In this study we compare five classification methods for detecting activation in fMRI data: Fishe... more In this study we compare five classification methods for detecting activation in fMRI data: Fisher linear discriminant, support vector machine, Gaussian nave Bayes, correlation analysis and k-nearest neighbor classifier. In order to enhance classifiers performance a variety of data preprocessing steps were employed. The results show that although kNN and linear SVM can classify active and nonactive voxels with less than 1.2% error, careful preprocessing of the data, including dimensionality reduction, outlier elimination, and denoising are important factors in overall classification.
The aim of this study is to assess the functional connectivity from resting state functional magn... more The aim of this study is to assess the functional connectivity from resting state functional magnetic resonance imaging (fMRI) data. Spectral clustering algorithm was applied to the realistic and real fMRI data acquired from a resting healthy subject to find functionally connected brain regions. In order to make computation of the spectral decompositions of the entire brain volume feasible, the
It has been shown that under min-sum (MS) decoding, scaling the messages at the output of check n... more It has been shown that under min-sum (MS) decoding, scaling the messages at the output of check nodes can improve the performance of regular low-density parity-check (LDPC) codes. However, for irregular codes designed for the sum-product decoder, linear scaling can hinder the performance. The problem of code design for MS and linear scaling min-sum (LSMS) decoders have been recently investigated. It is shown that the gap to the capacity for LSMS codes is better than MS codes, but compared to sum-product codes the gap is still considerable. In this letter, a modified MS decoding is proposed and studied. We use the stability analysis of density evolution to show that the proposed method allows for a larger fraction of edges connected to degree-2 variable nodes than LSMS codes. Finally, by designing codes based on the modified method, we show that compared to MS and LSMS codes, a smaller gap to the capacity can indeed be achieved while the complexity of decoding remains essentially the same.
Design of low-density parity-check (LDPC) codes suitable for all channels which exhibit a given c... more Design of low-density parity-check (LDPC) codes suitable for all channels which exhibit a given capacity C is investigated. Such codes are referred to as universal LDPC codes. First, based on numerous observations, a conjecture is put forth that a code working on N equal-capacity channels, also works on any convex combination of these N channels. As a supporting evidence, we prove that a code satisfying the stability condition on N channels, also satisfies the stability condition on the convex hull of these N channels. Then, a channel decomposition method is suggested which spans any given channel with capacity C in terms of a number of identical-capacity basis channels. We expect codes that work on the basis channels to be suitable for any convex combination of the bases, i.e., all channels with capacity C. Such codes are found over a wide range of rates. An upper bound on the achievable rate of universal LDPC codes is suggested. Through examples, it is shown that our codes achieve rates extremely close to this upper bound. In comparison with existing LDPC codes designed for a given channel, significant performance gain is reported when codes are used over various channels of equal capacity.
Low-density parity-check (LDPC) codes have been used for communication over a two-user Gaussian b... more Low-density parity-check (LDPC) codes have been used for communication over a two-user Gaussian broadcast channel. It has been shown in the literature that the optimal decoding of such system requires joint decoding of both user messages at each user. Also, a joint code design procedure should be performed. We propose a method which uses a novel labeling strategy and is based on the idea behind the bit-interleaved coded modulation. This method does not require joint decoding and/or joint code optimization. Thus, it reduces the overall complexity of near-capacity coding in broadcast channels. For different rate pairs on the boundary of the capacity region, pairs of LDPC codes are designed to demonstrate the success of this technique.
This paper present a new method for multiple response optimization (MRO). Multiresponse problems ... more This paper present a new method for multiple response optimization (MRO). Multiresponse problems comprise three stages: data gathering, model building and optimization. The most work in MRO don't consider the results of modeling stage while these outcomes can help in achieving the solution. In this paper, we incorporate the obtained results from stage of model building, i. e. the least
In this study we compare five classification methods for detecting activation in fMRI data: Fishe... more In this study we compare five classification methods for detecting activation in fMRI data: Fisher linear discriminant, support vector machine, Gaussian nave Bayes, correlation analysis and k-nearest neighbor classifier. In order to enhance classifiers performance a variety of data preprocessing steps were employed. The results show that although kNN and linear SVM can classify active and nonactive voxels with less than 1.2% error, careful preprocessing of the data, including dimensionality reduction, outlier elimination, and denoising are important factors in overall classification.
The aim of this study is to assess the functional connectivity from resting state functional magn... more The aim of this study is to assess the functional connectivity from resting state functional magnetic resonance imaging (fMRI) data. Spectral clustering algorithm was applied to the realistic and real fMRI data acquired from a resting healthy subject to find functionally connected brain regions. In order to make computation of the spectral decompositions of the entire brain volume feasible, the
It has been shown that under min-sum (MS) decoding, scaling the messages at the output of check n... more It has been shown that under min-sum (MS) decoding, scaling the messages at the output of check nodes can improve the performance of regular low-density parity-check (LDPC) codes. However, for irregular codes designed for the sum-product decoder, linear scaling can hinder the performance. The problem of code design for MS and linear scaling min-sum (LSMS) decoders have been recently investigated. It is shown that the gap to the capacity for LSMS codes is better than MS codes, but compared to sum-product codes the gap is still considerable. In this letter, a modified MS decoding is proposed and studied. We use the stability analysis of density evolution to show that the proposed method allows for a larger fraction of edges connected to degree-2 variable nodes than LSMS codes. Finally, by designing codes based on the modified method, we show that compared to MS and LSMS codes, a smaller gap to the capacity can indeed be achieved while the complexity of decoding remains essentially the same.
Design of low-density parity-check (LDPC) codes suitable for all channels which exhibit a given c... more Design of low-density parity-check (LDPC) codes suitable for all channels which exhibit a given capacity C is investigated. Such codes are referred to as universal LDPC codes. First, based on numerous observations, a conjecture is put forth that a code working on N equal-capacity channels, also works on any convex combination of these N channels. As a supporting evidence, we prove that a code satisfying the stability condition on N channels, also satisfies the stability condition on the convex hull of these N channels. Then, a channel decomposition method is suggested which spans any given channel with capacity C in terms of a number of identical-capacity basis channels. We expect codes that work on the basis channels to be suitable for any convex combination of the bases, i.e., all channels with capacity C. Such codes are found over a wide range of rates. An upper bound on the achievable rate of universal LDPC codes is suggested. Through examples, it is shown that our codes achieve rates extremely close to this upper bound. In comparison with existing LDPC codes designed for a given channel, significant performance gain is reported when codes are used over various channels of equal capacity.
Low-density parity-check (LDPC) codes have been used for communication over a two-user Gaussian b... more Low-density parity-check (LDPC) codes have been used for communication over a two-user Gaussian broadcast channel. It has been shown in the literature that the optimal decoding of such system requires joint decoding of both user messages at each user. Also, a joint code design procedure should be performed. We propose a method which uses a novel labeling strategy and is based on the idea behind the bit-interleaved coded modulation. This method does not require joint decoding and/or joint code optimization. Thus, it reduces the overall complexity of near-capacity coding in broadcast channels. For different rate pairs on the boundary of the capacity region, pairs of LDPC codes are designed to demonstrate the success of this technique.
This paper present a new method for multiple response optimization (MRO). Multiresponse problems ... more This paper present a new method for multiple response optimization (MRO). Multiresponse problems comprise three stages: data gathering, model building and optimization. The most work in MRO don't consider the results of modeling stage while these outcomes can help in achieving the solution. In this paper, we incorporate the obtained results from stage of model building, i. e. the least
Uploads
Papers by Mahdi Ramezani