Beiyu Lin

Ph.D. Student

Center for Advanced Studies in Adaptive Systems (CASAS) lab

School of Electrical Engineering and Computer Science

Washington State University

Contact: beiyu.lin@wsu.edu

Lab: EME206
         
____________________________________________________________________________________________________________________
       
 Education                    Vitae                        Research                         Publications                      Projects                   

____________________________________________________________________________________________________________________

News

04/05/2018: I got the travel grant to attend Google I/O 2018, May 8th - 10th, Mountain View, CA!
04/02/2018: I am selected to participate in the Elson S. Floyd College of Medicine 2018 Hackathon, April 13th - 15th, Spokane, WA!
02/21/2018: I passed the Ph.D. Qualifying Exam!
02/09/2018: Our poster abstract has been accepted for presentation at 2018 GPSA Research Exposition, March 30th!
10/06/2017: I got an intern offer from Honeywell for summer 2018 and accepted it!
08/17/2017: I got the travel grant to attend Google Summer of Code 2017 Mentor Summit, Oct. 13th - 14th, Sunnyvale, CA!
07/17/2017: I got EECS's Scholarship to atttend 2017 Grace Hopper Celebrating, Oct. 4th-6th, Orlando, FL!


Education

Ph.D. in Computer Science, Washington State University Jan. 2016-Present. GPA: 3.8 Advisor: Dr. Diane J. Cook

Research
I am a Ph.D. student and have been using data to understand the general principles underlying human behavior in smart environments. To do this, I have been applying big data and machine learning technologies to do data analysis by using Python and R with well-defined methods and algorithms, as well as exploring and developing new methods and algorithms.

One project I have been working on is granted by the Department of Energy and by the U.S. Environmental Protection Agency's Science to Achieve Results (STAR) program. Our research is about Integrated Measurements and Modeling Using US Smart Homes to Assess Climate Change and Human Behaviors Impact on Indoor Air Quality.

One project that I just finished is about Population Modeling. Our study identifies and models the patterns of human daily routines in 99 smart homes with diverse participants, and provides insights on behavior patterns and detection of deviations that indicate potential health problem. Not only can this lead to more effective medical interventions, but these findings may benefit other fields.

My current work is to extend modeling of human behavior patterns to Markov chains. We try to provide evidence to support or deny the postulate that human behavior in certain groups is random or Markovian.

My research interests include: human dynamics, smart home, machine learning, data mining, technology applications of healthcare, and compute science education.

2018 Publications
    • Yibo Huangfu, Nathan Lima, Patrick O'Keeffe, Beiyu Lin, Diane J. Cook, Von P. Walden, William M. Kirk, Shelley N. Pressley, Brian K. Lamb, Bertram T. Jobson. Indoor air toxic gases levels in a net-zero energy house under multiple ven-tilation system settings, has been accepted as a podium presentation at INDOOR AIR 2018, the 15th Conference of the International Society of Indoor Air Quality and Climate (ISIAQ).
    • Yibo Huangfu, Nathan Lima, Patrick O'Keeffe, Beiyu Lin, Diane J. Cook, Von P. Walden, William M. Kirk, Shelley N. Pressley, Brian K. Lamb, Bertram T. Jobson. The major role of temperature on indoor concentrations of air toxic VOCs in 9 houses based on in-situ high time resolution measurements, has been accepted as a podium presentation at INDOOR AIR 2018, the 15th Conference of the International Society of Indoor Air Quality and Climate (ISIAQ).
2017 Publications (Journal Articles)

Projects: Indoor Air Quality    Population Modeling
Indoor Air Quality
Part 1: data visualization and transformation: smarthome-based human behavior detection (click a graph to zoom in).
                   
Part 2: finding the relationship between human behavior and indoor air quality based on three regression analyses and we report correlation coefficients that are moderate or large (r >= 0.3).
                                                                                             Summarized results
                                                                              IAQ1
                                                                                              IAQ2  
Part 3: feature extraction based on three learning algorithms.
                                                                             Results for aggregated dataset
                                                                             Results for IAQ1
                                                                             Results for IAQ2


Population Modelling

Part 1: Data Collection and Processing (click a graph to zoom in)..
                              A list of 82 distributions that are used for the model fitting.
                A complete list of home descriptive parameters.

Part 2: outlier detection and model fitting
             Part 2.1: Modeling Fitting for the Personal Hygiene inter-event time based on all the smart home data.
             
                
               

             Part 2.2: outlier detection and model fitting for seven routine activities).
              ( seven activities of daily routine: Work, Sleep, Relax, Cook, Eat, Personal Hygiene, and Wash Dishes. )

Part 3: summarized results of modeling at population level and among subpopulations