Sen (Forrest) Yang

I am a Ph.D. candidate in Electrical and Computer Engineering at Rutgers University under the supervision of Professor Ivan Marsic. Before joining Rutgers, I worked for Huawei Technologies Co. Ltd. and obtained my B.A. degree in Communication Engineering at Nanjing University of Posts and Telecommunication.

My research interests lie at Data Mining, Machine Learning, Deep Learning, Process Mining, and Software Engineering in Data Visual Analytics.

My expected graduation time is October 2018. I am actively seeking full-time positions as machine learning scientist or data scientist. Feel free to contact me if you have related positions opening.

Contact:   forrest DOT yang AT rutgers.edu  |  Resume |  Google Scholar |  Linkedin

 

News


Dec 01, 18 I joined LinkedIn AI, working in the Data Standardization and Knowledge Graph team
Apr 30, 18 Two papers accepted by ICHI 2018
Apr 24, 18 One paper submitted to JBI
Apr 12, 18 One paper submitted to ECML-PKDD 2018
Apr 12, 18 One paper accepted by ICCDA 2018
Oct 01, 17 One paper accepted by ICDM 2017 Workshop DMBIH 2017
Aug 23, 17 I will present my work @ ICHI 2017
Aug 13, 17 I will present my work "A Data-Driven Process Recommender Framework" @ KDD 2017
Aug 01, 17 Presented my summer internship research to Marcus Weldon, the president of Bell Labs and CTO of Nokia.
Jul 21, 17 Short paper accepted by IEEE Intelligent Informatics Bulletin
Jul 13, 17 Received $1000 travel award from KDD 2017
Jul 11, 17 Received $750 travel award from ICHI 2017 Conference
Jun 26, 17 Two papers accepted by ICHI 2017 Conference

 

Research

 

Smart Trauma Resuscitation Decision Support System (funded by NIH)
I am currently working on a NIH project to build a Decision Support System for Smart Trauma Resuscitation Room using data mining, machine learning and process mining techniques. During trauma resuscitation, multidisciplinary teams rapidly identify and treat potentially life threatening injuries, then develop and execute a short-term management plan for the identified injuries. To improve medical team performance and reduce the adverse outcomes on the patients, we are developing a computerized decision support system for trauma resuscitations and other fast-paced, high-risk critical care settings. The system monitors workflow and alerts users of errors, allowing remedial actions to be taken to prevent adverse outcomes.

 

Process Mining
Process mining aims to discover, monitor and improve real world processes by extracting knowledge from activity logs. There are three main problems in process mining, process discovery, conformance checking and model enhancement. Process discovery takes activity logs as input and produce data-driven graphical models. Conformance checking tries to align the activity logs with process models to highlight the differences and commonalities. Model enhancement repairs the process model with activity logs. My research focus on developing new techniques and algorithms to address the above problems. In addition, I explored a new research direction, the process recommender system (PRS). PRS aims to provide people with real-time step-by-step recommendations on real world processes.

 

Data Visualization (spcial focus on Processes Logs)
Limited amount of applications or packages are available for process logs (or called temporal event sequences). The existing data visual analytics tools also have difficulties in visualizing big process data. My goal to provide user-friendly, easy-interpretable and machine learning based visual interactive tools for process anlysis. Working together with the students I supervised, we have developed two applications, VIT-PLA 1.0 and VIT-PLA 2.0. VIT-PLA stands for Visual Interactive Tool for Process Log Analysis. The 1.0 version is a Java-based application (Java, JavaSwing). The 2.0 version is web-based application (JSP, D3.js).

 

Big Data Analytics
Big data analytics is important and promising. With the support of Hadoop (distributed storage/computing) and cloud computering, we are able to uncover insights from extremely large amount of data. However, deep learning techniques have so far been very limitedly used in most big data problems. The main challenge lies at how to formalize of real worl data into a structured format that fits with deep learning frameworks. Therefore, my research in big data analytics focus on applying deep learning techniques on existing data mining problems. My data source mainly comes from public data challenges.

 

Automated Feature Extraction from Time Series: Deep Learning Approach
As my research topic in Bell Labs, I am pursuing deep learning techniques for automated feature extraction from time series. Traditional time series feature learning relies hand-designed features, e.g., peaks, trend, max, FFT, CWT, ARIMA. Selection of these features need human intuition and domian knowledge. Such feature leaning process is labor intensive and biased to human expectations. We are develop deep learning techniques to learn deep time series features automatically.

 

Publications

Conference Papers

 

Medical Workflow Modeling Using Alignment-Guided State-Splitting HMM

Sen Yang, Moliang Zhou, Shuhong Chen, Xin Dong, Omar Ahmed, Randall S. Burd, Ivan Marsic
IEEE International Conference on Healthcare Informatics (ICHI), 2017

 

Evaluation of Trace Alignment Quality and its Application in Medical Process Mining

Moliang Zhou, Sen Yang, Xinyu Li, Shuyu Lv, Shuhong Chen, Ivan Marsic, Richard A. Farneth, Randall S. Burd
IEEE International Conference on Healthcare Informatics (ICHI), 2017

 

A Data-driven Process Recommender Framework

Sen Yang, Xin Dong, Leilei Sun, Yichen Zhou, Richard A. Farneth, Hui Xiong, Randall S. Burd, Ivan Marsic
Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2017
Paper  |  Promotion Video

 

Duration-Aware Alignment of Process Traces

Sen Yang, Moliang Zhou, Rachel Webman, JaeWon Yang, Aleksandra Sarcevic, Ivan Marsic and Randall S. Burd
16th Industrial Conference on Data Mining ICDM 2016, Mar 2016
Paper | Slides

 

VITPLA: Visual Interactive Tool on Process Log Analysis

Sen Yang, Xin Dong, Moliang Zhou, Rachel Webman, JaeWon Yang, Aleksandra Sarcevic, Ivan Marsic and Randall S. Burd
KDD 2016 Workshop on Interactive Data Exploration and Analytics (IDEA)
Paper | Poster

 

Posters

 

Semi-synthetic Trauma Resuscitation Process Data Generator

Sen Yang, YiChen Zhou, Yifeng Guo, Richard A. Farneth, Ivan Marsic, Burd S. Randall
IEEE international Conference on Healthcare Informatics 2017

 

Coding Error Detection for Manually-coded Activity Logs: Case Study with Endotracheal Intubation

Sen Yang, Yichen Zhou, Shuhong Chen, Alexis Sandler, Ivan Marsic and Randall S. Burd
2016 MidAtlantic Bioinformatics Conference
Poster

 

Automatic Workflow Capture and Analysis for Improving Trauma Resuscitation Outcomes

Sen Yang
IEEE international Conference on Healthcare Informatics 2016
Abstract | Poster

 

Working Experience

Summer 2017 Nokia Bell Labs, Murray Hill, NJ
  Data Scientist Intern, Internet of things (IoT), with Dr.Jin Cao
Aug 2014 - Now Children's National Medical Center, Washington, D.C.
  Data Scientist, Medical Process Analysis, with Dr. Randall S. Burd
Aug 2014 - Now Rutgers Univerisity, New Brunswick, NJ
  Research Assistant, with Dr. Ivan Marsic
Sep 2012 - Jun 2012 Huawei Technologies Co. Ltd, Shenzhen, China
  Software Engineer in GSM, LTE Network Maintenance
Aug 2011 - May 2012 Nanjing University of Posts and Telecommunications, Nanjing, China
  Research Assitant, Peter Grünberg Research Center, with Dr.Jinyong Wang
Summer 2011 China Telecom, Xuzhou, China
  Network Engineer Intern

 

 

Academic Services

Lectures and Talks

 Software Engineering (Undergraduate 14:332:452) @ Rutgers, 2017
 Tutorial of Deep Learning @ Bell Labs, 2017
 Invited (4 out of 32 interns) to present my summer internship research "Automated Feature Learning from Time Series: The Deep Learning Approach" to Marcus Weldon, president of Bell Labs and CTO of Nokia @ Bell Labs, 2017

Student Volunteer and Travel Awards

 @ KDD 2017 (with $1000 Travel Award)
 @ ICHI 2017 (with $750 Travel Award)
 @ ICHI 2016 (with $1000 Travel Award)
 Received $100 Travel Award from Rutgers Engineering School

Students Supervised

2017
Chenghe (MS, Stat @ Rutgers)
Shiyue (MS, ECE @ Rutgers)
Jingyuan (MS, ECE @ Rutgers)
Vancha (BA, ECE @ Rutgers)
Yifeng (MS, ECE @ Rutgers)
Weiqing (MS, ECE @ Rutgers)
Qiyan (MS, ECE @ Rutgers)
Yanhao (MS, CS @ Rutgers)
Dawei (MS, ECE @ Rutgers)
Xiaoyi (MS, ECE @ Rutgers)
Ayush (BA, CS @ Rutgers)
2016
Xin (PhD, CS @ Rutgers)
Shuyu (SDE @ Amazon)
Yichen (SDE @ Amazon)
Shun @ Orchestrade
Shubhank (Master Thesis)
Haiyue
2015
Gang (SDE @ Microsoft)
Mehul (Analyst @ Goldman Sachs)
Lingnan (SDE @ Amazon)
Jingsong (SDE @ Amazon)
Aditya (Hitachi Data Systems)
Shuhong (BA, CS @ Rutgers)
2014
Moliang (PhD, ECE @ Rutgers)
Junwei (SDE @ Amazon)
Bowen (SDE @ ALK)

 

 

Advisor


Ivan Marsic

 

 

Other


Life is short. Follow your heart.