Browsing by Subject "Graph"

Now showing 1 - 4 of 4

Open Access
A plug-in graph neural network to boost temporal sensitivity in fMRI analysis
(IEEE, 2024-09) Şıvgın, Irmak; Bedel, Hasan Atakan; Ozturk, Saban; Çukur, Tolga
Learning-based methods offer performance leaps over traditional methods in classification analysis of high-dimensional functional MRI (fMRI) data. In this domain, deep-learning models that analyze functional connectivity (FC) features among brain regions have been particularly promising. However, many existing models receive as input temporally static FC features that summarize inter-regional interactions across an entire scan, reducing the temporal sensitivity of classifiers by limiting their ability to leverage information on dynamic FC features of brain activity. To improve the performance of baseline classification models without compromising efficiency, here we propose a novel plug-in based on a graph neural network, GraphCorr, to provide enhanced input features to baseline models. The proposed plug-in computes a set of latent FC features with enhanced temporal information while maintaining comparable dimensionality to static features. Taking brain regions as nodes and blood-oxygen-level-dependent (BOLD) signals as node inputs, GraphCorr leverages a node embedder module based on a transformer encoder to capture dynamic latent representations of BOLD signals. GraphCorr also leverages a lag filter module to account for delayed interactions across nodes by learning correlational features of windowed BOLD signals across time delays. These two feature groups are then fused via a message passing algorithm executed on the formulated graph. Comprehensive demonstrations on three public datasets indicate improved classification performance for several state-of-the-art graph and convolutional baseline models when they are augmented with GraphCorr.
Open Access
Attributed relational graphs for cell nucleus segmentation in fluorescence microscopy images
(IEEE, 2013) Arslan, S.; Ersahin, T.; Cetin-Atalay, R.; Gunduz-Demir, C.
More rapid and accurate high-throughput screening in molecular cellular biology research has become possible with the development of automated microscopy imaging, for which cell nucleus segmentation commonly constitutes the core step. Although several promising methods exist for segmenting the nuclei of monolayer isolated and less-confluent cells, it still remains an open problem to segment the nuclei of more-confluent cells, which tend to grow in overlayers. To address this problem, we propose a new model-based nucleus segmentation algorithm. This algorithm models how a human locates a nucleus by identifying the nucleus boundaries and piecing them together. In this algorithm, we define four types of primitives to represent nucleus boundaries at different orientations and construct an attributed relational graph on the primitives to represent their spatial relations. Then, we reduce the nucleus identification problem to finding predefined structural patterns in the constructed graph and also use the primitives in region growing to delineate the nucleus borders. Working with fluorescence microscopy images, our experiments demonstrate that the proposed algorithm identifies nuclei better than previous nucleus segmentation algorithms. © 2012 IEEE.
Open Access
Parallel direct and hybrid methods based on row block partitioning for solving sparse linear systems
(2017-08) Torun, Fahreddin Şükrü
Solving system of linear equations is a kernel operation in many scienti c and industrial applications. These applications usually give rise to linear systems in which the coe cient matrix is very large and sparse. The need for solving these large and sparse systems within a reasonable time necessitates e cient and e ective parallel solution methods. In this thesis, three novel approaches are proposed for reducing the parallel solution time of linear systems. First, a new parallel algorithm, ParBaMiN, is proposed in order to nd the minimum 2-norm solution of underdetermined linear systems, where the coe cient matrix is in the form of column overlapping block diagonal. The conducted experiments demonstrate the scalability of ParBaMiN on both shared and distributed memory architectures. Secondly, a new graph theoretical partitioning method is introduced in order to reduce the number of iterations in block Cimmino algorithm. Experimental results validate the e ectiveness of the proposed partitioning method in terms of reducing the required number of iterations. Finally, we propose a new parallel hybrid method, BCDcols, which further reduces the number of iterations of block Cimmino algorithm for matrices with dense columns. BCDcols combines the block Cimmino iterative algorithm and a dense direct method for solving the system. Experimental results show that BCDcols signi cantly improves the convergence rate of block Cimmino method and hence reduces the parallel solution time.
Open Access
Scalable layout of large graphs on disk
(2015) Yaşar, Abdurrahman
We are witnessing an enormous growth in social networks as well as in the volume of data generated by them. As a consequence, processing this massive amount of data has become a major problem. An important portion of this data is in the form of graphs. In recent years, several graph processing and management systems emerged to handle large-scale graphs. The primary goal of these systems is to run graph algorithms in an efficient and scalable manner. Unlike relational data, graphs are semi-structured in nature. Thus, storing and accessing graph data using secondary storage requires new solutions that can provide locality of access for graph processing workloads. In this work, we propose a novel scalable disk layout technique for graphs, which aims at reducing the I/O cost of diskbased graph processing algorithms. To achieve this goal, we designed a scalable Map/Reduce-style method called ICBP, which can divide the graph into a series of disk blocks that contain sub-graphs with high locality. Furthermore, ICBP can order the resulting blocks on the disk to further reduce non-local accesses. We experimentally evaluated ICBP to showcase its scalability, layout quality, as well as the effectiveness of automatic parameter tuning for ICBP. We also deployed the graph layouts generated by ICBP to the Neo4j [1] graph database management system. Our experimental results show that the default layout results in 1.5 to 2.5 times higher running times compared to ICBP.