unsupervised realm, delving into the data's inherent structure without the need for predefined labels or categories. This methodology proves invaluable in navigating complex datasets, where hidden patterns await discovery.
I used logistic regression using a dataset from: https://www.kaggle.com/datasets/uciml/breast-cancer-wisconsin-data about the prediction of Breast Cancer if it's Malignant (M) or Benign (B)
This project focuses on the comprehensive cleaning and preprocessing of student academic performance data stored in CSV format. Through meticulous data wrangling techniques, it addresses key preprocessing steps to ensure data quality and usability. This includes identifying and removing duplicate entries, eliminating irrelevant columns to streamline analysis, standardizing letter case for consistency, and performing basic analysis and visualization to gain insights into the dataset. By enhancing data integrity and accessibility, this preprocessing pipeline lays a solid foundation for further analysis and modeling tasks, facilitating informed decision-making in educational settings.
This project focuses on the implementation of dimensionality reduction techniques for preprocessing purposes, aiming to expedite model training while minimizing information loss. Leveraging the capabilities of the Keras API within the TensorFlow ecosystem, we explore three prominent dimensionality reduction models: PCA (Principal Component Analysis), t-SNE (t-Distributed Stochastic Neighbor Embedding), and autoencoder.
This project delves into the realm of academic performance analysis, leveraging feature engineering and data preprocessing techniques to extract valuable insights from the Students Academic Performance Dataset. By meticulously crafting and refining features, we aim to uncover hidden patterns and relationships within the data, ultimately enhancing our understanding of factors influencing student success.
In this project, we delve into linear regression modeling using the diabetes dataset to investigate the potential linear relationship between age and blood pressure, essential variables for predicting diabetes onset. The journey begins with a comprehensive view of the dataset, where we carefully select age and blood pressure as primary predictors, crucial for our predictive task. Next, we embark on data preprocessing steps, including scaling, to ensure uniformity and compatibility across features, enhancing model performance. Utilizing the train-test split methodology, we partition the dataset into separate sets for model training and evaluation, paving the way for robust performance assessment. During implementation, we reshape the train-test datasets to meet the requirements of the fit() function, ensuring smooth model training without data dimensionality issues. Finally, we evaluate our model's performance using the R-squared (R^2) metric, providing insights into its predictive capabilities and overall effectiveness.
In this project, the focus is on mastering Q-Learning, a fundamental value-based reinforcement learning (RL) algorithm renowned for estimating action quality in specific states. The iterative nature of Q-Learning enables the algorithm to continuously refine its estimates based on observed rewards, ultimately optimizing decision-making processes within an environment.
Dive into the realm of salary survey analysis with our project, centered around the comprehensive examination of the Ask A Manager Salary Survey 2021 dataset.
Our journey begins with meticulous data cleaning and preprocessing, ensuring that the dataset is primed and ready for in-depth analysis.
Through rigorous cleaning procedures, we remove inconsistencies, handle missing values, and standardize data formats, ensuring data integrity and reliability.
Next, we embark on preprocessing steps tailored to optimize the dataset for analysis, including feature scaling, encoding categorical variables, and handling outliers.
In this project, we harness the power of transfer learning with MobileNetV2 to streamline the process of human and horse prediction. Leveraging pre-trained weights from the MobileNetV2 architecture, we embark on a journey of training, validation, and optimization to fine-tune the algorithm for our specific classification task.
This project presents a comprehensive demonstration of various clustering algorithms using the Scikit-Learn library on diverse synthetic datasets. Through visual comparisons, we offer insights into the behavior and performance of different clustering algorithms across a range of scenarios, aiding in the understanding of their efficacy in various contexts.
By leveraging synthetic datasets with distinct characteristics, such as varying shapes, densities, and distributions, we showcase how different clustering algorithms respond to different data structures. From K-means and hierarchical clustering to DBSCAN and Gaussian mixture models, each algorithm's strengths and weaknesses are highlighted through visual representations, allowing for an intuitive comparison of their clustering outcomes.
Through this demonstration, practitioners gain valuable insights into the suitability of different clustering algorithms for specific data types and distributions, empowering informed decision-making in real-world clustering tasks. Join us as we unravel the nuances of clustering algorithms and their performance across diverse datasets, facilitating a deeper understanding of unsupervised learning techniques.
Meet SunSeeker, the innovative Arduino-powered robot designed to harness the power of the sun with unmatched efficiency. SunSeeker isn't just a robot – it's a sustainable energy solution that leverages solar panels to capture sunlight and convert it into stored electrical energy, ready for practical use whenever and wherever it's needed, even in emergencies.
This project implements a smart attendance system using an Arduino microcontroller, RFID technology, and a GSM module to send text message notifications to mobile phones. The system is designed to streamline the process of taking attendance and provide real-time updates to parents or guardians when a student is present.
This Arduino project is designed to roam around the house, detecting and monitoring for any break-ins or movements. When movement is detected, a buzzer will sound. The robot is also built with obstacle avoidance capabilities.
A project focused on developing a MOSQUITO-PERSON AGENT-BASED SIMULATION using the GAMA Platform. The simulation models the interactions between mosquitoes and humans within a specified environment, aiming to study the dynamics of mosquito-borne disease transmission. By leveraging the powerful modeling and simulation capabilities of GAMA, this project allows for detailed agent behavior customization and environmental configuration.
A project focused on developing a WATER-DISTRIBUTION AGENT-BASED SIMULATION using the GAMA Platform.