I'm Ziyuan Shen. I am a master graduate from Duke University. I major in Electrical and Computer Engineering, with a course focus on software design, machine learning and data science. I worked at Duke Institute for Health Innovation as a data scientist intern.
My research interest lies in medical machine learning and precision medicine. My dream is to apply my technical skills to real applications and improve human beings' health conditions.
August 2018 - May 2020
Major: Electrical and Computing Engineering
Course Focus: Machine Learning and Data Science
Overall GPA: 3.97/4.0
Coursework:
September 2014 - June 2018
Major: Information Science and Engineering
Thesis: Synthesizing Bayesian System Using Chemical Reaction Networks
Overall GPA: 3.72/4.0
Coursework:
June 2012 - August 2012
Overall GPA: 3.85/4.0
Coursework:
Data Scientist Intern
Internship at DIHI to work with ongoing machine learning projects related to healthcare. I use data science technologies to manipulate large-scale hospital data, and develop predictive models for clinical use. Develop full-stack applications to monitor patients heart rate for clinical use.
Research Assistant
Conduct DNA computing research regarding DNN (Deep Neural Network), Markov chain computation and digital logic synthesis.
R, HTML, Shiny App Run App
R, HTML, GGplot, Javascript, Shiny App Run App
In this paper, it is presented a methodology for implementing arbitrarily constructed time-homogenous Markov chains with biochemical systems. Not only discrete but also continuous-time Markov chains are allowed to be computed.
In this paper, by revealing the common probability base, we aim to implement the most fundamental element of DNN, a neuron, using chemical reaction networks (CRNs).
This timely overview study introduces combinational logic synthesized in DNA computing from both analog and digital perspectives separately. State-of-the-art research progress is summarized for interested readers to quick understand DNA computing, initiate discussion on existing techniques and inspire innovation solutions.
It is common that probability theory and stochastic process, especially Markov chains, have long been used to study and explain the behaviors of chemical reaction networks (CRNs). Nonetheless, this paper sees things from a reverse angle, devoting itself in synthesizing common probability theory and stochastic process with CRNs. The main motivation is to imitate and explore the evolution of large-scale and complex practical systems based on CRNs, by making use of the inherent parallelism and randomness.
This design approach, which stores logic information in keysmith and releases it through key, primarily focuses on the underlying state transitions behind the required logic rather than the electronic circuit representation. Therefore, it can be uniformly and easily employed to implement any synchronous sequential logic with molecular reactions.
Here, a succinct and systematic approach based on reversible uni-molecular reactions is proposed for any time-homogeneous Markov chain, no matter it is discrete or continuous. For the chemical reaction networks (CRNs), molecular concentrations at time t reflect the probability distribution of the continuous-time Markov chain at time t. The final concentrations indicate the steady state of the Markov chain.
Considering the common knowledge that probability theory has long been used to explain stochastic behaviors of chemical reactions, this paper devotes itself to synthesizing probability theory based on molecular computation.