<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Home | Daeun's Portfolio</title><link>https://ddaaan.github.io/en/</link><atom:link href="https://ddaaan.github.io/en/index.xml" rel="self" type="application/rss+xml"/><description>Home</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Tue, 15 Jul 2025 00:00:00 +0000</lastBuildDate><image><url>https://ddaaan.github.io/media/logo_hu25717422b3b0790f0566abe2caaf12f9_60927_300x300_fit_lanczos_3.png</url><title>Home</title><link>https://ddaaan.github.io/en/</link></image><item><title>U.S. Exchange Program</title><link>https://ddaaan.github.io/en/experience/cards/unlv/</link><pubDate>Tue, 15 Jul 2025 00:00:00 +0000</pubDate><guid>https://ddaaan.github.io/en/experience/cards/unlv/</guid><description/></item><item><title>Energy Consumption Analysis for LLM Training in Edge Environments</title><link>https://ddaaan.github.io/en/publication/2025-edge-llm-power/</link><pubDate>Thu, 01 May 2025 00:00:00 +0000</pubDate><guid>https://ddaaan.github.io/en/publication/2025-edge-llm-power/</guid><description/></item><item><title>Performance Analysis of Lightweight LLMs on Heterogeneous Jetson Platforms</title><link>https://ddaaan.github.io/en/publication/2025-jetson-quant-llm/</link><pubDate>Thu, 01 May 2025 00:00:00 +0000</pubDate><guid>https://ddaaan.github.io/en/publication/2025-jetson-quant-llm/</guid><description/></item><item><title>NearDeal: Hyperlocal O2O Platform for Local Businesses</title><link>https://ddaaan.github.io/en/project/neardeal/</link><pubDate>Sat, 01 Mar 2025 00:00:00 +0000</pubDate><guid>https://ddaaan.github.io/en/project/neardeal/</guid><description>&lt;h2 id="-project-overview">💡 Project Overview&lt;/h2>
&lt;p>&lt;strong>NearDeal&lt;/strong> is a &lt;strong>hyperlocal O2O platform&lt;/strong> designed to help small business owners &lt;strong>boost their sales in real time&lt;/strong>.&lt;br>
It enables merchants to issue coupons or event promotions during &lt;strong>off-peak hours&lt;/strong>, while users can &lt;strong>easily discover nearby participating stores&lt;/strong> and access local deals instantly.&lt;/p>
&lt;hr>
&lt;h2 id="-key-features">🌟 Key Features&lt;/h2>
&lt;h3 id="-for-users-customers">👨‍👩‍👧 For Users (Customers)&lt;/h3>
&lt;ul>
&lt;li>View real-time affiliate store and coupon information&lt;/li>
&lt;li>Search nearby stores based on user location&lt;/li>
&lt;li>Download and manage coupon usage history&lt;/li>
&lt;li>Automatically categorize partner stores by university college&lt;/li>
&lt;/ul>
&lt;h3 id="-for-merchants">🧾 For Merchants&lt;/h3>
&lt;ul>
&lt;li>Register and manage store profiles&lt;/li>
&lt;li>Issue or expire coupons in real time&lt;/li>
&lt;li>Visualize sales statistics (daily, weekly, monthly)&lt;/li>
&lt;li>Promote events through push notifications&lt;/li>
&lt;/ul>
&lt;h3 id="-for-schools--university-partnerships">🏫 For Schools &amp;amp; University Partnerships&lt;/h3>
&lt;ul>
&lt;li>Provide affiliate store information pages by department&lt;/li>
&lt;li>Support collaborations with on-campus groups and clubs&lt;/li>
&lt;/ul>
&lt;hr>
&lt;h2 id="-tech-stack">⚙️ Tech Stack&lt;/h2>
&lt;ul>
&lt;li>&lt;strong>Frontend&lt;/strong>: React, Vite, TailwindCSS&lt;/li>
&lt;li>&lt;strong>Backend&lt;/strong>: Spring Boot (Java 21), JPA&lt;/li>
&lt;li>&lt;strong>Database&lt;/strong>: MySQL&lt;/li>
&lt;li>&lt;strong>Deployment&lt;/strong>: Vercel (Frontend), AWS EC2 (Backend)&lt;/li>
&lt;li>&lt;strong>Version Control&lt;/strong>: GitHub Actions, Docker&lt;/li>
&lt;/ul>
&lt;hr>
&lt;h2 id="-project-highlights">🚀 Project Highlights&lt;/h2>
&lt;ul>
&lt;li>Built with &lt;strong>React SPA architecture&lt;/strong> for a fast and seamless user experience&lt;/li>
&lt;li>Clean &lt;strong>Spring Boot REST API&lt;/strong> backend structure&lt;/li>
&lt;li>Efficient data management with &lt;strong>MySQL + JPA&lt;/strong>&lt;/li>
&lt;li>&lt;strong>Automated frontend deployment&lt;/strong> through Vercel CI/CD&lt;/li>
&lt;/ul>
&lt;hr>
&lt;h2 id="-future-plans">📍 Future Plans&lt;/h2>
&lt;ul>
&lt;li>Implement &lt;strong>AI-based coupon recommendation algorithms&lt;/strong>&lt;/li>
&lt;li>Develop &lt;strong>automated marketing tools&lt;/strong> for small businesses&lt;/li>
&lt;li>Expand &lt;strong>university-wide partnership integrations&lt;/strong> for Jeonbuk National University&lt;/li>
&lt;/ul>
&lt;hr>
&lt;h2 id="-github-repository">🔗 GitHub Repository&lt;/h2>
&lt;p>&lt;a href="https://github.com/dodohy25n/NearDeal_Server" target="_blank" rel="noopener">https://github.com/dodohy25n/NearDeal_Server&lt;/a>&lt;/p></description></item><item><title>Integrated Data Analysis and Automated Report Generation System</title><link>https://ddaaan.github.io/en/project/capston/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://ddaaan.github.io/en/project/capston/</guid><description>&lt;h2 id="-project-overview">💡 Project Overview&lt;/h2>
&lt;p>This system provides an &lt;strong>end-to-end data analysis service&lt;/strong> that allows users to upload their data and perform &lt;strong>search, automatic preprocessing, preview, RAG-based chatbot Q&amp;amp;A, and automatic Korean report generation&lt;/strong>.&lt;br>
By integrating Streamlit and Flask, it delivers both a user-friendly interface and powerful backend analytical capabilities.&lt;/p>
&lt;hr>
&lt;h2 id="-key-features">🌟 Key Features&lt;/h2>
&lt;ul>
&lt;li>&lt;strong>Data Search&lt;/strong>: Enables fast data retrieval using an integrated database.&lt;/li>
&lt;li>&lt;strong>Upload and Analysis&lt;/strong>: Users can upload and analyze their own datasets.&lt;/li>
&lt;li>&lt;strong>Automatic Preprocessing &amp;amp; Preview&lt;/strong>: Handles missing values and data type preprocessing automatically, with schema and sample data preview.&lt;/li>
&lt;li>&lt;strong>RAG-based Chatbot&lt;/strong>: Supports natural language Q&amp;amp;A using the user-selected file as the context.&lt;/li>
&lt;li>&lt;strong>Automatic Korean Report Generation&lt;/strong>: Summarizes LLM responses into a structured Korean report available for download.&lt;/li>
&lt;/ul>
&lt;hr>
&lt;h2 id="-tech-stack">⚙️ Tech Stack&lt;/h2>
&lt;ul>
&lt;li>&lt;strong>Language&lt;/strong>: Python&lt;/li>
&lt;li>&lt;strong>Framework&lt;/strong>: Streamlit, Flask&lt;/li>
&lt;li>&lt;strong>Server/Infra&lt;/strong>: Docker&lt;/li>
&lt;li>&lt;strong>Models&lt;/strong>: KURE-v1 (Embedding), Qwen3 (LLM)&lt;/li>
&lt;/ul>
&lt;hr>
&lt;h2 id="-project-highlights">🚀 Project Highlights&lt;/h2>
&lt;ul>
&lt;li>&lt;strong>RAG Architecture&lt;/strong>: Uploaded files are stored in S3, parsed, preprocessed, and embedded (via KURE-v1) for vector-based retrieval.&lt;/li>
&lt;li>&lt;strong>LLM Integration&lt;/strong>: Context generated from vector search is passed to the Qwen3 model for response summarization and rendered into a report template.&lt;/li>
&lt;li>&lt;strong>Docker-based Deployment&lt;/strong>: The project is containerized for seamless deployment across local and server environments.&lt;/li>
&lt;li>&lt;strong>Comprehensive Troubleshooting Documentation&lt;/strong>: Detailed notes on Docker setup and issue resolution were recorded.
&lt;blockquote>
&lt;p>🔧 &lt;a href="https://www.notion.so/Docker-Trouble-Shooting-1d284dccb3788007bf86c6856df9e8e6" target="_blank" rel="noopener">Docker Setup / Troubleshooting Guide&lt;/a>&lt;/p>
&lt;/blockquote>
&lt;/li>
&lt;/ul>
&lt;hr>
&lt;h2 id="-github-repository">🔗 GitHub Repository&lt;/h2>
&lt;p>&lt;a href="https://github.com/Ddaaan/capston" target="_blank" rel="noopener">https://github.com/Ddaaan/capston&lt;/a>&lt;/p></description></item><item><title>Development and Operation of Jeonnam Office of Education Survey Website</title><link>https://ddaaan.github.io/en/project/jne-survey/</link><pubDate>Thu, 01 Aug 2024 00:00:00 +0000</pubDate><guid>https://ddaaan.github.io/en/project/jne-survey/</guid><description>&lt;h2 id="-project-overview">💡 Project Overview&lt;/h2>
&lt;p>This project was commissioned by the &lt;strong>Jeollanam-do Office of Education&lt;/strong>, aimed at creating an integrated platform for conducting and managing democracy-related surveys across schools.&lt;br>
The platform was developed and operated using Django as the backend framework.&lt;/p>
&lt;p>&lt;strong>Service Link&lt;/strong>: &lt;a href="http://jndedu-school-democracy.kr/" target="_blank" rel="noopener">http://jndedu-school-democracy.kr/&lt;/a> (Hosting terminated)&lt;/p>
&lt;hr>
&lt;h2 id="-key-features">🌟 Key Features&lt;/h2>
&lt;h3 id="-users-students-parents-faculty">👩‍🏫 Users (Students, Parents, Faculty)&lt;/h3>
&lt;ul>
&lt;li>Participate in customized surveys according to user type (student, parent, or faculty)&lt;/li>
&lt;li>Access announcements and download attachments from the resources section&lt;/li>
&lt;li>View educational resources related to school democracy&lt;/li>
&lt;/ul>
&lt;h3 id="-administrators-school--regional-office--main-office">🧑‍💻 Administrators (School / Regional Office / Main Office)&lt;/h3>
&lt;ul>
&lt;li>Role-based admin accounts with tiered access (school, regional office, headquarters)&lt;/li>
&lt;li>Create and manage announcements or resources with file uploads&lt;/li>
&lt;li>Real-time statistics by school, region, and education level&lt;/li>
&lt;li>Visualize and export statistics by question or category&lt;/li>
&lt;/ul>
&lt;hr>
&lt;h2 id="-tech-stack">⚙️ Tech Stack&lt;/h2>
&lt;ul>
&lt;li>&lt;strong>Language&lt;/strong>: Python 3.11.9&lt;/li>
&lt;li>&lt;strong>Framework&lt;/strong>: Django&lt;/li>
&lt;li>&lt;strong>Database&lt;/strong>: MySQL&lt;/li>
&lt;li>&lt;strong>Server&lt;/strong>: Ubuntu + Nginx&lt;/li>
&lt;li>&lt;strong>Deployment&lt;/strong>: Gunicorn, crontab (automatic reboot scheduling)&lt;/li>
&lt;/ul>
&lt;hr>
&lt;h2 id="-key-learnings">🧠 Key Learnings&lt;/h2>
&lt;ul>
&lt;li>&lt;strong>High-Traffic Management&lt;/strong>: Gained hands-on experience handling sudden traffic spikes in a live environment by optimizing Nginx and Gunicorn configurations.&lt;/li>
&lt;li>&lt;strong>Database Optimization&lt;/strong>: Solved Django ORM N+1 query problems using &lt;code>select_related&lt;/code> and &lt;code>prefetch_related&lt;/code>, and minimized DB load for complex queries with &lt;code>annotate&lt;/code> and &lt;code>aggregate&lt;/code>.&lt;/li>
&lt;li>&lt;strong>Server Operations&lt;/strong>: Learned to maintain stable Ubuntu-based servers using scheduled crontab tasks for automatic reboots and monitoring.&lt;/li>
&lt;/ul>
&lt;blockquote>
&lt;p>👉 &lt;a href="https://www.notion.so/12184dccb3788007a936ed1918ffab09?pvs=21" target="_blank" rel="noopener">Detailed Learnings on Site Operation&lt;/a>&lt;/p>
&lt;/blockquote>
&lt;hr>
&lt;h2 id="-github-repository">🔗 GitHub Repository&lt;/h2>
&lt;p>&lt;a href="https://github.com/Ddaaan/EduWebCode" target="_blank" rel="noopener">https://github.com/Ddaaan/EduWebCode&lt;/a>&lt;/p></description></item><item><title>CanCheck: A Mobile App for Identifying Canned Drinks for the Visually Impaired</title><link>https://ddaaan.github.io/en/project/cancheck/</link><pubDate>Sat, 01 Jun 2024 00:00:00 +0000</pubDate><guid>https://ddaaan.github.io/en/project/cancheck/</guid><description>&lt;h2 id="-project-overview">💡 Project Overview&lt;/h2>
&lt;p>CanCheck is an Android application designed to help visually impaired users identify canned beverages.&lt;br>
It uses the smartphone camera to detect cans in real-time through an object detection model (YOLOv5), then announces the detected label via TTS (Text-to-Speech) audio output.&lt;/p>
&lt;hr>
&lt;h2 id="-key-features">🌟 Key Features&lt;/h2>
&lt;ul>
&lt;li>&lt;strong>Real-time Object Detection&lt;/strong>: Optimized the YOLOv5 model for mobile to detect canned beverages in real time.&lt;/li>
&lt;li>&lt;strong>Voice Guidance (TTS)&lt;/strong>: Announces the detected can name through speech output, allowing users to identify beverages without visual information.&lt;/li>
&lt;li>&lt;strong>Dataset Creation&lt;/strong>: Built a custom dataset by web crawling and manual labeling using Roboflow.&lt;/li>
&lt;li>&lt;strong>Model Training&lt;/strong>: Trained the YOLOv5 model on Google Colab, optimized and deployed it on the Android app.&lt;/li>
&lt;/ul>
&lt;hr>
&lt;h2 id="-tech-stack">⚙️ Tech Stack&lt;/h2>
&lt;ul>
&lt;li>&lt;strong>Language&lt;/strong>: Java, Python&lt;/li>
&lt;li>&lt;strong>Tools&lt;/strong>: Android Studio, Google Colab, Roboflow&lt;/li>
&lt;li>&lt;strong>Model&lt;/strong>: YOLOv5 (Object Detection), Google TTS API&lt;/li>
&lt;/ul>
&lt;hr>
&lt;h2 id="-github-repository">🔗 GitHub Repository&lt;/h2>
&lt;p>&lt;a href="https://github.com/Ddaaan/CanCheck" target="_blank" rel="noopener">https://github.com/Ddaaan/CanCheck&lt;/a>&lt;/p></description></item><item><title>Undergraduate Researcher</title><link>https://ddaaan.github.io/en/experience/cards/lab/</link><pubDate>Fri, 01 Mar 2024 00:00:00 +0000</pubDate><guid>https://ddaaan.github.io/en/experience/cards/lab/</guid><description/></item><item><title>SW Major Mentoring</title><link>https://ddaaan.github.io/en/experience/cards/swmentor/</link><pubDate>Sun, 01 Oct 2023 00:00:00 +0000</pubDate><guid>https://ddaaan.github.io/en/experience/cards/swmentor/</guid><description/></item><item><title>About</title><link>https://ddaaan.github.io/en/about/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://ddaaan.github.io/en/about/</guid><description/></item><item><title>About</title><link>https://ddaaan.github.io/en/en/about/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://ddaaan.github.io/en/en/about/</guid><description/></item></channel></rss>