@rahmath145
Computer Science graduate with a strong interest in Data Analytics and Software Engineering. Experienced in developing applications and websites, processing and visualizing data, and applying fundamental programming concepts, data structures, object-oriented programming, software testing, and problem-solving.
1
Services
5
Projects
$20 – $100
per project
Implemented a CNN-based bird species classifier using EfficientNetB0 transfer learning to distinguish four grain‑eating bird species and an unknown class from images collected via eBird.org. The model, built in Python with TensorFlow/Keras, was trained on 224×224 RGB images, evaluated with stratified 5‑fold cross‑validation, and achieved ~82 % test accuracy. The project leverages Jupyter Notebooks, Google Colab GPU runtime, and libraries such as NumPy, pandas, OpenCV, and scikit‑learn for data preprocessing, training, and performance reporting.
A static landing page for Desa Banjaran with an accompanying admin panel built entirely in vanilla JavaScript. The site is deployed on Cloudflare Pages, uses Cloudflare Workers for backend logic, stores media in Cloudflare R2, and persists data in a Neon PostgreSQL database. The project relies on Node.js 22 for local development and includes scripts for testing, linting, and deployment.
SimDoc is a Flutter‑based document management system that uses Firebase for authentication, Firestore, Storage, and Cloud Functions to provide secure, role‑based access, hierarchical categorization, file upload/download, and audit logging. The app follows a clean architecture with a Riverpod + BLoC hybrid state‑management approach, leveraging the Repository pattern for data abstraction and encapsulated business logic. Core technologies include Dart/Flutter, Firebase services, Riverpod, BLoC, and SharedPreferences for local persistence.
An interactive web‑based Business Intelligence dashboard built with JavaScript, featuring dynamic multi‑dimensional filtering, real‑time KPI scorecards, and 13 data visualizations (charts, doughnut, bar, line, stacked). The application includes a high‑performance transaction grid with instant search, sticky headers, and outlier badges, all powered by client‑side re‑aggregation and a clean, modular architecture.
A modern, minimalistic portfolio website showcasing education, skills, and experience/projects sections with collapsible panels. Built with HTML5, CSS3, and vanilla JavaScript, it offers a responsive design that works on both mobile and desktop. The site includes a light mode (warm yellow‑orange) and a dark mode toggle for user preference.
