Kuldip K. Paliwal

Griffith University, Southport, Queensland, Australia

Are you Kuldip K. Paliwal?

Claim your profile

Publications (275)200.51 Total impact

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Because a nearly constant distance between two neighbouring Cα atoms, local backbone structure of proteins can be represented accurately by the angle between Cαi−1CαiCαi+1 (θ) and a dihedral angle rotated about the CαiCαi+1 bond (τ). θ and τ angles, as the representative of structural properties of three to four amino-acid residues, offer a description of backbone conformations that is complementary to φ and ψ angles (single residue) and secondary structures (>3 residues). Here, we report the first machine-learning technique for sequence-based prediction of θ and τ angles. Predicted angles based on an independent test have a mean absolute error of 9° for θ and 34° for τ with a distribution on the θ-τ plane close to that of native values. The average root-mean-square distance of 10-residue fragment structures constructed from predicted θ and τ angles is only 1.9Å from their corresponding native structures. Predicted θ and τ angles are expected to be complementary to predicted ϕ and ψ angles and secondary structures for using in model validation and template-based as well as template-free structure prediction. The deep neural network learning technique is available as an on-line server called Structural Property prediction with Integrated DEep neuRal network (SPIDER) at http://sparks-lab.org. © 2014 Wiley Periodicals, Inc.
    Journal of Computational Chemistry 09/2014; · 3.84 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In protein fold recognition, a protein is classified into one of its folds. The recognition of a protein fold can be done by employing feature extraction methods to extract relevant information from protein sequences and then by using a classifier to accurately recognize novel protein sequences. In the past, several feature extraction methods have been developed but with limited recognition accuracy only. Protein sequences of varying lengths share the same fold and therefore they are very similar (in a fold) if aligned properly. To this, we develop an amino acid alignment method to extract important features from protein sequences by computing dissimilarity distances between proteins. This is done by measuring distance between two respective position specific scoring matrices of protein sequences which is used in a support vector machine framework. We demonstrated the effectiveness of the proposed method on several benchmark datasets. The method shows significant improvement in the fold recognition performance which is in the range of 4.3% to 7.6% compared to several other existing feature extraction methods.
    Journal of Theoretical Biology 03/2014; · 2.35 Impact Factor
  • Source
  • Source
    Belinda Schwerin, Kuldip Paliwal
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper we investigate an alternate, RI-modulation (R = real, I = imaginary) AMS framework for speech enhancement, in which the real and imaginary parts of the modulation signal are processed in secondary AMS procedures. This framework offers theoretical advantages over the previously proposed modulation AMS frameworks in that noise is additive in the modulation signal and noisy acoustic phase is not used to reconstruct speech. Using the MMSE magnitude estimation to modify modulation magnitude spectra, initial experiments presented in this work evaluate if these advantages translate into improvements in processed speech quality. The effect of speech presence uncertainty and log-domain processing on MMSE magnitude estimation in the RI-modulation framework is also investigated. Finally, a comparison of different enhancement approaches applied in the RI-modulation framework is presented. Using subjective and objective experiments as well as spectrogram analysis, we show that RI-modulation MMSE magnitude estimation with speech presence uncertainty produces stimuli which has a higher preference by listeners than the other RI-modulation types. In comparisons to similar approaches in the modulation AMS framework, results showed that the theoretical advantages of the RI-modulation framework did not translate to an improvement in overall quality, with both frameworks yielding very similar sounding stimuli, but a clear improvement (compared to the corresponding modulation AMS based approach) in speech intelligibility was found.
    Speech Communication. 01/2014; 58:49–68.
  • [Show abstract] [Hide abstract]
    ABSTRACT: As the performance of hardware is limited, the focus has been to develop objective, optimized and computationally efficient algorithms for a given task. To this extent, fixed-point and approximate algorithms have been developed and successfully applied in many areas of research. In this paper we propose a feature selection method based on fixed-point algorithm and show its application in the field of human cancer classification using DNA microarray gene expression data. In the fixed-point algorithm, we utilize between-class scatter matrix to compute the leading eigenvector. This eigenvector has been used to select genes. In the computation of the eigenvector, the eigenvalue decomposition of the scatter matrix is not required which significantly reduces its computational complexity and memory requirement.
    International Journal of Knowledge-based and Intelligent Engineering Systems. 01/2014; 18(1):55-59.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In protein fold recognition, a protein is classified into one of its folds. The recognition of a protein fold can be done by employing feature extraction methods to extract relevant information from protein sequences and then by using a classifier to accurately recognize novel protein sequences. In the past, several feature extraction methods have been developed but with limited recognition accuracy only. Protein sequences of varying lengths share the same fold and therefore they are very similar (in a fold) if aligned properly. To this, we develop an amino acid alignment method to extract important features from protein sequences by computing dissimilarity distances between proteins. This is done by measuring distance between two respective position specific scoring matrices of protein sequences which is used in a support vector machine framework. We demonstrated the effectiveness of the proposed method on several benchmark datasets. The method shows significant improvement in the fold recognition performance which is in the range of 4.3–7.6% compared to several other existing feature extraction methods.
    Journal of Theoretical Biology 01/2014; 354:137–145. · 2.35 Impact Factor
  • Roger Chappel, Kuldip Paliwal
    [Show abstract] [Hide abstract]
    ABSTRACT: This work highlights the need to adapt teaching methods in digital signal processing (DSP) on speech to suit shifts in generational learning behavior, furthermore it suggests the use of integrating theory into a practical smart phone or tablet application as a means to bridge the gap between traditional teaching styles and current learning styles. The application presented here is called “Speech Enhancement for Android (SEA)” and aims at assisting in the development of an intuitive understanding of course content by allowing students to interact with theoretical concepts through their personal device. SEA not only allows the student to interact with speech processing methods, but also enables the student to interact with their surrounding environment by recording and processing their own voice. A case study on students studying DSP for speech processing found that by using SEA as an additional learning tool enhanced their understanding and helped to motivate students to engage in course work by way of having ready access to interactive content on a hand held device. This paper describes the platform in detail acting as a road-map for education institutions, and how it can be integrated into a DSP based speech processing education framework.
    Speech Communication. 01/2014; 57:13–38.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Prediction of the structural classes of proteins can provide important information about their functionalities as well as their major tertiary structures. It is also considered as an important step towards protein structure prediction problem. Despite all the efforts have been made so far, finding a fast and accurate computational approach to solve protein structural class prediction problem still remains a challenging problem in bioinformatics and computational biology. In this study we propose segmented distribution and segmented auto covariance feature extraction methods to capture local and global discriminatory information from evolutionary profiles and predicted secondary structure of the proteins. By applying SVM to our extracted features, for the first time we enhance the protein structural class prediction accuracy to over 90% and 85% for two popular low-homology benchmarks that have been widely used in the literature. We report 92.2% and 86.3% prediction accuracies for 25PDB and 1189 benchmarks which are respectively up to 7.9% and 2.8% better than previously reported results for these two benchmarks. By proposing segmented distribution and segmented auto covariance feature extraction methods to capture local and global discriminatory information from evolutionary profiles and predicted secondary structure of the proteins, we are able to enhance the protein structural class prediction performance significantly.
    BMC Genomics 01/2014; 15 Suppl 1:S2. · 4.40 Impact Factor
  • Source
    Belinda Schwerin, Kuldip Paliwal
    [Show abstract] [Hide abstract]
    ABSTRACT: The speech transmission index (STI) is a well known measure of intelligibility, most suited to the evaluation of speech intelligibility in rooms, with stimuli subjected to additive noise and reverberance. However, STI and its many variations do not effectively represent the intelligibility of stimuli containing non-linear distortions such as those resulting from processing by enhancement algorithms. In this paper, we revisit the STI approach and propose a variation which processes the modulation envelope in short-time segments, requiring only an assumption of quasi-stationarity (rather than the stationarity assumption of STI) of the modulation signal. Results presented in this work show that the proposed approach improves the measures correlation to subjective intelligibility scores compared to traditional STI for a range of noise types and subjected to different enhancement approaches. The approach is also shown to have higher correlation than other coherence, correlation and distance measures tested, but is unsuited to the evaluation of stimuli heavily distorted with (for example) masking based processing, where an alternative approach such as STOI is recommended.
    Speech Communication. 01/2014;
  • [Show abstract] [Hide abstract]
    ABSTRACT: Investigation of genes, using data analysis and computer-based methods, has gained widespread attention in solving human cancer classification problem. DNA microarray gene expression datasets are readily utilized for this purpose. In this paper, we propose a feature selection method using improved regularized linear discriminant analysis technique to select important genes, crucial for human cancer classification problem. The experiment is conducted on several DNA microarray gene expression datasets and promising results are obtained when compared with several other existing feature selection methods.
    Machine Vision and Applications 01/2014; 25(3). · 1.10 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Protein fold recognition (PFR) is considered as an important step towards the protein structure prediction problem. Despite all the efforts that have been made so far, finding an accurate and fast computational approach to solve the PFR still remains a challenging problem for bioinformatics and computational biology. In this study, we propose the concept of segmented-based feature extraction technique to provide local evolutionary information embedded in position specific scoring matrix (PSSM) and structural information embedded in the predicted secondary structure of proteins using SPINE-X. We also employ the concept of occurrence feature to extract global discriminatory information from PSSM and SPINE-X. By applying a support vector machine (SVM) to our extracted features, we enhance the protein fold prediction accuracy for 7.4 percent over the best results reported in the literature. We also report 73.8 percent prediction accuracy for a data set consisting of proteins with less than 25 percent sequence similarity rates and 80.7 percent prediction accuracy for a data set with proteins belonging to 110 folds with less than 40 percent sequence similarity rates. We also investigate the relation between the number of folds and the number of features being used and show that the number of features should be increased to get better protein fold prediction results when the number of folds is relatively large.
    IEEE/ACM Transactions on Computational Biology and Bioinformatics 01/2014; 11(3):510-519. · 1.62 Impact Factor
  • Alok Sharma, Kuldip K. Paliwal, Seiya Imoto, Satoru Miyano
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper we present QR based principal component analysis (PCA) method. Similar to the singular value decomposition (SVD) based PCA method this method is numerically stable. We have carried out analytical comparison as well as numerical comparison (on Matlab software) to investigate the performance (in terms of computational complexity) of our method. The computational complexity of SVD based PCA is around $ 14dn^{2} $ flops (where d is the dimensionality of feature space and n is the number of training feature vectors); whereas the computational complexity of QR based PCA is around $ 2dn^{2} \, + \,2dth $ flops (where t is the rank of data covariance matrix and h is the dimensionality of reduced feature space). It is observed that the QR based PCA is more efficient in terms of computational complexity.
    International Journal of Machine Learning and Cybernetics. 12/2013;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Protein Fold Recognition (PFR) is considered as a critical step towards the protein structure prediction problem. PFR has also a profound impact on protein function determination and drug design. Despite all the enhancements achieved by using pattern recognition-based approaches in the protein fold recognition, it still remains un-solved and its prediction accuracy remains limited. In this study, we propose a new model based on the concept of mixture of physicochem-ical and evolutionary features. We then design and develop two novel overlapping segmented-based feature extraction methods. Our proposed methods capture more local and global discriminatory information than previously proposed approaches for this task. We investigate the impact of our novel approaches using the most promising attributes selected from a wide range of physicochemical-based attributes (117 attributes) which is also explored experimentally in this study. By using Support Vector Machine (SVM) our experimental results demonstrate a signifi-cant improvement (up to 5.7%) in the protein fold prediction accuracy compared to previously reported results found in the literature.
    26th Australasian Joint Conference on Artificial Intelligence, Dunedin, New Zealand; 12/2013
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Assigning a protein into one of its folds is a transitional step for discovering three dimensional protein structure, which is a challenging task in bimolecular (biological) science. The present research focuses on: 1) the development of classifiers, and 2) the development of feature extraction techniques based on syntactic and/or physicochemical properties. Apart from the above two main categories of research, we have shown that the selection of physicochemical attributes of the amino acids is an important step in protein fold recognition and has not been explored adequately. We have presented a multi-dimensional successive feature selection (MD-SFS) approach to systematically select attributes. The proposed method is applied on protein sequence data and an improvement of around 24% in fold recognition has been noted when selecting attributes appropriately. The MD-SFS has been applied successfully in selecting physicochemical attributes of the amino acids. The selected attributes show improved protein fold recognition performance.
    BMC Bioinformatics 07/2013; 14(1):233. · 3.02 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Protein fold recognition (PFR) is considered as an important step towards the protein structure prediction problem. It also provides crucial information about the functionality of the proteins. Despite all the efforts that have been made during the past two decades, finding an accurate and fast computational approach to solve PFR still remains a challenging problem for bioinformatics and computational biology. It has been shown that extracting features which contain significant lo-cal and global discriminatory information plays a key role in addressing this problem. In this study, we propose the concept of segmented-based feature extraction technique to provide local evolutionary information embedded in Position Specific Scoring Matrix (PSSM) and structural information embedded in the predicted secondary structure of proteins using SPINE-X. We also employ the concept of occurrence feature to extract global discriminatory information from PSSM and SPINE-X. By applying a Support Vector Machine (SVM) to our extracted features, we enhance the protein fold prediction accuracy to 7.4% over the best results reported in the literature.
    Eighth IAPR International Conference on Pattern Recognition in Bioinformatics, Nice, France; 06/2013
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Determining the structural class of a given protein can pro-vide important information about its functionality and its general ter-tiary structure. In the last two decades, the protein structural class pre-diction problem has attracted tremendous attention and its prediction accuracy has been significantly improved. Features extracted from the Position Specific Scoring Matrix (PSSM) have played an important role to achieve this enhancement. However, this information has not been adequately explored since the protein structural class prediction accu-racy relying on PSSM for feature extraction still remains limited. In this study, to explore this potential, we propose segmentation-based feature extraction technique based on the concepts of amino acids' distribution and auto covariance. By applying a Support Vector Machine (SVM) to our extracted features, we enhance protein structural class prediction ac-curacy up to 16% over similar studies found in the literature. We achieve over 90% and 80% prediction accuracies for 25PDB and 1189 benchmarks respectively by solely relying on the PSSM for feature extraction.
    Eighth IAPR International Conference on Pattern Recognition in Bioinformatics, Nice, France; 06/2013
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Better understanding of structural class of a given protein reveals important information about its overall folding type and its domain. It can also be directly used to provide critical information on general tertiary structure of a protein which has a profound impact on protein function determination and drug design. Despite tremendous enhancements made by pattern recognition-based approaches to solve this problem, it still remains as an unsolved issue for bioinformatics that demands more attention and exploration. In this study, we propose a novel feature extraction model that incorporates physicochemical and evolutionary-based information simultaneously. We also propose overlapped segmented distribution and autocorrelation-based feature extraction methods to provide more local and global discriminatory information. The proposed feature extraction methods are explored for 15 most promising attributes that are selected from a wide range of physicochemical-based attributes. Finally, by applying an ensemble of different classifiers namely, Adaboost.M1, LogitBoost, naive Bayes, multilayer perceptron (MLP), and support vector machine (SVM) we show enhancement of the protein structural class prediction accuracy for four popular benchmarks.
    IEEE/ACM transactions on computational biology and bioinformatics / IEEE, ACM 05/2013; 10(3):564-575. · 2.25 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Discovering a three dimensional structure of a protein is a challenging task in biological science. Classifying a protein into one of its folds is an intermediate step for deciphering the three dimensional protein structure. The protein fold recognition can be done by developing feature extraction techniques to accurately extract all the relevant information from a protein sequence and then by employing a suitable classifier to label an unknown protein. Several feature extraction techniques have been developed in the past but with limited recognition accuracy only. In this work, we have developed a feature extraction technique which is based on bi-grams computed directly from Position Specific Scoring Matrices and demonstrated its effectiveness on a benchmark dataset. The proposed technique exhibits an absolute improvement of around 10% compared with existing feature extraction techniques.
    Journal of Theoretical Biology 12/2012; · 2.35 Impact Factor
  • Source
    Belinda Schwerin, Kuldip Paliwal
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper investigates an alternate modulation (RI-modulation) AMS-based framework for speech enhancement, in which real and imaginary parts of the modulation signal are processed in secondary AMS procedures. We propose to apply MMSE magnitude estimation in this framework, and using subjective experiments, show that MMSE RI-modulation magnitude estimation produces stimuli which is preferred by listeners over RI-modulation spectral subtraction. Experiments presented also show that while this framework is suited to speech enhancement and offers theoretical advantages over the modulation AMS framework, resulting stimuli had similar quality to that produced by the corresponding modulation AMS-based method. Index Terms: speech enhancement, MMSE short-time spectral magnitude estimator, modulation magnitude spectrum
    SST, Sydney, Australia; 12/2012
  • Alok Sharma, Kuldip K. Paliwal
    [Show abstract] [Hide abstract]
    ABSTRACT: A two-stage linear discriminant analysis technique is proposed that utilizes both the null space and range space information of scatter matrices. The technique regularizes both the between-class scatter and within-class scatter matrices to extract the discriminant information. The regularization is conducted in parallel to give two orientation matrices. These orientation matrices are concatenated to form the final orientation matrix. The proposed technique is shown to provide better classification performance on face recognition datasets than the other techniques.
    Pattern Recognition Letters 07/2012; 33(9):1157–1162. · 1.27 Impact Factor

Publication Stats

3k Citations
200.51 Total Impact Points

Institutions

  • 1995–2014
    • Griffith University
      • School of Engineering
      Southport, Queensland, Australia
  • 2012
    • University of the South Pacific
      • School of Engineering and Physics
      Suva City, Central, Fiji
  • 2003
    • Idiap Research Institute
      Martigny, Valais, Switzerland
    • Norwegian University of Science and Technology
      Nidaros, Sør-Trøndelag, Norway
  • 1981–1999
    • Tata Institute of Fundamental Research
      Mumbai, Mahārāshtra, India
  • 1996
    • Carnegie Mellon University
      Pittsburgh, Pennsylvania, United States
  • 1991
    • AT&T Labs
      Austin, Texas, United States
    • University of Michigan
      • Department of Electrical Engineering and Computer Science (EECS)
      Ann Arbor, MI, United States