Location: Computer Science Building, rm 150/151
This event will consist of three short talks:
Speaker: Sheila Werth
Title: Evaluating Features for Broad Species Based Classification of Bird Observations using Dual-Polarized Doppler Weather Radar
Abstract: Wind energy is one of the fastest-growing segments of the world energy market; however, wind energy facilities can have detrimental effects on wildlife, especially birds and bats. The ability to monitor vulnerable species in the vicinity of proposed wind sites could enable site selection that favors more vulnerable species, but current monitoring tools lack this classification capability. This work analyzes polarimetric and Doppler measurements of migrating birds for species based variation. A novel two stage feature extraction technique was developed to enable comparison between birds. Stage one involves mapping time changing radar measurements to the birds behavioral state in time (i.e. flapping and gliding); stage two uses this behavioral state information to produce temporal and statistical features that describe the frequency and appearance of these different behavioral states. General trends of temporal features (ex. wing-beat frequency) in the dataset match Ecological literature and validate the feature extraction approach. Preliminary clustering of bird detection data suggests possible species based subgroups of targets, although a larger dataset is needed for further validation.
Speaker: Kevin Winner
Title: Probabilistic Inference with Generating Functions for Poisson Latent Variable Models
Abstract: Graphical models with latent count variables arise in a number of fields. Standard exact inference techniques such as variable elimination and belief propagation do not apply to these models because the latent variables have countably infinite support. As a result, approximations such as truncation or MCMC are employed. We present the first exact inference algorithms for a class of models with latent count variables by developing a novel representation of countably infinite factors as probability generating functions, and then performing variable elimination with generating functions. Our approach is exact, runs in pseudo-polynomial time, and is much faster than existing approximate techniques. It leads to better parameter estimates for problems in population ecology by avoiding error introduced by approximate likelihood computations.
Speaker: Garrett Bernstein
Title: Consistently Estimating Markov Chains with Noisy Aggregate Data
Abstract: We address the problem of estimating the parameters of a time-homogeneous Markov chain given only noisy, aggregate data. This arises when a population of individuals behave independently according to a Markov chain, but individual sample paths cannot be observed due to limitations of the observation process or the need to protect privacy. Instead, only population-level counts of the number of individuals in each state at each time step are available. When these counts are exact, a conditional least squares (CLS) estimator is known to be consistent and asymptotically normal. We initiate the study of method of moments estimators for this problem to handle the more realistic case when observations are additionally corrupted by noise. We show that CLS can be interpreted as a simple ``plug-in'' method of moments estimator. However, when observations are noisy, it is not consistent because it fails to account for additional variance introduced by the noise. We develop a new, simpler method of moments estimator that bypasses this problem and is consistent under noisy observations. This paper was presented at AISTATS 2016.
Sheila Werth defended her MS in Electrical Engineering at UMass Amherst in 2016. In the past, she has worked at Georgia Tech Research Institute and MIT Lincoln Laboratory. Currently, she works in signal and image processing for radar applications at The MITRE Co. in Bedford MA.
Kevin Winner is a PhD candidate advised by Dr. Dan Sheldon in the Machine Learning for Data Science (MLDS) lab at the College of Information and Computer Sciences, UMass Amherst. His research focuses on developing machine learning techniques for modeling population dynamics of critically endangered species where data is inherently scarce. His other research interests include remote sensing of migratory bird species using doppler weather radar and estimating the habitat requirements and interaction dynamics of animal communities from GPS collar data.
Garrett Bernstein is a third-year PhD student in MLDS, advised by Dan Sheldon. His research explores graphical models for aggregate data, with applications in bird migration and differential privacy. Previous to UMass he worked at MIT Lincoln Laboratory and received a Bachelors (Applied Physics) and Masters (Computer Science) from Cornell University.