TY - GEN
T1 - Secure Privacy Preserving across Personal Health Data and Single Cell Genomics Research INSPIRE Academic Pedagogy - Merging Big Data Multiplatform with Deep Learning
AU - Yang, Mary Qu
AU - Yu, Shucheng
AU - Cruz-Neira, Carolina
AU - Yang, William
AU - Tudoreanu, M. Eduard
AU - Li, Dan
AU - Zhang, Yifan
AU - He, Qingfang
AU - Guan, Renchu
AU - Wang, Richard Y.
AU - Zhao, Wenbing
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2018/12/4
Y1 - 2018/12/4
N2 - Enhancing student academic performance and transdisciplinary ability is challenging, but the time and effort put into accomplishing this ambitious feat is priceless. We develop secure privacy preserving across Personal Health Data (PHD) repository and single-cell genomics research for building an Innovative Systematic Pedagogy for Integrated Research - Education (INSPIRE) (http://americancse.org/events/csce2017/csce17-awards). In this paper we further build a novel, eclectic, and insightful framework based on classical and popular machine learning approaches to help us meet the educational challenge. Our framework focuses on using integrative research technologies to help solve 'Education's Performance Prediction Data Mining Crisis' (EPPDMC), by putting to rest issues associated with mining and making best use of big data for educational enhancement, such as multi-source education acquisition, data fusion, and unstructured data analysis. We exploit the uses of deep learning, text classification, and semi-supervised learning approaches to solve challenging problems that educators face when analyzing multiplatform big data involved in education, research and training students. Based on new machine learning approached we developed for genomic big-data research and in combination with machine learning methods (http://americancse.org/events/csce2017/keynotes-lectures/yang-talk) and the vast availability of education data available to us, not only can we utilize structured, unstructured, and even multi-media data, but while engaging in leaning intelligent thinking along the way, we can also maximize the utilization of big data by studying the motion and performance of these data. Hence we build the INSPIRE model that can further incorporate Student Face Expression in Class (SFEiC) to help educators and managers make further improvements as they become involved in the teaching-learning process. This research further facilitates the effectiveness of the INSPIRE model.
AB - Enhancing student academic performance and transdisciplinary ability is challenging, but the time and effort put into accomplishing this ambitious feat is priceless. We develop secure privacy preserving across Personal Health Data (PHD) repository and single-cell genomics research for building an Innovative Systematic Pedagogy for Integrated Research - Education (INSPIRE) (http://americancse.org/events/csce2017/csce17-awards). In this paper we further build a novel, eclectic, and insightful framework based on classical and popular machine learning approaches to help us meet the educational challenge. Our framework focuses on using integrative research technologies to help solve 'Education's Performance Prediction Data Mining Crisis' (EPPDMC), by putting to rest issues associated with mining and making best use of big data for educational enhancement, such as multi-source education acquisition, data fusion, and unstructured data analysis. We exploit the uses of deep learning, text classification, and semi-supervised learning approaches to solve challenging problems that educators face when analyzing multiplatform big data involved in education, research and training students. Based on new machine learning approached we developed for genomic big-data research and in combination with machine learning methods (http://americancse.org/events/csce2017/keynotes-lectures/yang-talk) and the vast availability of education data available to us, not only can we utilize structured, unstructured, and even multi-media data, but while engaging in leaning intelligent thinking along the way, we can also maximize the utilization of big data by studying the motion and performance of these data. Hence we build the INSPIRE model that can further incorporate Student Face Expression in Class (SFEiC) to help educators and managers make further improvements as they become involved in the teaching-learning process. This research further facilitates the effectiveness of the INSPIRE model.
KW - Deep Learning
KW - Innovative Systematic Pedagogy for Integrated Research and Education (INSPIRE)
KW - Secure privacy preserving across Personal Health Data (PHD)
KW - Single-cell genomics
UR - http://www.scopus.com/inward/record.url?scp=85060587551&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85060587551&partnerID=8YFLogxK
U2 - 10.1109/CSCI.2017.219
DO - 10.1109/CSCI.2017.219
M3 - Conference contribution
AN - SCOPUS:85060587551
T3 - Proceedings - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017
SP - 1244
EP - 1251
BT - Proceedings - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017
A2 - Tinetti, Fernando G.
A2 - Tran, Quoc-Nam
A2 - Deligiannidis, Leonidas
A2 - Yang, Mary Qu
A2 - Yang, Mary Qu
A2 - Arabnia, Hamid R.
T2 - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017
Y2 - 14 December 2017 through 16 December 2017
ER -