Ekta Shah - Academia.edu (original) (raw)
Papers by Ekta Shah
Lecture Notes in Computer Science, 2014
This study makes use of non-linear unmixing model to unmix pixels of hyperspectral imagery in a h... more This study makes use of non-linear unmixing model to unmix pixels of hyperspectral imagery in a heterogenous mangrove forest. This model takes into account the multi-path effects of radiation between endmember spectra that may occur before final interception by the sensor. Non linear models represent naturally occurring situations more accurately such as that commonly found within the mangrove forests where a variety of species co-exist as a mixed stand. This paper analyses the classification accuracy of linear and non-linear unmixing models for discrimination of mangrove species in the Sunderban Delta, India. On analysis, it has been found that linear unmixing has successfully identified mangrove species which exist as a pure patch whereas the non-linear model has been able to discriminate between species more accurately in a heterogenous patch. 10 dominant mangrove species have been identified in the study area and the results validated through field visits and RMSE values.
2013 International Conference on Communication and Signal Processing, 2013
The present study is the first attempt to make use of hyperspectral data in the Sunderban eco-geo... more The present study is the first attempt to make use of hyperspectral data in the Sunderban eco-geographic province to enable species level discrimination of mangroves. Our objective here, is to unmix hypespectral images using non-linear spectral unmixing techniques by taking into account the higher order interactions of light that occurs among different target endmembers (mangrove species). The linear mixing models have also provided a good abstraction of the mixing process, but some naturally occurring situations exist where nonlinear models provide the most accurate assessment of endmember abundance. It has been noted that the nonlinear models have been successful in estimating the abundances for the different endmembers in places where the non-linear situation is prevalent within the mangrove forests with several layers of tree canopy considered to be present one above the other. For such a situation, the second order interaction among the endmembers have been considered. This paper applies and compares the classification accuracy of non-linear techniques using the two methods shown in the Bilinear Model. They are Nascimento's and Fan's Bilinear model for unmixing hyperspectral images. On comparison, Fan's model has been able to classify mixed mangrove species more accurately than Nascimento's model. It has been possible to identify 7 dominant pure and mixed mangrove species present in the study area.
IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2020
In the past few decades, both gene expression data and protein-protein interaction (PPI) networks... more In the past few decades, both gene expression data and protein-protein interaction (PPI) networks have been extensively studied, due to their ability to depict important characteristics of disease-associated genes. In this regard, the paper presents a new gene prioritization algorithm to identify and prioritize cancer-causing genes, integrating judiciously the complementary information obtained from two data sources. The proposed algorithm selects disease-causing genes by maximizing the importance of selected genes and functional similarity among them. A new quantitative index is introduced to evaluate the importance of a gene. It considers whether a gene exhibits a differential expression pattern across sick and healthy individuals, and has a strong connectivity in the PPI network, which are the important characteristics of a potential biomarker. As disease-associated genes are expected to have similar expression profiles and topological structures, a scalable non-linear graph fusion technique, termed as ScaNGraF, is proposed to learn a disease-dependent functional similarity network from the co-expression and common neighbor based similarity networks. The proposed ScaNGraF, which is based on message passing algorithm, efficiently combines the shared and complementary information provided by different data sources with significantly lower computational cost. A new measure, termed as DiCoIN, is introduced to evaluate the quality of a learned affinity network. The performance of the proposed graph fusion technique and gene selection algorithm is extensively compared with that of some existing methods, using several cancer data sets.
Intelligent Information and Database Systems, 2017
The most important objective of human genetics research is the discovery of genes associated to a... more The most important objective of human genetics research is the discovery of genes associated to a disease. In this respect, a new algorithm for gene selection is presented, which integrates wisely the information from expression profiles of genes and protein-protein interaction networks. The rough hypercuboid approach is used for identifying differentially expressed genes from the microarray, while a new measure of similarity is proposed to exploit the interaction network of proteins and therefore, determine the pairwise functional similarity of proteins. The proposed algorithm aims to maximize the relevance and functional similarity, and utilizes it as an objective function for the identification of a subset of genes that it predicts as disease genes. The performance of the proposed algorithm is compared with other related methods using some cancer associated data sets.
IEEE/ACM transactions on computational biology and bioinformatics, Jan 3, 2016
One of the most significant research issues in functional genomics is insilico identification of ... more One of the most significant research issues in functional genomics is insilico identification of disease related genes. In this regard, the paper presents a new gene selection algorithm, termed as SiFS, for identification of disease genes. It integrates the information obtained from interaction network of proteins and gene expression profiles. The proposed SiFS algorithm culls out a subset of genes from microarray data as disease genes by maximizing both significance and functional similarity of the selected gene subset. Based on the gene expression profiles, the significance of a gene with respect to another gene is computed using mutual information. On the other hand, a new measure of similarity is introduced to compute the functional similarity between two genes. Information derived from the protein-protein interaction network forms the basis of the proposed SiFS algorithm. The performance of the proposed gene selection algorithm and new similarity measure, is compared with that ...
Lecture Notes in Computer Science, 2015
One of the important problems in functional genomics is how to select the disease genes. In this ... more One of the important problems in functional genomics is how to select the disease genes. In this regard, the paper presents a new similarity measure to compute the functional similarity between two genes. It is based on the information of protein-protein interaction networks. A new gene selection algorithm is introduced to identify disease genes, integrating judiciously the information of gene expression profiles and protein-protein interaction networks. The proposed algorithm selects a set of genes from microarray data as disease genes by maximizing the relevance and functional similarity of the selected genes. The performance of the proposed algorithm, along with a comparison with other related methods, is demonstrated on colorectal cancer data set.
Information Sciences, 2017
One of the important problems in functional genomics is how to select the disease genes. In this ... more One of the important problems in functional genomics is how to select the disease genes. In this regard, the paper presents a new gene selection algorithm, termed as RelSim, to identify disease genes. It integrates judiciously the information of gene expression profiles and protein-protein interaction networks. A new similarity measure is introduced to compute the functional similarity between two genes. It is based on the information of protein-protein interaction networks. The new similarity measure offers an efficient way to calculate the functional similarity between two genes. The proposed algorithm selects a set of genes as disease genes, considering both microarray and protein-protein interaction data, by maximizing the relevance and functional similarity of the selected genes. While gene expression profiles are used to identify differentially expressed genes, the proteinprotein interaction networks help to compute the functional similarity among genes. The performance of the proposed algorithm, along with a comparison with other related methods, is demonstrated on several colon cancer data sets.
Lecture Notes in Computer Science, 2014
This study makes use of non-linear unmixing model to unmix pixels of hyperspectral imagery in a h... more This study makes use of non-linear unmixing model to unmix pixels of hyperspectral imagery in a heterogenous mangrove forest. This model takes into account the multi-path effects of radiation between endmember spectra that may occur before final interception by the sensor. Non linear models represent naturally occurring situations more accurately such as that commonly found within the mangrove forests where a variety of species co-exist as a mixed stand. This paper analyses the classification accuracy of linear and non-linear unmixing models for discrimination of mangrove species in the Sunderban Delta, India. On analysis, it has been found that linear unmixing has successfully identified mangrove species which exist as a pure patch whereas the non-linear model has been able to discriminate between species more accurately in a heterogenous patch. 10 dominant mangrove species have been identified in the study area and the results validated through field visits and RMSE values.
2013 International Conference on Communication and Signal Processing, 2013
The present study is the first attempt to make use of hyperspectral data in the Sunderban eco-geo... more The present study is the first attempt to make use of hyperspectral data in the Sunderban eco-geographic province to enable species level discrimination of mangroves. Our objective here, is to unmix hypespectral images using non-linear spectral unmixing techniques by taking into account the higher order interactions of light that occurs among different target endmembers (mangrove species). The linear mixing models have also provided a good abstraction of the mixing process, but some naturally occurring situations exist where nonlinear models provide the most accurate assessment of endmember abundance. It has been noted that the nonlinear models have been successful in estimating the abundances for the different endmembers in places where the non-linear situation is prevalent within the mangrove forests with several layers of tree canopy considered to be present one above the other. For such a situation, the second order interaction among the endmembers have been considered. This paper applies and compares the classification accuracy of non-linear techniques using the two methods shown in the Bilinear Model. They are Nascimento's and Fan's Bilinear model for unmixing hyperspectral images. On comparison, Fan's model has been able to classify mixed mangrove species more accurately than Nascimento's model. It has been possible to identify 7 dominant pure and mixed mangrove species present in the study area.
IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2020
In the past few decades, both gene expression data and protein-protein interaction (PPI) networks... more In the past few decades, both gene expression data and protein-protein interaction (PPI) networks have been extensively studied, due to their ability to depict important characteristics of disease-associated genes. In this regard, the paper presents a new gene prioritization algorithm to identify and prioritize cancer-causing genes, integrating judiciously the complementary information obtained from two data sources. The proposed algorithm selects disease-causing genes by maximizing the importance of selected genes and functional similarity among them. A new quantitative index is introduced to evaluate the importance of a gene. It considers whether a gene exhibits a differential expression pattern across sick and healthy individuals, and has a strong connectivity in the PPI network, which are the important characteristics of a potential biomarker. As disease-associated genes are expected to have similar expression profiles and topological structures, a scalable non-linear graph fusion technique, termed as ScaNGraF, is proposed to learn a disease-dependent functional similarity network from the co-expression and common neighbor based similarity networks. The proposed ScaNGraF, which is based on message passing algorithm, efficiently combines the shared and complementary information provided by different data sources with significantly lower computational cost. A new measure, termed as DiCoIN, is introduced to evaluate the quality of a learned affinity network. The performance of the proposed graph fusion technique and gene selection algorithm is extensively compared with that of some existing methods, using several cancer data sets.
Intelligent Information and Database Systems, 2017
The most important objective of human genetics research is the discovery of genes associated to a... more The most important objective of human genetics research is the discovery of genes associated to a disease. In this respect, a new algorithm for gene selection is presented, which integrates wisely the information from expression profiles of genes and protein-protein interaction networks. The rough hypercuboid approach is used for identifying differentially expressed genes from the microarray, while a new measure of similarity is proposed to exploit the interaction network of proteins and therefore, determine the pairwise functional similarity of proteins. The proposed algorithm aims to maximize the relevance and functional similarity, and utilizes it as an objective function for the identification of a subset of genes that it predicts as disease genes. The performance of the proposed algorithm is compared with other related methods using some cancer associated data sets.
IEEE/ACM transactions on computational biology and bioinformatics, Jan 3, 2016
One of the most significant research issues in functional genomics is insilico identification of ... more One of the most significant research issues in functional genomics is insilico identification of disease related genes. In this regard, the paper presents a new gene selection algorithm, termed as SiFS, for identification of disease genes. It integrates the information obtained from interaction network of proteins and gene expression profiles. The proposed SiFS algorithm culls out a subset of genes from microarray data as disease genes by maximizing both significance and functional similarity of the selected gene subset. Based on the gene expression profiles, the significance of a gene with respect to another gene is computed using mutual information. On the other hand, a new measure of similarity is introduced to compute the functional similarity between two genes. Information derived from the protein-protein interaction network forms the basis of the proposed SiFS algorithm. The performance of the proposed gene selection algorithm and new similarity measure, is compared with that ...
Lecture Notes in Computer Science, 2015
One of the important problems in functional genomics is how to select the disease genes. In this ... more One of the important problems in functional genomics is how to select the disease genes. In this regard, the paper presents a new similarity measure to compute the functional similarity between two genes. It is based on the information of protein-protein interaction networks. A new gene selection algorithm is introduced to identify disease genes, integrating judiciously the information of gene expression profiles and protein-protein interaction networks. The proposed algorithm selects a set of genes from microarray data as disease genes by maximizing the relevance and functional similarity of the selected genes. The performance of the proposed algorithm, along with a comparison with other related methods, is demonstrated on colorectal cancer data set.
Information Sciences, 2017
One of the important problems in functional genomics is how to select the disease genes. In this ... more One of the important problems in functional genomics is how to select the disease genes. In this regard, the paper presents a new gene selection algorithm, termed as RelSim, to identify disease genes. It integrates judiciously the information of gene expression profiles and protein-protein interaction networks. A new similarity measure is introduced to compute the functional similarity between two genes. It is based on the information of protein-protein interaction networks. The new similarity measure offers an efficient way to calculate the functional similarity between two genes. The proposed algorithm selects a set of genes as disease genes, considering both microarray and protein-protein interaction data, by maximizing the relevance and functional similarity of the selected genes. While gene expression profiles are used to identify differentially expressed genes, the proteinprotein interaction networks help to compute the functional similarity among genes. The performance of the proposed algorithm, along with a comparison with other related methods, is demonstrated on several colon cancer data sets.