The Graphical Models Toolkit (GMTK) is a toolkit for rapidly prototyping statistical models using dynamic graphical models (DGMs) and dynamic Bayesian networks (DBNs). It can be used for speech and language processing, bioinformatics, activity recognition, and any time series application. It features exact and approximate inference, many built-in factors including dense, sparse, and deterministic conditional probability tables, native support for ARPA backoff-based factors and factored language models, parameter sharing, gamma and beta distributions, dense and sparse Gaussian factors, heterogeneous mixtures, deep neural network factors, and time-inhomogeneous trellis factors, arbitrary order embedded Markov chains, a GUI graph viewer, and much more.
HEALPix is a set of scientific tools implementing the Hierarchical Equal Area isoLatitude Pixelation of the sphere. As suggested in the name, this pixelation produces a subdivision of a spherical surface in which every single pixel covers the same surface area. HEALPix provides various programs and libraries in C, C++, Fortran, GDL/IDL, Java, and Python which facilitate discretization, simulation, processing, analysis, and visualization of data on the sphere up to very high resolution. It is the state-of-the-art program used in astronomy and cosmology to deal with massive full-sky data sets.
Isoline Retrieval uses supervised statistical classification to retrieve isolines from cross-track scanning or similar satellites. It contains software to generate training data using collocation or radiative transfer simulations, as well as routines to interpolate the final fields using a variation of multi-linear interpolation or kernel estimation. The currently-supported satellites are the Advance Microwave Sounding Unit (AMSU) series and, to a lesser extent, the Global Ozone Measurement Experiment (GOME). An ambitious researcher, however, could easily adapt the codes to a similar satellite.
JoomlaWatch allows you to watch your Web site visitors and bots in real-time from the administration menu, particularly their IP addresses, countries they come from, geographical location on a map, which pages they are viewing, and their browser and operating system. It creates daily and all-time stats from this information plus unique, pageload, and total hits statistics. Furthermore, you can block harmful IP addresses, see blocked attempts stats, evaluate the trend charts, and create goals based on many parameters. In the frontend, it can show the top countries, user, and visit information for certain periods of time.
JunkBox is a lightweight Web application that can track your files and record every single click. You can get the total number of hits and statistics on who downloaded your files, and how and when. It is completely transparent, so every link looks like an ordinary link to an ordinary file.
KeyFrog monitors the keyboard and visualizes its usage statistics. The user can obtain much information about keyboard activity: the intensity of keyboard usage, how was it distributed in time, which applications were used, etc. This may be very useful, for example, to developers to monitor their productivity. The environment being monitored is the X Window System (text applications are explicitly supported if run inside an X terminal).
LibBi is used for state-space modelling and Bayesian inference on high-performance computer hardware, including multi-core CPUs, many-core GPUs (graphics processing units), and distributed-memory clusters. The staple methods of LibBi are based on sequential Monte Carlo (SMC), also known as particle filtering. These methods include particle Markov chain Monte Carlo (PMCMC) and SMC2. Other methods include the extended Kalman filter and some parameter optimization routines. LibBi consists of a C++ template library and a parser and compiler, written in Perl, for its own modelling language.