ECE/CS 498: Mobile Computing and Applications (Sp 2019)
Foundations, techniques, algorithms, and applications

mobile sensing
 Time and Location:
  M/W, 3-4:20pm @ ECE 2013
 Instructor:                 Romit Roy Choudhury
 Email:                        croy@illinois.edu
 Office hours:             After class

 Course TA:               Ashutosh Dhekne
                                    (dhekne2@illinois.edu)    
                                   
 TA hours:                  Wednesday 2pm-3pm (CSL 261)

 Prerequisites:            Linear Algebra, Probability
                                     Programming (Py or Matlab)

 Course Description:
 This course will teach a variety of ideas, concepts, techniques, and algorithms, that are all crucial to understanding and developing mobile systems and        applications.
The course will begin from first principles and ramp up to real-world systems and technologies. Keywords related to this course includes: GPS, drones, motion tracking, localization, data analytics, acoustics, IMU sensors, mobile security, privacy, data analytics, pattern matching, etc.

Course Topics:

0. Foundations:
    - We will start from absolute basics, and cover important modules from linear algebra, probability, and data/signal processing.
    - We will assume that you do not recall anything from prior courses (even if you have taken them).
    - The course is designed with both CS and ECE students in mind, particularly those inclined to software systems and algorithms.

1. GPS and Indoor Localization:
    - Understanding GPS, understanding why indoor positioning still not available ...
    - Location fingerprinting (WiFi, magnetic, BLE), crowd-sourcing, mapping.
    - Unsupervised data-driven learning, clustering, sensor fusion, filtering, simultaneous localization and mapping (SLAM).

2. Activity and Gesture Recognition (Humans and Objects):
    - Understanding IMU (accelerometer, gyroscope, compass)
    - Can a smartwatch track human gestures and activities? Can embedded IMUs track the motion of a fast-moving baseball?
    - Motion models and filtering techniques, introduction to Hidden Markov Models (HMM), Kalman Filters, Particle Filters.

3. Smart Homes and IoT:
    - Ambience sensing (WiFi and Alexa): Can users be tracked from WiFi reflections? Can Alexa learn human activities from everyday sound?
    - Wireless sensing techniques: presence detection, device-free tracking, FMCW, Doppler.
    - Acoustic analytics: Angle of Arrival (AoA), beamforming, blind estimation, mood and hierarchical context classification.

4. Wearable Computing:
    - Next generation of wearable devices: finger rings, ear-buds, smart clothing.
    - Rings: Vibration and ultrasound, receiving vibrations (with IMU and microphone), body-channels.
    - Hearables and earables: noise cancellation, bone conduction, motion to speech recovery, binaural sounds, energy optimization (wake-on-speech)

5. Autonomous Systems (Cars and Drones):
    - Core challenges in autonomous systems: sensing, computing, communications + actuation.
    - Robotic wireless networks, 5G networks, cell-tower on flying drones, ray-tracing, channel optimization.
    - Cars: LIDAR, RADAR, and vision, sensor fusion, relative map creation.

6. Mobile Privacy and Security:
    - Why personal, always-ON devices are a major challenge in security and privacy
    - Side channel attacks, inference algorithms, hardware loopholes, sensor data leaks.
    - Case studies: location privacy, password typing, Alexa attacks, IMU fingerprints, acoustic drone attack, clock leaks, etc.



 Grading Information:

    - Homework (2):                          15%
    - Paper reviews (10):                   15%
    - 1 mid-term exam:                      25%
    - Final project (part 1 + 2):         15% + 30%

    Final project can be implemented on the the platform of your choice.
    You can focus on building a real system (on smartphones, smartwatches, drones, Echo, etc.) that has a practical and useful application ...
    or focus on developing a challenging algorithm (on MATLAB, Python, C++, etc.) without worrying about utility and practical considerations.



Course Calendar
(subject to change)
Lecture Content:
Material:
Deadlines and ToDo Items:
Introduction:
- Overview slides

Foundations:
- Linear algebra refresher
- Introduction to signal processing
- Probability refresher

- linAlg-notes1,   linAlg-notes2
-
FFT-foundations
- Probability-notes


- HW1 (math basics)
HW1 Due: Feb 18, 2019, 11:59pm
Submit PDF on compass2g
Mobile sensors:
- Overview of sensors on mobile devices

IMU Sensors Slides

Tutorial by Ashutosh Dhekne
GPS and Indoor Localization:
- GPS and differential GPS (review first 6 pages of SafetyNet)
- WiFi localization (RADAR), Ambience localization (SS)
- Unsupervised localization (UnLoc)
- Direction finding, beamforming, and angle of arrival (AoA)
- RF localization (ArrayTrack)

- GPS slides
- RADAR, SS slides
- UnLoc slides
- Beamforming notes, AoA+ notes
- ArrayTrack slides

- MP1 (Step Counter in Android) (released)
- Final Project Topics
- RADAR Paper review due (Friday, Feb 22, 2019 (11:59pm))
Motion Tracking:
- Foundations of 3D orientation
- Ball and player tracking for sports analytics
- Foundations of Bayesian inference and tracking (HMM, Viterbi, Kalman filters)
- Map matching (Zee), and Arm tracking (ArmTrak)

- Video on understanding IMU
- 3D orientation notes, slides
- iBall slides
- HMM notes, Viterbi notes
- Zee slides, ArmTrak slides

- HW2 (localization, motion tracking, orientation)

- iBall review due

Gesture Recognition:
- Time synchronization and ranging (2-way, 3-way), X-Correlation, Doppler, FMCW
- BeepBeep (designs ranging)
- AAMouse (uses Doppler)
- CAT (uses FMCW), WiTrack, FingerIO

- Time Sync notes
- Auto, cross correlation notes
- Doppler notes
- FMCW notes


- MP2 (Walking Trajectory in Android)
- BeepBeep review due
- AAMouse review due
Pattern Matching:
- Dynamic time warping (DTW), Remote control (uWave)
- Finger tracking (MoLe), Smart toys (Buzz)

- DTW slides, uWave slides
- MoLe slides, Buzz slides

-
- Final Project Part 1
Sensor Security and Privacy:
- Side channels, Non-linearity, Acoustic side channels (Backdoor)
- Vibraphone, Gyrophone, DroneCrash
- IMU fingerprinting, AccelPrint

- Non-linearity notes
- Vibra/Gyrophone slides
- Fingerprinting notes, Accel slides
 
-
-
-
Sensor Fusion:
- Practical AR (OverLay), Visual fingerprinting (InSight)
- 3D orientation from GPS signals (SafetyNet)

- OverLay slides, Insight slides
- SafetyNet (2) slides

-
-Final Project Due