FAIRIO: A Throughput-oriented Algorithm for Differentiated I/O Performance

Providing differentiated service in a consolidated storage environment is a challenging task. To address this problem, we introduce FAIRIO, a cycle-based I/O scheduling algorithm that provides differentiated service to workloads concurrently accessing a consolidated RAID storage system. FAIRIO enforces proportional sharing of I/O service through fair scheduling of disk time. During each cycle of the algorithm, I/O requests are scheduled according to workload weights and disk-time utilization history. Experiments, which were driven by the I/O request streams of real and synthetic I/O benchmarks and run on a modified version of DiskSim, provide evidence of FAIRIO’s effectiveness and demonstrate that fair scheduling of disk time is key to achieving differentiated service in a RAID storage system. In particular, the experimental results show that, for a broad range of workload request types, sizes, and access characteristics, the algorithm provides differentiated storage throughput that is within 10% of being perfectly proportional to workload weights; and, it achieves this with little or no degradation of aggregate throughput. The core design concepts of FAIRIO, including service-time allocation and history-driven compensation, potentially can be used to design I/O scheduling algorithms that provide workloads with differentiated service in storage systems comprised of RAIDs, multiple RAIDs, SANs, and hypervisors for Clouds.     

Digestibility and nutritional value of crude oil from three amaranth species

Oils from a selection ofAmaranthus caudatus, A. hypochondriacus andA. cruentus were extracted with hexane. The crude oils were analyzed for acid value, saponification and iodine number, and were included in basal casein diets for rat studies at 5 and 10% levels to replace equal amounts of refined cottonseed oil. The oils fromA. cruentus andA. hypochondriacus were similar in the oil properties studied and different fromA. caudatus. At either 5 or 10% food intake levels, weight gain and PER were not statistically different from values reported for cottonseed oil. True digestibility of amaranth oil was lower than that of cottonseed oil.A. cruentus oil gave the lowest digestibility. Oil levels induced statistical differences in food intake and digestibility. Oils fromA. caudatus, A. hypochondriacus and cottonseed induced similar serum cholesterol levels, while oil fromA. cruentus gave statistically higher values. Hemoglobin, hematocrit and serum proteins were similar among all groups. Microscopic analysis of the organs of the rats revealed some changes that were also found in cottonseed oil-fed rats. It was concluded that crude amaranth oil has lower digestibility than cottonseed oil, but that it is not responsible for growth-depressing effects when the seed is fed raw as compared to processed materials.     

Evaporation of polymer-solvent mixtures

Summary The Stefan-Winkelmann diffusion technique has been used to determine vapor pressures of high boiling point compound-solvents mixtures. Data are reported at a temperature of 67°C for the mixtures polyphenyl ether (6 rings) — benzene and carbowax 1500 — benzene and at a temperature of 100°C for the mixtures polyphenyl ether (6 rings) — toluene and tricresylphosphate-toluene. The range of concentration is only limited by the appearance of a solid phase, and results are in good agreement with those determined by vapor pressure osmometry.Nomenclature A Vapour source - B Flowing gas phase - c Concentration, g-mol/cm³ - D_AB Molecular diffusion coefficient, cm₂/s - h_i Total interface depth, cm - K Parameter defined by equation (6), dimensionless - I Polymer or high boiling point compound - M_A Molecular weight - N_AZ Molar flux, g-mol/(cm₂) (s) - P_A Partial pressure at the interface, atm - P Total pressure, atm - R Gas constant, (atm) (cm₃) / (°K) (g-mol) - T Temperature, °K - t Time, s - Y_A Molar fraction at the interface, dimensionless - z_o Initial interface depth, cm - z_i Drop of the interface depth, cm - z Interface position Greek Letters _A Density of the liquid phase, g/cm³     

An embedding approach for the design of state‐feedback tracking controllers for references with jumps

We study the problem of designing state‐feedback controllers to track time‐varying state trajectories that may exhibit jumps. Both plants and controllers considered are modeled as hybrid dynamical systems, which are systems with both continuous and discrete dynamics, given in terms of a flow set, a flow map, a jump set, and a jump map. Using recently developed tools for the study of stability in hybrid systems, we recast the tracking problem as the task of asymptotically stabilizing a set, the tracking set, and derive conditions for the design of state‐feedback tracking controllers with the property that the jump times of the plant coincide with those of the given reference trajectories. The resulting tracking controllers guarantee that solutions of the plant starting close to the reference trajectory stay close to it and that the difference between each solution of the controlled plant and the reference trajectory converges to zero asymptotically. Constructive conditions for tracking control design in terms of LMIs are proposed for a class of hybrid systems with linear maps and input‐triggered jumps. The results are illustrated by various examples. Copyright © 2013 John Wiley & Sons, Ltd.     

Approximate similarity search for online multimedia services on distributed CPU–GPU platforms

Similarity search in high-dimensional spaces is a pivotal operation for several database applications, including online content-based multimedia services. With the increasing popularity of multimedia applications, these services are facing new challenges regarding (1) the very large and growing volumes of data to be indexed/searched and (2) the necessity of reducing the response times as observed by end-users. In addition, the nature of the interactions between users and online services creates fluctuating query request rates throughout execution, which requires a similarity search engine to adapt to better use the computation platform and minimize response times. In this work, we address these challenges with Hypercurves, a flexible framework for answering approximate k-nearest neighbor (kNN) queries for very large multimedia databases. Hypercurves executes in hybrid CPU–GPU environments and is able to attain massive query-processing rates through the cooperative use of these devices. Hypercurves also changes its CPU–GPU task partitioning dynamically according to the observed load, aiming for optimal response times. In our empirical evaluation, dynamic task partitioning reduced query response times by approximately 50 % compared to the best static task partition. Due to a probabilistic proof of equivalence to the sequential kNN algorithm, the CPU–GPU execution of Hypercurves in distributed (multi-node) environments can be aggressively optimized, attaining superlinear scalability while still guaranteeing, with high probability, results at least as good as those from the sequential algorithm.     

The Building Blocks of a PaaS

Traditional cloud computing providers enable developers to program and deploy applications in the cloud by using platform as a service (PaaS) providers. Despite the benefits of such an approach, this service model usually comes with a high level of the lock in effect into the service provider. The lock in effect occurs when a software developer needs to change its cloud provider. When this happens, it usually means a major application rewrite, specific for the new PaaS. This paper details the initial results of a project whose goal is to build a PaaS where vendor lock in does not occur. With this PaaS, developers wishing to deploy their applications into the cloud may continue to program using their usual development environments. There are no necessary changes required to make the application PaaS compatible. As a proof of concept, we developed an open source PaaS management application as a regular web application and then deployed it on the cloud.     

Stream fusion for multi-stream automatic speech recognition

Multi-stream automatic speech recognition (MS-ASR) has been confirmed to boost the recognition performance in noisy conditions. In this system, the generation and the fusion of the streams are the essential parts and need to be designed in such a way to reduce the effect of noise on the final decision. This paper shows how to improve the performance of the MS-ASR by targeting two questions; (1) How many streams are to be combined, and (2) how to combine them. First, we propose a novel approach based on stream reliability to select the number of streams to be fused. Second, a fusion method based on Parallel Hidden Markov Models is introduced. Applying the method on two datasets (TIMIT and RATS) with different noises, we show an improvement of MS-ASR.     

Neural Network and Classification Approach in Identifying Customer Behavior in the Banking Sector: A Case Study of an International Bank

The customer relationship focus for banks is in development of main competencies and strategies of building strong profitable customer relationships through considering and managing the customer impression, influence on the culture of the bank, satisfactory treatment, and assessment of valued relationship building. Artificial neural networks (ANNs) are used after data segmentation and classification, where the designed model register records into two class sets, that is, the training and testing sets. ANN predicts new customer behavior from previously observed customer behavior after executing the process of learning from existing data. This article proposes an ANN model, which is developed using a six‐step procedure. The back‐propagation algorithm is used to train the ANN by adjusting its weights to minimize the difference between the current ANN output and the desired output. An evaluation process is conducted to determine whether the ANN has learned how to perform. The training process is halted periodically, and its performance is tested until an acceptable result is obtained. The principles underlying detection software are grounded in classical statistical decision theory.     

A hardware design of a massive-parallel, modular NN-based vector quantizer for real-time video coding

This report describes the design of a modular, massive-parallel, neural-network (NN)-based vector quantizer for real-time video coding. The NN is a self-organizing map (SOM) that works only in the training phase for codebook generation, only at the recall phase for real-time image coding, or in both phases for adaptive applications. The neural net can be learned using batch or adaptive training and is controlled by an inside circuit, finite-state machine-based hard controller. The SOM is described in VHDL and implemented on electrically (FPGA) and mask (standard-cell) programmable devices.