Biometrics and forensics integration using deep multi-modal semantic alignment and joint embedding

My advisor (Dr. Harry Wechsler) and I just published a paper entitled "Biometrics and forensics integration using deep multi-modal semantic alignment and joint embedding" in Pattern Recognition Letters. In the paper, we show some results about multi-modal (text / image) models and their application as a source of biometric information that is useful for forensic investigations.

The paper can be found here:

http://www.sciencedirect.com/science/article/pii/S0167865517300430

A multi-scale approach to data-driven mass migration analysis

Here is a link to the proceedings for the Workshop on Data Science for Social Good (SoGood 2016), containing a paper for which I was one of the authors: https://www.dropbox.com/s/rey5462zl2m67by/proceedings_SoGood16.pdf?dl=0

The paper was entitled "A multi-scale approach to data-driven mass migration analysis".

Abstract:
A system for scenario analysis and forecasting of mass migration is presented. The system consists of a family of multi-scale models to address the need of responding agencies for better situational awareness, short and medium-term forecasts of migration patterns, and assess impact of changes on the ground. Such insights allow for better planning and resource allocations to address migrant needs. The analytical frame-work consists of three separate models (a) a global push-pull model to estimate macro-patterns, (b) a time-series prediction model for estimating future boundary conditions of crisis regions, and (c) a detailed network
ow model that models population diffusion within the crisis region and allows  for  scenario  modeling.  The  paper  presents  the  framework  using the European refugee crisis as a case study. In addition, overall system design, practical considerations, end-user applications, and limitations of the modeling approach are discussed.