Browsing RPI Theses Open Access by Author "Embrechts, Mark J."
Now showing items 1-5 of 5
-
Advances in property-encoded molecular surface methods : PEST, PROLICSS, and pH-sensitive protein descriptors
Sundling, C. Matthew L. (Rensselaer Polytechnic Institute, Troy, NY, 2007-12)Presented here are three property-encoded molecular surface-based methods: PEST, PROLICSS, and pH-senstitive protein descriptors. PEST (Property-Encoded Surface Translator) generates whole-molecule alignment free surface ... -
Approximating covariance matrices using low rank perturbations with applications to accent identification and social network clustering
Purnell, Jonathan (Rensselaer Polytechnic Institute, Troy, NY, 2010-08) -
Mining local and global patterns for complex data classification
Li, Geng (Rensselaer Polytechnic Institute, Troy, NY, 2013-08)In the second part of this thesis, we study the challenging problem of graph classification. With the proliferation of graph data, there has been a lot of interest in recent years to develop effective methods for classifying ... -
Semantically enabled neural network modeling of major depressive disorder
Xiao, Yuezhang (Rensselaer Polytechnic Institute, Troy, NY, 2012-08)We then describe our user case: we combine this portal with our second order differential equation and neural network model for depressive data analysis. Both the design methods and learning algorithm are discussed in this ... -
Towards intelligent trajectory optimisation in astrodynamics
Sprague, Christopher Iliffe (Rensselaer Polytechnic Institute, Troy, NY, 2017-05)In this work trajectory optimisation is explored through four different avenues, namely: 1. Direct Methods, 2. Heuristics, 3. Reinforcement learning, 4. Supervised Learning Each method builds off of its preceding session. ...