• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.11a
• /
• pp.175-178
• /
• 2006

본 논문에서는 주요성분분석과 상호정보 추정을 조합한 입력변수선택 기법을 제안하였다. 여기서 주요성분분석은 2차원 통계성을 이용하여 입력변수 간의 독립성을 찾기 위함이고, 상호정보의 추정은 적응적 분할을 이용하여 입력변수의 확률밀도함수를 계산함으로써 변수상호간의 종속성을 좀더 정확하게 측정하기 위함이다. 제안된 기법을 인위적으로 제시된 각 500개의 샘플을 가지는 6개의 독립신호와 1개의 종속신호를 대상으로 실험한 결과, 빠르고 정확한 변수의 선택이 이루어짐을 확인하였다.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.2
• /
• pp.1-9
• /
• 1998

ATM was adopted as the switching and multiplexing technique for BISDN which aims at transmitting traffics with various characteristics in a unified network. To construct these ATM networks, the most important aspect is the design of the switching system with high performance and different service capabilities. In this paepr, we analyze the performance of an input and output queueing switch with preemptive priority which is considered to be most suitable for ATM networks. For the analysis of an input queue, we model each input queue as two separate virtual input queues for each priority class and we approximage them asindependent Geom/Geom/1 queues. And we model a virtual HOL queue which consists of HOL cells of all virtual input queues which have the same output address to obtain the mean service time at each virtual input queue. For the analysis of an output quque, we obtain approximately the arrival process into the output queue from the state of the virtual HOL queue. We use a Markov chain method to analyze these two models and obtain the maximum throughput of the switch and the mean queueing delay of cells. and analysis results are compared with simulation to verify that out model yields accurate results.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.29A no.8
• /
• pp.34-40
• /
• 1992

This paper shows a new relational formula of multiplexing gain versus variable input bit rates useful for designing Nx1 ATM(Asynchronous Transfer Mode) multiplexer which mixes several asynchronous bit streams with different transmission rates. The relation between multiplexing gain and input bit stream speeds is derived from the occupied mean lenght(the width per unit time) of cells and the occupation probability of the number of cells at an arbitrary instant when the rates of the periodic cell strams change randomly. And the relation between multiplexing gain and variable bit rates from different number of input bit streams is analyzed accordingly. Under the condition of unlimited multiplexing speed, the more number of input bit streams increases, the bigger the multiplexing gain becomes. While for the case which restricts the multiplexing speed to a limited value, the multiplexing gain becomes smaller contrarily as the number of input bit streams continues too invrease beyond a boundary value. It is shown that for designing an ATM multiplexer according to the latter case, the combination of input bit streams should be determined such as its total bit rate is lower thean, but most apprpaximate to, the multiplexed output speed. Also the general formula evaluating the most significant parameters which should be needed to design the multiplexer is derived.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.12
• /
• pp.59-65
• /
• 1998

In this paper, a novel rail-to-rail input stage circuit with improved transconductance Is designed. Its excellent performances over whole common-mode input voltage Vcm range is demonstrated by circuit simulator HSPICE. The novel input stage circuit comprises additional 4 input transistors and 4 current sources/sinks. It maintains DC currents of signal amplifying transistors when one of the differential input stage circuits operates, but it reduces these currents to 1/4 when both differential input stage circuits operates, As a result, a operational amplifier with the novel circuit maintains nearly constant transconductance performance and unity-gain frequency in strong inversion region. The novel circuit allows an optimal frequency compensation and uniform operational amplifier performance over whole Vcm range.

• Journal of the Korea Convergence Society
• /
• v.11 no.10
• /
• pp.45-51
• /
• 2020

Recently, many games provide data related to the users' game play, and there have been a few studies that predict opponent move by combining machine learning methods. This study predicts opponent move using match data of a real-time strategy game named ClashRoyale and a multi-label classification based on machine learning. In the initial experiment, binary card properties, binary card coordinates, and normalized time information are input, and card type and card coordinates are predicted using random forest and multi-layer perceptron. Subsequently, experiments were conducted sequentially using the next three data preprocessing methods. First, some property information of the input data were transformed. Next, input data were converted to nested form considering the consecutive card input system. Finally, input data were predicted by dividing into the early and the latter according to the normalized time information. As a result, the best preprocessing step was shown about 2.6% improvement in card type and about 1.8% improvement in card coordinates when nested data divided into the early.

• Journal of Intelligence and Information Systems
• /
• v.5 no.1
• /
• pp.103-123
• /
• 1999

Input filtering as a preprocessing method is so much crucial to get good performance in time series forecasting. There are a few preprocessing methods (i.e. ARMA outputs as time domain filters, and Fourier transform or wavelet transform as time-frequency domain filters) for handling time series. Specially, the time-frequency domain filters describe the fractal structure of financial markets better than the time domain filters due to theoretically additional frequency information. Therefore, we, first of all, try to describe and analyze specially some issues on the effectiveness of different filtering methods from viewpoint of the performance of a neural network based forecasting. And then we discuss about neural network model architecture issues, for example, what type of neural network learning architecture is selected for our time series forecasting, and what input size should be applied to a model. In this study an input selection problem is limited to a size selection of the lagged input variables. To solve this problem, we simulate on analyzing and comparing a few neural networks having different model architecture and also use an embedding dimension measure as chaotic time series analysis or nonlinear dynamic analysis to reduce the dimensionality (i.e. the size of time delayed input variables) of the models. Throughout our study, experiments for integration methods of joint time-frequency analysis and neural network techniques are applied to a case study of daily Korean won / U. S dollar exchange returns and finally we suggest an integration framework for future research from our experimental results.

• The Journal of the Korea Contents Association
• /
• v.20 no.2
• /
• pp.472-477
• /
• 2020

The purpose of this study is to correct the error of lower weight input method as an alternative to reduce the specific absorption rate(SAR) in MRI. In order to prove that the SAR values not change according to the weight entered into the patient information, the 50kg phantom is placed in the coil and the input weight is changed from 10 to 100 in 10kg units to compare the SAR values. As a result, T1-weighted images had a SAR rate of 0.2W/kg and T2-weighted images had an average of 0.4W/kg. In conclusions, the SAR does not change according to the weight input by the technician before the scan, a lower weight when inputting patient information cannot be an alternative to reduce the SAR.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.11
• /
• pp.473-478
• /
• 2022

Evaluation learning based on code testing is becoming a popular solution in programming education via Online judge(OJ). In the recent past, many papers have been published on how to detect plagiarism through source code similarity analysis to support OJ. However, deep learning-based research to support automated tutoring is insufficient. In this paper, we propose Input & Output side FiLM models to predict whether the input code will pass or fail. By applying Feature-wise Linear Modulation(FiLM) technique to GRU, our model can learn combined information of Java byte codes and problem information that it tries to solve. On experimental design, a balanced sampling technique was applied to evenly distribute the data due to the occurrence of asymmetry in data collected by OJ. Among the proposed models, the Input Side FiLM model showed the highest performance of 73.63%. Based on result, it has been shown that students can check whether their codes will pass or fail before receiving the OJ evaluation which could provide basic feedback for improvements.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.4E
• /
• pp.112-119
• /
• 2004

This paper presents a method for the automatic recognition of pitch accents with no prior knowledge about the phonetic content of the signal (no knowledge of word or phoneme boundaries or of phoneme labels). The recognition algorithm used in this paper is a time-delay recurrent neural network (TDRNN). A TDRNN is a neural network classier with two different representations of dynamic context: delayed input nodes allow the representation of an explicit trajectory F0(t), while recurrent nodes provide long-term context information that can be used to normalize the input F0 trajectory. Performance of the TDRNN is compared to the performance of a MLP (multi-layer perceptron) and an HMM (Hidden Markov Model) on the same task. The TDRNN shows the correct recognition of $91.9{\%}\;of\;pitch\;events\;and\;91.0{\%}$ of pitch non-events, for an average accuracy of $91.5{\%}$ over both pitch events and non-events. The MLP with contextual input exhibits $85.8{\%},\;85.5{\%},\;and\;85.6{\%}$ recognition accuracy respectively, while the HMM shows the correct recognition of $36.8{\%}\;of\;pitch\;events\;and\;87.3{\%}$ of pitch non-events, for an average accuracy of $62.2{\%}$ over both pitch events and non-events. These results suggest that the TDRNN architecture is useful for the automatic recognition of pitch accents.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.05a
• /
• pp.473-476
• /
• 2003

Nowaday, Internet is doing the role of a large distributed information service tenter and various information and database servers managing it are in distributed network environment. However, the we have several difficulties in deciding the server to disposal input data depending on data properties. In this paper, we designed server mining mechanism and Intellectual data mining system architecture for the best efficiently dealing with input data pattern by using neural network among the various data in distributed environment. As a result, the new input data pattern could be operated after deciding the destination server according to dynamic binding method implemented by neural network. This mechanism can be applied Datawarehous, telecommunication and load pattern analysis, population census analysis and medical data analysis.