• ETRI Journal
• /
• v.42 no.5
• /
• pp.748-760
• /
• 2020

MapReduce is a framework that can process huge datasets in parallel and distributed computing environments. However, a single machine failure during the runtime of MapReduce tasks can increase completion time by 50%. MapReduce handles task failures by restarting the failed task and re-computing all input data from scratch, regardless of how much data had already been processed. To solve this issue, we need the computed key-value pairs to persist in a storage system to avoid re-computing them during the restarting process. In this paper, the task failure resilience (TFR) technique is proposed, which allows the execution of a failed task to continue from the point it was interrupted without having to redo all the work. Amazon ElastiCache for Redis is used as a non-volatile cache for the key-value pairs. We measured the performance of TFR by running different Hadoop benchmarking suites. TFR was implemented using the Hadoop software framework, and the experimental results showed significant performance improvements when compared with the performance of the default Hadoop implementation.

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.11
• /
• pp.976-983
• /
• 2002

We presents a modified variable dimension filter with input estimation for maneuvering target tracking. The conventional variable dimension filter with input estimation(VDIE) consists of the input estimation(IE) technique and the variable dimension(VD) filter. In the VDIE, the IE technique is used for estimation of a maneuver onset time and its magnitude in the least square sense. The detection of the maneuver is declared according to the estimated magnitude of the maneuver. The VD filter structure is applied for the adaptation to the maneuver of the target after compensating the filter parameter with respect to the estimated maneuver when the detection of the maneuver is declared. The VDIE is known as one of the best maneuvering target tracking filter based on a single filter. However, it requires too much computational burden since the IE technique is performed at every sampling instance and thus it is computationally inefficient. We propose another variable dimension filter with input estimation named 'Modified VDIE' which combines VD filter with If technique. Modified VDIE has less computational load than the original one by separating maneuver detection and input estimation. Simulation results show that the proposed VDIE is more efficient and outperforms in terms of computational load.

• Journal of Magnetics
• /
• v.2 no.3
• /
• pp.96-100
• /
• 1997

A spin valve structure of NiO(40 nm)/Co(2 nm)/Cu(2.6 nm)/Co(x nm)/Ta(5 nm) has been investigated for the application of magnetic random access memory (MRAM). The spin valve structure exhibited very large difference in the coercivities between pinned and free layers, a relatively high GMR ratio, and a low free layer coercivity. The spin valves were prepared by sputtering and were characterized by dc 4-point probe, and VSM. The spin valves with combined free layer exhibited a maximun GMR ratio of 10.4% with a free layer coercivity of about 82 Oe. The spin valves with a single 10 nm thick a-CoNbZr free layer exhibited a GMR ratio of about 4.3% with a free layer coercivity of about 12 Oe. The GMR ratio of the spin valves increased by addition of Co between Cu and a-CoNbZr. It has been confirmed that the coercivity of free layer can be decreased by increasing the thickness of a-CoNbZr. It has been confirmed that the coercivity of free layer can be decreased by increasing the thickness of a-CoNbZr layer without losing the GMR ratio substantially, which was mainly due to high resistivity of the amorphous "layers".

• The Bulletin of The Korean Astronomical Society
• /
• v.37 no.2
• /
• pp.228.1-228.1
• /
• 2012

Digital waveform generation technology for SAR payload can be divided into DDS(Direct Digital Synthesizer) method and Memory Mapped(M/M) method. DDS is the single chip which consists of the Sine Table, NCO(Numerically Controlled Oscillator), DAC, and so on. DDS method is a very simple method because the circuit configuration is not complex but has a disadvantage that can not control phase and amplitude easily by using NCO. M/M method has the complexity of the circuit configuration because it requires the memories which stores the waveforms, the control circuits, and DAC. And this method should apply the high interface technology for being compatible with the wide bandwidth of the digital signal and has the difficulty for PCB design because the number of the signal lines should be increased according to the number of the data bits for DAC. Although it has several disadvantages, this method has the capability of pre-distortion function which can compensate the phase and amplitude characteristics of the system and also has an excellent advantage to make any arbitrary waveform, so this method is considered as an important technology with DDS method. This research describes the technological trends of the waveform generator for the SAR payload and analyzes the characteristics of the technology.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.10C
• /
• pp.937-944
• /
• 2002

The current fast-growing Internet traffic is demanding more and more network capacity. Photonic packet switching offers high-speed, data rate/format transparency, and configurability, which are some of the important characteristics needed in future networks supporting different forms of data. In this paper, we define that optical backbone networks for IP transport consist of optical packet core switches and optical fibers. We propose a multi-link photonic packet switch managing as single media which unifies the whole bandwidth of multiple wavelengths on the optical fiber in the WDM optical networks. The proposed switch uses optical packet memories of output link equally as well as using the WDM buffer. So it cuts down the required number of buffers and realizes of the optical packet memory economically.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.12C
• /
• pp.1642-1651
• /
• 2004

Advance of internet access technology requires more internet bandwidth and high-speed packet processing. IP address lookups in routers are essential elements which should be performed in real time for packets arriving tens-of-million packets per second. In this paper, we proposed a new architecture for efficient IP address lookup. The proposed scheme produces multiple balanced trees stored into a single SRAM. The proposed scheme performs sequential binary searches on multiple trees. Performance evaluation results show that p개posed architecture requires 301.7KByte SRAM to store about 40,000 prefix samples, and an address lookup is achieved by 11.3 memory accesses in average.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.1 no.2
• /
• pp.169-181
• /
• 1997

Some association rules can have very high confidence in a sub-interval or a subrange of the domain, though not quite high confidence in the whole domain. In this paper, we define a ranged association rule, an association with high confidence worthy of special attention in a sub-domain, and further propose an efficient algorithm which finds out ranged association rules. The proposed algorithm is data-driven method in a sense that hypothetical subranges are built based on data distribution itself. In addition, to avoid redundant database scanning, we devise an effective in-memory data structure, that is collected through single database scanning. The simulation shows that the suggested algorithm has reliable performance at the acceptable time cost in actual application areas.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.8
• /
• pp.1921-1929
• /
• 1997

This paper describes a direct transmission method of multimedia data stream between a multimedia data processor and a communication interface without using system memory. I propose the direct transfer method of multimedia data through the single data path, without additional data path between a multimedia data processor and a communication interface in multimedia platforms. The hardware architecture and functions for the direct transfer method is defined. Procedure to transfer multimedia data to and from the multimedia data processor is described by means of control flow chart. Comparing the proposed method with general methods, I show that the proposed method can decrease number of bus accesses and bus cycles.

• Nuclear Engineering and Technology
• /
• v.49 no.6
• /
• pp.1240-1249
• /
• 2017

An essential component of the neutron transport solver is the resonance self-shielding calculation used to determine equivalence cross sections. The neutron transport code, MPACT, is currently using the subgroup self-shielding method, in which the method of characteristics (MOC) is used to solve purely absorbing fixed-source problems. Recent efforts incorporating multigroup kernels to the MOC solvers in MPACT have reduced runtime by roughly $2{\times}$. Applying the same concepts for self-shielding and developing a novel lumped parameter approach to MOC, substantial improvements have also been made to the self-shielding computational efficiency without sacrificing any accuracy. These new multigroup and lumped parameter capabilities have been demonstrated on two test cases: (1) a single lattice with quarter symmetry known as VERA (Virtual Environment for Reactor Applications) Progression Problem 2a and (2) a two-dimensional quarter-core slice known as Problem 5a-2D. From these cases, self-shielding computational time was reduced by roughly $3-4{\times}$, with a corresponding 15-20% increase in overall memory burden. An azimuthal angle sensitivity study also shows that only half as many angles are needed, yielding an additional speedup of $2{\times}$. In total, the improvements yield roughly a $7-8{\times}$ speedup. Given these performance benefits, these approaches have been adopted as the default in MPACT.

• Journal of Preventive Medicine and Public Health
• /
• v.46 no.sup1
• /
• pp.22-27
• /
• 2013

The purpose of this study was to examine the beneficial effects of a new cognitive intervention program designed for the care and prevention of dementia, namely Learning Therapy. The training program used systematized basic problems in arithmetic and Japanese language as training tasks. In study 1, 16 individuals in the experimental group and 16 in the control group were recruited from a nursing home. In both groups, all individuals were clinically diagnosed with senile dementia of the Alzheimer type. In study 2, we performed a single-blind, randomized controlled trial in our cognitive intervention program of 124 community-dwelling seniors. In both studies, the daily training program using reading and arithmetic tasks was carried out approximately 5 days a week, for 15 to 20 minutes a day in the intervention groups. Neuropsychological measures were determined simultaneously in the groups both prior to and after six months of the intervention. The results of our investigations indicate that our cognitive intervention using reading and arithmetic problems demonstrated a transfer effect and they provide convincing evidence that cognitive training maintains and improves the cognitive functions of dementia patients and healthy seniors.