Addfilter is a command-line application which adds and removes filter drivers for a given drive or volume. It is intended to demonstrate how to insert a filter driver into the driver stack of a device. The sample illustrates how to do this by using the SetupDi APIs. The sample works on both x86 and Alpha platforms. It has only been tested in a 32-bit environment. Since Addfilter is not a driver, it does not deal with Plug and Play or Power Management.
FPFilter is a sample disk filter driver that demonstrates how a disk failure prediction filter driver could be implemented. A failure prediction filter driver can predict when a disk may fail and notify the disk driver stack of this condition.
The flpydisk sample is a floppy driver that resides in the directory \\Ntddk\Src\Storage\Fdc\Flpydsk. It is similar to a class driver in that it sits a level above the floppy disk controller in the driver stack, and brokers communication between the application level and the low-level driver. The floppy driver takes commands from the application and then calls routines in the controller which will in turn perform the actual interaction with the device. The sample compiles in 64-bit, but has not been tested in this environment. It is compatible with x86 and Alpha platforms.
This version of the code is compatible only with the AT89C2051 due to the
location of the data buffer and stack in RAM. The code may be modified to
work with the AT89C1051 by relocating or resizing the buffer and stack to
fit into the smaller amount of RAM available in the AT89C1051.
The Small C compiler translates a subset of the C language into
assembly language. It runs under PC/MS-DOS 2.1 and later. Small
C is compatible with the Microsoft and Small Mac assemblers.
Small C takes full advantage of the ability of these assemblers
to generate relocatable object code, to maintain libraries of
relocatable modules, and to link separately compiled program
modules. It supports a small memory model with one code and one
data/stack segment.
Description: FASBIR(Filtered Attribute Subspace based Bagging with Injected Randomness) is a variant of Bagging algorithm, whose purpose is to improve accuracy of local learners, such as kNN, through multi-model perturbing ensemble.
Reference: Z.-H. Zhou and Y. Yu. Ensembling local learners through multimodal perturbation. IEEE Transactions on Systems, Man, and Cybernetics - Part B: Cybernetics, 2005, vol.35, no.4, pp.725-735.
Description: S-ISOMAP is a manifold learning algorithm, which is a supervised variant of ISOMAP.
Reference: X. Geng, D.-C. Zhan, and Z.-H. Zhou. Supervised nonlinear dimensionality reduction for visualization and classification. IEEE Transactions on Systems, Man, and Cybernetics - Part B: Cybernetics, 2005, vol.35, no.6, pp.1098-1107.
