Yubo Wang

Yubo Wang

Master of science student of the CISE department

University of Florida


I’m a master’s student at the University of Florida Computer & Information Science & Engineering Department. My intentional research interests include but are not limited to Machine Learning, Artificial Intelligence, and Data Mining. My hobbies include car racing and traveling. I’m also a fan of the LA Lakers and LeBron James, and my favorite F1 racer is Sebastian Vettel.

I’m currently seeking a Ph.D. position in 2021 Fall!


  • Machine Learning
  • Artificial Intelligence
  • Data Mining


  • MSc in Computer Science, 2019-Now

    University of Florida

  • BSc in Computer Science, 2015-2019

    Jilin University






Scientific Research Experiences


The Integrated Computing and Intelligent Construction Lab, University of Florida

Jul 2020 – Present Gainesville, USA

Advisior: Dr. Eric Jing Du

Experiences include:

  • Using the human body time series data to find the cognitive latency between human gaze and hand movement

Health Information Lab, Jilin University

Aug 2017 – Jun 2019 Jilin, China

Advisior: Dr. Fengfeng Zhou

Experiences include:

  • Developed efficient feature selection and prediction algorithms for the high-dimensional biomedical data
  • Analyzed biological OMIC data, clinical blood test, biomedical imaging data, physiological data.

Academic Activities

CIS Online Research Program In Big Data Algorithm

  • Advisor: Dr. David P. Woodruff
  • Course name: Algorithms for Big Data
  • Used the HyperFAS Liveness detection algorithm based on MobileNetV3, combined with PULSE algorithm, to improve the generation accuracy and success rate of pulse algorithm.
  • Article: Improved PULSE: (Photo Up sampling via Latent Space Exploration of Generative Models) Using Anti-spoofing System, took advantage of Latent Space Exploration from PULSE and a facial liveliness detection algorithm to receive a more accurate and rational outcome.

Summer 2018 Deep Learning Workshop at the University of Florida

  • Project: Establish and train an NN model using TensorFlow on the Fashion-MNIST dataset.
  • Obtained Team Leadership Award.

Jilin University College Student Innovation and Entrepreneurship Training Project

  • Served as group leader to organize the division of labor and work docking.
  • Used machine learning (LightGBM model) to deal with traffic volume prediction on busy road junctions.

National College Students Mathematics Modeling Contest

  • Used k-means clustering algorithm and logistic regression algorithm, established cluster analysis model of task area distribution and multiple linear regression models and task completion Logistic model by using Python and Google Earth.
  • Awarded First Prize in Jilin division.

Honors & Awards

School-level First Class Academic Scholarship

Team Leadership Award in the 2018 Summer Deep Learning Workshop at the University of Florida

School-level Individual Scholarship

University Excellent Student Leader

School-level Third Class Academic Scholarship


Human Intent Prediction in Human-Robot Collaboration – A Pipe Maintenance Example

Abstract: Human-robot collaboration has gained its popularity in various civil engineering applications. The key to a successful human-robot collaboration is the design of an intelligent robot system that is aware of human intents and can predict human motions. Despite the advances in human intent prediction in the context of human-robot collaboration, challenges still present. Most intelligent systems can only predict human motions based on the repetitive patterns of human behaviors in well-defined tasks, for a relatively short period of time. A method that is capable of capturing the changing characteristics of human motions and predict human motions in dynamic and open workplaces is needed. This paper proposes an innovative analytical method that predicts human motions using the Long Short-Term Memory (LSTM) with incremental learning. A virtual reality based human subject experiment (n=120) was performed to collect the gaze tracking data and the corresponding two-hands motion data in a pipe maintenance task. First, the relationship between the gaze focus and the hand motion is explored via the symbolic aggregate approximation (SAX) to identify the latency between a person’s gaze focus direction and the hand motions. Then the continuous time series data of gaze focus is used to predict the motions of two hands, with eye-hand delays adjustments incorporated. The proposed method can significantly improve the accuracy of human motion prediction in a complex pipe maintenance task, and thus benefit a better design of collaborative robotic systems.