CS/ECE 434: Mobile Computing and Applications

flier

 Location:
                   ECE 2015
 Instructor URL:       Romit Roy Choudhury
 Email:                        croy@illinois.edu
 Office hours:             After class

 Course TA:               Zhijian Yang
                                    zhijian7@illinois.edu    
                                   
 TA hours:                  Thu, 10:30am, CSL 241

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

Course Topics:
 
Math Foundations (from scratch)

      Linear Algebra, Data/Signal Processing, Probability and Learning

GPS, WiFi, Sensor Fusion

      Algorithms: Triangulation, Trilateration, Clustering, SLAM, Kalman filter

       Applications: Outdoor and indoor localization, mapping, IoT

IMU Sensors, Motion Tracking

      Algorithms: Dead reckoning, PCA, Hidden Markov Models (HMM), Kalman Filters

      Applications: Activity tracking, Gesture recognition, Sports analytics, wearable computing

Microphone, Speakers

      Algorithms: SVD, Noise Cancellation, Dynamic Time Warping, 3D Binaural Sounds

      Applications: Acoustic Sensing, Voice Assistants, Earphone computing

Camera, Light

      Algorithms: SIFT/SURF, Wavelets, 3D Point clouds, Structure from motion (SfM)

      Applications: Augmented reality, Visual Communication, Shadow sensing

Wireless Radios (WiFi, BLE, 5G)

      Algorithms: Beamforming, Time of Flight (ToF), Clock synchronization, FMCW, Doppler

      Applications: Presence detection, Liquid identification, Bio-monitoring, Digital agriculture

Mobile Sensing, Spatial Diversity

      Algorithms: Synthetic aperture, RF imaging, Particle filter

      Applications: Drones, Autonomous vehicles

Security and Privacy

      Algorithms: Classification, Non-linearity, Viterbi decoding, MLE, Stochastic gradient descent

      Applications: Fingerprinting, side channel, inference

Emerging areas: Edge computing, battery-free devices, Earable computing,

   Grading Information:
    - Homework, Assignmeents:       20%
    - Paper reviews (~10):                 15%
    - 1 mid-term exam (Apr. 8th):     25%
    - Final project:                             40% (you can use platform of your choice, e.g., MATLAB, Python, Java, Android, etc.)
    - Project report (5+ pgs):             Only for 4 credit students

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)
Mobile sensors:
- Overview of sensors on mobile devices

IMU Sensors Slides
MP1
GPS and WiFi based Localization (outdoor and indoor):
- GPS basics, trilateration, acquisition, correlation, time offsets
  (read Section 1 and 2 of CO-GPS, skim SafetyNet)

- WiFi trilateration (RADAR), fingerprinting
- Sensor fusion: ambience sensing (SS), Unsupervised loc. (UnLoc)

- Direction finding, beamforming, and angle of arrival (AoA)
- RF triangulation (ArrayTrack)
- In-body localization (ReMix)

- Linearize video and SafetyNet slides


- RADAR, SS slides
- UnLoc slides
- Beamforming notes, AoA+ notes
- Delay and Sum AoA algorithm
- Classical AoA algorithms (see Sec. 3)
- ArrayTrack slides, [ReMix slides]

Reviews: CO-GPS and UnLoc
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)

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

Microphone and Speakers:
- Gradient decent, Filtering, Active Noise Cancellation (MUTE)
- Multipath beamforming, voice localization (VoLoc)
- Binaural Head Related Transfer Functions (HRTF), Acoustic AR
- Earphone computing, DTW algorithm, IMU-based speech recognition




- DTW slides

Security and Privacy:
- Non-linear frequency synthesis, Inaudible voice attacks (BackDoor, LipRead)
- Accelerometer fingerprinting (CCS paper)
- Ear-canal authentication (Paper from NEC)
- Side channel sensing (MoLe, Vibraphone, Gyrophone)

- Backdoor slides


- MoLe slides, Vibra, Gyrophone slides

Camera and Light:
- Visual fingerprinting and sensor fusion (Insight, OverLay)


- OverLay slides, Insight slides


FINAL EXAM: Project demos