• Journal of the Korea Society of Computer and Information
• /
• v.15 no.12
• /
• pp.11-18
• /
• 2010

In this paper, We suggest new strategies on non-interactive agents applied in a prey pursuit problem of multi agent research. The structure of the prey pursuit problem by grid space(Four agent & one prey). That is allied agents captured over one prey. That problem has long been known in interactive, non-interactive of multi agent research. We trying hard to find its own solution from non-interactive agent method on not in the same original environment(circular environment). We used ACS applied Direction vector to learning and decide on a direction. Exchange of information between agents have been previously presented (an interactive agent) out of the way information exchange ratio (non-interactive agents), applied the new method. Can also solve the problem was to find a solution. This is quite distinct from the other existing multi agent studies, that doesn't apply interactive agents but independent agent to find a solution.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.12
• /
• pp.2533-2540
• /
• 2009

Performance of processing protocols is one most important goal in a network or systems constituting the network. Measurement of performance, thus, is an essential element to not only establish the network but also develop systems. A projection in vector mathematics is the transformation of points and lines in one plane onto another plane by connecting corresponding points on the two planes with parallel lines. This is a method, as an application of vector mathematics, which is widely used in engineering as well to consider elements dedicated to the measurement object. This paper proposes a sound methodology for measuring the performance of the SIP protocol, which is based on the projection. The SIP protocol is a typical standard protocol for call-processing in the internet telephony of Next Generation Convergence Network. Owing to use the projected protocol which excludes unnecessary operation paths, the methodology can be effective in implementation and resource utilization. This paper also presents a process based on the proposed methodology to measure the performance of a SIP proxy server.

• Journal of Intelligence and Information Systems
• /
• v.13 no.1
• /
• pp.81-90
• /
• 2007

This paper shows an intelligent disease diagnosis system for public. Our system deals with 30 diseases and their typical symptoms selected based on the report from Ministry of Health and Welfare, Korea. Technically, the system uses a modified FCM algorithm for clustering diseases and the input vector consists of the result of user-selected questionnaires. The modified FCM algorithm improves the quality of clusters by applying symmetrically measure based on the fuzzy theory so that the clusters are relatively sensitive to the shape of the pattern distribution. Furthermore, we extract the highest 5 diseases only related to the user-selected questionnaires based on the fuzzy membership function between questionnaires and diseases in order to avoid diagnosing unrelated disease.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2012.05a
• /
• pp.887-887
• /
• 2012

기후변화에 의한 강우패턴의 변화는 강우량 및 강우강도의 증가로 대표되며 국립기상연구소 (2011)에 의하면 현재와 같은 탄소배출이 줄어들지 않는다면 2050년 우리나라의 강수량은 16% 증가하고 일 강수량 80mm 이상의 호우발생일수가 60%이상 증가될 것으로 전망하고 있다. 이와 같이 기후변화로 인해 발생빈도가 증가추세인 집중호우는 산사태와 같은 2차 피해를 유발하고 있으며 강우의 예측 및 실시간 모니터링은 재해 예방 및 수자원관리, 국가 방재역량 강화를 위해 연구되어야 할 분야이다. 이에 본 연구에서는 광역적 강우자료로서 미국 NOAA의 기후예측센터에 의해 제공되는 글로벌 강우량 CMORPH와 지상 강우자료와의 비교 분석을 통해 CMORPH 자료의 수자원 분야 이용 가능성을 분석하는 것을 목적으로 한다. CMORPH는 고급의 시공간적 해상도를 가지며, 단기간의 기후 예측센터 모핑(morphing) 방법에 의한 "CMORPH"라 불리우는 강우평가 알고리즘과 새로운 위성 기반 기술을 이용하여 개발되었다. CMORPH 기술에 의해 생산된 글로벌 강우 추정은 저궤도 위성 수동 마이크로파(passive microwaves, PMW) 관측으로부터 유도되고, 그 형태는 전적으로 정지궤도 위성(geostationary satellite) 적외선(IR) 데이터로부터 얻어진 공간적 전파 정보 (모션 벡터)를 통해 전송된다. 이 기술은 PMW 데이터로부터 유도된 비교적 고품질의 추정 강우를 전파하기 위하여 30분 간격의 정지궤도 위성 IR 이미지로부터 파생된 모션 벡터를 이용하며, 때때로 레이더보다 더 나은 성능을 보이기도 하고(Apip 등 2010), CMORPH의 지역적 제공범위는 $60^{\circ}N-60^{\circ}S$이고 2002년 12월부터 제공하고 있다. 본 연구에서는 CMORPH 자료 중 2002년 12월부터 제공하는 3시간 누가강우 자료를 수집하였고, 자료의 정확도 분석은 갑천유역을 대상으로 하였다. 3시간 누가 강우량을 1일 누가 강우량으로 변환한 후 금강홍수통제소의 갑천 유역 강우관측소 5곳의 강우자료를 티센 평균에 의한 유역 평균강우자료와 비교하였다. 2009년 1년간의 지상관측자료와 CMORPH자료를 비교한 결과 가 0.34 정도로 분석되었으나 추가 연구를 통해 마이크로 웨이브 강우자료 및 3시간 강우자료, 그리고 30분 강우자료의 분석을 통해 다양한 형태의 강우자료 확보뿐만 아니라 광역적인 강우특성 분석도 가능하여 연구 결과의 동아시아지역 등으로 확대 적용할 수 있을 것으로 기대한다.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.38 no.2
• /
• pp.205-210
• /
• 2014

Recently, pattern recognition methods have been widely used by researchers for fault diagnoses of mechanical systems. A pattern recognition method determines the soundness of a mechanical system by detecting variations in the system's vibration characteristics. Hidden Markov models (HMMs) and artificial neural networks (ANNs) have recently been used as pattern recognition methods in various fields. In this study, a HMM-ANN hybrid method for the fault diagnosis of a mechanical system is introduced, and a rotating wind turbine blade with a crack is selected for fault diagnosis. The existence, location, and depth of said crack are identified in this research. For improving the diagnostic accuracy of the method in spite of the presence of noise, a moment with a few specific frequencies is applied to the structure.

• Smart Media Journal
• /
• v.6 no.2
• /
• pp.33-41
• /
• 2017

Railway point machines act as actuators that provide different routes to trains by driving switchblades from the current position to the opposite one. Since point failure caused by the aging effect can significantly affect railway operations with potentially disastrous consequences, replacement detection of point machine at an appropriate time is critical. In this paper, we propose a replacement condition detection method of point machine in railway condition monitoring systems using electrical current signals, after analyzing and relabeling domestic in-field replacement data by means of OLAP(On-Line Analytical Processing) operations in the multidimensional data cube into "does-not-need-to-be replaced" and "needs-to-be-replaced" data. The system enables extracting suitable feature vectors from the incoming electrical current signals by DWT(Discrete Wavelet Transform) with reduced feature dimensions using PCA(Principal Components Analysis), and employs SVM(Support Vector Machine) for the real-time replacement detection of point machine. Experimental results with in-field replacement data including points anomalies show that the system could detect the replacement conditions of railway point machines with accuracy exceeding 98%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.9
• /
• pp.1682-1688
• /
• 2008

The Counterpropagation algorithm(CP) is a combination of Kohonen competition network as a hidden layer and the outstar structure of Grossberg as an output layer. CP has been used in many real applications for pattern matching, classification, data compression and statistical analysis since its learning speed is faster than other network models. However, due to the Kohonen layer's winner-takes-all strategy, it often causes instable learning and/or incorrect pattern classification when patterns are relatively diverse. Also, it is often criticized by the sensitivity of performance on the learning rate. In this paper, we propose an enhanced CP that has multiple Kohonen layers and dynamic controlling facility of learning rate using the frequency of winner neurons and the difference between input vector and the representative of winner neurons for stable learning and momentum learning for controlling weights of output links. A real world application experiment - pattern recognition from passport information - is designed for the performance evaluation of this enhanced CP and it shows that our proposed algorithm improves the conventional CP in learning and recognition performance.

• The Journal of Society for e-Business Studies
• /
• v.26 no.3
• /
• pp.67-80
• /
• 2021

The node embedding technique for learning graph representation plays an important role in obtaining good quality results in graph mining. Until now, representative node embedding techniques have been studied for homogeneous graphs, and thus it is difficult to learn knowledge graphs with unique meanings for each edge. To resolve this problem, the conventional Triple2Vec technique builds an embedding model by learning a triple graph having a node pair and an edge of the knowledge graph as one node. However, the Triple2 Vec embedding model has limitations in improving performance because it calculates the relationship between triple nodes as a simple measure. Therefore, this paper proposes a feature extraction technique based on a graph convolutional neural network to improve the Triple2Vec embedding model. The proposed method extracts the neighborliness vector of the triple graph and learns the relationship between neighboring nodes for each node in the triple graph. We proves that the embedding model applying the proposed method is superior to the existing Triple2Vec model through category classification experiments using DBLP, DBpedia, and IMDB datasets.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.5
• /
• pp.496-502
• /
• 2021

Recently, deep speaker embedding approach has been widely used in text-independent speaker verification, which shows better performance than the traditional i-vector approach. In this work, to improve the deep speaker embedding approach, we propose a novel method called group-based speaker embedding which incorporates group information. We cluster all speakers of the training data into a predefined number of groups in an unsupervised manner, so that a fixed-length group embedding represents the corresponding group. A Group Decision Network (GDN) produces a group weight, and an aggregated group embedding is generated from the weighted sum of the group embeddings and the group weights. Finally, we generate a group-based embedding by adding the aggregated group embedding to the deep speaker embedding. In this way, a speaker embedding can reduce the search space of the speaker identity by incorporating group information, and thereby can flexibly represent a significant number of speakers. We conducted experiments using the VoxCeleb1 database to show that our proposed approach can improve the previous approaches.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.3
• /
• pp.79-84
• /
• 2021

A feature extraction method capable of reflecting features well while mainaining the properties of data is required in order to process high-dimensional data. The principal component analysis method that converts high-level data into low-dimensional data and express high-dimensional data with fewer variables than the original data is a representative method for feature extraction of data. In this study, we propose a principal component analysis method based on adaptive correlation when selecting principal component variables in principal component analysis for data feature extraction when the data is high-dimensional. The proposed method analyzes the principal components of the data by adaptively reflecting the correlation based on the correlation between the input data. I want to exclude them from the candidate list. It is intended to analyze the principal component hierarchy by the eigen-vector coefficient value, to prevent the selection of the principal component with a low hierarchy, and to minimize the occurrence of data duplication inducing data bias through correlation analysis. Through this, we propose a method of selecting a well-presented principal component variable that represents the characteristics of actual data by reducing the influence of data bias when selecting the principal component variable.