• Journal of the Korean Society of Radiology
• /
• v.15 no.4
• /
• pp.547-554
• /
• 2021

In order to quickly and accurately diagnose pneumonia on a chest X-ray image, different batch sizes of 4, 8, 16, and 32 were applied to the same Xception deep learning model, and modeling was performed 3 times, respectively. As a result of the performance evaluation of deep learning modeling, in the case of modeling to which batch size 32 was applied, the results of accuracy, loss function value, mean square error, and learning time per epoch showed the best results. And in the accuracy evaluation of the Test Metric, the modeling applied with batch size 8 showed the best results, and the precision evaluation showed excellent results in all batch sizes. In the recall evaluation, modeling applied with batch size 16 showed the best results, and for F1-score, modeling applied with batch size 16 showed the best results. And the AUC score evaluation was the same for all batch sizes. Based on these results, deep learning modeling with batch size 32 showed high accuracy, stable artificial neural network learning, and excellent speed. It is thought that accurate and rapid lesion detection will be possible if a batch size of 32 is applied in an automatic diagnosis study for feature extraction and classification of pneumonia in chest X-ray images using deep learning in the future.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.10
• /
• pp.1423-1431
• /
• 2022

Volatility is one of the variables that the Black-Scholes model requires for option pricing. It is an unknown variable at the present time, however, since the option price can be observed in the market, implied volatility can be derived from the price of an option at any given point in time and can represent the market's expectation of future volatility. Although volatility in the Black-Scholes model is constant, when calculating implied volatility, it is common to observe a volatility smile which shows that the implied volatility is different depending on the strike prices. We implement supervised learning to target implied volatility by adding V-KOSPI to ease volatility smile. We examine the estimation performance of KOSPI200 index options' implied volatility using various Machine Learning algorithms such as Linear Regression, Tree, Support Vector Machine, KNN and Deep Neural Network. The training accuracy was the highest(99.9%) in Decision Tree model and test accuracy was the highest(96.9%) in Random Forest model.

• Proceedings of the KSR Conference
• /
• 2011.05a
• /
• pp.1701-1708
• /
• 2011

A typical day in the subway transportation is used by hundreds of thousands are also concerned about the safety of the various workrooms with high underground fire or other less than in the subway users could be damaging even to be raised and there. In 2010, in fact, room air through vents in the fire because smoke and toxic gas accident victims, and train service suspended until such cases are often reported. In response to these incidents in subway stations, even if the latest IT technology, wireless sensor network technology and intelligent video surveillance technology by integrating fire and structural integrity, such as a comprehensive integrated surveillance system to monitor the development of intelligent urban transit system and are under study. In this study, prior to the application of the monitoring system into the field stations, authors carried out the ZigBee-based wireless sensor networks performance analyzation in the Chungmuro station. The test results at a communications room and ventilation room of the station are summarized and analyzed.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.47 no.8
• /
• pp.99-107
• /
• 2010

In a single frequency network (SFN) for Advanced Television Systems Committee (ATSC) terrestrial digital television (DTV) system, the interferences induced by the multiple transmitters and/or repeaters using the same frequency are inevitable. Since the presence of interferences results in performance degradation of the SFN, it is crucial to manipulate the interferences by adjusting the transmit power and timing of each transmitter and repeater. In the ATSC terrestrial DTV system, in order to facilitate the interference manipulation process, a transmitter identification (TxID) signal which is uniquely embedded in the signal to be transmitted from each transmitter and repeater is recommended. Even though the injection level of the TxID signal is much lower than the DTV signal, the TxID signal injection infects the DTV signal. Hence, the effect of the TxID signal on the DTV signal must be investigated before deployment. In this paper, the effect of the TxID signal on the performance of legacy DTV receivers under additive white Gaussian noise and multipath channel environments is investigated not only with computer simulation but also with laboratory and field tests. The test results show that the average threshold of visibility degradation of the legacy DTV receivers due to the TxID signal injection is less than 0.2 dB at the TxID injection level of -30 dB.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.25 no.5
• /
• pp.1043-1057
• /
• 2015

In order to recognize intelligent threats quickly and detect and respond to them actively, major public bodies and private institutions operate and administer an Intrusion Detection Systems (IDS), which plays a very important role in finding and detecting attacks. However, most IDS alerts have a problem that they generate false positives. In addition, in order to detect unknown malicious codes and recognize and respond to their threats in advance, APT response solutions or actions based systems are introduced and operated. These execute malicious codes directly using virtual technology and detect abnormal activities in virtual environments or unknown attacks with other methods. However, these, too, have weaknesses such as the avoidance of the virtual environments, the problem of performance about total inspection of traffic and errors in policy. Accordingly, for the effective detection of intrusion, it is very important to enhance security monitoring, consequentially. This study discusses a plan for the reduction of false positives as a plan for the enhancement of security monitoring. As a result of an experiment based on the empirical data of G, rules were drawn in three types and 11 kinds. As a result of a test following these rules, it was verified that the overall detection rate decreased by 30% to 50%, and the performance was improved by over 30%.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.42 no.8 s.338
• /
• pp.35-42
• /
• 2005

This paper describes novel flip-flops with improved robustness and reduced power consumption. Variable sampling window flip-flop (VSWFF) adjusts the width of the sampling window according to input data, providing robust data latching as well as shorter hold time. The flip-flop also reduces power consumption for higher input switching activities as compared to the conventional low-power flip-flop. Clock swing-reduced variable sampling window flip-flop (CSR-VSWFF) reduces clock power consumption by allowing the use of a small swing clock. Unlike conventional reduced clock swing flip-flops, it requires no additional voltage higher than the supply voltage, eliminating design overhead related to the generation and distribution of this voltage. Simulation results indicate that the proposed flip-flops provide uniform latency for narrower sampling window and improved power-delay product as compared to conventional flip-flops. To evaluate the performance of the proposed flip-flops, test structures were designed and implemented in a $0.3\mu m$ CMOS process technology. Experimental result indicates that VSWFF yields power reduction for the maximum input switching activity, and a synchronous counter designed with CSR-VSWFF improves performance in terms of power consumption with no use of extra voltage higher than the supply voltage.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.49 no.2
• /
• pp.23-31
• /
• 2012

With advance of high bandwidth network infrastructure, the requirement is dramatically increasing to cooperate between the users who are far from each other and make use of bulk data. However, as the prominent data transmission protocol, it is well known that TCP suffers some degrees of inefficiency for bulk data transmission when RTT is relatively big. So, some works are on going to suggest a new transmission method to utilize the bandwidth in effective. UDT(UDP-based Data Transfer protocol) is one of these. It is a UDP based application level protocol which can guarantee reliability and stability. much like as TCP. In this paper, we present a design and implementation of UDT based bulk data transmission tool by applying parallel and compressive techniques. The implementation result is examined to measured its performance improvement on a real test-bed, and then compared with existing bulk data transmission tools. Experimental results show that proposed tool is more stable and shows greater performance than that of native UDT. Especially, the performances show 244% improvement in RTT 400ms without losses and 229% in RTT 250ms with 0.005% losses respectively.

• Corrosion Science and Technology
• /
• v.9 no.4
• /
• pp.147-152
• /
• 2010

Conventional paints for conversion coating applications in steel production derived mainly from water-based polymer dispersions containing several additives actually show good general performance, but suffer from poor scratch and abrasion resistance during use. The reason for this is because the relatively soft organic binder matrix dominates the mechanical surface properties. In order to maintain the high quality and decorative function of coated steel sheets, the mechanical performance of the surface needs to be improved significantly. In fact the wear resistance should be enhanced without affecting the optical appearance of the coatings by using appropriate nanoparticulate additives. In this direction, nanocomposite coating compositions (Nanomer$^{(R)}$) have been derived from water-based polymer dispersions with an increasing amount of surface-modified nanoparticles in aqueous dispersion in order to monitor the effect of degree of filling with rigid nanoparticles. The surface of nanoparticles has been modified for optimum compatibility with the polymer matrix in order to achieve homogeneous nanoparticle dispersion over the matrix. This approach has been extended in such a way that a more expanded hybrid network has been condensed on the nanoparticle surface by a hydrolytic condensation reaction in addition to the quasi-monolayer type small molecular surface modification. It was expected that this additional modification will lead to more intensive cross-linking in coating systems resulting in further improved scratch-resistance compared to simple addition of nanoparticles with quasi-monolayer surface modification. The resulting compositions have been coated on zinc-galvanized steel and cured. The wear resistance and the corrosion protection of the modified coating systems have been tested in dependence on the compositional change, the type of surface modification as well as the mixing conditions with different shear forces. It has been found out that for loading levels up to 50 wt.-% nanoparticles, the mechanical wear resistance remains almost unaffected compared to the unmodified resin. In addition, the corrosion resistance remained unaffected even after $180^{\circ}$ bending test showing that the flexibility of coating was not decreased by nanoparticle addition. Electron microscopy showed that the inorganic nanoparticles do not penetrate into the organic resin droplets during the mixing process but rather formed agglomerates outside the polymer droplet phase resulting in quite moderate cross linking while curing, because of viscosity. The proposed mechanisms of composite formation and cross linking could explain the poor effect regarding improvement of mechanical wear resistance and help to set up new synthesis strategies for improved nanocomposite morphologies, which should provide increased wear resistance.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.7
• /
• pp.18-25
• /
• 2014

To increase wireless capacity, the concurrent use of multiple wireless interfaces on different frequency bands, called aggregation, can be considered. In this paper, we focus on aggregation of multiple Wi-Fi interfaces with packet-level traffic spreading between the interfaces. Two aggregation schemes, link bonding and multipath TCP (MPTCP), are tested and compared in a dualband Wi-Fi radio system with their Linux implementation. Various test conditions such as traffic types, network delay, locations, interface failures and configuration parameters are considered. Experimental results show that aggregation increases throughput performance significantly over the use of a single interface. Link bonding achieves lower throughput than MPTCP due to duplicate TCP acknowledgements (ACKs) resulting from packet reordering and filtering such duplicate ACKs out is considered as a possible solution. However, link bonding is fast responsive to links' status changes such as a link failure. It is shown that different combinations of interface weights for packet spread in link bonding result in different throughput performance, envisioning a spatio-temporal adaptation of the weights. We also develop a mathematical model of power consumption and compare the power efficiency of the schemes applying different power consumption profiles.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.4
• /
• pp.789-795
• /
• 2020

Many deaths have been reported due to the worldwide pandemic of COVID-19. In order to prevent the further spread of COVID-19, it is necessary to quickly and accurately read images of suspected patients and take appropriate measures. To this end, this paper introduces a deep learning-based COVID-19 chest X-ray reading technique that can assist in image reading by providing medical staff whether a patient is infected. First of all, in order to learn the reading model, a sufficient dataset must be secured, but the currently provided COVID-19 open dataset does not have enough image data to ensure the accuracy of learning. Therefore, we solved the image data number imbalance problem that degrades AI learning performance by using a Stacked Generative Adversarial Network(StackGAN++). Next, the DenseNet-based classification model was trained using the augmented data set to develop the reading model. This classification model is a model for binary classification of normal chest X-ray and COVID-19 chest X-ray, and the performance of the model was evaluated using part of the actual image data as test data. Finally, the reliability of the model was secured by presenting the basis for judging the presence or absence of disease in the input image using Grad-CAM, one of the explainable artificial intelligence called XAI.