• The Journal of the Korea institute of electronic communication sciences
• /
• v.6 no.1
• /
• pp.34-42
• /
• 2011

In an effort to the practical realization of phonetic typewriter, we concentrate on the classification of consonants in this paper. Since many of consonants do not show periodic behavior in time domain and thus the validity for Fourier analysis of them are not convincing, vector quantization (VQ) via LBG clustering is first performed to check if the feature vectors of MFCC and LPCC are ever meaningful for consonants. Experimental results of VQ showed that it's not easy to draw a clear-cut conclusion as to the validity of Fourier analysis for consonants. For classification purpose, two kinds of neural networks are employed in our study: self organizing map (SOM) and learning vector quantization (LVQ). Results from SOM revealed that some pairs of phonemes are not resolved. Though LVQ is free from this difficulty inherently, the classification accuracy was found to be low. This suggests that, as long as consonant classification by LVQ is concerned, other types of feature vectors than MFCC should be deployed in parallel. However, the combination of MFCC/LVQ was not found to be inferior to the classification of phonemes by language-moded based approach. In all of our work, LPCC worked worse than MFCC.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.5
• /
• pp.432-441
• /
• 2002

Though many services offer useful information on internet, computer users are not so familiar with such services that they need an assistant system to use the services easily In the case of web sites, for example, the operators answer the users e-mail questions, but the increasing number of users makes it hard to answer the questions efficiently. In this paper, we propose an assistant system which responds to the users questions automatically and helps them browse the Hanmail Net FAQ (Frequently Asked Question) conceptually. This system uses two-level self-organizing map (SOM): the keyword clustering SOM and document classification SOM. The keyword clustering SOM reduces a variable length question to a normalized vector and the document classification SOM classifies the question into an answer class. Experiments on the 2,206 e-mail question data collected for a month from the Hanmail net show that this system is able to find the correct answers with the recognition rate of 95% and also the browsing based on the map is conceptual and efficient.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.3
• /
• pp.223-230
• /
• 2001

Since self-organizing map (SOM) preserves the topology of ordering in input spaces and trains itself by unsupervised algorithm, it is Llsed in many areas. However, SOM has a shortcoming: structure cannot be easily detcrmined without many trials-and-errors. Structure-adaptive self-orgnizing map (SASOM) which can adapt its structure as well as its weights overcome the shortcoming of self-organizing map: SASOM makes use of structure adaptation capability to place the nodes of prototype vectors into the pattern space accurately so as to make the decision boundmies as close to the class boundaries as possible. In this scheme, the initialization of weights of newly adapted nodes is important. This paper proposes a method which optimizes SASOM with genetic algorithm (GA) to determines the weight vector of newly split node. The leanling algorithm is a hybrid of unsupervised learning method and supervised learning method using LVQ algorithm. This proposed method not only shows higher performance than SASOM in terms of recognition rate and variation, but also preserves the topological order of input patterns well. Experiments with 2D pattern space data and handwritten digit database show that the proposed method is promising.

• Journal of Institute of Control, Robotics and Systems
• /
• v.4 no.3
• /
• pp.378-383
• /
• 1998

A FOV, that stands for "Field Of View", refers to the maximum area where a camera could be wholly seen. If a FOV of CCD camera cannot the cover overall inspection area, the overall inspection area should be divided into sub-areas of size FOV. In this paper, we propose a new neural network-based FOV generation method by using a newly modified self-organizing map(SOM) which has multiple structure based on a self-organizing map, and uses new training rule that is composed of the movement, creation and deletion terms. Then, experiment results using real PCB indicate the superiority of the method developed in this study to the existing sequential method.al method.

• Journal of Korean Society on Water Environment
• /
• v.25 no.5
• /
• pp.735-741
• /
• 2009

In order to support the basic information for planning and performing the environment management such as Total Maximum Daily Loads (TMDLs), it is highly recommended to understand the spatial distribution of water quality and runoff data in the unit watersheds. Therefore, in the present study, we applied Self-Organizing Map (SOM) to detect the characteristics of spatial distribution of Biological Oxygen Demand (BOD) concentration and runoff data which have been measured in the Yeongsan, Seomjin, and Tamjin River basins. For the purpose, the input dataset for SOM was constructed with the mean, standard deviation, skewness, and kurtosis values of the respective data measured from the stations of 22-subbasins in the rivers. The results showed that the $4{\times}4$ array structure of SOM was selected by the trial and error method and the best performance was revealed when it classified the stations into three clusters according to the basic statistics. The cluster-1 and 2 were classified primarily by the skewness and kurtosis of runoff data and the cluster-3 including the basic statistics of YB_B, YB_C, and YB_D stations was clearly decomposed by the mean value of BOD concentration showing the worst condition of water quality among the three clusters. Consequently, the methodology based on the SOM proposed in the present study can be considered that it is highly applicable to detect the spatial distribution of BOD concentration and runoff data and it can be used effectively for the further utilization using different water quality items as a data analysis tool.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2008.05a
• /
• pp.2066-2070
• /
• 2008

본 연구는 인공신경망(Artificial Neural Networks: ANNs)기법의 일종인 자기조직화(Self Organizing Map: SOM) 이론을 이용한다. 자기조직화 특성을 이용하여 스스로 학습이 가능하고, 구조상 수행이 빨라 학습 단계에 소요되는 시간을 줄 일 수 있는 장점을 가진 자기조직화 이론을 도입하고, 수질자료 중 전체 유기물의 양을 나타내며 난분해성 물질에 대한 해석이 가능하고 재현성이 탁월한 TOC 와 강우-유출량 자료의 분포적 양상과 특징을 분석하여 예측을 위한 모형화 과정에 기여하고자 한다. 최적의 Map Size와 Map Array 결정을 위해 수집된 강우와 유출량자료 및 TOC 자료에 대해 Garcia의 경험식을 이용하여 Map을 구성하는 단위구조의 총 수(M)를 산정하여 M값에 따른 종방향 및 횡방향 크기를 결정하는 다수의 Map 크기를 검토하고, 또한 Map 배열은 2차원 배열의 사각형배열(Rectangular array)과 육각형배열(Hexagonal array)에 대해서도 복합적으로 검토하여 최적의 특성조건을 결정하여 강우-유출 및 TOC 관계의 분할특성을 분석한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.5
• /
• pp.642-646
• /
• 2006

The fuzzy TAM(Topographical Attentive Mapping) network is a supervised method of pattern analysis which is composed of input layer, category layer, and output layer. But if we don't know the target value of the pattern, the network can not be trained. In this case, the target value can be replaced by a result induced by using an unsupervised neural network as the SOM (Self-organizing Map). In this paper, we apply the results of SOM to fuzzy TAM network and show its usefulness through the case study.

• Journal of Korean Society on Water Environment
• /
• v.27 no.6
• /
• pp.794-803
• /
• 2011

Self Organizing Map (SOM) was applied for pattern classification of hydrological and water quality data measured at Jangseong Reservoir on a monthly basis. The primary objective of the present study is to understand better data characteristics and relationship between the data. For the purpose, two SOMs were configured by a methodologically systematic approach with appropriate methods for data transformation, determination of map size and side lengths of the map. The SOMs constructed at the respective measurement stations for water quality data (JSD1 and JSD2) commonly classified the respective datasets into five clusters by Davies-Bouldin Index (DBI). The trained SOMs were fine-tuned by Ward's method of a hierarchical cluster analysis. On the one hand, the patterns with high values of standardized reference vectors for hydrological variables revealed the high possibility of eutrophication by TN or TP in the reservoir, in general. On the other hand, the clusters with low values of standardized reference vectors for hydrological variables showed the patterns with high COD concentration. In particular, Clsuter1 at JSD1 and Cluster5 at JSD2 represented the worst condition of water quality with high reference vectors for rainfall and storage in the reservoir. Consequently, SOM is applicable to identify the patterns of potential eutrophication in reservoirs according to the better understanding of data characteristics and their relationship.

• Journal of KIISE:Software and Applications
• /
• v.28 no.12
• /
• pp.875-884
• /
• 2001

Although the self organizing map (SOM) is widely utilized in such fields of data visualization and topology preserving mapping, since it should have the topology fixed before trained, it has some shortcomings that it is difficult to apply it to practical problems, and classification capability is quite low despite better clustering performance. To overcome these points this paper proposes the dynamic topology preserving self-organizing map(DTSOM) that dynamically splits the output nodes on the map and trains them, and attempts to improve the classification capability by combining multiple DTSOMs K-Winner method has been applied to combine DTSOMs which produces K outputs with winner node selection method. This produces even better performance than the conventional combining methods such as majority voting weighting, BKS Bayesian, Borda, Condorect and reliability sum. DTSOM remedies the shortcoming of determining the topology in advance, and the classification rate increases significantly by combing multiple maps trained with different features. Experimental results with handwritten digit recognition indicate that the proposed method works out to problems of conventional SOM effectively so to improve the classification rate to 98.1%.

• Korean Journal of Environmental Biology
• /
• v.25 no.2
• /
• pp.149-157
• /
• 2007

This study focused on patterning waterbirds occurrences at the western costal area of the Korean Peninsula in winter and relating the occurrence patterns with their environmental factors. Waterbird communities were monitored at 10 different study areas, and the composition of land cover as environmental factors was estimated at each study area. Overall dabbling ducks were the most abundant with 84% of total individuals, followed by shorebird and diving ducks. Species Anae platyrhynchos was the first dominant species, and Anas formosa was the second one. Self-organizing map (SOM), an unsupervised artificial neural network, was applied for patterning wintering waterbird communities, and identified 6 groups according to the differences of communities compositions. Each group reflected the differences of indicator species as well as their habitats.