• Journal of KIISE:Computing Practices and Letters
• /
• v.10 no.2
• /
• pp.134-145
• /
• 2004

With rapid growth in the amount of data transferred on the Internet, traditional storage systems have reached the limits of their capacity and performance. SAN (Storage Area Network), which connects hosts to disk with the Fibre Channel switches, provides one of the powerful solutions to scale the data storage and servers. In this environment, the maintenance of data consistency among hosts is an important issue because multiple hosts share the files on disks attached to the SAN. To preserve data consistency, each host can execute the disk I/O whenever disk read and write operations are requested. However, frequent disk I/O requests cause the deterioration of the overall performance of a SAN cluster. In this paper, we introduce a SANtopia global buffer manager to improve the performance of a SAN cluster reducing the number of disk I/Os. We describe the design and algorithms of the SANtopia global buffer manager, which provides a buffer cache sharing mechanism among the hosts in the SAN cluster. Micro-benchmark results to measure the performance of block I/O operations show that the global buffer manager achieves speed-up by the factor of 1.8-12.8 compared with the existing method using disk I/O operations. Also, File system micro-benchmark results show that SANtopia file system with the global buffer manager improves performance by the factor of 1.06 in case of directories and 1.14 in case of files compared with the file system without a global buffer manager.

• 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.

• Journal of KIISE:Computing Practices and Letters
• /
• v.9 no.6
• /
• pp.623-634
• /
• 2003

In this paper, we propose a collaborative multimedia authoring system. Our authoring system represents a multimedia presentation in a 3D coordinate system. One axis represents the traditional timeline information (T-zone), and the other two axes represent spatial coordinates (XY-zone). Our system represents a visual media objects as a 3D parallelepipeds and audio media objects as cylinders. This interface allows for simultaneous authoring and manipulation of both the temporal and the spatial aspects of a presentation. Using our system, users can design multimedia presentations collaboratively in the unified spatio-temporal space while freely traversing the spatial domain and the temporal domain without changing the context of authoring. In addition, we suggest an efficient mechanism of concurrency control for shared objects generated by our collaborative writing system. The mechanism is mainly based on the user awareness, the multiple versions, and the access permission of shared objects. Our concurrency control mechanism is designed to keep data consistency by minimizing the collision due to the delay or the failure of network communication and to allow maximum responsiveness for users using optimistic concurrency control. Also, the mechanism maximize the responsiveness by refining the locking granularity and applying different concurrency control mechanisms to each.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.17 no.3
• /
• pp.167-173
• /
• 2014

In this work, based on the blade element-momentum theory (BEMT), we proposed the geometry of a lab-scale horizontal axis tidal turbine with a diameter of 80cm, which can demonstrate the maximum power coefficient, and investigated the effect of blade pitch angle increase on the power coefficient. For validation of the computed power coefficients by the BEMT, we also computed the power coefficient using the computational fluid dynamics (CFD) for each case. For the CFD, 15 times of the turbine radius was used for the length and diameter of the computational domain, and the open boundary condition was prescribed at the boundary of the computational domain. The maximum power coefficients of the turbine acquired by the BEMT and CFD were about 48%, showing a good agreement. Both of the power coefficients computed by the BEMT and CFD tended to decrease when the blade pitch angle increases. The two power coefficients for a given tip-speed ratio were in good agreement. Through the present study, we have confirmed that we can trust the proposed geometry and the computed power coefficients based on the BEMT.

• Journal of Internet Computing and Services
• /
• v.15 no.4
• /
• pp.33-42
• /
• 2014

Hand-signal is an effective communication means in the situation where voice cannot be used for expression especially for soldiers. Vision-based approaches using cameras as input devices are widely suggested in the literature. However, these approaches are not suitable for soldiers that have unseen visions in many cases. in addition, existing special-glove approaches utilize the information of fingers only. Thus, they are still lack for soldiers' hand-signal recognition that involves not only finger motions, but also additional information such as the rotation of a hand. In this paper, we have designed and implemented a new recognition system for six military hand-signal motions, i. e., 'ready', 'move', quick move', 'crawl', 'stop', and 'lying-down'. For this purpose, we have proposed a finger-recognition method and motion-recognition methods. The finger-recognition method discriminate how much each finger is bended, i. e., 'completely flattened', 'slightly flattened', 'slightly bended', and 'completely bended'. The motion-recognition algorithms are based on the characterization of each hand-signal motion in terms of the three axes. Through repetitive experiments, our system have shown 91.2% of correct recognition.

• Journal of Biomedical Engineering Research
• /
• v.23 no.4
• /
• pp.269-279
• /
• 2002

When we inject a current into an electrically conducting subject such as a human body, voltage and current density distributions are formed inside the subject. The current density within the subject and injection current in the lead wires generate a magnetic field. This magnetic flux density within the subject distorts phase of spin-echo magnetic resonance images. In Magnetic Resonance Current Density Imaging (MRCDI) technique, we obtain internal magnetic flux density images and produce current density images from $\bigtriangledown{\times}B/\mu_\theta$. This internal information is used in Magnetic Resonance Electrical Impedance Tomography (MREIT) where we try to reconstruct a cross-sectional resistivity image of a subject. This paper describes numerical techniques of computing voltage. current density, and magnetic flux density within a subject due to an injection current. We use the Finite Element Method (FEM) and Biot-Savart law to calculate these variables from three-dimensional models with different internal resistivity distributions. The numerical analysis techniques described in this paper are used in the design of MRCDI experiments and also image reconstruction a1gorithms for MREIT.

• Nuclear Engineering and Technology
• /
• v.23 no.4
• /
• pp.444-455
• /
• 1991

An accurate and fast running NEDAR model for calculating radial power profile throughout fuel life in both solid and annular pellets for existing and advanced CANDU-PHWR-fuel was developed in this work. This model contains resultant flux depression equations and neutron depression data tables which have been developed for CANDU-PHWR fuel of pellet with the diameter 8.0 to 19.5 mm and enrichment 0.71-6.0 wt % U-235, over a bumup range of 0 to 840 MWh /kgU (35000 MWD/T). In order to obtain the neutron flux distribution in the fuel pellet, the CE-HAMMER physics code was run for a neutron flux spectrum appropriate to a CANDU-PHWR to give predictions of radial power profile for several ranges of fuel design parameters. The results, which were calculated by the CE-HAMMER physics code, were fitted to an equation which is solved in terms of Bessel and exponential functions in order to obtain the parameters, $textsc{k}$, $\beta$ and λ in the resultant equation. The present NEDAR model produce a radial profile which, when normalized to unity at the pellet surface, is slightly higher than the profile of the original ELESIM data table. The predictions of the fission gas release by KAFEPA-NEDAR are in slightly better agreement with the experiments than those of ELESIM. The NEDAR model described in this study has been shown to provide an effective, reliable, and accurate method for determining radial power profiles in CANDU-PHWR fuel rods without incurring a significant increase in computing time.

• Journal of Digital Convergence
• /
• v.14 no.1
• /
• pp.1-11
• /
• 2016

Currently Korean government is rushing the new electronic government system introduced as 'platform e-government' with big data and cloud computing technologies and systems, ultimately intending to provide the public institution services customized from the integrated counter or window for the heterogeneous resident services. In this regard, this study suggested how to design the new metadata information system in which mutual integration of information systems can take place, where heterogeneous services can be shared efficiently at the application and data unit, as a separate application that can provide a single one- stop service for residents' petition at the integrated level in the back-office based on the public data in possession of each of government ministries and related organizations. If this proposed system is implemented, the achievement of customized public service can be advanced one step forward in processing the petitions of the residents by organically connected link between 'Demand Chain' and 'Supply Chain' in the integrated window. In other words, it could be made possible through the unification of both the 'Supply Chain' performed in the office space of the officials at the back-office level and the 'Demand Chain' performed in the living space of the residents at the front-office level.

• KIPS Transactions on Computer and Communication Systems
• /
• v.7 no.1
• /
• pp.9-18
• /
• 2018

Enhancing performance of big data analytics in distributed environment has been issued because most of the big data related applications such as machine learning techniques and streaming services generally utilize distributed computing frameworks. Thus, optimizing performance of those applications at Spark has been actively researched. Since optimizing performance of the applications at distributed environment is challenging because it not only needs optimizing the applications themselves but also requires tuning of the distributed system configuration parameters. Although prior researches made a huge effort to improve execution performance, most of them only focused on one of three performance optimization aspect: application design, system tuning, hardware utilization. Thus, they couldn't handle an orchestration of those aspects. In this paper, we deeply analyze and model the application processing procedure of the Spark. Through the analyzed results, we propose performance optimization schemes for each step of the procedure: inner stage and outer stage. We also propose appropriate partitioning mechanism by analyzing relationship between partitioning parallelism and performance of the applications. We applied those three performance optimization schemes to WordCount, Pagerank, and Kmeans which are basic big data analytics and found nearly 50% performance improvement when all of those schemes are applied.

• Journal of KIISE:Computing Practices and Letters
• /
• v.7 no.2
• /
• pp.141-150
• /
• 2001

Manufacturing conb'ol applications consist of concurrent active components such as robots, AGV's (Automatic Guided Vehicles), and conveyors. Running of manufacturing control programs is interactions among those components. We can enhance the productivity and extendability of manufacturing control applications by using the object-oriented teclmology that models those components as reusable objects. But the objects in current object-oriented technology that encapsulate state and behavior infonnation are passive in a sense that those respond only when messages are sent to them. In this paper, we introduce the Distributed Active Object Systems (DAGS) approach that SUPPOltS active objects. Since active objects encapsulate control infonnation in addition to state and behavior information under COREA/Java-based distributed environment, they can represent manufacturing control components better than the objects in ordimuy object-oriented technology. TIus control infonnation provides an object with a featme that can monitor its own status as well as other object's status connected by intelface valiables. Active objects can initiate a behavior according to the change of those status. Therefore, we can sb-uctmally assemble self-initiating active objects by using intelface variables to construct a system without describing bow to control distributed objects by using message passing. As the DAOS approach supports object composability, we can enhal1ce the productivity and extendability of disbibuted manufactming control applications even better than the ordil1alY object-oriented approach. Also, the DAOS approach supports better component reusability with active objects that encapsulate control information .