The purpose of this program is to teach a computer to classify plants via their leaves. You just need to input the image of a leaf(acquired from scanner or camera), then the computer can tell you what kind of plant it is.
niftilib is a collection of i/o routines for the nifti1 neuroimage data format. C (nifticlib), Java (niftijlib), Matlab (niftimatlib), and Python (pynifti) code is available. For nifti format info see: http://nifti.nimh.nih.gov/
A library for fast computation of Gauss transforms in multiple dimensions, using the Improved Fast Gauss Transform and Approximate Nearest Neighbor searching. This library is useful for efficient Kernel Density Estimation (KDE) using a Gaussian kernel.
AERST is a C++ tool to simulate AER (Address-Event-Representation)-based systems
A Matlab/Octave toolbox to design, simulate, and analyze optical communication systems. Open source, fast (using MEX), user-friendly and customizable, it includes cutting-edge solutions for: modulation formats, performance estimation, fiber propagation.
Toolboxes for SPM (http://www.fil.ion.ucl.ac.uk/spm/) developed at Freiburg Brain Imaging (http://fbi.uniklinik-freiburg.de/)
Analysis of undersea fish videos
The Fish4knowledge project investigated: information abstraction and storage methods for analyzing undersea video data (from 10E+15 pixels to 10E+12 units of information), machine and human vocabularies for detecting & describing fish, flexible process architectures to process the data and scientific queries and effective specialised user query interfaces. A combination of computer vision, database storage, workflow and human computer interaction methods were used to achieve this. The project used live video feeds from 10 underwater cameras as a testbed for investigating more generally applicable methods for capture, storage, analysis and querying of multiple video streams. We collated a public database from 3 years containing video summaries of the observed fish and associated descriptors. Expert web-based interfaces were developed for use by marine researchers, allowing unprecedented access to live and previously stored videos, or previously extracted information.
NBT is an open source Matlab toolbox for the computation and integration of neurophysiological biomarkers. NBT allows for easy implementation of new biomarkers, and incorporates an online wiki with extensive help and tutorials.
QCF is a toolbox of Quantum Computing Functions for Matlab and Octave. It is based on the syntax of Nielsen & Chuang's book 'Quantum Computing and Quantum Information'. It includes simulations of the Grover and Deutsch algorithms and a pdf tutorial.
The NUMIPAD library implements several methods/algorithms to solve inverse problems and adaptive decomposition (i.e. Tikhonov regularization, Total Variation, Basis Pursuit, etc.)
A pythonic interface to MATLAB
This package lets Python users interface and communicate with MATLAB from Python. Pymatlab makes it easier for users to integrate a project with a large MATLAB codebase into python scripts by using MATLAB scripts as a part of the python program. The basic functionality of this package is to send data from Python to MATLAB's workspace to be able to run Matlab function on the data. After processing you retrieve back data to python. This enables you to process data with Mathlab's built in functions, toolboxes or Matlab-scripts. It is also possible to use MATLAB's to generate plots or other graphics. The package uses Numpy's ndarrays and translates them into MATLAB's mxarrays using Python's ctypes and Matlab's mx library. The interface to MATLAB's workspace in done through MATLAB's engine library.
This project aims to develop and share fast frequent subgraph mining and graph learning algorithms. Currently we release the frequent subgraph mining package FFSM and later we will include new functions for graph regression and classification package
Metabolomics Bioinformatics Tools
Our bioanalytical research exploits practical and efficient high-throughput technologies for the analyses of complex mixtures derived from living systems. This will facilitate the development of preventive, predictive and personalized medicine for specific diseases and will promote health and wellness. We use a number of high-throughput analytical platforms including multidimensional liquid chromatography-mass spectrometry (MDLC-MS) for proteomics, and for metabolomics; liquid chromatography-mass spectrometry (LC-MS), and comprehensive two-dimensional gas chromatography-mass spectrometry (GCxGC/TOF-MS). Each type of analysis affords limited analyte coverage of molecules present in a patient sample and therefore provides only a partial molecular profile for an individual patient. These diverse analytical data must be integrated with advanced bioinformatics methods for accurate evaluation of health and detection of disease susceptibility.
An Open-Source Library for Low-Power Approximate Computing Modules
The “lpACLib” library contains the VHDL description of accurate and approximate versions of several arithmetic modules (like adders and multiplier of different bit-widths) and accelerators. Moreover, it also provides the corresponding software behavioral models/implementations developed in C and MATLAB to enable quality characterization. Besides our novel designs, it also contains implementations for several state-of-the-art arithmetic modules and their approximate versions. This open-source library facilitates research and development in approximate computing at higher abstraction levels, and to facilitate reproducible research and comparisons. In case of usage, please refer to our publication: Muhammad Shafique, Rehan Hafiz, Semeen Rehman, Walaa El-Harouni, Jörg Henkel, "Cross-Layer Approximate Computing: From Logic to Architectures", Design Automation Conference (DAC), 2016. Contributors: Authors, Vanshika Baoni, M. Abdullah Hanif http://ces.itec.kit.edu/lpACLib.php
Octave Eclipse GUI
Octave development environment built upon Eclipse's Dynamic Languages Toolkit (http://www.eclipse.org/dltk/). Distributed as an Update site for Eclipse 3.7 Indigo and Indigo-based package for several platforms. Supports search, autocompletion, launching scripts, interactive console, debug and integrated plotting on Octave versions 3.2.x, 3.4.x and 3.6.x. The current goal is to make it running out-of-box on multiple platforms. Currently only Linux and Windows are supported. Mac support is possible. The project needs a maintainer for Mac version, since I don't have Mac to build Octclipse and test it on this platform. Also, it is worth to support Eclipse 4.0 Juno with DLTK 4.
Brain imaging software produced by the Brain Research Imaging Centre of The University of Edinburgh.
Image Acquisition Dynamic Link Library for Matlab and C/C++. It is free acquisition tool for those who has no money for MATLAB(R) Image Acquisition Toolbox and want to capture images from FireWire cameras. It is based on CMU driver.
This site contains four packages of Mass and mass-based density estimation. 1. The first package is about the basic mass estimation (including one-dimensional mass estimation and Half-Space Tree based multi-dimensional mass estimation). This packages contains the necessary codes to run on MATLAB. 2. The second package includes source and object files of DEMass-DBSCAN to be used with the WEKA system. 3. The third package DEMassBayes includes the source and object files of a Bayesian classifier using DEMass. DEMassBayes.7z has jar file to be used with WEKA and a readme file listing parameters used. The source files are included in DEMassBayes_Source.7z. 4. The four package is MassTER includes source and JAR file to be used with WEKA system..
Cell decomposition is one of the first applicable solution for path planning - robot path planning. The algorithm aims to find free areas (cells not occupied by obstacles) in the configuration space, and build a graph of adjacency for these cells.
This project applies an interpretation of a k-NN algorithm to a library of GPS commuter data for speed prediction. The overall goal is to lay the foundation for a power management protocol for use in electric vehicles with hybrid energy storage.
The Matlab SRTM Library is designed to be an easy-to-use interface for importing and manipulating NASA's Shuttle Radar Topography Mission (SRTM) Digital Elevation Model (DEM) dataset.
Extended Marcatili method for Rectangular Waveguides in Matlab
We recently extended Marcatili’s approximate analytical approach for the description of light propagation in rectangular waveguides to the regime of (silicon) high-index-contrast waveguides. This software is a Matlab implementation of the method.
An Octave / LUA scripting language project dedicated to modeling electric motors inside the "Finite Element Method Magnetics" (FEMM) 2-D simulation program. Created to design a motor that fits inside a car wheel, experimenting in many degrees of freedo
Tool for visualizing artificial neural networks in Matlab using the Matlab Neural Network Toolbox (see wiki for details).
Lloyd's Algorithm-based Volumetric Analysis for AFM Images
This MATLAB-based program enables analysis of AFM images. In particular, it allows the user to measure the volume of all distinguishable features in an image and to isolate and sort those particles. As the name implies, LAVA uses Lloyd's Algorithm, also known as k-means sorting, to identify a small set of volumes representative of the actual distribution of particle in the image. Although developed for determining feature volume, LAVA is also completely compatible with other types of image analysis, such as fluorescence intensity. Work is in progress to provide three-channel functionality, allowing comparison of relative intensity of red, green, and blue channels in multi-color images.