Distributed hoeffding trees for pocket data mining

Collaborative mining of distributed data streams in a mobile computing environment is referred to as Pocket Data Mining PDM. Hoeffding trees techniques have been experimentally and analytically validated for data stream classification. In this paper, we have proposed, developed and evaluated the adoption of distributed Hoeffding trees for classifying streaming data in PDM applications. We have identified a realistic scenario in which different users equipped with smart mobile devices run a local Hoeffding tree classifier on a subset of the attributes. Thus, we have investigated the mining of vertically partitioned datasets with possible overlap of attributes, which is the more likely case. Our experimental results have validated the efficiency of our proposed model achieving promising accuracy for real deployment.

Dynamic group communication for large-scale parallel data mining

Exascale systems are the next frontier in high-performance computing and are expected to deliver a performance of the order of 10^18 operations per second using massive multicore processors. Very large- and extreme-scale parallel systems pose critical algorithmic challenges, especially related to concurrency, locality and the need to avoid global communication patterns. This work investigates a novel protocol for dynamic group communication that can be used to remove the global communication requirement and to reduce the communication cost in parallel formulations of iterative data mining algorithms. The protocol is used to provide a communication-efficient parallel formulation of the k-means algorithm for cluster analysis. The approach is based on a collective communication operation for dynamic groups of processes and exploits non-uniform data distributions. Non-uniform data distributions can be either found in real-world distributed applications or induced by means of multidimensional binary search trees. The analysis of the proposed dynamic group communication protocol has shown that it does not introduce significant communication overhead. The parallel clustering algorithm has also been extended to accommodate an approximation error, which allows a further reduction of the communication costs. The effectiveness of the exact and approximate methods has been tested in a parallel computing system with 64 processors and in simulations with 1024 processing elements.

Scalable and fault tolerant failure detection and consensus

Future extreme-scale high-performance computing systems will be required to work under frequent component failures. The MPI Forum's User Level Failure Mitigation proposal has introduced an operation, MPI_Comm_shrink, to synchronize the alive processes on the list of failed processes, so that applications can continue to execute even in the presence of failures by adopting algorithm-based fault tolerance techniques. This MPI_Comm_shrink operation requires a fault tolerant failure detection and consensus algorithm. This paper presents and compares two novel failure detection and consensus algorithms. The proposed algorithms are based on Gossip protocols and are inherently fault-tolerant and scalable. The proposed algorithms were implemented and tested using the Extreme-scale Simulator. The results show that in both algorithms the number of Gossip cycles to achieve global consensus scales logarithmically with system size. The second algorithm also shows better scalability in terms of memory and network bandwidth usage and a perfect synchronization in achieving global consensus.

Distributed mining of molecular fragments

In real world applications sequential algorithms of data mining and data exploration are often unsuitable for datasets with enormous size, high-dimensionality and complex data structure. Grid computing promises unprecedented opportunities for unlimited computing and storage resources. In this context there is the necessity to develop high performance distributed data mining algorithms. However, the computational complexity of the problem and the large amount of data to be explored often make the design of large scale applications particularly challenging. In this paper we present the first distributed formulation of a frequent subgraph mining algorithm for discriminative fragments of molecular compounds. Two distributed approaches have been developed and compared on the well known National Cancer Institute’s HIV-screening dataset. We present experimental results on a small-scale computing environment.

Efficient mining of discriminative molecular fragments

Frequent pattern discovery in structured data is receiving an increasing attention in many application areas of sciences. However, the computational complexity and the large amount of data to be explored often make the sequential algorithms unsuitable. In this context high performance distributed computing becomes a very interesting and promising approach. In this paper we present a parallel formulation of the frequent subgraph mining problem to discover interesting patterns in molecular compounds. The application is characterized by a highly irregular tree-structured computation. No estimation is available for task workloads, which show a power-law distribution in a wide range. The proposed approach allows dynamic resource aggregation and provides fault and latency tolerance. These features make the distributed application suitable for multi-domain heterogeneous environments, such as computational Grids. The distributed application has been evaluated on the well known National Cancer Institute’s HIV-screening dataset.

Accessing biodiversity resources in computational environments from workflow applications

In the Biodiversity World (BDW) project we have created a flexible and extensible Web Services-based Grid environment for biodiversity researchers to solve problems in biodiversity and analyse biodiversity patterns. In this environment, heterogeneous and globally distributed biodiversity-related resources such as data sets and analytical tools are made available to be accessed and assembled by users into workflows to perform complex scientific experiments. One such experiment is bioclimatic modelling of the geographical distribution of individual species using climate variables in order to predict past and future climate-related changes in species distribution. Data sources and analytical tools required for such analysis of species distribution are widely dispersed, available on heterogeneous platforms, present data in different formats and lack interoperability. The BDW system brings all these disparate units together so that the user can combine tools with little thought as to their availability, data formats and interoperability. The current Web Servicesbased Grid environment enables execution of the BDW workflow tasks in remote nodes but with a limited scope. The next step in the evolution of the BDW architecture is to enable workflow tasks to utilise computational resources available within and outside the BDW domain. We describe the present BDW architecture and its transition to a new framework which provides a distributed computational environment for mapping and executing workflows in addition to bringing together heterogeneous resources and analytical tools.

Parallel Monte Carlo approach for integration of the rendering equation

This paper is addressed to the numerical solving of the rendering equation in realistic image creation. The rendering equation is integral equation describing the light propagation in a scene accordingly to a given illumination model. The used illumination model determines the kernel of the equation under consideration. Nowadays, widely used are the Monte Carlo methods for solving the rendering equation in order to create photorealistic images. In this work we consider the Monte Carlo solving of the rendering equation in the context of the parallel sampling scheme for hemisphere. Our aim is to apply this sampling scheme to stratified Monte Carlo integration method for parallel solving of the rendering equation. The domain for integration of the rendering equation is a hemisphere. We divide the hemispherical domain into a number of equal sub-domains of orthogonal spherical triangles. This domain partitioning allows to solve the rendering equation in parallel. It is known that the Neumann series represent the solution of the integral equation as a infinity sum of integrals. We approximate this sum with a desired truncation error (systematic error) receiving the fixed number of iteration. Then the rendering equation is solved iteratively using Monte Carlo approach. At each iteration we solve multi-dimensional integrals using uniform hemisphere partitioning scheme. An estimate of the rate of convergence is obtained using the stratified Monte Carlo method. This domain partitioning allows easy parallel realization and leads to convergence improvement of the Monte Carlo method. The high performance and Grid computing of the corresponding Monte Carlo scheme are discussed.

Novel material combinations for enhanced infrared filter performance

The introduction of non-toxic fluride compounds as direct replacements for Thorium Fluoride (ThF4) has renewed interest in the use of low index fluoride compounds in high performance infrared filters. This paper reports the results of an investigation into the effects of combining these low index materials, particularly Barium Fluoride (BaF2), with the high index material Lead Telluride (PbTe) in bandpass and edge filters. Infrared filter designs using conventional and the new material ombination are compared, and infrared filters using these material combinations have been manufactured and have been shown to suffer problems with residual stress. A possible solution to this problem utilising Zinc Sulphide (ZnS) layers with compensating compressive stress is discussed.

Acceleration and visualization of Dynamic Network Optimization

With the emerging prevalence of smart phones and 4G LTE networks, the demand for faster-better-cheaper mobile services anytime and anywhere is ever growing. The Dynamic Network Optimization (DNO) concept emerged as a solution that optimally and continuously tunes the network settings, in response to varying network conditions and subscriber needs. Yet, the DNO realization is still at infancy, largely hindered by the bottleneck of the lengthy optimization runtime. This paper presents the design and prototype of a novel cloud based parallel solution that further enhances the scalability of our prior work on various parallel solutions that accelerate network optimization algorithms. The solution aims to satisfy the high performance required by DNO, preliminarily on a sub-hourly basis. The paper subsequently visualizes a design and a full cycle of a DNO system. A set of potential solutions to large network and real-time DNO are also proposed. Overall, this work creates a breakthrough towards the realization of DNO.