About the Course
Do you want to learn about cool emerging technologies like using smartphones to diagnose diseases and health disorders? Do you want to explore novel interfaces that will redefine the future of virtual reality systems? Everyday, we are awash in wireless signals that are used for communication, but did you know that we can also leverage these signals for many other applications. Our smartphones today are full of highly capable sensors that we can use to do everything from healthcare monitoring to motion tracking. Our class explores the unconventional approaches that allow ubiquitous sensors and signals to solve real world problems. You will gain hands on experience applying signal processing and machine learning algorithms to tackle issues that affect millions of people. Students from all areas of computer science and engineering are welcome, there are no prerequisites.
Important Dates
Schedule
Date |
Material |
Sept 26 |
Introduction and History of Mobile Systems
The Computer for the 21st Century (Scientific American 1991)
What next, Ubicomp? Celebrating an intellectual disappearing act (UbiComp 2012)
Charting Past, Present, and Future Research in Ubiquitous Computing (Transactions on Computer-Human Interaction 2000)
Slides: Ubiquitous computing, historical context, present and future
|
Sept 28 |
Sensing Systems and Signal Processing
Making Sense of Sensing Systems: Five Questions for Designers and Researchers (CHI 2002)
OmniTouch: Wearable Multitouch Interaction Everywhere (UIST 2011)
ViBand: High-Fidelity Bio-Acoustic Sensing Using Commodity Smartwatch Accelerometers (UIST 2016)
Slides: Fast fourier transform, Resonance, Nyquist theorem, Modulation techniques, Packetization (error detection/correction), Cross-correlation
|
Oct 3 |
Wireless Sensing
Whole-home gesture recognition using wireless signals (MobiCom '13)
FingerIO : Using Sonar for Fine-Grained Finger Tracking (CHI '16)
Soli: ubiquitous gesture sensing with millimeter wave radar (SIGGRAPH '16)
Slides: OFDM, Doppler effect
|
Oct 5 |
Through-body interaction
Enabling On-Body Transmissions with Commodity Devices (UbiComp '16)
Skintrack: Using The Body As An Electrical Waveguide For Finger Tracking On The Skin (CHI '16)
Slides: IMU usage on phone, smoothing, zero-crossing, machine learning basics, capacitive and galvanic coupling
|
Oct 10 |
Activity Recognition
A long term evaluation of sensing modalities for activity recognition (UbiComp '07)
Inferring activities from interaction with objects (Pervasive Computing '04) (Optional)
Slides: Sensors, decision trees, cross-validation, ROC curves
|
Oct 12 |
Fabrication
3D Printing Wireless Connected Objects (SIGGRAPH Asia '17)
Wireless Analytics for 3D Printed Objects (UIST '18) (Optional)
Design and Fabrication by Example (SIGGRAPH '14)
Slides: 3D printing, antenna design, backscatter, constraint optimization
|
Oct 17 |
Localization 1
RADAR: An in-building RF-based User location and tracking system (INFOCOM '00)
ZEE: Zero effort crowdsourcing for indoor localization (MobiCom '12)
|
Oct 19 |
Class cancelled
|
Oct 24 |
Localization 2
Lend me your arms: The use and implications of humancentric RFID (Elsevier '06)
Slides: RSSI based localization, Time of arrival estimation, angle of arrival esetimation
|
Oct 26 |
Mobile health 1
Smart Homes that Monitor Breathing and Heart Rate (CHI '15)
Contactless Sleep Apnea Detection on Smartphones (MobiSys '15)
|
Oct 31 |
Mobile health 2
Guest lecture: Alex Mariakakis
BiliScreen: Smartphone-Based Scleral Jaundice Monitoring for Liver and Pancreatic Disorders (IMWUT '17)
HemaApp: Noninvasive Blood Screening for Hemoglobin using Smartphone Cameras (UbiComp'15)
|
Nov 2 |
Self Driving Cars
Guest lecture: Patrick Lancaster
Autonomous Driving in Urban Environments: Boss and the Urban Challenge (JFR '08)
|
Nov 7 |
Low-power systems
Guest lecture: Vamsi Talla
Ambient Backscatter: Wireless Communication Out of Thin Air (SIGCOMM '13)
Optional: Powering the Next Billion Devices with Wi-Fi (CoNext '15)
Slides
|
Nov 9 |
Smart homes 1
Surface MIMO: Using Conductive Surfaces For MIMO Between Small Devices (MobiCom '18)
Data Storage and Interaction using Magnetized Fabric (UIST '18)
Slides 1, Slides 2
|
Nov 14 |
Smart homes 2
Wall++: Room-Scale Interactive and Context-Aware Sensing (CHI '18)
Quasistatic Cavity Resonance for Ubiquitous Wireless Power Transfer (PLOS One '17)
|
Nov 16 |
Discuss class projects
|
Nov 21 |
Class cancelled
|
Nov 23 |
No class. University holiday. |
Nov 28 |
Deep learning
Slides: Image classification, Convolutional neural networks, Transfer learning, Keras
|
Nov 30 |
Security and privacy
Slides
|
Dec 5 |
Bio computing
Guest lecture: Vikram Iyer
|
Dec 7 |
Commercializing your research
|
Grading and Evaluation
Your grade will be based on 3 homework assignments, summaries of class readings and a final project.
Homework
COLLABORATION POLICY: Homework must be done individually: each student must hand in their own answers. In addition, each student must write and submit their own code in the programming part of the assignment (we may run your code). It is acceptable, however, for students to collaborate in figuring out answers and helping each other solve the problems. You must also indicate on each homework with whom you collaborated.
RE-GRADING POLICY: All grading related requests must be submitted to the TA via email only. Office hours and in person discussions are limited solely to asking knowledge related questions, not grade related questions. If you feel that we have made an error in grading your homework, please let us know with a written explanation, and we will consider the request. Please note that regrading of a homework may cause your grade to go up or down on the entire homework set.
LATE POLICY: Homeworks must be submitted by the posted due date. There is no credit for late work. The homework scoring system of above is an attempt to minimize the harshness of this policy.
NO EXCEPTIONS WILL BE GIVEN TO THE GRADING POLICIES (unless based on university policies, e.g. medical reasons). IF YOU ARE NOT ABLE TO COMPLY WITH THE LATE HOMEWORK POLICY, DUE TO TRAVEL, CONFERENCES, OTHER DEADLINES, OR ANY OTHER REASON, DO NOT ENROLL IN THE COURSE.
HONOR CODE: As we sometimes reuse problem set questions from previous years, covered by papers and webpages, we expect the students not to copy, refer to, or look at the solutions in preparing their answers (referring to unauthorized material is considered a violation of the honor code). Similarly, we expect students not to google directly for answers. The homework is to help you think about the material, and we expect you to make an honest effort to solve the problems. If you do happen to use other material, it must be acknowledged clearly with a citation on the submitted solution. For more information, please see the CSE Academic Misconduct policy that this course adheres to.
Project
You will work independently or with a partner on a mobile systems project spanning most of the quarter ending with a poster presentation and written report. The project should address a novel question. The components of the project are
- Project Proposal (15 points): A one page maximum description of your project with: 1) project title, 2) Project idea (two paragraphs), 3) Software/hardware you will write/make and/or use, 4) papers to read (include 1-3 relevant papers), 5) will you have a teammate?, and 6) what will you complete by the milestone (experimental results are expected)?
- Poster presentation (20 points): We will hold a poster session in the Atrium of the Paul Allen Center. Each team will be given a stand to present a poster summarizing the project motivation, methodology, and results. The poster session will give you a chance to show off the hard work you put into your project, and to learn about the projects of your peers. Both one large poster or several pinned pages are OK (fonts should be easily readable from 5 feet away).
- Project Report (65 points): Your write up should be 8 pages maximum. You should describe the task you solved, your approach, the algorithms, the results, and the conclusions of your analysis. Note that, as with any conference, the page limits are strict! Papers over the limit will not be considered.
Readings
Your participation in the forum discussion for each day will be graded on a scale from 0 to 3.
- 0: If you do not participate.
- 1: If your participation seems weak and does not convince us you read, understood, and considered the readings.
- 2: If your participation shows you read and understood the readings and had something interesting to say. This will be the most common grade.
- 3: Reserved for especially insightful participation.
It is generally easy to find something to criticize in any piece of research. But focusing exclusively on the potential flaws of research is generally not productive. You will generally find it more intellectually worthwhile to focus on aspects of work that are particularly well done, new ideas are prompted by a piece of work, or what you might have done differently if you conducted the research. This will also lead to much more valuable discussions.
Potential topics for discussion are:
- What idea or innovation enabled this, what more might be done based on that idea or innovation?
- What new questions or research agendas are suggested by this research?
- How might this research have informed some other research you have seen?
- What aspects of this work were particularly well done or effective?
- If you had conducted this research, what would you have done differently?