• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2013.10a
• /
• pp.320-324
• /
• 2013

A crack identification method using an equivalent bending stiffness for cracked beam and committee of neural networks is presented. The equivalent bending stiffness is constructed based on an energy method for a straight thin-walled pipe, which has a through-the-thickness crack, subjected to bending. Several numerical analysis for a steel cantilever pipe using the equivalent bending stiffness are carried out to extract the natural frequencies and mode shapes of the cracked beam. The extracted modal properties are used in constructing a training patterns of a neural network. The input to the neural network consists of the modal properties and the output is composed of the crack location and size. Multiple neural networks are constructed and each individual network is trained independently with different initial synaptic weights. Then, the estimated crack locations and sizes from different neural networks are averaged. Experimental crack detection is carried out for 3 damage cases using the proposed method, and the identified crack locations and sizes agree reasonably well with the exact values.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2009.01a
• /
• pp.169-172
• /
• 2009

본 논문은 SOM을 이용하여 비행슈팅게임을 하는 게이머의 긴장과 이완상태를 학습한다. 학습된 SOM을 이용해 게이머의 새로운 심박데이터가 입력되었을 때 긴장과 이완 상태에서 플레이하는 게이머의 인식을 제안한다. 게이머들은 비행슈팅게임을 플레이하면서 게임 환경들의 패턴들에 익숙해진다. 게이머들은 반복하면서 지루해지면서 자연스럽게 긴장감도 떨어지게 된다. 만약 긴장이완 정도를 알 수 있다면 게이머의 상태에 맞게 게임환경을 조절하여 긴장감을 유지할 수 있을 것이다. 본 연구에서는 비행슈팅게임을 하는 게이머의 심박신호를 이용하여 게이머의 긴장이완상태를 신경망 SOM으로 분류한다. SOM은 주어진 입력패턴에 정확한 답을 정해주지 않고 자기 스스로 학습하여 해답을 찾는 신경망중의 하나이다. 따라서 게이머의 심박신호는 SOM 학습을 통해 게이머의 긴장과 이완상태들을 군집화 할 수 있다. 비행슈팅게임을 20회 반복 플레이하여 SOM으로 게이머의 심박신호를 입력해 본 결과 긴장이완상태를 인식 할 수 있었다.

• Asia pacific journal of information systems
• /
• v.16 no.3
• /
• pp.49-65
• /
• 2006

This study proposes a model for customer segmentation using the psychological characteristics of Internet banking customers. The model was developed through two phased clustering method, called SONN-HC by integrating self-organizing neural networks (SONN) and hierarchical clustering (HC) method. We applied the SONN-HC method to internet banking customer segmentation and performed an empirical analysis with 845 cases. The results of our empirical analysis show the psychological characteristics of Internet banking customers have significant differences among four clusters of the customers created by SONN-HC. From these results, we found that the psychological characteristics of Internet banking customers had an important role of planning a strategy for customer segmentation in a financial institution.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.04a
• /
• pp.1041-1042
• /
• 2010

본 연구 과제에서 살펴보고자 하는 내용은 기업을 운영하는 구성원의 능력을 평가하는 방법을 통해 업무능력과 평가결과와의 연관성을 분석하여 살펴보고자 한다. 본 연구에서는 특정기업이 활용하는 직원평가 프로그램에 대해 분석하고 그 프로그램에 의해 수개월동안 축적된 자료를 분석하여 업무평가결과와 기업 구성원의 성향 및 매출 기여도를 분석 하였다. 본 연구에서 채택한 방법은 군집 분석 방법 중의 하나 인 다층전방향 신경망 분석을 이용하였다. 본 연구결과는 평가에서 우수한 점수를 받은 기업 구성원은 기업 전반을 운영하는 운영진에 위치해 있는 경향을 보이고 매출과의 연관성에서 다른 직원 대비 우수하게 나왔다. 본 연구는 특정집단을 대상으로 한 것으로서 한계성을 가지며 여러 집단을 같은 프로그램으로 운영시 나오는 결과를 살펴보는 것을 향후 과제로 남겨 놓았다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.662-663
• /
• 2020

최근 MPEG 에서는 인공신경망 모델을 다양한 딥러닝 프레임워크에서 상호운용 가능한 포맷으로 압축 표현할 수 있는 NNR(Compression of Neural Network for Multimedia Content Description and Analysis) 표준화를 진행하고 있다. 본 논문에서는 MPEG-NNR 에서 CNN 모델을 압축하기 위한 지역 비선형 양자화(Local Non-linear Quantization: LNQ) 기법을 제시한다. 제안하는 LNQ 는 균일 양자화된 CNN 모델의 각 계층의 가중치 행렬 블록 단위로 추가적인 비선형 양자화를 적용한다. 또한, 제안된 LNQ 는 가지치기(pruning)된 모델의 경우 블록내의 영(zero) 값의 가중치들은 그대로 전송하고 영이 아닌 가중치만을 이진 군집화를 적용한다. 제안 기법은 음성 분류를 위한 CNN 모델(DCASE Task)의 압축 실험에서 기존 균일 양자화를 대비 동일한 분류 성능에서 약 1.78 배 압축 성능 향상이 있음을 확인하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.9
• /
• pp.1905-1912
• /
• 2009

Clustering results based on the FCM algorithm sometimes produces undesirable clustering result through data distribution in the clustered space because data is classified by comparison with membership degree which is calculated by the Euclidean distance between input vectors and clusters. Symmetrical measurement of clusters and fuzzy theory are applied to the classification to tackle this problem. The enhanced FCM algorithm has a low impact with the variation of changing distance about each cluster, middle of cluster and cluster formation. Improved hybrid network of applying FCM algorithm is proposed to classify patterns effectively. The proposed enhanced FCM algorithm is applied to the learning structure between input and middle layers, and normalized delta learning rule is applied in learning stage between middle and output layers in the hybrid network. The proposed algorithms compared with FCM-based RBF network using Max_Min neural network, FMC-based RBF network and HCM-based RBF network to evaluate learning and recognition performances in the two-dimensional coordinated data.

• Journal of Korea Water Resources Association
• /
• v.51 no.5
• /
• pp.383-393
• /
• 2018

The regional frequency analysis is the method which uses not only sample of target station but also sample of neighborhood stations in which are classified as hydrological homogeneous regions. Consequently, identification of homogeneous regions is a very important process in regional frequency analysis. In this study, homogeneous regions for regional frequency analysis of precipitation were identified by the self-organizing map (SOM) which is one of the artificial neural network. Geographical information and hourly rainfall data set were used in order to perform the SOM. Quantization error and topographic error were computed for identifying the optimal SOM map. As a result, the SOM model organized by $7{\times}6$ array with 42 nodes was selected and the selected stations were classified into 6 clusters for rainfall regional frequency analysis. According to results of the heterogeneity measure, all 6 clusters were identified as homogeneous regions and showed more homogeneous regions compared with the result of previous study.

• The Korean Journal of Applied Statistics
• /
• v.16 no.2
• /
• pp.321-333
• /
• 2003

Self-organizing map (SOM), a unsupervised learning neural network, has been developed by T. Kohonen since 1980's. Main application areas were pattern recognition and text retrieval. Because of that, it has not been spread to statisticians until late. Recently, SOM's are frequently drawn in data mining fields. Kohonen's SOM, however, needs improvements to become a statistician's standard tool. First, there should be a good guideline as for the size of map. Second, an enhanced visualization mode is wanted. In this study, principal components self-organizing map (PC-SOM), a modification of Kohonen's SOM, is proposed to meet such needs. PC-SOM performs one-dimensional SOM during the first stage to decompose input units into node weights and residuals. At the second stage, another one-dimensional SOM is applied to the residuals of the first stage. Finally, by putting together two stages, one obtains two-dimensional SOM. Such procedure can be easily expanded to construct three or more dimensional maps. The number of grid lines along the second axis is determined automatically, once that of the first axis is given by the data analyst. Furthermore, PC-SOM provides easily interpretable map axes. Such merits of PC-SOM are demonstrated with well-known Fisher's iris data and a simulated data set.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.3
• /
• pp.289-293
• /
• 2005

Pattern classification extracts various types of pattern information expressing objects in the real world and decides their class. The top priority of pattern classification technologies is to improve the performance of classification and, for this, many researches have tried various approaches for the last 40 years. Classification methods used in pattern classification include base classifier based on the probabilistic inference of patterns, decision tree, method based on distance function, neural network and clustering but they are not efficient in analyzing a large amount of multi-dimensional data. Thus, there are active researches on multiple classifier systems, which improve the performance of classification by combining problems using a number of mutually compensatory classifiers. The present study identifies problems in previous researches on multiple SVM classifiers, and proposes BORSE, a model that, based on 1:M policy in order to expand SVM to a multiple class classifier, regards each SVM output as a signal with non-linear pattern, trains the neural network for the pattern and combine the final results of classification performance.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.2
• /
• pp.423-428
• /
• 2017

These days, various and tons of education information are rapidly increasing and spreading due to Internet and smart devices usage. Recently, as e-Learning usage increasing, many instructors and students (learners) need to set a goal to maximize learners' result of education and education system efficiency based on big data analytics via online recorded education historical data. In this paper, the author applied Word2Vec algorithm (neural network algorithm) to find similarity among education words and classification by clustering algorithm in order to objectively recognize and analyze online recorded education historical data. When the author applied the Word2Vec algorithm to education words, related-meaning words can be found, classified and get a similar vector values via learning repetition. In addition, through experimental results, the author proved the part of speech (noun, verb, adjective and adverb) have same shortest distance from the centroid by using clustering algorithm.