Publications
-
Neural network joint modeling via context-dependent projection
We propose a context-dependent linear projection approach which considers neighboring words. Experimental results showed that the proposed approach further improves NNJM by 0.5 BLEU for English-Iraqi Arabic translation in N-best…
-
Unravelling Glucan Recognition Systems by Glycome Microarrays Using the Designer Approach and Mass Spectrometry
We describe construction of a "glucome" microarray, the first sequence-defined glycome-scale microarray, using a "designer" approach from targeted ligand-bearing glucans in conjunction with a novel high-sensitivity mass spectrometric sequencing method.
-
Discovery of the First Small-Molecule Opioid Pan Antagonist with Nanomolar Affinity at Mu, Delta, Kappa, and Nociceptin Opioid Receptors
Since this is the first ligand containing the trans-(3R,4R)-dimethyl-4-(3-hydroxyphenyl)piperidine opioid antagonist pharmacophore to have affinity for the NOP receptor, we explored the structural determinants of its NOP binding affinity.
-
Balanced Designs for Deeper Learning in an Online Introductory CS Course for Middle School Students
This paper describes our efforts to use the design-based research methodology to design a 6-week middle school course on the OpenEdX platform for blended in-class learning.
-
Design-Based Research for Deeper Learning in an Online Introductory CS Course for Middle School Students
This paper describes our efforts to use the design-based research methodology to design a 6-week middle school course on the OpenEdX platform for blended in-class learning.
-
Discrete Vs. Dense Times in the Analysis of Cyber-Physical Security Protocols
This paper investigates the foundational differences and the impacts on the analysis when using models with discrete time and models with dense time.
-
Softsad: Integrated frame-based speech confidence for speaker recognition
In this paper we propose softSAD: the direct integration of speech posteriors into a speaker recognition system instead of using speech activity detection (SAD).
-
Advances in deep neural network approaches to speaker recognition
In this work, we report the same achievement in DNN-based SID performance on microphone speech. We consider two approaches to DNN-based SID: one that uses the DNN to extract features,…
-
Using Technology and Evidence to Promote Cultures of Educational Innovation: The Example of Science and Mathematics Education
To increase the opportunities for students to learn the knowledge and skills that are valued in the 21st century, education must become more innovative.
-
Improved speaker recognition using DCT coefficients as features
We recently proposed the use of coefficients extracted from the 2D discrete cosine transform (DCT) of log Mel filter bank energies to improve speaker recognition over the traditional Mel frequency…
-
Effects of feature type, learning algorithm and speaking style for depression detection from speech
We systematically study the effects of feature type, machine learning approach, and speaking style (read versus spontaneous) on depression prediction in the AVEC-2014 evaluation corpus.
-
AKI in Hospitalized Children: Comparing the pRIFLE, AKIN, and KDIGO Definitions
This study applied the Pediatric RIFLE, AKI Network, and Kidney Disease Improving Global Outcomes criteria to a cohort of hospitalizations to compare AKI incidence and outcomes in ICU and non-ICU…