Download Resume

Hi I'm Mengxuan Ma

Data Scientist & Machine Learning Engineer

I'm a Ph.D. student in the Department of Electrical Engineering and Computer Science at University of Missouri - Columbia. I am working as a graduate research assistant at Center for Eldercare and Rehabilitation Technology, University of Missouri. I have research experience in Machine Learning, Artificial Intelligence, Human-Computer Interaction, Computer Vision. I'm looking for a data scientist position.

My Skills

Programming

Python (sklearn, pandas, numpy), SQL, C#, C/ C++, MATLAB, HTML, Verilog, VHDL, Assembly language

Python

90%

SQL

85%

C++/C

75%

C#

75%

Analysis Techniques

Classical & Penalized Regression Methods, Decision Tree, Support Vector Machine, Clustering Algorithms, Deep learning. A/B testing.

Caffe

60%

Tensorflow, Keras

65%

Pytorch

65%

Spark

65%

Education

2016-Present (Expected May 2020)

Doctoral Degree in Electrical & Computer Engineering
University of Missouri-Columbia

Overall GPA: 3.81/4

August 2013 - December 2015

Master of Science of Electrical Engineering
University of Missouri-Columbia

Overall GPA: 3.85/4

September 2009 - June 2013

Bachelor of Engineering
Beijing Jiaotong University, China

Overall GPA: 3.19/4

Work Experience

McNerney Management Group, Inc.

Web Application Development Internship: June - August 2018

  • ● Developed a customer relationship management web application that helps agents and staffs manage complex business database and information.
  • ● Designed and implemented a MySQL database to store the data of clients and employees with different roles.
  • ● Implemented the register and login panel, admin panel and to-do-list function in the web application.

Center for Eldercare and Rehabilitation Technology, College of Electrical Engineering and Computer Science

Graduate Research Assistant: August 2016 - Present

Lorem ipsum dolor sit amet, consectetur adipiscing elits, sed do mod, tempor ets incididunt ut labore et dolore magna aliqua. Ut enim adtiesm minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat.

Projects

Daily Activity Recognition and Assessment System for Stroke Rehabilitation

  • - Developed a daily activity logging system to record depth frames and skeletal joint data of a stroke patient.
  • - Investigated variety depth sensors to provide a more efficient and stable system including the Microsoft Kinect, a VicoVR sensor TVico sensor and a compact standalone system using the Orbbec sensor.
  • - Proposed a Convolutional-De-Convolutional Networks to recognize actions from the recorded depth videos.
  • - Tested the algorithm on real-life cooking videos in four different kitchen environments with ten participants. The action recognition accuracy for real-life continuous unsegmented videos was 87.5%.
  • - Performed quantitative assessments for each recognized action. The proposed reaching, speed, efficiency and smoothness metrics were employed to assess hand motions using the collected skeletal joint data.

Movie Recommendation System

  • - Implemented a movie recommendation system using Collaborative Filtering algorithms.
  • - To predict the ratings for movies accurately, two models were investigated. An Alternating Least Squares (ALS) model was implemented using Spark APIs and an autoencoder network was implemented on Tensorflow platform.
  • - Implemented models were evaluated using the MovieLens 1M dataset. 70% of the data were randomly selected for training and the rest of the data was used for testing. The mean square errors of ALS model and autoencoder network on test set were 0.877 and 0.989, respectively.

Long-term Kinect-based Stroke Rehabilitation Game Assessment

  • - Implemented a module to perform longitudinal motion assessments for a Kinect-based stroke rehabilitation game.
  • - Preprocessed the collected data by removing the duplicate samples, filling the missing samples and filtering the noise.
  • - Performed upper-body kinematic assessment using range of motion measures, efficiency and smoothness measures.
  • - Evaluated the structure of hand movement trajectories by applying a density-based algorithm, OPTICS.
  • - Performed the longitudinal assessments using polynomial regression for eight stroke patients to evaluate their recovery statuses.

Angel-Echo: A Personalized Health Care Application

  • - Designed a personal health monitoring system that allows a user to acquire health information with a speech interface.
  • - Developed a system that received health information (heart rate, steps and skin temperature) collected from the Angel Sensor via Bluetooth GATT Protocol, and then stored the data to the Amazon DynamoDB database.
  • - Designed a new Amazon Echo skill on Amazon Web Service (AWS) to handle users’ health-related requests, fetch the corresponding data from the database, organize the data to responses, and forward them to the Alexa Voice Service.
  • - Tested the Amazon Echo speech recognition accuracy on different populations. The voices from the younger subjects were more accurately recognized than the elderly subjects where the misunderstanding rate was 2.6% lower.