Wenzhao Xu (许文肇)

About Me

Hey, Welcome to my page. I am Wenzhao Xu, you can call me Wenzhao (although I usually leave Wen as my name :) ). Currently, I am an Machine Learning Engineer in Mobiuspace, Shenzhen, focusing on Ads area. I use Python, Scala, Spark, and Tensorflow to build machine learning models and write some Java code to deploy models. Other tools/languages I have used are R, C++ and D3. Before joining Amazon, I was an Applied Scientist in Amazon and a Data Scientist in Indeed. I also interned at Dow AgroSciences at UIUC Research Park and Bosch Research and Technology Center

I got my Ph.D. in Environmental Engineering at the University of Illinois at Urbana-Champaign (UIUC) in 2017. My thesis (Understanding Great Lakes Monitoring Data for Decision Support: Sensor Data Analysis on River Plumes, Deep Chlorophyll Layers and Hypoxiafocus ) focus on data mining and geostatistics to analyze spatial or spatio-temporal sensor data for the environmental system. I got my M.S of Hydraulic Engineering in 2012, thesis focus on reservior multi-stage optimization algorithms.

See more information on my LinkedIn

Projects

Thesis

Geostatistical analysis on river plume in Lake Michigan with Towed Undulating Vehicle Data Analyzing Tools (github) (R, RShiny, Paper )

Thermocline and DCL automated identification in Great Lakes from Seabird CTD sensor data (github) (Python, Flask) Paper )

Spatio-temporal interpolation, outlier detection and visualization of hypoxia in Lake Erie from DO loggers (github) (R, RShiny, Paper submitted)

Adaptive Reservoir Operation Model Incorporating Nonstationary Inflow Prediction (Paper)

Class Assignments & Projects

Data Analysis/Data Visualization

Statistical learning: regression/classifier (gist)
Embeded space and attractor in non-linear time series analysis of water quality data (R)
Kaggle sensor data classification (Description , Repo)
Kaggle cooking recipt text classification (Description , gist)
Dissolved oxygen sensor data spatial and temporal visualization (D3, ThreeJS)
Classification on Peaking Opera and pop music (matlab,R) (gist)

Optimization, Numerical Analysis and Parallel Programming

CS450 Course Homework and Project (Python) (Description)
Parallel Programming (C) (Desription)

Artifical Intelligence (C++)

Maze Search (Description) (Repo)
Game (Description) (Repo)
Naive Bayesian Classifier (Description) (Repo)
Reinforcement Learning (Description) (Repo)

Other

Simulation of a Wireless Parking Lot Based on nesC and TOSSIM (Repo)
Identification of Greenness on Navigation Routes based on Google Street View (Python, Matlab, R) (gist)
Database/SQL (SQL/Python/PHP/Html) (e.g. EISA website)