Monitor CPU and RAM usage of a process (and its children) (cpumemlog)
cpumemlog.sh is a Bash shell script that monitors CPU and RAM usage of a given process and its children. The main aim for writing this script was to get insight about the behaviour of a process and to spot bottlenecks without GUI tools, e.g., cpumemlog.sh it is very useful to spot that the computationally intensive process on a remote server died due to hitting RAM limit or something of that sort. The statistics about CPU, RAM, and all that are gathered from the system utility ps. While the utility top can be used for this interactively, it is tedious to stare at its dynamic output and quite hard to spot consumption at the peak and follow the trends etc. Yet another similar utility is time, which though only gives consumption of resources at the peak. cpumemlogplot.R is a companion R script to cpumemlog.sh used to summarize and plot the gathered data.

A Wrapper Around rjags to Streamline JAGS Analyses (jagsUI)
This package provides a set of wrappers around rjags functions to run Bayesian analyses in JAGS (specifically, via libjags). A single function call can control adaptive, burn-in, and sampling MCMC phases, with MCMC chains run in sequence or in parallel. Posterior distributions are automatically summarized (with the ability to exclude some monitored nodes if desired) and functions are available to generate figures based on the posteriors (e.g., predictive check plots, traceplots). Function inputs, argument syntax, and output format are nearly identical to the R2WinBUGS/R2OpenBUGS packages to allow easy switching between MCMC samplers.

Adaptive Neuro Fuzzy Inference System in R (anfis)
The package implements ANFIS Type 3 Takagi and Sugeno’s fuzzy if-then rule network with the following features: (1) Independent number of membership functions(MF) for each input, and also different MF extensible types. (2) Type 3 Takagi and Sugeno’s fuzzy if-then rule (3) Full Rule combinations, e.g. 2 inputs 2 membership funtions -> 4 fuzzy rules (4) Hibrid learning, i.e. Descent Gradient for precedents and Least Squares Estimation for consequents (5) Multiple outputs.

Functional programming in R (lambda.r)
Provides a syntax for writing functional programs in R. Lambda.R has a clean syntax for defining multi-part functions with optional guard statements. Simple pattern matching is also supported. Types can be easily defined and instantiated using the same functional notation. Type checking is integrated and optional, giving the programmer complete flexibility over their application or package.

Ensembles of Caret Models (caretEnsemble)
Functions for creating ensembles of caret models: caretList, caretEnsemble, and caretStack. caretList is a convenience function for fitting multiple caret::train models to the same dataset. caretEnsemble will make a linear combination of these models using greedy forward selection, and caretStack will make linear or non-linear combinations of these models, using a caret::train model as a meta-model.

Orthogonal Nonlinear Least-Squares Regression (onls)
Orthogonal Nonlinear Least-Squares Regression using Levenberg-Marquardt minimization.