Machine Learning Language Processing

Qingbao Yu (PhD) Mobile phone: 505-***-****

Permanent Resident of US Email: ad5rs3@r.postjobfree.com

Github: https://github.com/ythinkingg Address: 10847 Deborah Dr. Potomac. MD 20854 Strong Skills

• Machine Learning: Logistic Regression, Naïve

Bayes, Decision Tree, Random Forest, KNN, SVM,

Linear Regression, Neural Network.

• Deep learning: Graph Neural Networks, CNN, RNN.

• Natural language processing, A/B testing, ETL.

• Hugging Face: transformers, Large Language Models

• Python: tensorflow, keras, pytorch, sklearn, NLTK, pyG, numpy, scipy, matplotlib, seaborn.

• Python pandas: data preparation, cleaning, statistical analysis, visualization, manipulation.

• SQL: join tables, subqueries, filtering, grouping, ordering, data manipulation, sets theory.

• R tidyverse dplyr: data manipulation, visualization, wrangling, analysis; ggplot: visualization.

• Data driven methods: Graph theory-based analysis, ICA, PCA, clustering.

• MySQL, PostgreSQL, git version control,

• Anaconda, Jupyter, Spyder, VS code,

• Tableau, power BI.

• Linux systems, ubuntu, redhat, Debian, shell, bash. Highlighted Projects:

• Apply Naïve Bayes, Logistic Regression, CNN,

RNN, LSTM, GRU on text language data to classify

movie reviews, topics.

• Apply transformers, pre-trained Large Language

Models (LLM, BERT, GPT from Hugging Face) to

perform text language processing projects.

• Apply SVM, Decision Tree, Random Forest, Graph

Neural Network, Logistic Regression, Naïve Bayes,

Neural Networks on Skin Conductance data and

fMRI brain imaging data to classify high pain VS low pain.

• Apply linear regression, graph theory analysis, ICA, PCA, clustering, machine learning on fMRI brain

imaging data, EEG, SCR, genetic, human behavior

data.

• Apply SQL to analyze open-source game data to

figure out golden year of video games.

Work Experience

MRI data analyst 2018.05 – 2023.12

NIH/NCCIH Bethesda, MD, USA

• Apply machine learning models (linear regression, logistic regression, naïve bayes, KNN, SVM, random forest, graph neural networks), and data-driven

method ICA, PCA on SCR data, fMRI human brain

neuroimaging data, and other open-source datasets.

• Apply linear mixed model to analyze human behavior data.

• Coding skills: python, R, Matlab. bash, tcsh.

Research Scientist 2014.01 – 2018.05

Postdoctoral fellow 2009.09 – 2014.01

Medical Image Analysis Lab,

The Mind Research Network Albuquerque, NM, USA

• Develop new pipelines of data processing by

combining graph theory-based analysis and data-

driven method ICA, PCA, clustering to analyze fMRI human brain neuroimaging data, EEG data, genetic

data.

• Coding skills: Matlab, R, Python

PhD 2003.09 - 2009.01

Institute of neuroinformatics, Dalian University of Technology Dalian, China

• Apply linear regression, statistical methods to fMRI brain imaging data, EEG data, human behavior data.

• Coding skills: Matlab, VB.net, ASP.net, SQL server, C, HTML, javascript.

Education

Dalian University of Technology Dalian, China

Bachelor of Physics 2003.07

Institute of neuroinformatics, Dalian University of Technology Dalian, China

Ph.D. of Biomedical Engineering: Neuroinformatics

2009.01

Contact this candidate