Hi, I'm Kaede

Embedded Software Engineer Intern

CNH Industrial

Project 1 — Self-Learning Parameter Estimation

• Worked on improving parameter estimation for an articulated vehicle guidance-control feature
• Designed a self-learning parameter estimation algorithm to improve estimation accuracy and support feature development

Project 2 — AI-Powered Machine Log Analysis Agent

• Developed an AI-powered agent to help engineers retrieve relevant machine logs and automatically generate visualizations for root-cause investigation
• Used natural-language queries to identify relevant engineering data and streamline the data preparation process for analysis

Research Assistant — Scottish Gaelic NLP

Cornell College · in collaboration with Edinburgh Napier University

Developed two neural network models for Scottish Gaelic, a low-resource language.

Part-of-Speech Tagger

• Built a BiLSTM-based neural network to tag 87K tokens from the ARCOSG dataset
• Achieved 89% accuracy across 223 unique PoS tags
• Visualized architecture with input, hidden, and output layers

Next-Word Prediction (Small Language Model)

• Preprocessed and trained on 1M tokens using an LSTM model from the Institutional Books Corpus
• Predicted next words in Gaelic phrases