• Journal of IKEEE
• /
• v.20 no.1
• /
• pp.89-93
• /
• 2016

In this paper, we proposed SIMT based Image Signal Processor which can apply various image preprocessing algorithms and allow parallel processing of application programs such as image recognition. Conventional ISP has the hard-wired image enhancement algorithm of which the processing speed is fast, but there was difficult to optimize performance depending on various image processing algorithms. The proposed ISP improved the processing time applying SIMT architecture and processed a variety of image processing algorithms as an instruction based processor. We used Xilinx Virtex-7 board and the processing time compared to cell multicore processor, ARM Cortex-A9, ARM Cortex-A15 was reduced by about 71 percent, 63 percent and 33 percent, respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.2
• /
• pp.193-201
• /
• 2008

Using Network Coding in P2P systems yields great benefits, e.g., reduced download delay. The core notion of Network Coding is to allow encoding and decoding at intermediate nodes, which are prohibited in the traditional networking. However, improper implementation of Network Coding may reduce the overall performance of P2P systems. Network Coding cannot work with general arithmetic operations, since its arithmetic is over a Finite Field and the use of an efficient Finite Field arithmetic algorithm is the key to the performance of Network Coding. Also there are other important performance parameters in Network Coding such as Field size. In this paper we study how those factors influence the performance of Network Coding based systems. A set of experiments shows that overall performance of Network Coding can vary 2-5 times by those factors and we argue that when developing a network system using Network Coding those performance parameters must be carefully chosen.

• Tuberculosis and Respiratory Diseases
• /
• v.69 no.2
• /
• pp.75-80
• /
• 2010

The year of 2009~2010 brought a number of concepts and new ideas were evaluated with promising results. However, some studies that challenged many beliefs. In acute respiratory distress syndrome (ARDS), recent clinical studies took into consideration of pathophysiologic changes of respiratory system compliance. Meta-analysis of positive end-expiratory pressure trials showed survival benefit of high positive end-expiratory pressure in ARDS. Until now, prone positioning did not show survival benefit in patients with ARDS. Extracorporeal membrane oxygenation (ECMO) based management improved survival in patients with severe ARDS. ECMO can be a management option in severe ARDS. Sedation is a standard practice in critically ill patients needing mechanical ventilation. However, Danish group reported less sedation of critically ill patients receiving mechanical ventilation was associated with an increase in days without ventilation. Although this single center study has some limitations, the overall results are promising. Use of maximal sterile barrier precautions (mask, sterile gown, sterile gloves, and large sterile drapes) with chlorhexidine-impregnated dressing reduced central venous catheter related infection. Selective oropharyngeal decontamination (application of topical antibiotics in the oropharynx) reduced the mortality rate of an intensive care unit (ICU) population. Normoglycemia in Intensive Care Evaluation and Survival Using Glucose Algorithm Regulation (NICE-SUGAR) trial reported intensive glucose control increased mortality among adults in the ICU. Some of the results of above papers are promising. However, some ideas may need for more frequent individual assessment and increase the workload of ICU staffs. Before implementation of new practice in ICU, we should take into consideration of individual hospital situation including human and material resources.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.5
• /
• pp.34-45
• /
• 1997

In this paper, we present hardware implemcntation of self-organizing feature map (SOFM) neural networkwith constant adaptation gain and binary reinforcement function on FPGA. Whereas a tnme-varyingadaptation gain is used in the conventional SOFM, the proposed SOFM has a time-invariant adaptationgain and adds a binary reinforcement function in order to compensate for the lowered abilityof SOFM due to the constant adaptation gain. Since the proposed algorithm has no multiplication operation.it is much easier to implement than the original SOFM. Since a unit neuron is composed of 1adde $r_tracter and 2 adders, its structure is simple, and thus the number of neurons fabricated onFPGA is expected to he large. In addition, a few control signal: ;:rp sufficient for controlling !he neurons.Experimental results show that each componeni ot thi inipiemented neural network operates correctlyand the whole system also works well.stem also works well.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.3
• /
• pp.319-327
• /
• 2012

In this paper, we present a sign language recognition model which does not use any wearable devices for object tracking. The system design issues and implementation issues such as data representation, feature extraction and pattern classification methods are discussed. The proposed data representation method for sign language patterns is robust for spatio-temporal variances of feature points. We present a feature extraction technique which can improve the computation speed by reducing the amount of feature data. A neural network model which is capable of incremental learning is described and the behaviors and learning algorithm of the model are introduced. We have defined a measure which reflects the relevance between the feature values and the pattern classes. The measure makes it possible to select more effective features without any degradation of performance. Through the experiments using six types of sign language patterns, the proposed model is evaluated empirically.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.4C
• /
• pp.343-355
• /
• 2003

Fair bandwidth allocations at routers protect adaptive flows from non-adaptive ones and may simplify end-to end congestion control. However, traditional fair bandwidth allocation mechanisms, like Weighted Fair Queueing and Flow Random Early Drop, maintain state, manage buffera and perform packet scheduling on a per-flow basis. These mechanisms are more complex and less scalable than simple FIFO queueing when they are used in the interi or of a high-speed network. Recently, to overcome the implementation complexity problem and address the scalability and robustness, several fair bandwidth allocation mechanisms without per-flow state in the interior routers are proposed. Core-Stateless Fair Queueing and Rainbow Fair Queuing are approximates fair queueing in the core-stateless networks. In this paper, we proposed simple Layered Fair Queueing (SLFQ), another core-stateless mechanism to approximate fair bandwidth allocation without per-flow state. SLFQ use simple layered scheme for packet labeling and has simpler packet dropping algorithm than other core-stateless fair bandwidth allocation mechanisms. We presente simulations and evaluated the performance of SLFQ in comparison to other schemes. We also discussed other are as to which SLFQ is applicable.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.12C
• /
• pp.1617-1622
• /
• 2004

MPEG/Audio decoder for mobile multimedia systems requires low power consumption. Implementations of AV decoder using a single RISC processor often need high power consumption owing to cash-miss in case of insufficient cash memory. In this paper, we present a MPEG/Audio decoder for mobile handset applications and implement it on a RISC processor embedding a minimized DSP accelerator. Audio decoding algorithm is splined into two parts; computation intensive and control intensive parts. Those parts we, respectively, allocated to DSP and RISC core, which are designed to run in parallel to increase the processing efficiency. The proposed system implements MP3 and AAC decoders at l7MHz and 24MHz clocks, which are reductions of 48% and 40% of complexities in comparison with implementations on a single RISC processor. The proposed method is adequate for mobile multimedia applications with insufficient cash memory.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.3C
• /
• pp.278-286
• /
• 2010

Motion Compensated Frame Interpolation(MCFI) has been used to reduce motion jerkiness for dynamic scenes and motion blurriness for LCD-panel display as post processing for large screen and full HD(high definition) display. Conventionally, block matching algorithms (BMA) are widely used to do motion estimation for simplicity of implementation. However, there are still several drawbacks. So in this paper, we propose a novel shape-based ME algorithm to increase accuracy and reduce ME computational cost. To increase ME accuracy, we do motion estimation based on shape of moving objects. And only moving areas are included for motion estimation to reduce computational cost. The results show that the computational cost is 25 % lower than full search BMA, while the performance is similar or is better, especially in the fast moving region.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39B no.9
• /
• pp.606-613
• /
• 2014

The Internet of Things (IoT), which has recently attracted attention as next-generation IT industry, is based on a wired and wireless network platform that can connect various Things. However, it is challenging to implement the IoT platform because of the heterogeneity of the network. Particularly, the ZigBee transmission may be significantly harmed due to Wi-Fi with the relatively much higher power, and this is one of the reason making the platform implementation difficult. In this paper, the ZigBee transmission is measured and analyzed by the BEB algorithm for finding the slot time when ZigBee can transmit, and an actual transmission happens stochastically depending on the network environment. The simulation results show that it guarantees high success rate of the ZigBee transmission by overcoming Wi-Fi interference in the 2.4 GHz frequency band.

• Journal of Communications and Networks
• /
• v.18 no.4
• /
• pp.540-550
• /
• 2016

Since energy efficiency has become a significant concern for network infrastructure, next-generation network devices are expected to have embedded advanced power management capabilities. However, how to effectively exploit the green capabilities is still a big challenge, especially given the high heterogeneity of devices and their internal architectures. In this paper, we introduce a hierarchical power management architecture (HPMA) which represents physical components whose power can be monitored and controlled at various levels of a device as entities. We use energy aware state (EAS) as the power management setting mode of each device entity. The power policy controller is capable of getting information on how many EASes of the entity are manageable inside a device, and setting a certain EAS configuration for the entity. We propose the optimal local control policy which aims to minimize the router power consumption while meeting the performance constraints. A first-order Markov chain is used to model the statistical features of the network traffic load. The dynamic EAS configuration problem is formulated as a Markov decision process and solved using a dynamic programming algorithm. In addition, we demonstrate a reference implementation of the HPMA and EAS concept in a NetFPGA frequency scaled router which has the ability of toggling among five operating frequency options and/or turning off unused Ethernet ports.