The solution of large-scale sparse linear systems arises in numerous scientific and engineering problems. Typical examples involve study of many real world multi-physics problems and the analysis of electric power systems. The latter involve key functions such as contingency, power flow and state estimation whose analysis amounts at solving linear systems with thousands or millions of equations. As a result, efficient and accurate solution of such systems is of paramount importance. The methods for solving sparse systems are distinguished in two categories, direct and iterative. Direct methods are robust but require large amounts of memory, as the size of the problem grows. On the other hand, iterative methods provide better performance but may exhibit numerical problems. In addition, continuous advances in computer hardware and computational infrastructures imposes new challenges and opportunities. GPUs, multi-core CPUs, late memory and storage technologies (flash and phase change memories) introduce new capabilities to optimizing sparse solvers. This work presents a comprehensive study of the performance of some, state of the art, sparse direct and iterative solvers on modern computer infrastructure and aims to identify the limits of each method on different computing platforms. We evaluated two direct solvers in different hardware configurations, examining their strengths and weaknesses both in main memory (in-core) and secondary memory (out-of-core) execution in a series of representative matrices from multi-physics and electric grid problems. Also, we provide a comparison with an iterative method, utilizing a general purpose preconditioner, implemented both on a GPU and a multi-core processor. Based on the evaluation results, we observe that direct solvers can be as efficient as their iterative counterparts if proper memory optimizations are applied. In addition, we demonstrate that GPUs can be utilized as efficient computational platforms for tackling the analysis of electric power systems.
In this paper we present a platform for delivering multimedia presentations on cultural heritage. The platform aims to enhance cultural knowledge discovery by increasing access to museums' digital content. The platform generates rich media presentations considering the personal profile of the audience as well as its interests. The presentations may include text, images, video and sound and can be delivered via network. They can be attended either inside the museum or even outside of it e.g. in schools during a preparation class prior to a museum visit. The platform supports creation and editing of slides and presentations, updating existing presentations and projecting them, considering different roles and access levels for archeologists, tourist guides, educators and individuals.
In recent decades, the traditional monopolistic energy exchange market has been replaced by deregulated, competitive marketplaces in which electricity may be purchased and sold at market prices like any other commodity. As a result, the deregulation of the electricity industry has produced a demand for wholesale organized marketplaces. Price predictions, which are primarily meant to establish the market clearing price, have become a significant factor to an energy company’s decision making and strategic development. Recently, the fast development of deep learning algorithms, as well as the deployment of front-end metaheuristic optimization approaches, have resulted in the efficient development of enhanced prediction models that are used for electricity price forecasting. In this paper, the development of six highly accurate, robust and optimized data-driven forecasting models in conjunction with an optimized Variational Mode Decomposition method and the K-Means clustering algorithm for short-term electricity price forecasting is proposed. In this work, we also establish an Inverted and Discrete Particle Swarm Optimization approach that is implemented for the optimization of the Variational Mode Decomposition method. The prediction of the day-ahead electricity prices is based on historical weather and price data of the deregulated Greek electricity market. The resulting forecasting outcomes are thoroughly compared in order to address which of the two proposed divide-and-conquer preprocessing approaches results in more accuracy concerning the issue of short-term electricity price forecasting. Finally, the proposed technique that produces the smallest error in the electricity price forecasting is based on Variational Mode Decomposition, which is optimized through the proposed variation of Particle Swarm Optimization, with a mean absolute percentage error value of 6.15%.
Short text clustering is a popular problem that focuses on the unsupervised grouping of similar short text documents, or entitled entities. Since the short texts are currently being utilized in a vast number of applications, the problem in question has been rendered increasingly significant in the past few years. The high cluster homogeneity and completeness are two among the most important goals of all data clustering algorithms. However, in the context of short texts, their fulfilment is particularly difficult, because this type of data is typically represented by sparse vectors that collectively comprise a very high dimensional space. In this article we introduce VEPHC, a two-stage clustering algorithm designed to confront the sparseness and high dimensionality traits of short texts. During the first stage (or else, the VEP part), the initial feature vectors are projected onto a lower dimensional space by constructing and scoring variable-sized combinations of features (that is, terms). In the second stage (or else, the HC part), VEPHC improves the homogeneity and completeness of the generated clusters through split and merge operations that are based on the similarities of all inter-cluster elements. The experimental evaluation of VEPHC on two real-world datasets demonstrates its superior performance over numerous state-of-the-art clustering algorithms in terms of F1 scores and Normalized Mutual Information.
In the big data era, the efficient processing of large volumes of data has became a standard requirement for both organizations and enterprises. Since single workstations cannot sustain such tremendous workloads, MapReduce was introduced with the aim of providing a robust, easy, and fault-tolerant parallelization framework for the execution of applications on large clusters. One of the most representative examples of such applications is the machine learning algorithms which dominate the broad research area of data mining. Simultaneously, the recent advances in hardware technology led to the introduction of high-performing alternative devices for secondary storage, known as Solid State Drives (SSDs). In this paper we examine the perfor-mance of several parallel data mining algorithms on MapReduce clusters equipped with such modern hardware. More specifically, we investigate standard dataset preprocessing methods including vectorization and dimensionality reduction, and two supervised classifiers, Naive Bayes and Linear Regression. We compare the execution times of these algorithms on an experimental cluster equipped with both standard magnetic disks and SSDs, by employing two different datasets and by applying several different cluster configurations. Our experiments demonstrate that the usage of SSDs can accelerate the execution of machine learning methods by a margin which depends on the cluster setup and the nature of the applied algorithms.
This paper discusses a collaborative and innovative e-health system called EMOSNet, for the support of medical decision making in the case of amputated or mangled extremities. The goal of the proposed system is to provide communication and collaboration channels between orthopedists located in regional hospitals and special surgeons of the University Hospital of Larissa, in order to confront emergency orthopedic incidences. The main contribution of this work is the development of a suitable framework for the development of a collaborative and innovative e-health system. Using state of the art technology, we develop innovative services, contribute to standardization, interoperability and security issues and provide modeling and simulation techniques for educational purposes. More specifically, we describe a framework of e-health innovation and an overview of the design methodology that relate to e-health service innovation. Our methodology introduces a technological platform for the provision of services for the delivery of a number of e-health services, ranging from second-opinion request and collaboration among distant professionals to the support of medical decision making in the case of amputated or mangled extremities.
In smart cities residential homes are fully equipped with information networking and computing technologies and are connected to the power grid via intelligent meters. Connectivity of meters allows formation of groups of residents, which are physically close, and as a result individual consumptions can be aggregated into a shared consumption. In this paper an approach of unfolding shared consumption and making inferences about resident personal usage is presented. The proposed approach tackles the problem of unfolding as a multiobjective problem in which a set of residential profiles is fitted to the measured consumption. A solution to the multiobjective problem is sought by using the Non-dominated Sorting Genetic Algorithm-II (NSGA-II) that utilizes the Pareto optimality theory to identify an optimal solution. The approach is applied to a set electricity consumption signals for making inferences about the personal energy usage of residential participants in the shared consumption pattern.
