Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/eesunmoon/eesunmoon

Config files for my GitHub profile.
https://github.com/eesunmoon/eesunmoon

config github-config

Last synced: about 1 month ago
JSON representation

Config files for my GitHub profile.

Awesome Lists containing this project

README 

        
# Eesun Moon



I am currently pursuing a **Master of Science in Computer Science** at Columbia University, with a strong foundation in Machine Learning, Artificial Intelligence, and Natural Language Processing. I received my **Bachelor of Engineering** in Intelligent Mechatronics Engineering and Data Science from Sejong University in February 2024.



## Research Interests

Machine Learning, Artificial Intelligence, Data Science, Affective Computing, Natural Language Processing (NLP), Multimodal Processing



## Research Experience

I worked as a **Research Assistant** at the **Mobile Intelligent Embedded System Laboratory** at Sejong University from September 2021 to March 2024, under the supervision of **Professor Hyung Seok Kim**. During this time, I led several projects in AI and embedded systems, focusing on multimodal emotion recognition, edge computing, and human-robot interaction.



## Publications

| No. | Title | Status |

|:---:|:---:|:---:|

| 1 | Eesun Moon, A.S.M Sharifuzzaman Sugar, Hyung Seok Kim. "Multimodal Daily-life Emotional Recognition Using Heart Rate and Speech Data from Wearables." IEEE Access, vol. 12, pp. 96635-96648, 2024. [Link](https://doi.org/10.1109/ACCESS.2024.3427111) | Published in IEEE Access |

| 2 | Taein Kim, Eesun Moon, Hoyeon Kang, Hyung Seok Kim. "OMER-NPU: On-device Multimodal Emotion Recognition on Neural Processing Unit for Low Latency and Power Consumption." Neural Computing and Applications. *In submission* |

| 3 | Eesun Moon, Hyungseok Kim. "Multi-modal Emotion Recognition Using Physiological Sensor and Speech." In Proceedings of the 38th Annual Conference of ICROS 2023. [Link](https://www.dbpia.co.kr/journal/articleDetail?nodeId=NODE11480498#a) | Published in ICROS2023 |

| 4 | A. S. M. Sharifuzzaman Sagar, Samsil Arefin, Eesun Moon, Md Masud Pervez Prince, L. Minh Dang, Hyung Seok Kim. "An GP-Enhanced Non-linear function and Bayesian Conv-BLSTM based UWB range error mitigation method for LOS and NLOS Scenarios." Measurement. *In submission* |



## Professional Experience



### Machine Learning Engineer [📎]((https://github.com/EesunMoon/genai_soccer))

#### Humaner (Mar 2024 – May 2024)

- Developed a personalized support message generation system using **LangChain**, leveraging **OpenAI** and **RAG algorithms** to enhance message relevance and accuracy, while applying prompt engineering techniques to fine-tune model outputs

- Deployed using **Docker** and **AWS EC2**, collaborating with front-end engineers to ensure communication during live photo events.

- Delivered system to 500+ attendees at live photo events in professional soccer stadiums, increasing **user satisfaction by 20%**.



### Research Assistant [📎](https://github.com/EesunMoon/On-device_Multimodal_ER)

#### Mobile Intelligent Embedded System Laboratory, Sejong University (Sep 2021 – Mar 2024)

- Led multimodal signal processing projects for government agencies and corporations, utilizing **TensorFlow** and **MongoDB** on **Linux**

- Enhanced deep learning models for emotion recognition by integrating HR, EEG, speech, and image data through a score-based multimodal fusion method, achieving **99.68% classification accuracy**.

- Optimized and embedded multimodal emotion recognition models into **NPUs** (Mobilint’s MLA100) for On-device AI, reducing **average power consumption by 3.12 times** and **latency by 1.48 times** for edge computing.

- Submitted papers to **IEEE** (Institute of Electrical and Electronics Engineers) and **NCAA** (Neural Computing and Applications), presented a poster at **ICROS** (Institute of Control, Robotics, and Systems), and delivered live demonstrations at **KIST** (Korea Institute of Science and Technology).



## Projects



### Outfit Coordination Recommender System (Aug 2023 – Sep 2023) [📎](https://github.com/EesunMoon/genAI_Cor-Recom)

- Developed a generative AI-based outfit recommender system by fine-tuning large language models for personalized suggestions

- Constructed and preprocessed fine-tuning dataset of approximately 28,000 Q&A pairs using **KoNLPy** to optimize **KoAlpaca** with **LoRA**, achieving **80% satisfaction rate** from faculty and peers compared to previous models.



### Spam Detection on Social Networking Services (Mar 2022 – Jun 2022) [📎](https://github.com/EesunMoon/spam_review_detection)

- Spearheaded an information retrieval project using text analysis and NLP to classify social media posts as potential advertisements.

- Automated data collection with **Selenium**, analyzed text data sources using **KoNLPy**, and compared embedding techniques (TF-IDF, FastText, Doc2Vec, ELMo, BERT), achieving **0.8 cosine similarity** for advertisement classification.

- Implemented ranking algorithms to sort posts by decreasing likelihood of being advertisements, leading to **30% increase** in detection

- Awarded **1st place** in graduation project competition for demonstrating scalable spam detection solution in unstructured data.



### Stock Sentiment Analysis and Quantitative Modeling (Sep 2021 – Mar 2022) [📎](https://github.com/EesunMoon/JENQ)

- Correlated stock prices with financial statements from 2020 to 2021 for 50 companies, building quantitative models using **PyTorch** and comparing linear regression with LSTM for stock trend predictions

- Built a sentiment dictionary by extracting keywords from economic news articles using **BeautifulSoup**, analyzing stock price fluctuations within three days of publication to assess impact of keyword sentiment scores on stock prices