Parallel matrix inversion techniques

In this paper, we present techniques for inverting sparse, symmetric and positive definite matrices on parallel and distributed computers. We propose two algorithms, one for SIMD implementation and the other for MIMD implementation. These algorithms are modified versions of Gaussian elimination and they take into account the sparseness of the matrix. Our algorithms perform better than the general parallel Gaussian elimination algorithm. In order to demonstrate the usefulness of our technique, we implemented the snake problem using our sparse matrix algorithm. Our studies reveal that the proposed sparse matrix inversion algorithm significantly reduces the time taken for obtaining the solution of the snake problem. In this paper, we present the results of our experimental work.

Computing of high breakdown regression estimators without sorting on graphics processing units

We present an approach to computing high-breakdown regression estimators in parallel on graphics processing units (GPU).We show that sorting the residuals is not necessary, and it can be substituted by calculating the median. We present and compare various methods to calculate the median and order statistics on GPUs. We introduce an alternative method based on the optimization of a convex function, and showits numerical superiority when calculating the order statistics of very large arrays on GPUs.

Internet and distributed computing advancements : theoretical frameworks and practical applications

This book is a vital compendium of chapters on the latest research within the field of distributed computing, capturing trends in the design and development of Internet and distributed computing systems that leverage autonomic principles and techniques. The chapters provided within this collection offer a holistic approach for the development of systems that can adapt themselves to meet requirements of performance, fault tolerance, reliability, security, and Quality of Service (QoS) without manual intervention.

Network and traffic engineering in emerging distributed computing applications

This book focuses on network management and traffic engineering for Internet and distributed computing technologies, as well as present emerging technology trends and advanced platform

Hyperspherical cluster based distributed anomaly detection in wireless sensor networks

This article describes a distributed hyperspherical cluster based algorithm for identifying anomalies in measurements from a wireless sensor network, and an implementation on a real wireless sensor network testbed. The communication overhead incurred in the network is minimised by clustering sensor measurements and merging clusters before sending a compact description of the clusters to other nodes. An evaluation on several real and synthetic datasets demonstrates that the distributed hyperspherical cluster-based scheme achieves comparable detection accuracy with a significant reduction in communication overhead compared to a centralised scheme, where all the sensor node measurements are communicated to a central node for processing. .

Algebra skills and traps and diagnostic teaching for the future

Explores on some research about teaching and learning algebra and related classroom issues. Diagnostic instruments that may be used by senior secondary teachers in teaching algebra to senior classes; Strategies for remediating algebraic difficulties and misconceptions; Impact of technology on the algebra curriculum; Usefulness of copying algebraic expressions while using Computer Algebra Systems or mathematics processing software in a calculus class.

An efficient adaptive scheduling policy for high-performance computing

The advent of commodity-based high-performance clusters has raised parallel and distributed computing to a new level. However, in order to achieve the best possible performance improvements for large-scale computing problems as well as good resource utilization, efficient resource management and scheduling is required. This paper proposes a new two-level adaptive space-sharing scheduling policy for non-dedicated heterogeneous commodity-based high-performance clusters. Using trace-driven simulation, the performance of the proposed scheduling policy is compared with existing adaptive space-sharing policies. Results of the simulation show that the proposed policy performs substantially better than the existing policies.

Web 2.0 VDS : social networking as a facilitator of design education

In 2009, Deakin University and the Chinese University of Hong Kong trailed the use of Web 2.0 technologies to enhance learning outcomes in a third year architectural design studio that was modelled on the Virtual Design Studios (VDS) of past decades. The studio developed the VDS further by integrating a social learning environment into the blended learning experience. The Web 2.0 VDS utilised the social networking sites Ning.com, YouTube and Skype; various 3D modelling and video- and/or image-processing software; plus chat-software. These were used in combination to deliver lectures, communicate learning goals, disseminate learning resources, submit work, and provide feedback and comments on various design works in assessing students’ outcomes. This paper centres on issues of learning and teaching associated with the development of a Social Network VDS (SNVDS).

Editorial : advances in network and system security

Current parallel and distributed networks/systems are facing serious threats from network terrorism and crime, which cause huge financial loss and potential life hazard. As attacking tools are becoming more widely available, more easy-to-use, more sophisticated, and more powerful, more efforts have been made in building more effective, more intelligent, and more adaptive defense systems which are of distributed and networked nature. This special issue focuses on issues related to Network and System Security, such as authentication, access control, availability, integrity, privacy, confidentiality, dependability and sustainability of computer networks and systems.

Gender-common and -specific neuroanatomical basis of human anxiety-related personality traits

Exploration of the relationships between regional brain volume and anxiety-related personality traits is important for understanding preexisting vulnerability to depressive and anxiety disorders. However, previous studies on this topic have employed relatively limited sample sizes and/or image processing methodology, and they have not clarified possible gender differences. In the present study, 183 (male/female: 117/66) right-handed healthy individuals in the third and fourth decades of life underwent structural magnetic resonance imaging scans and Temperament and Character Inventory. Neuroanatomical correlates of individual differences in the score of harm avoidance (HA) were examined throughout the entire brain using voxel-based morphometry. We found that higher scores on HA were associated with smaller regional gray matter volume in the right hippocampus, which was common to both genders. In contrast, female-specific correlation was found between higher anxiety-related personality traits and smaller regional brain volume in the left anterior prefrontal cortex. The present findings suggest that smaller right hippocampal volume underlies the basis for higher anxiety-related traits common to both genders, whereas anterior prefrontal volume contributes only in females. The results may have implications for why susceptibility to stress-related disorders such as anxiety disorders and depression shows gender and/or individual differences.

Wootz steel project by electron backscatter diffraction

The data is from an electron backscatter diffraction (EBSD) study of the microstructure of high carbon ‘Wootz’ steel. The objective of the study is to infer an unknown thermomechanical history from observation and analysis of the final microstructure in various ancient artefacts (swords and tools), and then compare the findings with heat treatments of the ancient artefacts and modern attempts at duplication of the structure. Electron backscatter data reveals the orientation relationships between various phases in the material, particularly cementite and ferrite. The dataset is randomly structured and organised. The data is automatically generated by an electron backscattered diffraction system attached to a field emission scanning electron microscope. The dataset uses proprietary software (cannot be copied or distributed without complying with licensing agreements): Oxford HKL Channel 5. As the native formats are binary they cannot be read with standard software.

A comprehensive analytical subdomain model and its field solutions for surface-mounted permanent magnet machines

This paper presents a comprehensive analytical subdomain model together with its field solutions for predicting the magnetic field distributions in surface-mounted permanent magnet (PM) machines. The tooth tips and slotting effects during open-circuit, armature reaction, and on-load conditions are considered when deriving the model and developing its solutions. The model derivations and field solutions are extended from a previous model, and can be applied to PM machines with any combinations of slot and pole numbers and any magnetization patterns in the magnets. This model is initially formulated according to Laplace's and Poisson's equations in 2-D polar coordinates by the separation of variables technique in four subdomains, such as magnet, airgap, winding slots, and slot-openings. The field solution of each subdomain is obtained applying the appropriate boundary conditions and interface conditions between every two subdomains, respectively, which can precisely account for the mutual influence between slots. Finite element analysis (FEA) is later deployed to validate the analytical results in a surface-mounted PM machine that has nonoverlapping winding arrangement. For validation purposes, PM machines having 3-slot/2-pole with parallel magnetization and 12-slot/10-pole with either parallel or radial magnetizations are used for comparisons. Computation of global quantities for the motor which include the phase back-EMF and cogging torque is also included. The results indicate that the proposed analytical model can accurately predict the magnetic field distributions in each subdomain and the motor's global quantities, which are in good agreement with those obtained from the FEA.

Dominating set and network coding-based routing in wireless mesh networks

Wireless mesh networks are widely applied in many fields such as industrial controlling, environmental monitoring, and military operations. Network coding is promising technology that can improve the performance of wireless mesh networks. In particular, network coding is suitable for wireless mesh networks as the fixed backbone of wireless mesh is usually unlimited energy. However, coding collision is a severe problem affecting network performance. To avoid this, routing should be effectively designed with an optimum combination of coding opportunity and coding validity. In this paper, we propose a Connected Dominating Set (CDS)-based and Flow-oriented Coding-aware Routing (CFCR) mechanism to actively increase potential coding opportunities. Our work provides two major contributions. First, it effectively deals with the coding collision problem of flows by introducing the information conformation process, which effectively decreases the failure rate of decoding. Secondly, our routing process considers the benefit of CDS and flow coding simultaneously. Through formalized analysis of the routing parameters, CFCR can choose optimized routing with reliable transmission and small cost. Our evaluation shows CFCR has a lower packet loss ratio and higher throughput than existing methods, such as Adaptive Control of Packet Overhead in XOR Network Coding (ACPO), or Distributed Coding-Aware Routing (DCAR).

Dynamic strain-induced ferrite transformation (DSIT) in steels

The goal in the heat treatment or thermomechanical processing of steel is to improve the mechanical properties. For structural steel applications the general aim is to refine the ferrite grain size as this is the only method that improves both the strength and toughness simultaneously. For conventional hot rolling and accelerated cooling processes, it is difficult to refine the grain size below 5. μm without extensive alloying. However, it has been found that inducing transformation during deformation (i.e. dynamic transformation) can lead to grain sizes of the order of 1. μm, even in very simple steel compositions. The exact mechanism(s) for this transformation process are still being debated, and this has also been complicated by recent studies where such grain sizes can be obtained by static transformation from austenite that has been heavily deformed at low temperatures prior to the transformation. This chapter reviews the various major studies related in particular to dynamic transformation and considers the contributions from the deformed austenite structure developed prior to the transformation and the potential for dynamic recrystallisation of the ferrite. A key factor is proposed to be the early three-dimensional impingement of the ferrite which also provides an insight into cases where ultrafine grains are achieved statically.