• Smart Media Journal
• /
• v.7 no.3
• /
• pp.57-63
• /
• 2018

With many types of data generated in the shift of business environment as a result of growth of an organization or enterprise, there is a need to improve the data-processing efficiency in smarter means with a single domain model such as Data Lake. In particular, creating a logical single domain model from physical partitioned multi-site data by the finite resources of nature and shared economy is very important in terms of efficient operation of computing resources. Based on the advantages of the existing Data Lake framework, we define the CDA-Concept (connected data architecture concept) and functions of Data Lake Framework over Abyss Storage for integrating multiple sites in various application domains and managing the data lifecycle. Also, it performs the interface design and validation verification for Interface #2 & #3 of the connected data architecture-concept.

• Smart Structures and Systems
• /
• v.6 no.5_6
• /
• pp.561-578
• /
• 2010

This study proposes a multi-level damage localization strategy to achieve an effective damage detection system for civil infrastructure systems based on wireless sensors. The proposed system is designed for use of distributed computation in a wireless sensor network (WSN). Modal identification is achieved using the frequency-domain decomposition (FDD) method and the peak-picking technique. The ASH (angle-between-string-and-horizon) and AS (axial strain) flexibility-based methods are employed for identifying and localizing damage. Fundamentally, the multi-level damage localization strategy does not activate all of the sensor nodes in the network at once. Instead, relatively few sensors are used to perform coarse-grained damage localization; if damage is detected, only those sensors in the potentially damaged regions are incrementally added to the network to perform finer-grained damage localization. In this way, many nodes are able to remain asleep for part or all of the multi-level interrogations, and thus the total energy cost is reduced considerably. In addition, a novel distributed computing strategy is also proposed to reduce the energy consumed in a sensor node, which distributes modal identification and damage detection tasks across a WSN and only allows small amount of useful intermediate results to be transmitted wirelessly. Computations are first performed on each leaf node independently, and the aggregated information is transmitted to one cluster head in each cluster. A second stage of computations are performed on each cluster head, and the identified operational deflection shapes and natural frequencies are transmitted to the base station of the WSN. The damage indicators are extracted at the base station. The proposed strategy yields a WSN-based SHM system which can effectively and automatically identify and localize damage, and is efficient in energy usage. The proposed strategy is validated using two illustrative numerical simulations and experimental validation is performed using a cantilevered beam.

• Journal of KIISE:Computing Practices and Letters
• /
• v.9 no.6
• /
• pp.635-645
• /
• 2003

One of very important features that are necessarily supported by clustered parallel computer systems is a single I/O system image in which users can access both the local and remote I/O resources transparently. In this paper, we propose an efficient disk sharing technique supporting a single disk I/O system image architecture. The design separates the I/O subsystem of a cluster into the file system and a set of virtual hard disk drivers. The virtual hard disk driver deals with a hard disk in the remote node as a local hard disk. All services provided by it are performed in the device driver level without any modification of file systems. Users can, therefore, access all the disks in the cluster regardless of their locations. Our virtual hard disk driver is implemented under the linux, and also tested in a linux cluster system. We find by experiments that it can successfully support a single disk I/O space, and at the same time it shows better performance than NFS. We are sure that this paper can be a guideline for single I/O space of other devices to be easily constructed.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.7B
• /
• pp.450-463
• /
• 2005

This paper aims to find influencing factors for firms to adopt network equipments which based on Advanced Telecom Computing Architecture (ATCA). ATCA suggests a standardized specification for telecom equipments design. This new paradigm of developing network equipment provides benefits for network equipment manufacturers by reducing development time for new equipments with lower CapEx and OpEx. It also deliver oportunities for telecom services providers to exploit or test new services by replacing or upgrading part of total system with modular based network equipments. The research model basically depends on various researches based on Rogers' Innovation and Diffusion theory and it is verified through an empirical study for ninety-one domestic forms. Binary logistic regression was conducted to find the relationship between purchase intention and factors affecting new technology adoption. As a result, two factors such as scalability and cost/benefit effectiveness of the new system were statistically significant. Cluster analysis followed with those two variables. This helps TEMs (Telecom Equipments Manufacturers) get some implications on timing and target customers for diffusing the ATCA based technologies in the market.

• Journal of KIISE:Computing Practices and Letters
• /
• v.10 no.1
• /
• pp.49-56
• /
• 2004

Load imbalance is a serious impediment to achieving good performance in parallel processing. Global load balancing schemes cannot adequately manage to balance parallel tasks generated from a single application. Dynamic loop scheduling methods are known to be useful in balancing parallel loops on shared-memory multiprocessor machines. However, their centralized nature causes a bottleneck for the relatively small number of processors in a network of workstations because of order-of-magniture differences in communication overheads. Moreover, improvements of basis loops scheduling methods have not effectively dealt with irregularly distributed workloads in parallel loops, which commonly occur in applications for a network of workstation. In this paper, we present a new reconfigurable and decentralized balancing method for parallel loops on a network of workstations. Since our method supplements performance balancing with those tranditional load balancing methods, it minimizes the overall execution time.

• Journal of KIISE:Computing Practices and Letters
• /
• v.12 no.5
• /
• pp.286-299
• /
• 2006

Due to the continuing technical progress in the capabilities of modeling, simulation, and sensor devices, huge volume data with very high resolution are common. In scientific visualization, various interactive real-time techniques on high performance parallel computers to effectively render such large scale volume data sets have been proposed. In this paper, we present a mobile volume visualization system that consists of mobile clients, gateways, and parallel rendering servers. The mobile clients allow to explore the regions of interests adaptively in higher resolution level as well as specify rendering / viewing parameters interactively which are sent to parallel rendering server. The gateways play a role in managing requests / responses between mobile clients and parallel rendering servers for stable services. The parallel rendering servers visualize the specified sub-volume with rendering contexts from clients and then transfer the high quality final images back. This proposed system lets multi-users with PDA simultaneously share commonly interesting parts of huge volume, rendering contexts, and final images through CSCW(Computer Supported Cooperative Work) mode.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.11
• /
• pp.2827-2848
• /
• 2012

Previously, we described a social media cloud computing service environment (SMCCSE). This SMCCSE supports the development of social networking services (SNSs) that include audio, image, and video formats. A social media cloud computing PaaS platform, a core component in a SMCCSE, processes large amounts of social media in a parallel and distributed manner for supporting a reliable SNS. Here, we propose a Hadoop-based multimedia system for image and video transcoding processing, necessary functions of our PaaS platform. Our system consists of two modules, including an image transcoding module and a video transcoding module. We also design and implement the system by using a MapReduce framework running on a Hadoop Distributed File System (HDFS) and the media processing libraries Xuggler and JAI. In this way, our system exponentially reduces the encoding time for transcoding large amounts of image and video files into specific formats depending on user-requested options (such as resolution, bit rate, and frame rate). In order to evaluate system performance, we measure the total image and video transcoding time for image and video data sets, respectively, under various experimental conditions. In addition, we compare the video transcoding performance of our cloud-based approach with that of the traditional frame-level parallel processing-based approach. Based on experiments performed on a 28-node cluster, the proposed Hadoop-based multimedia transcoding system delivers excellent speed and quality.

• KIISE Transactions on Computing Practices
• /
• v.23 no.5
• /
• pp.299-303
• /
• 2017

By piling up hidden layers in artificial neural networks, deep learning is delivering outstanding performances for high-level abstraction problems such as object/speech recognition and natural language processing. Alternatively, deep-learning users often struggle with the tremendous amounts of time and resources that are required to train deep neural networks. To alleviate this computational challenge, many approaches have been proposed in a diversity of areas. In this work, two of the existing Apache Spark-based acceleration frameworks for deep learning (SparkNet and DeepSpark) are compared and analyzed in terms of the training accuracy and the time demands. In the authors' experiments with the CIFAR-10 and CIFAR-100 benchmark datasets, SparkNet showed a more stable convergence behavior than DeepSpark; but in terms of the training accuracy, DeepSpark delivered a higher classification accuracy of approximately 15%. For some of the cases, DeepSpark also outperformed the sequential implementation running on a single machine in terms of both the accuracy and the running time.

• The Journal of the Korea Contents Association
• /
• v.13 no.2
• /
• pp.32-43
• /
• 2013

These days, there are more and more IT research institutions which foresee cloud services as the predominant IT service in the near future and there, in fact, are actual cloud services provided by some IT leading vendors. Regardless of physical location of the service and environment of the system, cloud service can provide users with storage services, usage of data and software. On the other hand, cloud service has challenges as well. Even though cloud service has its edge in terms of the extent to which the IT resource can be freely utilized regardless of the confinement of hardware, the availability is another problem to be solved. Hence, this paper is dedicated to tackle the aforementioned issues; prerequisites of cloud computing for distributed file system, open source based Hadoop distributed file system, in-memory database technology and high availability database system. Also the author tries to body out the high availability mass distributed data management architecture in cloud service's perspective using currently used distributed file system in cloud computing market.

• Database Research
• /
• v.34 no.3
• /
• pp.58-68
• /
• 2018

Distributed computing helps to efficiently store and process large data on a cluster of multiple machines. The performance of distributed computing is greatly influenced depending on the state of the servers constituting the distributed system. In this paper, we propose a self-diagnosis system that collects log data in a distributed system, detects anomalies and visualizes the results in real time. First, we divide the self-diagnosis process into five stages: collecting, delivering, analyzing, storing, and visualizing stages. Next, we design a real-time self-diagnosis system that meets the goals of real-time, scalability, and high availability. The proposed system is based on Apache Flume, Apache Kafka, and Apache Storm, which are representative real-time distributed techniques. In addition, we use simple but effective moving average and 3-sigma based anomaly detection technique to minimize the delay of log data processing during the self-diagnosis process. Through the results of this paper, we can construct a distributed real-time self-diagnosis solution that can diagnose server status in real time in a complicated distributed system.