Project
Multivariate Time Series Clustering With Transformer
Purposed a novel framework for Multivariate Time Series Clustering With Transformer using the learnable representations in latent spaces of Transformer Encoder to achieve superior and efficient clustering re- sults in real-world experiments.
ProtectYourVoice: Detacting AI Generated Voice using Deep Learning
Applied a deep learning ResNet model with transfer learning techniques to classify spectrograms of human and AI-generated voices, achieving high test accuracy in the ASVspoof2019 competition.
Unfair-ToS: A GPT-Based Unfair Term Of Service Detector
Leveraging fine-tuned LLMs and the GPT-4 model to identify and highlight unfair or significant clauses within the Terms of Service agreements of major service providers.
Case Study Using the Optimal Temporal Clustering Framework
Introducing a novel temporal clustering framework and its applications, guaranteeing optimality and dynamic adaptation of clustering centers and labels across time.
Text Classification and Data Anaylsis on Cryptocurrency Related Tweets in PySpark Enviorment
Leveraging Pyspark to perform tranditional text data analysis and NLP learning tasks when the scale of samples is large. And using the trained model to construct an automatic hash-tagging system for incoming tweets.
Tranditional Statistical Learning: Classification in Self-Assessed Financial Health Status
Using German General Social Survey (ALLBUS), this project tend to classify the survey’s responses into one of the five categories from 1 to 5 which represent the “self-asset financial health” of samples.