Computing and Information Systems - Research Publications
Permanent URI for this collection
Search Results
1 - 10 of 16
-
ItemExploiting sparsity and low-rank structure for the recovery of multi-slice breast MRIs with reduced sampling error(SPRINGER HEIDELBERG, 2012-09)It has been shown that, magnetic resonance images (MRIs) with sparsity representation in a transformed domain, e.g. spatial finite-differences (FD), or discrete cosine transform (DCT), can be restored from undersampled k-space via applying current compressive sampling theory. The paper presents a model-based method for the restoration of MRIs. The reduced-order model, in which a full-system-response is projected onto a subspace of lower dimensionality, has been used to accelerate image reconstruction by reducing the size of the involved linear system. In this paper, the singular value threshold (SVT) technique is applied as a denoising scheme to reduce and select the model order of the inverse Fourier transform image, and to restore multi-slice breast MRIs that have been compressively sampled in k-space. The restored MRIs with SVT for denoising show reduced sampling errors compared to the direct MRI restoration methods via spatial FD, or DCT. Compressive sampling is a technique for finding sparse solutions to underdetermined linear systems. The sparsity that is implicit in MRIs is to explore the solution to MRI reconstruction after transformation from significantly undersampled k-space. The challenge, however, is that, since some incoherent artifacts result from the random undersampling, noise-like interference is added to the image with sparse representation. These recovery algorithms in the literature are not capable of fully removing the artifacts. It is necessary to introduce a denoising procedure to improve the quality of image recovery. This paper applies a singular value threshold algorithm to reduce the model order of image basis functions, which allows further improvement of the quality of image reconstruction with removal of noise artifacts. The principle of the denoising scheme is to reconstruct the sparse MRI matrices optimally with a lower rank via selecting smaller number of dominant singular values. The singular value threshold algorithm is performed by minimizing the nuclear norm of difference between the sampled image and the recovered image. It has been illustrated that this algorithm improves the ability of previous image reconstruction algorithms to remove noise artifacts while significantly improving the quality of MRI recovery.
-
ItemA new approach to enhance the performance of decision tree for classifying gene expression data(BMC Proceedings, 2013)BACKGROUND: Gene expression data classification is a challenging task due to the large dimensionality and very small number of samples. Decision tree is one of the popular machine learning approaches to address such classification problems. However, the existing decision tree algorithms use a single gene feature at each node to split the data into its child nodes and hence might suffer from poor performance specially when classifying gene expression dataset. RESULTS: By using a new decision tree algorithm where, each node of the tree consists of more than one gene, we enhance the classification performance of traditional decision tree classifiers. Our method selects suitable genes that are combined using a linear function to form a derived composite feature. To determine the structure of the tree we use the area under the Receiver Operating Characteristics curve (AUC). Experimental analysis demonstrates higher classification accuracy using the new decision tree compared to the other existing decision trees in literature. CONCLUSION: We experimentally compare the effect of our scheme against other well known decision tree techniques. Experiments show that our algorithm can substantially boost the classification performance of the decision tree.
-
ItemBetaSearch: a new method for querying β-residue motifs.(Springer Science and Business Media LLC, 2012-07-30)BACKGROUND: Searching for structural motifs across known protein structures can be useful for identifying unrelated proteins with similar function and characterising secondary structures such as β-sheets. This is infeasible using conventional sequence alignment because linear protein sequences do not contain spatial information. β-residue motifs are β-sheet substructures that can be represented as graphs and queried using existing graph indexing methods, however, these approaches are designed for general graphs that do not incorporate the inherent structural constraints of β-sheets and require computationally-expensive filtering and verification procedures. 3D substructure search methods, on the other hand, allow β-residue motifs to be queried in a three-dimensional context but at significant computational costs. FINDINGS: We developed a new method for querying β-residue motifs, called BetaSearch, which leverages the natural planar constraints of β-sheets by indexing them as 2D matrices, thus avoiding much of the computational complexities involved with structural and graph querying. BetaSearch exhibits faster filtering, verification, and overall query time than existing graph indexing approaches whilst producing comparable index sizes. Compared to 3D substructure search methods, BetaSearch achieves 33 and 240 times speedups over index-based and pairwise alignment-based approaches, respectively. Furthermore, we have presented case-studies to demonstrate its capability of motif matching in sequentially dissimilar proteins and described a method for using BetaSearch to predict β-strand pairing. CONCLUSIONS: We have demonstrated that BetaSearch is a fast method for querying substructure motifs. The improvements in speed over existing approaches make it useful for efficiently performing high-volume exploratory querying of possible protein substructural motifs or conformations. BetaSearch was used to identify a nearly identical β-residue motif between an entirely synthetic (Top7) and a naturally-occurring protein (Charcot-Leyden crystal protein), as well as identifying structural similarities between biotin-binding domains of avidin, streptavidin and the lipocalin gamma subunit of human C8.
-
ItemRetinal Image Matching Using Hierarchical Vascular Features(HINDAWI LTD, 2011)We propose a method for retinal image matching that can be used in image matching for person identification or patient longitudinal study. Vascular invariant features are extracted from the retinal image, and a feature vector is constructed for each of the vessel segments in the retinal blood vessels. The feature vectors are represented in a tree structure with maintaining the vessel segments actual hierarchical positions. Using these feature vectors, corresponding images are matched. The method identifies the same vessel in the corresponding images for comparing the desired feature(s). Initial results are encouraging and demonstrate that the proposed method is suitable for image matching and patient longitudinal study.
-
ItemA fast indexing approach for protein structure comparison(BMC, 2010)BACKGROUND: Protein structure comparison is a fundamental task in structural biology. While the number of known protein structures has grown rapidly over the last decade, searching a large database of protein structures is still relatively slow using existing methods. There is a need for new techniques which can rapidly compare protein structures, whilst maintaining high matching accuracy. RESULTS: We have developed IR Tableau, a fast protein comparison algorithm, which leverages the tableau representation to compare protein tertiary structures. IR tableau compares tableaux using information retrieval style feature indexing techniques. Experimental analysis on the ASTRAL SCOP protein structural domain database demonstrates that IR Tableau achieves two orders of magnitude speedup over the search times of existing methods, while producing search results of comparable accuracy. CONCLUSION: We show that it is possible to obtain very significant speedups for the protein structure comparison problem, by employing an information retrieval style approach for indexing proteins. The comparison accuracy achieved is also strong, thus opening the way for large scale processing of very large protein structure databases.
-
ItemBayesian statistical modelling of human protein interaction network incorporating protein disorder information.(Springer Science and Business Media LLC, 2010-01-25)BACKGROUND: We present a statistical method of analysis of biological networks based on the exponential random graph model, namely p2-model, as opposed to previous descriptive approaches. The model is capable to capture generic and structural properties of a network as emergent from local interdependencies and uses a limited number of parameters. Here, we consider one global parameter capturing the density of edges in the network, and local parameters representing each node's contribution to the formation of edges in the network. The modelling suggests a novel definition of important nodes in the network, namely social, as revealed based on the local sociality parameters of the model. Moreover, the sociality parameters help to reveal organizational principles of the network. An inherent advantage of our approach is the possibility of hypotheses testing: a priori knowledge about biological properties of the nodes can be incorporated into the statistical model to investigate its influence on the structure of the network. RESULTS: We applied the statistical modelling to the human protein interaction network obtained with Y2H experiments. Bayesian approach for the estimation of the parameters was employed. We deduced social proteins, essential for the formation of the network, while incorporating into the model information on protein disorder. Intrinsically disordered are proteins which lack a well-defined three-dimensional structure under physiological conditions. We predicted the fold group (ordered or disordered) of proteins in the network from their primary sequences. The network analysis indicated that protein disorder has a positive effect on the connectivity of proteins in the network, but do not fully explains the interactivity. CONCLUSIONS: The approach opens a perspective to study effects of biological properties of individual entities on the structure of biological networks.
-
ItemCombining real and virtual graphs to enhance data clustering(IEEE, 2010-11-18)
-
ItemScoreFinder: A Method for Collaborative Quality Inference on User-Generated Content(IEEE COMPUTER SOC, 2010)
-
ItemLayered Approach Using Conditional Random Fields for Intrusion Detection(IEEE COMPUTER SOC, 2010-01-01)
-
ItemOptimized algorithms for predictive range and KNN queries on moving objects(PERGAMON-ELSEVIER SCIENCE LTD, 2010-12)