Skip to content

Latest commit

 

History

History
54 lines (41 loc) · 3.13 KB

README.md

File metadata and controls

54 lines (41 loc) · 3.13 KB
Raw

Neural Network as a Weighted Order Statistic Filter - Analog CMOS Implementation

This is a hardware implementation of weighted order statistic (WOS) filter in CMOS 0.35 μm process using a specific recurrent neural network. Weighted order statistic filters can select kth largest value of a statistical sample with sample points being repeated based on their weight. Maximum, minimum, and median are special cases in their operation. One of their main applications is in signal processing and specifically in noise removal.

Description

The detailed description of the project can be found in our paper: pdf or IEEE Xplore. An analog circuit resembling a recurrent neural network is implemented in the project:

Weighted order statistic neural network

Each neuron in the first layer is designed to have a sign activation function, for which the circuit diagram is as follows:

Circuit of each neuron in the first layer

Thanks to the Kirchhoff's Current Law (KCL), the neuron in the second layer is made only by connecting the outputs of the first layer neurons and a current source (as the bias). As an illustration the results of applying the weighted order statistic filter on a few signals to find their max, min, and median can be seen here (red is the output):

WOS filter working as a max filter

WOS filter working as a min filter

WOS filter working as a median filter

The Code

The WOS network is implemented in HSPICE for simulation in the CMOS 0.35 μm process. In the time of the original simulations, a TSMC 0.35 μm technology file was used. You may use other technology files, probably with some minor alterations. The files under the netlists directory include a netlist of the proposed neuron in the project, and a netlist of the filter itself. The configuration in the latter is chosen to showcase the filter working as a median operator, whereas with minor changes (some hinted in the comments in the file) it can be changed to any other weighted order statistic filter, based on the explanations of the paper. It performs a range of DC sweep, transient, and corner tests.

Citation

You may cite the paper published as a part of this project.

@inproceedings{hoseini2010circuit,
  title={Circuit design of weighted order statistics filter based on neural network in CMOS process},
  author={Hoseini, Pourya and Mashoufi, Behbood},
  booktitle={2010 International Conference on Electronic Devices, Systems and Applications},
  pages={174--178},
  year={2010},
  organization={IEEE}
}

Developers

Pourya Hoseini

Contact

I can be reached at hoseini@nevada.unr.edu.