Emily R. Bartusiak

Emily R. Bartusiak

Auto-generated profile, based on publicly available information

Emily R. Bartusiak

Video and Image Processing Laboratory, School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 November 2023 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
EBEmily R. Bartusiak
Emily R. Bartusiak
MJMichael A. Jacobs
Michael A. Jacobs
MCMoses W. Chan
Moses W. Chan
MCMary L. Comer
Mary L. Comer
EDEdward Delp
Edward Delp
Hypersonic glide vehicles are a new class of vehicles that fly at hypersonic speeds and have high maneuverability. These fast-moving targets exhibit different flight characteristics compared to conventional vehicles, so traditional tracking and defense systems require new methods to contend with them. In this paper, we propose a machine learning method for predicting the behavior of hypersonic glide vehicles. Our method is based on a stochastic grammar, which is a mathematical framework that describes the possible transition patterns of sequences. We use the stochastic grammar to predict the transition patterns in hypersonic glide vehicle trajectories. Given a partial trajectory, our method uses the grammar to predict the hypersonic glide vehicle's future kinematics, such as its altitude, velocity, and acceleration. We evaluate our method on two datasets of simulated hypersonic glide vehicle trajectories and show that it can successfully predict hypersonic glide vehicle behavior, even in the presence of noise. We also show that our method can predict several minutes into the future and can accurately predict future hypersonic glide vehicle behavior based on shorter observation times. Our results suggest that our method has the potential to be a valuable tool for predicting behavior of hypersonic glide vehicles.

28 June 2023
Verified
Conference Paper
Open access
KBKratika Bhagtani
Kratika Bhagtani
EBEmily R. Bartusiak
Emily R. Bartusiak
AYAmit Kumar Singh Yadav
Amit Kumar Singh Yadav
PBPaolo Bestagini
Paolo Bestagini
EDEdward Delp
Edward Delp
The malicious use of synthetic speech has increased with the recent availability of speech generation tools. It is important to determine whether a speech signal is authentic (spoken by a human) or is synthesized and to determine the generation method used to create it. Identifying the synthesis method is known as synthetic speech attribution. In this paper, we propose the use of a transformer deep learning method that analyzes mel-spectrograms for synthetic speech attribution. Our method known as Patchout Spectrogram Attribution Transformer (PSAT) can distinguish new, unseen speech generation methods from those seen during training. PSAT demonstrates high performance in attributing synthetic speech signals. Evaluation on the DARPA SemaFor Audio Attribution Dataset and the ASVSpoof2019 Dataset shows that our method achieves more than 95% accuracy in synthetic speech attribution and performs better than existing deep learning approaches.

14 April 2022 in bioRxiv
Verified
Preprint
Open access
PDF file
EBEmily R. Bartusiak
Emily R. Bartusiak
MBMíriam Barrabés
Míriam Barrabés
ARAigerim Rymbekova
Aigerim Rymbekova
JGJulia Gimbernat-Mayol
Julia Gimbernat-Mayol
CLCayetana López
Cayetana López
AIAlexander G. Ioannidis
Alexander G. Ioannidis
We analyze dog genotypes ( i . e ., positions of dog DNA sequences that often vary between different dogs) in order to predict the corresponding phenotypes ( i . e ., unique observed characteristics). More specifically, given chromosome data from a dog, we aim to predict the breed, height, and weight. We explore a variety of linear and non-linear classification and regression techniques to accomplish these three tasks. We also investigate the use of a neural network (both in linear and non-linear modes) for breed classification and compare the performance to traditional statistical methods. We show that linear methods generally outperform or match the performance of non-linear methods for breed classification. However, we show that the reverse is true for height and weight regression. Finally, we evaluate the results of all of these methods based on the number of input features used in the analysis. We conduct experiments using different fractions of the full genomic sequences, resulting in input sequences ranging from 20 SNPs to ∼200k SNPs. In doing so, we explore the impact of using a very limited number of SNPs for prediction. Our experiments demonstrate that these phenotypes in dogs can be predicted with as few as 0.5% of randomly selected SNPs ( i . e ., 992 SNPs) and that dog breeds can be classified with 50% balanced accuracy with as few as 0.02% SNPs ( i . e ., 40 SNPs).