Xiaoyu Zhang
ESR-11
Topic:
Big Sensing intelligent warehouse for translation and clinical diagnosis study
Supervisor:
Prof Yi-Ke Guo, Imperial College London, United Kingdom
Xiaoyu Zhang received the Master’s degree in computer science from National University of Defense Technology (NUDT) in 2017 and the Bachelor degree in computer science from the same university in 2015. He also has completed a research internship on machine learning and mategenomics at BGI China in 2017 and a Mitacs Globalink Research Internship at University of Victoria (Canada) in 2014. He was selected to the Beijing Young Future Scientists Cultivation Program and attened a research project at Tsinghua University (China) from 2009 to 2010. He gained the Finalist Awards of 2017 IEEE International Scalable Computing Challenge (SCALE 2017). He has published 6 papers in BIBM, CCgrid, BMC Bioinformatics and ACM/IEEE Transactions. His current research interests include data science, high-performance computing and bioinformatics.
The objective of this ESR project is to develop Big Sensing intelligent warehouse for translation and clinical diagnosis study. This new data warehouse are designed with to handle the variety across subjects and provides better support for the processing, enable each subject to have measurement of arbitrary types of sensors with variable datatypes and support more flexible sensing analysis pipeline. Technically, the new database will be based on the No SQL database technology to handle variable data with an interface for high performance computing enable to process all the data in real-time. Machine Learning (ML) and Deep Learning (DL) based system to autonomous charting the genomic-sensing pathway, i.e. advance machine learning approaches will be diploid to extract the relationship between gene, omics and sensing, and therefore automatically build the pathway from gene and discovery the hiding medicine knowledge or hypothesis for future neurology research. By applying innovative ML & DL algorithms, an optimal Bayesian mixture prediction model and intelligent information management system will be developed.