Profile Details

Create Project

★★★★★

☆☆☆☆☆

USD 30 /hr

★★★★★

☆☆☆☆☆

Hire Dr. Yihong T.

United States

USD 30 /hr

AI/NLP & Computer Vision Researcher | Python | ChatGPT Prompts | Data Cleaning & Classification

Profile Summary

Hi! I’m a PhD researcher in Artificial Intelligence with hands-on experience in natural language processing (NLP), computer vision, and LLM applications. I help clients turn messy, multilingual, or scientific data into clear, usable insights. 🔧 I specialize in: • 🧠 Text Classification & NLP – Clean and label real-world text (social media, medical, research) • 🧼 Python Automation – Write scripts to clean, transform, and organize your data • ✍️ Prompt Engineering – Design smart ChatGPT prompts for chatbots, resumes, customer support • 👁️ Computer Vision Tasks – Detect and track biological structures like cells using image processing Projects I’ve Worked On: • 📱 Drug-Related TikTok Content Classification – Used Whisper + Python to analyze speech and transcribe drug mentions • 🧬 Ontology Population from Noisy Text – Extracted relationships from informal drug-related posts • 🗣️ Multilingual Speech Dataset (Chinese-English Code-Mix) – Fine-tuned Whisper for long YouTube speech segments • 🧪 Astrogolia Cell Detection & Tracking – Built a YOLO-based pipeline to detect, count, and measure movement of cells in time-series microscopy images • 📊 Data Labeling Pipelines – Wrote scripts to auto-classify posts using custom lexicons and NLP rules ✅ Tools & Skills: • Languages: Python, Bash • Libraries: OpenCV, YOLO, spaCy, pandas, scikit-learn, HuggingFace, Whisper • Tasks: Prompt design, speech recognition, text cleaning, cell detection, classification, data scripting • Extras: Multilingual (English, Chinese, learning Spanish, Korean, Japanese), academic writing & data reporting

Subject Matter Expertise

• ★ Artificial Intelligence
• ★ Deep Learning
• ★ Computer Vision
• ☆ Data Analysis
• ☆ Image Processing
• ☆ Data Processing
• ☆ Data Collection
• ☆ Machine Learning
• ☆ Text Mining & Analytics
• ☆ Natural Language Processing
• ☆ Neural Networks
• ☆ Python
• ☆ Matlab
• ☆ SQL
• ☆ Excel
• ☆ SAS
• ☆ Tensorflow
• ☆ LaTex
• ☆ Scikit-learn
• ☆ Hypothesis
• ☆ Peer Review
• ☆ Research Methodology
• ☆ Meta-Research
• ☆ Feasibility Studies
• ☆ Fact Checking
• ☆ Literature Search
• ☆ Gap Analysis
• ☆ Language Translation

Services

• Writing
• Research
• Data & AI
• Product Development

Writing Translation

Research Feasibility Study, Fact Checking, Gap Analysis, Secondary Data Collection

Data & AI Predictive Modeling, Image Processing, Image Analysis, Algorithm Design-ML, Text Mining & Analytics, Data Mining, Data Cleaning, Data Processing

Product Development Concept Development

Work Experience

Kansas State University

- Present

Education

Masters of Science

Kansas State University

May 2020 - Present

Certifications

• Naturally language processing

  Unity

  January 2025 - Present

Publications

CONFERENCE PAPER

Yihong Theis, Nathan H. Bean, Friday James, Timothy Tucker, Joshua Levi Weese, Russell Feldhausen (2025). Developing Computing Lessons for Rural High School Students .