• The Korean Journal of Cytopathology
• /
• v.4 no.1
• /
• pp.25-29
• /
• 1993

We describe cytologic findings of two cases of pilomatrixoma which had been cytologically misdiagnosed as suspicious malignant and malignant lesions in 35 year-old and 22 year-old females who presented a palpable neck mass. The cytologic smears showed many basaloid cells with a high nuclear-cytoplasmic ratio, nuclear hyperchromatism and prominent nucleoli, keratinized squamous cells with pyknotic nuclei, foreign body giant cells, and chronic inflammatory cells in necrotic back-ground. Retrospective view of this aspiration smear revealed that these findings were characteristic features of pilomatrixoma, and the evenly distributed chromatin pattern as well as the lack of nuclear pleomorphism were considered to be the differential points from malignant neoplasm. Pilomatrixoma is a benign neoplasm which should be included in differential diagnosis if the fine needle aspiration cytologic smear of a neck mass or subcutaneous mass of any site showed these features.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.2
• /
• pp.416-424
• /
• 2017

In this study, we propose a design of digits recognition system based on RBFNNs through a comparative study of pre-processing algorithms in order to recognize digits in handwritten. Histogram of Oriented Gradient(HOG) is used to get the features of digits in the proposed digits recognition system. In the pre-processing part, a dimensional reduction is executed by using Principal Component Analysis(PCA) and (2D)2PCA which are widely adopted methods in order to minimize a loss of the information during the reduction process of feature space. Also, The architecture of radial basis function neural networks consists of three functional modules such as condition, conclusion, and inference part. In the condition part, the input space is partitioned with the use of fuzzy clustering realized by means of the Fuzzy C-Means algorithm. Also, it is used instead of gaussian function to consider the characteristic of input data. In the conclusion part, the connection weights are used as the extended type of polynomial expression such as constant, linear, quadratic and modified quadratic. By using MNIST handwritten digit benchmarking database, experimental results show the effectiveness and efficiency of proposed digit recognition system when compared with other studies.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.4
• /
• pp.862-870
• /
• 2011

In this paper, we introduce a new topology of Radial Basis Function-based Polynomial Neural Networks (RPNN) that is based on a genetically optimized multi-layer perceptron with Radial Polynomial Neurons (RPNs). This study offers a comprehensive design methodology involving mechanisms of optimization algorithms, especially Fuzzy C-Means (FCM) clustering method and Particle Swarm Optimization (PSO) algorithms. In contrast to the typical architectures encountered in Polynomial Neural Networks (PNNs), our main objective is to develop a design strategy of RPNNs as follows : (a) The architecture of the proposed network consists of Radial Polynomial Neurons (RPNs). In here, the RPN is fully reflective of the structure encountered in numeric data which are granulated with the aid of Fuzzy C-Means (FCM) clustering method. The RPN dwells on the concepts of a collection of radial basis function and the function-based nonlinear (polynomial) processing. (b) The PSO-based design procedure being applied at each layer of RPNN leads to the selection of preferred nodes of the network (RPNs) whose local characteristics (such as the number of input variables, a collection of the specific subset of input variables, the order of the polynomial, and the number of clusters as well as a fuzzification coefficient in the FCM clustering) can be easily adjusted. The performance of the RPNN is quantified through the experimentation where we use a number of modeling benchmarks - NOx emission process data of gas turbine power plant and learning machine data(Automobile Miles Per Gallon Data) already experimented with in fuzzy or neurofuzzy modeling. A comparative analysis reveals that the proposed RPNN exhibits higher accuracy and superb predictive capability in comparison to some previous models available in the literature.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.9
• /
• pp.1749-1754
• /
• 2007

In this paper, we propose a new Intra-body communication system for bio-sensor which is one of applications in PAN(Personal Area Network) using body channel. The communication systems for bio-sensor network usually transmits a lot of data acquired in sensor to the receiver in wrist or waist. So we deign the intra-body modem with high data rate, low power, and small size which are achieved by baseband communication techniques. It is noted that the baseband transmission does not requires any analog IF and RF frontends, and can be operated in lower frequency than bandpass transmission. The proposed modem operates at 10MHz band according to the characteristics of intra-body channel, and shows the capability of 5Mbps data rate at distance of 20cm, with $BER=10^{-5}$. In addition, we implement the modem within $2{\times}2cm$ area.

• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.11
• /
• pp.251-262
• /
• 2019

In this paper, we propose a simulator that provides various algorithms of RBF networks on neuromorphic chips. To develop algorithms based on neuromorphic chips, the disadvantages of using simulators are that it is difficult to test various types of algorithms, although time is fast. This proposed simulator can simulate four times more types of network architecture than existing simulators, and it provides an additional a two-layer structure algorithm in particular, unlike RBF networks provided by existing simulators. This two-layer architecture algorithm is configured to be utilized for multiple input data and compared to the existing RBF for performance analysis and validation of utilization. The analysis showed that the two-layer structure algorithm was more accurate than the existing RBF networks.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.30 no.6
• /
• pp.518-521
• /
• 2019

In this paper, an active antenna module operating in the 60 GHz band is designed and fabricated by combining a commercial transmitter chip and patch array antenna. The designed module is composed of an antenna PCB and a PCB with a transmitter chip. The frequency-control and bias-control signals are applied to the transmitter chip, using an Arduino kit. A baseband I/Q signal is also applied to the chip. A ring hybrid balun converts the output of the transmitter module to a single output, which is the output of the transmitter chip that outputs a differential output. The output is delivered to the $2{\times}4$ microstrip patch array antenna PCB as a micro-computer connector. The radiation pattern of the millimeter-wave signal of the final output is compared with the simulation results. The measured radiation patterns of the fabricated active antenna module confirm that the positions of the 3 dB beam width and null point agree well with the simulation results.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.4
• /
• pp.279-286
• /
• 2021

In this study, we looked at the appearance of Edutech, which is being put into the educational field after Corona 19, with the advent of the 4th industrial revolution. In the era of the 4th industrial revolution, the infrastructure, data, and service of Smart Stick that actively utilized ICT became the main pillars of smart education. In particular, smart education is being implemented through e-learning, smart learning, and edutech, and on this basis, it has become possible through the expansion and use of the Internet and computers, the dissemination of smart devices, and a software foundation using big data. Based on this, it was confirmed that Edutech is being implemented through the establishment of a quarantine safety net, a learning safety net, and a care safety net for individual learners and safe life based on artificial intelligence. Lastly, in order for edutech education using big data to become a discourse for everyone, it is necessary to consider artificial intelligence and ethics in the use and application of edutech.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.123-123
• /
• 2021

도시하천유역이나 복합유역 등 지역적 성향을 고려한 도달시간 산정에 관한 연구는 현재까지도 미흡한 실정이다. 소규모 유역의 홍수량을 산정할 경우 유하시간보다 유입시간 비중이 상대적으로 크다. 그러나 유하시간만을 고려하여 도달시간을 산정할 때, 소규모 유역의 경우 하도가 없고 유역면적이 5km² 내외 또는 하도의 저류 효과를 기대할 수 없는 경우 도달시간이 짧아 홍수량이 과대 산정된다. 이를 극복하고자 재해영향성평가등의 협의 실무지침에서는 도달시간 이외에 매개변수인 저류상수를 인위적으로 증가시키는 방법을 제안하고 있다. 하지만 이 방법 역시 유역의 물리적인 특성을 나타내는 변수를 왜곡한다는 근복적인 문제를 완전히 해결하지 못하였다. 이에 본 연구에서는 기존 중·대규모 하천을 대상으로 수행된 연구결과를 바탕으로 제안된 홍수 도달시간 산정방법의 한계를 극복하고, 유입시간이 지배적인 소규모 복합유역에 적용 가능한 도달시간 산정방안을 제시하고자 한다. 이를 위해 실증실험을 통해 기존 유입시간 산정식을 개선하고, 도시수문 모니터링 시범유역에 적용하여 정확성을 평가하고자 하였다. 먼저, 홍수도달 시간 측정을 위한 강우유출 실내 실험장치를 제작하였다. 실험장치는 본체(길이3m×폭1.2m×높이0.8m)와 경사조절 장치(0~15도)를 포함하고 있다. 본체 전면부를 타공(ø10mm)하고 상·하단에서 지표와 기저유출을 집수하여 티핑버킷으로 유량을 측정하였고, 토체 내에는 토양수분센서를 설치하여 강우유출 발생시간 동안 토양수분 변화를 측정하였다. 본 연구에서는 하도흐름인 유하시간(Kraven 공식)을 계산하여 도달시간을 산정하기 보다 지표면 흐름인 유입시간(Kerby 공식)에 보정계수를 도입하여 도달시간을 산정하는 방안을 검토하였다. 실험 결과, 불투수 면적비율이 증가함에 따라 도달시간은 감소하고, 불투수 유역이 하류에 위치할수록 유출발생시간이 빨라졌다. 실증실험 결과를 바탕으로 도시수문 모니터링 시범유역에 적용하여 기존 유하시간과 저류상수를 보정하는 도달시간 산정방식(연속형 Kraven)과 유입시간을 보정한 도달시간 산정(수정 Kerby)으로 도출된 유출량을 실측 유량과 비교하였다. 그 결과 제안된 홍수도달시간 산정식에서 모의된 홍수량이 기존 방식과 유사하거나 우수한 첨두홍수량을 보였으며, 설계자 임의성이 배제된 일관성있는 해석값을 제시해 줄 것으로 판단된다.

• Journal of the Korean Society of Radiology
• /
• v.82 no.4
• /
• pp.953-958
• /
• 2021

High-altitude cerebral edema (HACE) is a potentially fatal neurological syndrome that develops in persons traveling to a high altitude. We report the case of a 49-year-old male who had traveled to a high altitude, and lost consciousness for a few hours. Susceptibility-weighted images revealed multiple, fine black pepper like microbleeds along the corpus callosum with several microbleeds in the left frontal and parietal subcortical white matter. The T2-weighted images did not show any abnormal signal intensities along the corpus callosum. The diffusion-weighted images revealed small nodular high signal intensities in the basal ganglia. This report describes the atypical radiologic findings of HACE showing multiple microbleeds along the corpus callosum, without abnormal high-signal intensity on T2-weighted images.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.4
• /
• pp.39-46
• /
• 2024

Many researchers make efforts to evaluate water quality using various models. Such models require a dataset without missing values, but in real world, most datasets include missing values for various reasons. Simple deletion of samples having missing value(s) could distort distribution of the underlying data and pose a significant risk of biasing the model's inference when the missing mechanism is not MCAR. In this study, to explore the most appropriate technique for handing missing values in water quality data, several imputation techniques were experimented based on existing KNN and MICE imputation with/without the generative neural network model, Autoencoder(AE) and Denoising Autoencoder(DAE). The results shows that KNN and MICE combined imputation without generative networks provides the closest estimated values to the true values. When evaluating binary classification models based on support vector machine and ensemble algorithms after applying the combined imputation technique to the observed water quality dataset with missing values, it shows better performance in terms of Accuracy, F1 score, RoC-AuC score and MCC compared to those evaluated after deleting samples having missing values.