Software Developer

ENG LIM PENJAN ANTONIO (임대한)

👋 About Me

Software engineer specializing in building scalable, user-centric mobile applications, with expertise in advanced data processing, algorithm optimization, and distributed systems, leveraging an AI/ML background. Spearheaded mobile application development across telecom and enterprise sectors, driving adoption of modern architectural patterns and Android best practices to enhance code maintainability and development efficiency. Proficient in Java, Kotlin, Python, and JavaScript, combining technical expertise with innovative problem-solving to deliver reliable, high-performing mobile solutions.

🛠️ Technical Skills

Core Android Development

Data Management & Storage

Additional Languages & Tools

📂 Projects Overview

Mobile Applications

Cubadebate News Reader - News app with personalized content delivery (2021) ⎆
Gas Consumption Manager - National utility tracking system (2021) ⎆
ACME App - Service ticket management solution (2021) ⎆
Yellow Pages - Enterprise directory with offline mapping (2020) ⎆
Government Portal - Official government platform application (2021) ⎆

Machine Learning Systems

Privacy-Preserving Federated Random Forest - Privacy-preserving distributed learning system (2023) ⎆
RoBERTa News Classification - Enhanced topic classification with synthetic data (2024) ⎆
Medical Data Classifier - Patient mortality prediction system (2023) ⎆
Information Retrieval System - Document indexing and search system (2024) ⎆

📱 Mobile Applications

Cubadebate News Reader

Feature-rich news reader app enabling personalized content delivery and comprehensive offline access (2021)

Overview:

Built customizable news feed system with dynamic category and topic selection interfaces, enabling personalized content delivery
Implemented offline caching for bookmarking full articles including images, reducing data usage by up to 30%
Designed real-time topic management system with dynamic search, post count display, and automatic list reordering, reducing average content discovery time from 2 minutes to 30 seconds
Integrated in-article text search, text-to-speech capability and voice recognition capabilities, increasing content accessibility by 40%
Built multi-level commenting interface, infinite scroll with efficient data loading, and SMS subscriptions, improving user engagement
Tech Stack: Android, Kotlin, MVVM, Room, Retrofit, Moshi, Navigation, Material Design, Glide, JSoup, Coroutines, ViewBinding

🔗 View Details

Gas Consumption Manager

National utility tracking system for automated consumption management (2021)

Overview:

Engineered comprehensive utility management app for the National Manufactured Gas Company
Implemented offline data persistence with automated consumption calculations
Created interactive visualization tools and reporting system, reducing operational times by 70%
Built streamlined communication channels with company offices, simplifying the customer support process
Tech Stack: Android, Kotlin, MVVM, Room, Jetpack, MPAndroidChart, Material Design, Coroutines

🔗 View Details

ACME App

Android ticket management app with custom calendar, offline functionality, and location services (2021)

Overview:

Fully offline-capable service ticket management app with responsive design implementation
Implemented interactive calendar with custom event visualization and Android Calendar Provider API integration, improving task scheduling efficiency
Embedded Google Maps functionality for address search and directions, reducing address lookup and navigation time by approximately 20%
Created user registration and authentication flows with input validation and error feedback
Tech Stack: Android, Kotlin, MVVM, Jetpack, Google Maps, Room, Material Design.

🔗 View Details

Yellow Pages

Mobile business directory app for Cuba’s telecommunications company combining business search with essential telecom services (2020)

Search businesses, access emergency numbers and business directories

Find government procedures, requirements and service schedules

Browse phone services, customer support and international calls

Explore mobile internet plans, connection settings and service options

Request advertising space, promote business and increase visibility

Overview:

Developed Cuba’s first Yellow Pages mobile app, implementing enterprise-grade API integration for real-time business search
Engineered offline vector mapping system reducing data usage by 85% through embedded map files for business geolocalization
Implemented automated background synchronization for offline access to government services and telephone information sections
Built responsive search interface with dynamic filters and efficient pagination handling
Executed comprehensive software testing, including unit, UI and compatibility tests, optimizing reliability and user experience
Tech Stack: Android, Java, SQLite, VTM Maps, WebView, HTML, JavaScript, SharedPreferences, JUnit

🔗 View Details

Government Portal

Android app for the official government portal of the city of Pinar del Rio, Cuba (2021)

Overview:

Modernized legacy codebase by integrating MVVM architecture, Coroutines and JetPack components, improving code maintainability and development workflow
Built classified ad feed featuring API integration, offline data caching, real-time synchronization, image carousels, and network status monitoring, improving user accessibility
Designed and implemented district representative portal with features like request submission, meeting schedule management and status tracking using Retrofit/Moshi, automating administrative processes
Integrated provincial council web portal, optimizing desktop UI for mobile through JavaScript injection and WebView customization
Tech Stack: Android, Kotlin, MVVM, Retrofit2, Room, Jetpack, ViewPager2, WebView, JavaScript, Coroutines

🔗 View Details

🔬 Machine Learning Systems

Privacy-Preserving Federated Random Forest

Privacy-preserving distributed learning system for collaborative model training (2023)

Training process for the privacy-preserving federated random forest model

Overview:

Designed and implemented a federated learning system for random forests enabling privacy-preserving distributed model training across multiple clients
Implemented parallel processing pipeline using Python’s ProcessPoolExecutor for efficient multi-client simulation and simultaneous model training, reducing training time by 60%
Introduced incremental learning mechanism that enables efficient integration of new clients without full model retraining, improving system scalability
Demonstrated system effectiveness through extensive testing across 7 benchmark datasets with sizes ranging up to 88,000 samples and 54 features, achieving a 10% performance improvement compared to the baseline approach
Published research in Expert Systems with Applications (SCIE Journal) and resulted in patent filing (Appl. No. 10-2024-0001659)
Tech Stack: Python, NumPy, Pandas, scikit-learn, Matplotlib, multiprocessing, Graphviz

🔗 View Details

RoBERTa News Classification

Enhanced topic classification model with synthetic data augmentation (2024)

RoBERTa model architecture

Overview:

Developed machine learning model for classifying sports news articles into 5 distinct categories using RoBERTa and BBC Sport dataset
Augmented limited training data using GPT-4 generated articles and prompt engineering techniques, improving classification accuracy to 99.5%
Employed zero-shot learning strategy to enhance diversity and versatility of the LLM generated articles
Executed comprehensive experiments evaluating model performance under various data configurations and training conditions
Developed and deployed web application using Streamlit, enabling real-time article classification with detailed performance visualizations
Tech Stack: Python, PyTorch, Hugging Face Transformers, GPT-4, Streamlit

🔗 View Details

Medical Data Classifier

Novel classification system for patient mortality prediction using electronic health records (2023)

Associative classifier - rule generation algorithm

Overview:

Developed custom associative classifier tailored for unbalanced healthcare datasets
Generated interpretable rules for medical decision-making, enabling healthcare experts to validate model predictions
Implemented efficient rule-pruning strategy, reducing rule set by 80% for enhanced model interpretability
Achieved superior performance metrics compared to traditional classifiers on real-world hospital data
Tech Stack: Python, NumPy, Pandas, scikit-learn, Jupyter

🔗 View Details

Information Retrieval System

Efficient implementation of Boolean and ranked document retrieval (2024)

Overview:

Reduced document processing time by 65% compared to sequential search by implementing SPIMI-based inverted indexing
Enhanced search precision through Boolean operator (AND, OR, NOT) based filtering
Implemented ranked retrieval using TF-IDF weighting and cosine similarity, improving search result relevance
Achieved 0.3 second average search response time for 466 English documents
Implemented system with optimized memory usage of 2.5MB
Tech Stack: Python, NLTK, SpaCy, NumPy, contractions

🔗 View Details

📫 Contact Information

Feel free to review my resume or reach out through LinkedIn or email for professional opportunities.