Chen Qiu                           


Phd candidate, Computer Science and Engineering
Michigan State University
Contact: qiuchen1@cse.msu.edu, Resume

         
                                                                  

 

About Me

 

Chen Qiu is a Ph.D candidate in Computer Science & Engineering Dept. of Michigan State University. He concentrates on mobile computing and is advised by Professor and Chair Dr. Matt W. Mutka. He works in eLANS Lab. He received his M.Sc. in Computer Science and his B.Sc. in Software Engineering from Xi'an Jiaotong University, China.


Research Highlights

Chen's Ph.D. study focuses on mobile computing and pervasive computing, and he has R&D experience on the following topics: 1) indoor location-based services using mobile APP, 2) indoor floorplan construction via mobile sensing, 3) data mining and machine learning on mobile and social networks, and 4) algorithm design and analysis.

1. Indoor Floor Plan Construction through Mobile Sensing

March 2015 - Present

Althoug individuals can determine their location outdoors on these maps via GPS, indoor mobile applications may also need to know the layout of rooms, doorways and hallways of buildings, however indoor maps of buildings are less prevalent. We design iFrame, a dynamic and light-weight approach that leverages existing mobile sensing capabilities for constructing indoor floor plans. We explore how iFrame users may collaborate and contribute to constructing 2-dimensional indoor maps by merely carrying smartphones or other mobile devices. The iFrame approach consists of four steps: 1) Abstract the unknown indoor map as a matrix; 2) Leverage collaborating mobile devices that incorporate three mobile sensing technologies (dead reckoning, Bluetooth and WiFi detections); 3) Combine the three methods by Curve Fit Fusion, and 4) Extend iFrame from one room to a whole building. We conducted a deployment study that shows iFrame is a light-weight and unattended approach that provides a dynamic skeleton map of a real building automatically. The layouts of 12 rooms are reconstructed within 5-10 minutes.

 

 

Selected Publications:

 

Chen Qiu; Matt W. Mutka. iFrame: Dynamic Indoor Map Construction through Automatic Mobile Sensing

IEEE International Conference on Pervasive Computing and Communications (PerCom), Sydney, Australia, March. 2016.

(Acceptance Ratio: 11.9%)

 

Chen Qiu; Matt W. Mutka. iFrame: Dynamic Indoor Map Construction through Automatic Mobile Sensing

Pervasive and Mobile Computing, Elsevier, 2016 (In Press).

 

2. Walk and Learn: improve indoor localization by machine learning outdoor movements on smartphones

March 2015 - Present

By employing accelerometers on smartphones, dead reckoning is an intuitive and common approach to generate a user's indoor motion trace on smartphones. Nevertheless, dead reckoning often deviates from the ground truth due to noise in the sensing data. We propose iLoom, an indoor localization approach that benefits by transferring learning from tracking outdoor motions to the indoor environment. Via sensing data on a smartphone, iLoom constructs two datasets: relatively accurate outdoor motions from GPS and less accurate indoor motions from accelerometers. Then, iLoom leverages Acceleration Range Box to improve a user's acceleration value used for computing dead reckoning. After using a transfer learning algorithm to the two datasets, iLoom boosts the Acceleration Range Box to achieve better indoor localization results. Through case studies on 15 volunteers, iLoom achieved localization accuracy of 0.28-0.51m.

 

Selected Publications:

 

Chen Qiu; Matt W. Mutka. Self-Improve Indoor Localization by Profiling Outdoor Movement on Smartphones.

The 18th IEEE International Symposium on a World of Wireless, Mobile, and Multimedia Networks (WoWMoM), Macau, China, Jun. 2017.

(Newly Accepted)

 

3. Improve Indoor Localization Accuracy via Smartphone

March 2013 - Present

Accurate indoor location information remains a challenge without incorporating extensive fingerprinting approaches or sophisticated infrastructures within buildings. Nevertheless, modern smartphones are equipped with sensors and radios that can detect movement and can be used to predict location. Dead reckoning applications on a smartphone may attempt to track a person's movement or locate a person within an indoor environment. However, smartphone positioning applications continue to be inaccurate. We propose our approaches (CRISP and AirLoc) to improve smartphone positioning, which leverages opportunities of the interaction of multiple smartphones, communications between mobile robots and smartphones, and smartphone users' walking behaviors.

 

Selected Publications:

 

Chen Qiu; Matt W. Mutka. Silent Whistle: Effective Indoor Positioning with Assistance from Acoustic Sensing on Smartphones..

The 18th IEEE International Symposium on a World of Wireless, Mobile, and Multimedia Networks (WoWMoM), Macau, China, Jun. 2017.

(Newly Accepted)

Chen Qiu; Matt W. Mutka. AirLoc: Mobile Robots Assisted Indoor Localization.

The 12th IEEE International Conference on Mobile Ad-hoc and Sensor Systems (MASS), Dallas, TX, Oct. 2015.

(Acceptance Ratio: 26.5%)

 

Chen Qiu; Matt W. Mutka. Cooperation among Smartphones to Improve Indoor Position Information.

The 16th IEEE International Symposium on a World of Wireless, Mobile, and Multimedia Networks (WoWMoM), Boston, MA, Jun. 2015.

(Acceptance Ratio: 21.5%)

 

Chen Qiu; Matt W. Mutka. CRISP: Cooperation among Smartphones to Improve Indoor Position Information.

Wireless Networks, Springer, 2016.

 

 

4. Crowd Density Estimation using Wireless Sensor Networks

August 2010 - April 2012

Crowd density estimating is critical in many applications (e.g., smart guide, crowd control, etc.), which is often conducted using pattern recognition technologies based on video surveillance. However, these methods are high cost, and cannot work well in low-light environments. We introduce a low cost crowd density estimating method using RSS analysis in Wireless Sensor Networks. The proposed approach is a device-free crowd counting approach without objects carrying any assistive device. We utilize the space-time relativity of crowd distribution to reduce the estimation errors. Our mechanism contains three phases: the training phase, the monitoring phase, and the calibrating phase. Experiments are implemented on Telos sensors. We also do large-scale simulations to verify the effectiveness.

 

Selected Publications:

 

Yaoxuan Yuan; Jizhong Zhao, Chen Qiu; Wei Xi. Estimating Crowd Density in an RF-based Dynamic Environment.

IEEE Sensors Journal, Vol. 13, No. 10, Oct. 2013.

 

Yaoxuan Yuan; Chen Qiu; Wei Xi; Jizhong Zhao. Crowd Density Estimation Using WSN.

The 7th IEEE International Conference on Mobile Ad-hoc and Sensor Networks (MSN). Beijing, China, Dec. 2011.  


Work Experience

Research and Software Development Intern at HP Labs

May 2016 - August 2016, HP inc., Palo Alto, CA

1) Design and implement an enterprise-level indoor localization algorithm for personal devices.
2) Develop corresponding indoor localization application on Android and Windows platforms.
3) Leverage Bluetooth Low Energy beacons and dead reckoning to compute real-time locations.
4) Leverage RabbitMQ and Amazon Web Services to store and analyze location data.

(Come on in, Loalization@HP! click for reading)

 

Reseach Assistant at MSU

August 2014 - present, Michigan State Univ., East Lansing, MI

1) R&D indoor localization solution using mobile applications.

2) R&D indoor floorplan construction by leveraging mobile sensing applications.

3) Data clustering and classification on mobile networks.

4) Algorithm design and analysis for mobile and sensor networks.

 

Teaching Assistant at MSU

August 2012 - present, Michigan State Univ., East Lansing, MI

CSE232    Programming II (C++)   Fall 12                     
CSE331    Data Structure and Algorithm   Spring 13                
CSE410    Operating System   Summer 13-15, Fall 16         
CSE335    Software Design (Objective-Oriented Programming and UML)   Fall 13                     
CSE476    Mobile App Development (Android)   Spring 14

Hold office hours, grade projects and exams, build course website, do lecture occasionally.


Courses

Advanced Computer Networks & Communication (CSE824)

Computer and Network Security (CSE825)

Design & Theory of Algorithms (CSE830)

Algorithmic Graph Theory (CSE835)

Data Mining (CSE881)


Professional Skills

Programming Language: Java, C/C#, Python, PHP, ASP, NesC, HTML

Web Development: J2EE, .Net

Mobile APP Development: Android

Data Management and Mining: MySQL, SQLserver,Weka, Matlab

Software Design: Rational Rose, ER win

Operating System: Linux, Windows, Android, TinyOS

Other: Amazon Web Services, Microsoft Office, Latex, SVN, Git

 

Experience in software development, mobile computing, big data analysis, and algorithm design.


Software

Bluetooth Crowd Sourcing Tool version 1.1

(Programed by Chen Qiu, can be installed on Android OS, click for downloading)