Flowsculpt is an open-source utility for solving the inverse problem in pillar programming. That is, given a fluid flow shape, what is the pillar sequence and inlet design that will produce such a shape? Our utility uses a customizable genetic algorithm to determine optimal pillar sequence and inlet flow design for a given fluid flow shape. Flowsculpt currently runs on Windows, Linux, and OS X operating systems, with minimal dependencies, and is freely available here:
Source code (BitBucket repository)
SETDiR: Scalable Extensible Toolkit for Dimensionality Reduction and Model Reduction
Stochastic Analysis and Materials Science research have witnessed an increasing use of data mining techniques in constructing viable stochastic models and in establishing structure-process-property relationships, respectively. Most scientific users are interested in an efficient and validated tool without worrying about the implementation details of the algorithms. This resulted in the development of SETDiR: Scalable Extensible Toolkit for Dimensionality Reduction. In this software suite, various linear and non-linear techniques are packaged into a modular, scalable framework with a graphical user interface. This interface helps to separate out the mathematics and computational aspects from applications, thus significantly enhancing utility to the general scientific community.
ARIA: Automatic Root Image Analysis
The root system is crucial for plant establishment as well as water and nutrient uptake. There is substantial genetic and phenotypic variation for root architecture, which gives opportunity for selection. Root traits, however, have not been used as selection criterion mainly due to the difficulty in measuring them, as well as their quantitative mode of inheritance. Seedling root traits offer an opportunity to study multiple individuals and to enable repeated measurements per year as compared to adult root phenotyping. We developed a new software framework to capture various traits from a single image of seedling roots. This framework is based on the mathematical notion of converting images of roots into an equivalent graph. This allows automated querying of multiple traits simply as graph operations. This framework is furthermore extendable to 3D tomography image data.
GRATE: GRaph based Analysis of TEM images
GRATE is an open-source framework for extracting molecular organization information from high resolution TEM images of polymer and small-molecule thin films. Written in MATLAB, it uses image processing and graph operations to rapidly identify and characterize crystalline regions. This identification aims to elucidate the effect of processing conditions on the film morphology and relate back to the electronic transport properties.
The code is hosted here.
PARyOpt: Parallel Asynchronous Remote baYesian Optimization
Source code: Bitbucket
Python Package: PyPI
Iron Deficiency Checker
Phenotyping is a critical component of plant research. Accurate and precise trait collection, when integrated with genetic tools, can greatly accelerate the rate of genetic gain in crop improvement. In 2016 we developed an end-to-end phenotyping workflow for disease severity phenotyping in soybeans, with a specific focus on the rapid and automatic assessment of Iron Deficiency Chlorosis (IDC). We trained a classifier using image processing based feature extraction linked to machine learning model. The resulting model was incorporated into this app to enable offline classification in the field. The app is still a proof-of-concept. The Android APK is available on request.