Applied Statistics & Computing
Although this division normally works in close collaboration
with the chemistry and nanotechnology faucet of Π, developing
methodologies that can enable the revelation of similarities or
disparities within multidimensional data sets acquired from
scientific experimentation or analyses within Π or/and helping in
the implementation of such methods that build theories and
uncovers new phenomena, they will also perform work that solely
involves their expertise.
Statistical methods typically used within the group includes
those used in the calculation of reliability, biometrics, time
series, forecasting, categorical data analysis, multivariate
analysis, independence determinations, statistical significance,
spatial statistics, the analysis of sparse data, Bayesian methods
and stochastic processes. Applied computing operations include
software engineering, artificial intelligence and distributive
systems. An active area of R&D within Π is in the fusion and
reduction of the dimensionality of datasets of amalgamated
disparate data by implementing multiple sequence alignment,
techniques for pattern discovery and feature detection, feature
selection, Principal Components Analysis (PCA) and Discriminant
Analysis, partitional and hierarchical clustering, classifier
design, classification and cross-validation techniques.
- Algorithm design, implementation and testing
- Chemometrics and Bioinformatics
- K9~Machine Learning
- Neural Networks
- Data Mining and Clustering
- 3D Image Analysis, Enhancement and Segmentation
- Feature extractions and Pattern Classification.
- Object Extraction and Recognition
Programming Languages: MATLAB, R, Visual C++, Java,
Visual Basic, OpenGL, DirectX, PERL, SQL, LabView
Operating Systems: Windows 95/98/ NT/2K/XP/VISTA, UNIX, Linux,
Sun Solaris, MAC-OS.
Application Software Packages: Adobe Photoshop, OPNET,
MS Access, POSER.