• 한국정보통신학회논문지
• /
• 제17권12호
• /
• pp.2843-2852
• /
• 2013

중첩된 환경의 이동 네트워크에서 이동 노드는 여러 개의 이동 라우터 중 하나를 선정하여 정보를 교환하게 된다. 이동 노드에게 기존의 상향식 또는 하향식 방법으로 지정된 이동 라우터는 최적의 이동 라우터가 아닐 수 있다. 이러한 경우, 이동 노드는 빈번한 핸드오버 및 바인딩 갱신을 발생시켜 이동 노드의 QoS(Quality of Service)를 저해 할 수 있다. 본 논문에서는 중첩된 환경의 이동 네트워크에서 이동 노드의 이동 특성과 이동 라우터의 QoS 정보를 기반으로 최적의 이동 라우터를 선정하는 방안을 제시한 후, MLP(Multi-layered Perceptron)를 이용하여 중첩 이동 네트워크의 이동 라우터 선정 방안을 학습시킨다. 학습된 MLP의 학습 결과와 실제 선정 결과를 분석하여 제안한 MLP 구조가 대규모의 중첩된 환경의 이동 네트워크에서 사용 가능함을 증명한다.

• 한국컴퓨터정보학회논문지
• /
• 제10권6호
• /
• pp.279-286
• /
• 2005

본 연구에서는 캐피탈시장에서의 고객신용예측을 위한 모형으로 여러 가지 인공신경망(Neural Network) 모형들을 유전자 알고리즘(Genetic Algorithm)을 이용하여 통합한 신용예측모형을 제안하였다. 10개의 학습된 인공신경망 모형들을 유전자알고리즘을 이용하여 종류별로 통합하여 MLP (Multi-Layered Perceptron), Linear, RBF(Radial Basis Function) 세 가지의 대표모델을 얻고 이를 다시 하나의 인공신경망 모델로 통합하였다. 이를 통합되기 이전의 각각의 인공신경망 모형들과 성능을 비교, 분석하여 본 연구에서 제안한 통합모형의 유효성과 통합방법의 타당성을 제시하였다.

• 지능정보연구
• /
• 제1권1호
• /
• pp.135-148
• /
• 1995

Neural Networks have been advocated as an alternative to statistical forecasting methods. However, the empirical evidences are not consistent. In the present experiments, multi-layered perceptron (MLP) are adopted as approximator to the time series generating processes. To prevent the MLP from being overfitted to the given time series, the information obtained from ARMA modeling is used to determine the architecture of MLP. The proposed approach was tested empirically using the subsamples of the 111 time series used in the first Markridakis Competition. The forecasting results were analyzed to find out the factors that affect the performance of MLP. The experimental results show that the proposed approach outperforms ARMA models in terms of fitting and forecasting accuracy. In addition, it is found that the use of deseasonalized data improves the forecasting accuracy of MLP.

• 한국음향학회지
• /
• 제13권6호
• /
• pp.5-14
• /
• 1994

이 논문은 오차역전달(error back-propagation) 알고리듬을 갖는 다층구조 퍼셉트런(Multi-Layered Perceptron)을 사용하여 우리말 단어음성을 화자종속으로 기계 인식하는 실험에 관한 연구 결과다. 대상단어는 시외 자동전화 지역번호표에서 임의로 선택한 50개 지역명이며, 이 중 43개는 2음절로 구성되어있고 나머지 7개는 3음절이다. 단어를 음소나 음절별로 분리(segmentation)하지 않고, 단어의 각 부분에서 골고루 추출된 특징성분을 신경망에 입력하는 방법을 사용했다. 그렇게 함으로써 발음지속시간에 관계없는 결과를 얻을 수 있으며, 이 때 사용된 특징 성분은 선형예측분석으로 구해진 PARCOR계수다. 전체학습과 구분학습의 비교, 프레임 갯수와 PARCOR차수에 대한 인식률의 의존도, 중간층 뉴런의 갯수에 대한 인식률의 변동, 그리고 출력층 뉴런의 구성 방법에 따른 비교 등 4가지 실험을 통하여 가장 최량의 조건을 찾아보고자 하였다. 이 연구를 발전시킨다면 실시간의 화자독립 소규모어휘 음성인식이 가능해질 것으로 보인다.

• Earthquakes and Structures
• /
• 제15권4호
• /
• pp.431-441
• /
• 2018

This study provides fragility-based assessment of seismic performance of reinforced concrete bridges. Seismic fragility curves were created using nonlinear analysis (NA) and artificial neural networks (ANNs). Nonlinear response history analyses were performed, in order to calculate the seismic performances of the bridges. To this end, 306 bridge-earthquake cases were considered. A multi-layered perceptron (MLP) neural network was implemented to predict the seismic performances of the selected bridges. The MLP neural networks considered herein consist of an input layer with four input vectors; two hidden layers and an output vector. In order to train ANNs, 70% of the numerical results were selected, and the remained 30% were employed for testing the reliability and validation of ANNs. Several structures of MLP neural networks were examined in order to obtain suitable neural networks. After achieving the most proper structure of neural network, it was used for generating new data. A total number of 600 new bridge-earthquake cases were generated based on neural simulation. Finally, probabilistic seismic safety analyses were conducted. Herein, fragility curves were developed using numerical results, neural predictions and the combination of numerical and neural data. Results of this study revealed that ANNs are suitable tools for predicting seismic performances of RC bridges. It was also shown that yield stresses of the reinforcements is one of the important sources of uncertainty in fragility analysis of RC bridges.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권7호
• /
• pp.1657-1670
• /
• 2013

The increase in the number of music files in smart phone and MP3 player makes it difficult to find the music files which people want. So, Query-by-Singing/Humming (QbSH) systems have been developed to retrieve music from a user's humming or singing without having to know detailed information about the title or singer of song. Most previous researches on QbSH have been conducted using musical instrument digital interface (MIDI) files as reference songs. However, the production of MIDI files is a time-consuming process. In addition, more and more music files are newly published with the development of music market. Consequently, the method of using the more common MPEG-1 audio layer 3 (MP3) files for reference songs is considered as an alternative. However, there is little previous research on QbSH with MP3 files because an MP3 file has a different waveform due to background music and multiple (polyphonic) melodies compared to the humming/singing query. To overcome these problems, we propose a new QbSH method using MP3 files on mobile device. This research is novel in four ways. First, this is the first research on QbSH using MP3 files as reference songs. Second, the start and end positions on the MP3 file to be matched are estimated by using multi-layered perceptron (MLP) prior to performing the matching with humming/singing query file. Third, for more accurate results, four MLPs are used, which produce the start and end positions for dynamic time warping (DTW) matching algorithm, and those for chroma-based DTW algorithm, respectively. Fourth, two matching scores by the DTW and chroma-based DTW algorithms are combined by using PRODUCT rule, through which a higher matching accuracy is obtained. Experimental results with AFA MP3 database show that the accuracy (Top 1 accuracy of 98%, with an MRR of 0.989) of the proposed method is much higher than that of other methods. We also showed the effectiveness of the proposed system on consumer mobile device.

• Geomechanics and Engineering
• /
• 제34권5호
• /
• pp.507-527
• /
• 2023

Accurately estimation of the geo-mechanical parameters in Artificial Ground Freezing (AGF) is a most important scientific topic in soil improvement and geotechnical engineering. In order for this, one way is using classical and conventional constitutive models based on different theories like critical state theory, Hooke's law, and so on, which are time-consuming, costly, and troublous. The others are the application of artificial intelligence (AI) techniques to predict considered parameters and behaviors accurately. This study presents a comprehensive data-mining-based model for predicting the Young's Modulus of frozen sand under the triaxial test. For this aim, several single and hybrid models were considered including additive regression, bagging, M5-Rules, M5P, random forests (RF), support vector regression (SVR), locally weighted linear (LWL), gaussian process regression (GPR), and multi-layered perceptron neural network (MLP). In the present study, cell pressure, strain rate, temperature, time, and strain were considered as the input variables, where the Young's Modulus was recognized as target. The results showed that all selected single and hybrid predicting models have acceptable agreement with measured experimental results. Especially, hybrid Additive Regression-Gaussian Process Regression and Bagging-Gaussian Process Regression have the best accuracy based on Model performance assessment criteria.

• 한국전자파학회논문지
• /
• 제21권12호
• /
• pp.1460-1466
• /
• 2010

본 논문은 바이스태틱 RCS와 모노스태틱 RCS를 이용하여 각각 표적 구분 실험을 수행하고 그 성능을 비교 분석하였다. 모노스태틱 및 바이스태틱 RCS로부터 특성을 추출하기 위하여 시간-주파수 영역 해석법인 STFT와 CWT를 이용하였으며, 다중 퍼셉트론 신경망을 구분기로 이용하였다. 실험 결과, 모노스태틱과 바이스태틱 RCS 모두 CWT가 STFT보다 더 나은 구분 성능을 보여주었다. 또한, STFT에서는 바이스태틱 RCS를 이용했을 때, CWT에서는 모노스태틱 RCS를 이용하였을 때 대체적으로 더 좋은 성능을 나타내었다. 결과적으로 본 논문을 통하여 바이스태틱 RCS도 모노스태틱 RCS처럼 표적 구분에 똑같이 적용할 수 있다는 것을 알 수 있었다.

• 상하수도학회지
• /
• 제25권4호
• /
• pp.581-589
• /
• 2011

Generally, treated water or raw water is transported into storage reservoirs which are receiving facilities of local governments from multi-regional water supply systems. A water supply control and operation center is operated not only to manage the water facilities more economically and efficiently but also to mitigate the shortage of water resources due to the increase in water consumption. To achieve the goal, important information such as the flow-rate in the systems, water levels of storage reservoirs or tanks, and pump-operation schedule should be considered based on the resonable water demand forecasting. However, it is difficult to acquire the pattern of water demand used in local government, since the operating information is not shared between multi-regional and local water systems. The pattern of water demand is irregular and unpredictable. Also, additional changes such as an abrupt accident and frequent changes of electric power rates could occur. Consequently, it is not easy to forecast accurate water demands. Therefore, it is necessary to introduce a short-term water demands forecasting and to develop an application of the forecasting models. In this study, the forecasting simulator for water demand is developed based on mathematical and neural network methods as linear and non-linear models to implement the optimal water demands forecasting. It is shown that MLP(Multi-Layered Perceptron) and ANFIS(Adaptive Neuro-Fuzzy Inference System) can be applied to obtain better forecasting results in multi-regional water supply systems with a large scale and local water supply systems with small or medium scale than conventional methods, respectively.

• 한국지리정보학회지
• /
• 제2권2호
• /
• pp.69-78
• /
• 1999

본 논문에서는 한반도의 지역별 강수량 예측을 위한 신경망 기법을 소개한다. 시계열 패턴 예측 문제에 적용될 수 있는 기존의 다양한 신경망 모델의 특성을 분석하고 이로부터 강수량 예측 문제에 적합한 모델 및 학습 알고리즘을 제시한다. 본 논문에서 제시하는 모델은 계층적구조의 신경망으로 각 노드의 출력값은 일정기간동안 버퍼에 저장되어 상위계층에 입력으로 작용한다. 본 연구에서는 제안된 모델에 대하여 이중연결형태의 시냅스 구조를 채택하고, 이에 대한 네트워크의 동작특성과 학습알고리즘 등을 정의한다. 이러한 이중연결구조는 기존의 다층퍼셉트론에서 바이어스 노드의 역할을 담당하며, 노드가 갖는 특징들간의 관계를 효과적으로 반영함으로써 기존의 전형적인 시계열 예측 신경망인 FIR(Finite Impulse Response) 네트워크와 비교할 때 학습의 효율을 개선시킨다. 제시된 이론은 월별 및 계절별 강수량 예측 실험에 적용하였다. 신경망 예측기의 학습자료로서 과거 수십년동안 관측된 강수량 데이터와 해수표면온도 데이터를 사용하며 예측 실험결과로부터 제시된 이론의 타당성을 고찰한다.