C. Raghavendra Rao

Correlating Fuzzy and Rough Clustering

With the gaining popularity of rough clustering, soft computing research community is studying relationships between rough and fuzzy clustering as well as their relative advantages. Both rough and fuzzy clustering are less restrictive than conventional clustering. Fuzzy clustering memberships are more descriptive than rough clustering. In some cases, descriptive fuzzy clustering may be advantageous, while in other cases it may lead to information overload. Many applications demand use of combined approach to exploit inherent strengths of each technique. Our objective is to examine correlation between these two techniques. This paper provides an experimental description of how rough clustering results can be correlated with fuzzy clustering results. We illustrate procedural steps to map fuzzy membership clustering to rough clustering. However, such a conversion is not always necessary, especially if one only needs lower and upper approximations. Experiments also show that descriptive fuzzy clustering may not always (particularly for high dimensional objects) produce results that are as accurate as direct application of rough clustering. We present analysis of the results from both the techniques.

Topology Aware Task Stealing for On-chip NUMA Multi-core Processors☆

Abstract “The On Chip NUMA Architectures (OCNA) introduce a new challenge namely memory-latency to the scheduling methods. The language run-times and libraries try to explore the processing power of these multiple cores by mapping the user-created tasks on to these cores by using suitable scheduling algorithms with load balancing support to improve throughput. The popular load balancing techniques used are work-sharing and work-stealing and many run-time systems such as Cilk, TBB and wool implement task stealing algorithm to schedule the tasks on to the cores by multiplexing the program generated tasks on to the native worker threads supported by the operating system. But the task stealing strategy applied in present run-time systems assumes the sharing the last level cache (LLC) and common shared bus among all cores on Chip Multi Processor. It tries to optimize the utilization without considering the presence of multiple On Die DRAM controllers and their topological arrangements. Current task stealing technique also suffers from problem of randomly choosing the victim worker queue. In this paper we address these issues and propose a solution for these problems by suggesting few optimizations. Our proposed task stealing strategy dynamically analyzes the topology of the underlying hardware connections and models the group of cores and connections as a logical topology tree. This logical tree is translated into multiple worker pools called stealing domains. By restricting the task stealing within these domains, this strategy is implemented and shows an average of 1.24 times better performance on NAS Parallel Benchmark programs compared to popular runtimes Cilk and OpenMP.

Performance Evaluation of Mesh - Based Multicast Routing Protocols in MANET's

Multicasting is a challenging task that facilitates group communication among the nodes using the most efficient strategy to deliver the messages over each link of the network. In spite of significant research achievements in recent years, efficient and extendable multicast routing in Mobile Ad Hoc Networks (MANETs) is still a difficult issue. This paper proposes the comparison of ODMR and PUMA protocol. As per the simulation results PUMA is better than ODMR.

Rough set based quality of service design for service provisioning in clouds

Quality of Service (QoS) is a broad term used to describe the overall experience a user or application will receive over a network. A rough set based approach is used to design a modified Cloud-QoS Management Strategy (MC-QoSMS). MC-QoSMS is a component of cloud broker that is used to allocate resources based on Service Level Agreement between users and providers for Infrastructure as a Service (IaaS) provisioning of cloud. Concept of reduct from rough set theory is used to allocate the best service provider to the clouds user with minimum searching time. The performance of the proposed system has been analyzed in terms of number of requests. It is reported that the system outperformed random algorithm by 25% and the round robin algorithm by 30% for 100 requests.

Gaussian Variogram Model for Printing Technology Identification

Tampering of documents is monotonically growing by posing challenges to forensic scientists. There is a great need to develop alternative solutions for forensic characterization of printers. This paper analyzes documents printed by various printers and characterizes them for identification purposes. Present study focuses on developing a model Gaussian Variogram Model (GVM) for identifying the print technology which produced the given document. This method characterizes print technology based on spatial variability. Homogeneous color region of images are taken as samples for the GVM data generation. The generated GVM data is taken as input to generate Reduct based Decision Tree (RDT), which gives rules to identify the source printer for the given test data. Performance analysis of the model is also presented. Developed method assists the document examiner in finding basic print pattern of printers and it is also helpful in classifying different print technology.

Automatic Gap Identification towards Efficient Contour Line Reconstruction in Topographic Maps

Automatic extraction and vectorization of contour lines from color topographic maps is an important precursor to obtaining useful information for many vector based GIS applications. In this work, a novel hybridized algorithm is developed for reconstructing the extracted contour lines from color topographic map. The extraction of contour lines from a topographic map leads to broken contour lines due to inherent characteristics of the map, thus posing a challenging problem of identifying gaps and then filling them. This has been addressed by developing algorithms based on connected components, graph theory, Expectation Maximization (EM) and numerical methods. Our algorithm operates by isolating the segments of those contours which have gaps and achieves in reducing the complexity of the matching of such segments by employing the EM algorithm. We also present a new scheme of filling gaps present in thick contours without the application of thinning algorithms.

An Efficient Gaussian Kernel Based Fuzzy-Rough Set Approach for Feature Selection

Fuzzy-rough set based feature selection is highly useful for reducing data dimensionality of a hybrid decision system, but the reduct computation is computationally expensive. Gaussian kernel based fuzzy rough sets merges kernel method to fuzzy-rough sets for efficient feature selection. This works aims at improving the computational performance of existing reduct computation approach in Gaussian kernel based fuzzy rough sets by incorporation of vectorized (matrix, sub-matrix) operations. The proposed approach was extensively compared by experimentation with the existing approach and also with a fuzzy rough set based reduct approaches available in Rough set R package. Results establish the relevance of proposed modifications.

An Efficient Approach for Fuzzy Decision Reduct Computation

Fuzzy rough sets is an extension of classical rough sets for feature selection in hybrid decision systems. However, reduct computation using the fuzzy rough set model is computationally expensive. A modified quick reduct algorithm (MQRA) was proposed in literature for computing fuzzy decision reduct using Radzikowska-Kerry fuzzy rough set model. In this paper, we develop a simplified computational model for discovering positive region in Radzikowska-Kerry’s fuzzy rough set model. Theory is developed for validation of omission of absolute positive region objects without affecting the subsequent inferences. The developed theory is incorporated in MQRA resulting in algorithm Improved MQRA (IMQRA). The computations involved in IMQRA are modeled as vector operations for obtaining further optimizations at implementation level. The effectiveness of algorithm(s) is empirically demonstrated by comparative analysis with several existing reduct approaches for hybrid decision systems using fuzzy rough sets.

Finding minimal resource allocation in grid with reliability and trust computations using 2-way split backward search

This paper aims at solving the problem of minimally allocating resources on the grid to maximize the grid service reliability with trust integration using deterministic state space search. This project develops modeling and evaluation algorithms to evaluate the grid service reliability. Based on the grid service reliability evaluation, we present a model for the grid resource allocation problem which uses trust to effectively solve it. The quantification of reliability depends upon many factors. Amongst them Task Processing Time, Communication Time & Rate of Failure of grid elements are the three most important factors. The reliability and trust factors plays a vital role in decision making for which resource allocation is minimal. This reliability and trust factors contributes as an important ingredient to the scheduler and resource manager that makes them more efficient. In this work it is assumed that the arrival rate of failure of grid elements follows the Poisson process.

Seed based fuzzy decision reduct for hybrid decision systems

Fuzzy rough sets is an extension to classical rough sets. The fuzzy rough set model is useful in feature selection for hybrid decision systems. Fuzzy decision reduct uses Radzikowskas Fuzzy Rough Set model for feature selection in hybrid decision systems. The computational complexity of fuzzy decision reduct computation makes it not suitable for large hybrid decision systems. In this paper, an approach is developed for computing fuzzy decision reduct by seed reduct using a suitable discretization of quantitative conditional attributes. Fuzzy decision reduct is computed for original decision system by evolving over seed reduct. Theoretical analysis and experimental results on benchmark decision systems validate that the method has achieved significant computational gains over normal approach without loss of classification accuracy.