fairyofdata Goto Github PK

• I'm Baek Jiheon, an Undergraduate Student Majoring Data Science.
• I'm interested in Data analysis, ML/DL. Especially NLP, NLU, Prompt Engineering.
• Feel free to reach out to me via [email protected] or my linkedin account 📧

• Department of Information Convergence Undergraduate Student (Kwangwoon University)
• Data Youth Campus: NLP-based Deep Learning Course (Hankuk University of Foreign Studies)
• K-Digital Training: Data Science/Engineering Course (Samsung SDS Multicampus)

Main Stack:

Currently studying:

Interested in:

Main Tools:

• 2023.12. Item-based Movie Recommendation Systyem Collaborative Filtering (TBU)
  • Tools: PyTorch, Apache Spark, Python Libraries(Pandas, IMDBpy, BeautifulSoup, Sklearn)
• 2023.10. Tournament simulator Android app using SQLite
  • Tools: SQLite, Android Studio, Android SDK, XML, Java, Kotlin
• 2023.08. Deep learning-based voice phishing and smishing detector
  • Tools: PyTorch, Hugging Face, OPENAI API(Whisper), Python Libraries(Pandas, NLTK, Mecab, Gradio), Django
• 2023.06. Analysis of correlation between apartment-to-station distance and average price per space
  • Tools: Python Libraries(Pandas, numpy, Matplotlib, Seaborn, Haversine, Geopy, Folium)
• 2022.08. Yolo v5 based Side dish recipe recommendation using food ingredient Object recognition
  • Tools: PyTorch, Tableau, Apache Spark, Python Libraries(OpenCV, YOLO, imgaug, Albumentations)
• 2022.06. Deep learning-based Swear word Detector
  • Tools: Python Libraries(Pandas, Selenium, BeautifulSoup, NLTK, KoNLPy, Fasttext), Django

• Non-native speakers pronounciation correcting to use Phoneme-based STT
• Syntax-based Korean-Japanese bilingual NLP with Morpheme-based tokenizing (KoNLPy,Mecab)
• BERT-derived model Performance improvement study (e.g. KoELECTRA + Bi-GRU Model Performance compareing)
• Recommendation Algorithm focused on Sentence-Classification (e.g. Music Recommendation based on Lyrics simminarity)