• Proceedings of the Korea Water Resources Association Conference
• /
• 2009.05a
• /
• pp.1292-1295
• /
• 2009

일반적으로 유역의 기저유출 산정에는 적용의 간편성을 이유로 수평직선분리법, N-day법등을 주로 사용해 왔으며 이를 단기호우사상에 대한 모의에 적용해 왔다. 그러나 수평직선분리법이나 N-day에의한 기저유량의 산출은 연구자의 주관성이 반영될 수 있는 가능성이 다분하며 총 유출에 대한 기저 유출의 기여가 상대적으로 크게 되는 장기유출모의에 이용하기에는 효율적이지 못할 뿐 아니라 분석을 수행하는 사람에 따라서 그 결과에 많은 차이가 있을 수 있다. 그래서 최근에는 이러한 문제를 해결하기 위해서 다양한 'Digital Filtering' 방법이 수문곡선 분리에 많이 사용되고 있다. Eckhardt 필터는 출력의 신호대 잡음비가 최소화를 목적함수로 사용하는 최적선형필터의 형태를 갖고 있으며, BFImax 변수 값을 이용하여 수문분석 시 대수층별 특성을 반영할 수 있는 장점을 지니고 있다. 따라서 BFImax 변수 값에 따라서 분리된 직접유출과 기저유출 값에는 상당한 차이가 발생할 수 있는데, 정확한 수문분석을 위해서는 연구대상 유역 내 대수층의 특성에 가장 부합되는 BFImax 변수 값을 구하여야 하는 어려움이 있다. 이러한 문제를 해결하기 위하여 감수곡선 분석방법과 최적화 기법을 이용하여 BFImax 변수 값을 결정해 주는 모듈을 사용하고 있다. 금강유역의 수문곡선분리를 위해 먼저 금강 유역 내 관측소의 강우 및 수위 일 자료를 수집하고 수위자료는 동향, 옥천, 천천, 청성, 호탄지점의 자료를 이용하였다. 관측단위는 일 단위를 사용하였다. 분리된 수문곡선에 대한 검증은 지하수관측이나 중간유출에 대한 관측에 한계가 있기 때문에 정량적인 검증은 쉽지 않은 상황이고 수문곡선에 대한 시각적 판단에 의지하고 있다. 하지만 효과적인 기저유출분리가 가능해진다면 하천 건천화에 대한 정확한 진단과 함께 기후변화에 따른 지하수 및 지표수 영향에 대한 보다 신뢰도 있는 전망이 가능해지므로 매우 중요한 연구 분야라 판단된다.

• Journal of Intelligence and Information Systems
• /
• v.7 no.2
• /
• pp.51-63
• /
• 2001

In supervised machine learning, an induction algorithm, which is able to extract rules from data with learning capability, provides a useful tool for data mining. Practical induction algorithms are known to degrade in prediction accuracy and generate complex rules unnecessarily when trained on data containing superfluous features. Thus it needs feature subset selection for better performance of them. In feature subset selection on the induction algorithm, wrapper method is repeatedly run it on the dataset using various feature subsets. But it is impractical to search the whole space exhaustively unless the features are small. This study proposes a heuristic method that uses sensitivity analysis of neural networks to the wrapper method for generating rules with higher possible accuracy. First it gives priority to all features using sensitivity analysis of neural networks. And it uses the wrapper method that searches the ordered feature space. In experiments to three datasets, we show that the suggested method is capable of selecting a feature subset that improves the performance of the induction algorithm within certain iteration.

• Journal of Korea Multimedia Society
• /
• v.4 no.4
• /
• pp.333-338
• /
• 2001

In this paper, fuzzy-ARTMAP equalizer is developed mainly for overcoming the obstacles, such as complexity and long training, in implementing the previously developed neural-basis equalizers. The proposed fuzzy-ARTMAP equalizer is fast and easy to train and includes capabilities not found in other neural network approaches a small number of parameters, no requirements for the choice of initial weights, no risk of getting trapped in local minima, and capability of adding new data without retraining previously trained data. In simulation studies, binary signals were generated at random from linear channel with Gaussian noise. The performance of the proposed equalizer is compared with other neural net basis equalizers, such as MLP and RBF equalizers. The fuzzy ARTMAP equalizer combines relatively simple structure and fast processing speed; it gives accurate results for nonlinear problems that cannot be solved with a linear equalizer.

• The KIPS Transactions:PartB
• /
• v.19B no.1
• /
• pp.19-26
• /
• 2012

The rapid increase of information imposes new demands of content management. The purpose of automatic audio segmentation and classification is to meet the rising need for efficient content management. With this reason, this paper proposes a high-accuracy algorithm that segments audio signals and classifies them into different classes such as speech, music, silence, and environment sounds. The proposed algorithm utilizes support vector machine (SVM) to detect audio-cuts, which are boundaries between different kinds of sounds using the parameter sequence. We then extract feature vectors that are composed of statistical data and they are used as an input of fuzzy c-means (FCM) classifier to partition audio-segments into different classes. To evaluate segmentation and classification performance of the proposed SVM-FCM based algorithm, we consider precision and recall rates for segmentation and classification accuracy for classification. Furthermore, we compare the proposed algorithm with other methods including binary and FCM classifiers in terms of segmentation performance. Experimental results show that the proposed algorithm outperforms other methods in both precision and recall rates.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.1
• /
• pp.1-5
• /
• 2003

In this paper, we realized a system that converts the character images of the printed Korean alphabet (Hangul) to the editable text documents by using the black and white CCD camera, We were able to abstract the contours information of the character which is based on the structural character by using the boundary tracing technique that is strong to the noise on the character recognition. By using the contours information, we recognized the horizontal vowels and vertical vowels of the character image and classify the character into the six patterns. After that, the character is divided to the unit of the consonant and vowel. The vowels are recognized by using the maximum length projection. The separated consonants are recognized by comparing the inputted pattern with the standard pattern that has the phase information of the boundary line change. We realized a system that the recognized characters are inputted to the word editor with the editable KS Hangul completion type code.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.2
• /
• pp.175-180
• /
• 2015

In this paper, GPS / GLONASS receiving a small active antenna is proposed. A microstrip patch antenna which supports dual-band (GPS and GLONASS) was optimized. The antenna size is $13{\times}13{\times}3.6mm$. The jig was changed to confirm the proposed antenna characteristic size, was adjusted to feed gap of the patch antenna, it was confirmed by change in LNA shield case or not. The antenna jig size is $65.6{\times}13{\times}0.8mm$. The maximum gain of the GPS band is 3.78dBi, the maximum gain of the GLONASS bands is 4dBi. To amplify the Satellite reception signal level, one-stage low noise amplifier(LNA) was designed. The LNA chip was using the BGA715 N7, the LNA gain is 19.9dB. The utilization possibility of the GPS / GLONASS receiving a small active antenna could be confirmed according to compare and analyze the simulation and measurement data.

• Journal of the Korean Society of Radiology
• /
• v.9 no.7
• /
• pp.439-443
• /
• 2015

An electrical signals of a conventional radiation medical imaging sensor are obtained by charge integration method. In this study, the polycrystalline cadmium telluride(p-CdTe) film was fabricated by a thermal evaporation method for the photon counting sensor development with excellent resolution in low exposure dose. From the fabricated p-CdTe sensor, the physical properties(SEM, XRD) and the electrical properties(leakage current, x-ray sensitivity, SNR) were evaluated. As a result, the leakage current of below $5nA/cm^2$ and $7{\mu}C/cm^2-R$ of the X-ray sensitivity were showed in below $1V/{\mu}m$. In addition, the signal to noise ratio showed the values of above 5000 at operating voltage.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.1
• /
• pp.119-124
• /
• 2014

In this paper, A GSm/WCDMA band antenna which can be confirmed positioning information of a container by using the GPS/GLONASS bands on one board and can be sent the positioning information to the mobile communication network in real time is designed. A microstrip patch antennas which supports dual-band (GPS and GLONASS) was optimized. The antenna size is $25{\times}25{\times}5[mm]$. A chip monopole antennas which supports dual-band (GSM and WCDMA) was optimized. The antenna size is $27{\times}8{\times}3.2[mm]$. To amplify the Satellite reception signal level, two-stage low noise amplifier(LNA) was designed. The LNA gain is 27[dB]. The size of Jig for antennas measuring is $100{\times}30{\times}1[mm]$.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.8
• /
• pp.18-26
• /
• 2015

Measuring the heart rate during exercise is important to properly control the amount of exercise. With the recent advent of smart device usage, there is a dramatic increase in interest in devices for the real-time measurement of the heart rate during exercise. During intensive exercise, accurate heart rate estimation from wrist-type photoplethysmography (PPG) signals is a very difficult problem due to motion artifact (MA). In this study, we propose an efficient algorithm for an accurate estimation of the heart rate from wrist-type PPG signals. For the twelve data sets, the proposed algorithm achieves the average absolute error of 1.38 beat per minute (BPM) and the Pearson correlation between the estimates and the ground-truth of heart rate was 0.9922. The proposed algorithm presents the strengths in an accurate estimation together with a fast computation speed, which is attractive in application to wearable devices.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.29 no.10
• /
• pp.745-751
• /
• 2018

This paper reports on the design of a multiband multiple-input and multiple-output(MIMO) antenna for long-term evolution(LTE) vehicular communication and includes an analysis of the throughput field test results that were acquired by mounting the antenna to a vehicle. The antenna used for the field test was designed as a planar structure and included multiple stubs to obtain multiband resonant characteristics operating in the LTE(0.8~0.9 GHz, 1.7~2.2 GHz), Wi-Fi(2.4~2.48 GHz), and wireless access in vehicular environments (WAVE)(5.8~5.9 GHz) frequency bands. For the field test, antenna prototypes were mounted on the dashboard and roof of a vehicle and connected to the experimental LTE modem. The data transfer rate(throughput), signal-to-interference-plus-noise ratio(SINR), and reference signal received quality(RSRQ) were measured and analyzed in various real-world radio wave environments. Based on these results, the relationship between the SINR and throughput according to the field intensity is confirmed.