Courses

< Back to Courses

ECED 6530: Random Processes and Estimation Theory

About Course

Instructor: Dr. Christian Schlegel, FIEEE, Professor and NSERC Chair
 
Probability theory: mathematical model, conditional probabilities, random variables, cdf and pdf, transformation of random variables, conditional densities, statistical averages. Random processes concept; ensemble, stationarity, ergodicity, correlation and covariance, power spectral density, calculation and measurement of ACF, AVF and PSD, Gaussian random processes, noise. Transmission of random processes through linear systems: time-invariant systems, non-stationary processes, random walks.
 
Estimation theory: basics, best estimators, conditional expectation, parametric estimation theory, Fisher information, Cramer-Rao lower bound, Bayesian estimation, minimum mean-square error estimation (MMSE), recursive MMSE formulations, Kalman filtering concepts, the extended Kalman filter and applications, the unscented transform, unscented Kalman filter, particle filtering.
 
Prerequisites: Background information, Pages 1-12 of course notes
Evaluation:
  • Midterm Exam
  • Project Study, report in a paper of length no more then 5 pages (conference style). 
Dal Course Fall 2017: 
We meet Tuesdays 11:30 am -- 2:30 pm (or as announced in class), starting September 5, 2017. Please subscribe to the Twitter feed @UmdccChair for up-to-date information. See Dalhousie class schedule for details: Dal Calendar
 
Below is an archive of past student project report. Those marked with ♦ are A+ contributions.
 
Past Student Projects (2016):
Kalman Filters for Robotic Vehicle Localization (by Marco Andreetto) ♦
Particle Filtering applied to diffusion MRI data: Particle Filtering Tractography (by Guglia Berto) ♦
Kalman Filtering: Problem Statement, Simulation and Real Application for Tracking Objects in Videos (by Mattia Bonomi) ♦
A Sequential Unscented Minimum Mean Square Error Estimator for Finding Avalanche Buried (by Mirko Brentari) ♦
Random Data Arrival Analysis in Coupling Data Transmission for Multiple-Access Communication (by Farshid Vanosfaderani)
An implementation of the classical estimation theory in a special case - Using WiTrack to locate the moving target (Jiacheng Guo)
Evaluation of Support Aided Kalman Filter for Tracking Sparse Underwater Channel (Murwan Bashir)
Unscented Kalman Filter for MIMO Performance Analysis (Sagar Basavaraju)
 
Past Student Projects (2015):
Comparison of four algorithms (SLIM, Basis Pursuit Sparse Estimation, LSE and Windowing based method) for channel estimation (Zahra Alavizadeh)
Minimum Mean Square Equalization techniques applicable for underwater acoustic channels (Afolarin Engwande)
Data Detection and Noise Minimization for Receivers in Underwater Acoustic Environments (Nitisha Sharma)
Modeling AUV Localization Error in a Long Baseline Acoustic Positioning System (Dugald Thomson) ♦
 
Past Student Projects (2014):
Application of Autoregressive Models in WSSUS Channel Estimation (Habib Mirhedayati Roudsari)
Diffraction on Random Surfaces (Jan Chochol)
Acoustic Channel Estimation Using Kalman Filtering (Xiao Liu)
Automatic Modulation Detection (Alireza Karami)
Approximate Message-passing(AMP) Algorithms for Sparse Channel Estimation (Danqing Yin)
Estimating Parameters of Deterioration Models Using Bayesian Estimation (Hanna Lo)
Inertial Orientation Tracking based on MEMS Gyroscope (Hui Xiong)
Stochastic Job Shop Scheduling (Milad Akrami)
 
Past Student Projects (2014):
The Poisson Waiting Time Distribution: Analysis and Application (Kyle Park) ♦
Side Channel Power Analysis A Link to Communications & Channel Equalization (Colin O'Flynn) ♦
Sparse Estimation and the Cramer-Rao Lower Bound (David McNutt) ♦
LDPC Coding and Decoding and its Application to Binary Erasure Channels (Ali Bassam)
Random Channel Estimation using Wiener Filtering (Paul Dickson)
A Derivation of Applying Random Network Coding (Zichao Zhou)

Course Materials

Course Assignments