• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10a
• /
• pp.640-642
• /
• 2001

침입 탐지 시스템의 초점이 호스트와 운영체제 탐지에서 네트워크 탐지로 옮겨가고 있고 단순만 오용 탐지 기법에서 이를 개선한 지능적인 비정상 행위 탐지 기법에 관한 연구들이 진행되고 있다. 이러한 연구들 중에는 네트워크 프로토콜의 트래픽 특성을 이용하여 비표준 포트의 사용이나 표준 포트에 대한 비표준 방법에 의한 침입을 탐지하고자 하는 노력도 있다. 본 연구에서는 실시간으로 패턴 매칭이 가능하고, 적응력이 뛰어난 신경망 알고리즘을 이용하여 네트워크 서비스들에 대한 트래픽을 수집, 특성에 따라 분석.클러스터링하고 그 결과를 바탕으로 보다 향상된 침입 탐지가 가능한 시스템을 제안한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.4
• /
• pp.336-339
• /
• 2001

The ozone forecasting systems have many problems because the mechanism of the ozone concentration is highly complex, nonlinear, and nonstationary. Especially, the performance of the prediction results in the high-level ozone concentration are not good. This paper describes the modeling method of the ozone prediction system using neuro-fuzzy approaches and fuzzy clustering methods. The dynamic polynomial neural network (DPNN) based upon a typical algorithm of GMDH (group method of data handling) is a useful method for data analysis, the identification of nonlinear complex systems, and prediction of dynamical systems.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.05a
• /
• pp.187-190
• /
• 2001

Due to the recent proliferation of the internet, it is broadly granted that the necessity of the automatic document categorization has been on the rise. Since it is a heavy time-consuming work and takes too much manpower to process and classify manually, we need a system that categorizes them automatically as their contents. In this paper, we propose the automatic E-mail response system that is based on 2 hierarchical document clustering methods. One is to get the final result from the classifier trained seperatly within each class, after clustering the whole documents into 3 groups so that the first classifier categorize the input documents as the corresponding group. The other method is that the system classifies the most distinct classes first as their similarity, successively. Neural networks have been adopted as classifiers, we have used dendrograms to show the hierarchical aspect of similarities between classes. The comparison among the performances of hierarchical and non-hierarchical classifiers tells us clustering methods have provided the classification efficiency.

• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.197-206
• /
• 2021

GPR data is used for underground exploration. The data gathered are interpreted by experts based on experience as the underground facilities often reflect GPR. In addition, GPR data are different in the noise and characteristics of the data depending on the equipment, environment, etc. This often results in insufficient data with accurate labels. Generally, a large amount of training data have to be obtained to apply CNN models that exhibit high performance in image classification problems. However, due to the characteristics of GPR data, it makes difficult to obtain sufficient data. Finally, this makes neural networks unable to learn based on general supervised learning methods. This paper proposes an image classification method considering data characteristics to ensure that the accuracy of each label is similar. The proposed method is based on semi-supervised learning, and the image is classified using clustering techniques after extracting the feature values of the image from the neural network. This method can be utilized not only when the amount of the labeled data is insufficient, but also when labels that depend on the data are not highly reliable.

• Convergence Security Journal
• /
• v.23 no.4
• /
• pp.61-70
• /
• 2023

Clustering is an unsupervised learning method that involves grouping data based on features such as distance metrics, using data without known labels or ground truth values. This method has the advantage of being applicable to various types of data, including images, text, and audio, without the need for labeling. Traditional clustering techniques involve applying dimensionality reduction methods or extracting specific features to perform clustering. However, with the advancement of deep learning models, research on deep clustering techniques using techniques such as autoencoders and generative adversarial networks, which represent input data as latent vectors, has emerged. In this study, we propose a deep clustering technique based on deep learning. In this approach, we use an autoencoder to transform the input data into latent vectors, and then construct a vector space according to the cluster structure and perform k-means clustering. We conducted experiments using the MNIST and Fashion-MNIST datasets in the PyTorch machine learning library as the experimental environment. The model used is a convolutional neural network-based autoencoder model. The experimental results show an accuracy of 89.42% for MNIST and 56.64% for Fashion-MNIST when k is set to 10.

• KIISE Transactions on Computing Practices
• /
• v.22 no.7
• /
• pp.315-319
• /
• 2016

Recurrent neural network based language models (RNN LM) have shown improved results in language model researches. The RNN LMs are limited to post processing sessions, such as the N-best rescoring step of the wFST based speech recognition. However, it has considerable vocabulary problems that require large computing powers for the LM training. In this paper, we try to find the 1st pass N-gram model using word embedding, which is the simplified deep neural network. The class based language model (LM) can be a way to approach to this issue. We have built class based vocabulary through word embedding, by combining the class LM with word N-gram LM to evaluate the performance of LMs. In addition, we propose that part-of-speech (POS) tagging based LM shows an improvement of perplexity in all types of the LM tests.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.1
• /
• pp.35-47
• /
• 2002

This paper proposes a self organizing RBF neural network equalizer for the equalization of digital communications. It is the most important for the equalizer using the RBF neural network to estimate the RBF centers correctly and quickly, which are the desired channel states. However, the previous RBF equalizers are not used in the actual communication system because of some drawbacks that the number of channel states has to be known in advance and many centers are necessary. Self organizing neural network equalizer proposed in this paper can implement the equalization without prior information regarding the number of channel states because it selects RBF centers among the signals that are transmitted to the equalizer by the new addition and removal criteria. Furthermore, the proposed equalizer has a merit that is able to make a equalization with fewer centers than those of prior one by the course of the training using LMS and clustering algorithm. In the linear, nonlinear and standard telephone channel, the proposed equalizer is compared with the optimal Bayesian equalizer for the BER performance, the symbol decision boundary and the number of centers. As a result of the comparison, we can confirm that the proposed equalizer has almost similar performance with the Bavesian enualizer.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2004.05b
• /
• pp.1280-1284
• /
• 2004

본 논문에서는 월 댐유입량을 예측하는데 있어서 뉴로-퍼지 시스템의 적용성을 검토하였다. 뉴로-퍼지 알고리즘으로 퍼지이론과 신경망이론의 결합형태인 ANFIS(Adaptive Neuro-Fuzzy Inference System)를 이용하여 모형을 구성하였다. ANFIS의 공간분야에 의한 제어규칙의 선정에 있어 퍼지변수가 증가함에 따라 제어규칙이 기하급수적으로 증가하는 단점을 해결하기 위해 퍼지 클러스터링(Fuzzy flustering)방법 중 하나인 차감 클러스터링(Subtractive Clustering)을 사용하였다. 또한 본 연구에서는 기후인자들을 인력으로 하여 모형을 구성하였으며 각각 학습기간과 검정기간으로 나누어 학습기간에는 모형의 매개변수 최적화를, 검정기간에는 최적화된 모형의 매개변수를 검정하는 순으로 연구를 수행하였다. 예측 길과, ANFIS는 댐유입량 예측시 입력자료의 종류가 많아질수록 예측능력 더욱 정확한 것으로 판단된다.

• Journal of Internet Computing and Services
• /
• v.8 no.3
• /
• pp.19-32
• /
• 2007

This paper present a new face recognition method based on LVQ neural net to construct a real time face recognition system. The previous researches which used PCA, LDA combined neural net usually need much time in training neural net. The supervised LVQ neural net needs much less time in training and can maximize the separability between the classes. In this paper, the proposed method transforms the input face image by PCA and LDA sequentially into low-dimension feature vectors and recognizes the face through LVQ neural net. In order to make the system robust to external light variation, light compensation is performed on the detected face by max-min normalization method as preprocessing. PCA and LDA transformations are applied to the normalized face image to produce low-level feature vectors of the image. In order to determine the initial centers of LVQ and speed up the convergency of the LVQ neural net, the K-Means clustering algorithm is adopted. Subsequently, the class representative vectors can be produced by LVQ2 training using initial center vectors. The face recognition is achieved by using the euclidean distance measure between the center vector of classes and the feature vector of input image. From the experiments, we can prove that the proposed method is more effective in the recognition ratio for the cases of still images from ORL database and sequential images rather than using conventional PCA of a hybrid method with PCA and LDA.

• 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.