• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.4
• /
• pp.354-358
• /
• 2001

This paper presents a fuzzy neural network model which solves the underutilization problem. This fuzzy neural network has both stability and flexibility because it uses the control structure similar to AHT(Adaptive Resonance Theory)-l neural network. And this fuzzy nenral network does not need to initialize weights and is less sensitive to noise than ART-l neural network is. The learning rule of this fuzzy neural network is the modified and fuzzified version of Kohonen learning rule and is based on the fuzzification of leaky competitive leaming and the fuzzification of conditional probability. The similarity measure of vigilance test, which is performed after selecting a winner among output neurons, is the relative distance. This relative distance considers Euclidean distance and the relative location between a datum and the prototypes of clusters. To compare the performance of the proposed fuzzy neural network with that of Kohonen Self-Organizing Feature Map the IRIS data and Gaussian-distributed data are used.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.10
• /
• pp.293-302
• /
• 2016

Since the electricity is produced and consumed simultaneously, predicting the electric load and securing affordable electric power are necessary for reliable electric power supply. In particular, a university campus is one of the highest power consuming institutions and tends to have a wide variation of electric load depending on time and environment. For these reasons, an accurate electric load forecasting method that can predict power consumption in real-time is required for efficient power supply and management. Even though various influencing factors of power consumption have been discovered for the educational institutions by analyzing power consumption patterns and usage cases, further studies are required for the quantitative prediction of electric load. In this paper, we build an electric load forecasting model by implementing and evaluating various machine learning algorithms. To do that, we consider three building clusters in a campus and collect their power consumption every 15 minutes for more than one year. In the preprocessing, features are represented by considering periodic characteristic of the data and principal component analysis is performed for the features. In order to train the electric load forecasting model, we employ both artificial neural network and support vector machine. We evaluate the prediction performance of each forecasting model by 5-fold cross-validation and compare the prediction result to real electric load.

• The Transactions of the Korea Information Processing Society
• /
• v.2 no.6
• /
• pp.995-1001
• /
• 1995

The structure of a typical pattern recognition consists a pre-processing, a feature extraction(algorithm) and classification or recognition. In classification, when widely varying patterns exist in same category, we need the clustering which organize the similar patterns. Clustering algorithm is two approaches. Firs, statistical approaches which are k-means, ISODATA algorithm. Second, neural network approach which is T. Kohonen's LVQ(Learning Vector Quantization). Nikhil R. Palet al proposed the GLVQ(Generalized LVQ, 1993). This paper suggest the efficient feature extraction methods of handwritten numerals in GLVQ clustering network. We use the handwritten numeral data from 21's authors(ie, 200 patterns) and compare the proportion of misclassified patterns for each feature extraction methods. As results, when we use the projection combination method, the classification ratio is 98.5%.

• KIISE Transactions on Computing Practices
• /
• v.23 no.5
• /
• pp.299-303
• /
• 2017

By piling up hidden layers in artificial neural networks, deep learning is delivering outstanding performances for high-level abstraction problems such as object/speech recognition and natural language processing. Alternatively, deep-learning users often struggle with the tremendous amounts of time and resources that are required to train deep neural networks. To alleviate this computational challenge, many approaches have been proposed in a diversity of areas. In this work, two of the existing Apache Spark-based acceleration frameworks for deep learning (SparkNet and DeepSpark) are compared and analyzed in terms of the training accuracy and the time demands. In the authors' experiments with the CIFAR-10 and CIFAR-100 benchmark datasets, SparkNet showed a more stable convergence behavior than DeepSpark; but in terms of the training accuracy, DeepSpark delivered a higher classification accuracy of approximately 15%. For some of the cases, DeepSpark also outperformed the sequential implementation running on a single machine in terms of both the accuracy and the running time.

• Journal of KIISE:Software and Applications
• /
• v.32 no.11
• /
• pp.1136-1146
• /
• 2005

Fingerprint classification is useful in an automated fingerprint identification system (AFIS) to reduce the matching time by categorizing fingerprints. Based on Henry system that classifies fingerprints into S classes, various techniques such as neural networks and support vector machines (SVMs) have been widely used to classify fingerprints. Especially, SVMs of high classification performance have been actively investigated. Since the SVM is binary classifier, we propose a novel classifier-combination model, multiple decision templates (MuDTs), to classily fingerprints. The method extracts several clusters of different characteristics from samples of a class and constructs a suitable combination model to overcome the restriction of the single model, which may be subject to the ambiguous images. With the experimental results of the proposed on the FingerCodes extracted from NIST Database4 for the five-class and four-class problems, we have achieved a classification accuracy of $90.4\%\;and\;94.9\%\;with\;1.8\%$ rejection, respectively.

• Journal of KIISE:Software and Applications
• /
• v.30 no.11
• /
• pp.1072-1079
• /
• 2003

This study is purported for suggesting a new clustering algorithm that enables incremental categorization of numerous documents. The suggested algorithm adopts the natures of the spherical k-means algorithm, which clusters a mass amount of high-dimensional documents, and the fuzzy ART(adaptive resonance theory) neural network, which performs clustering incrementally. In short, the suggested algorithm is a combination of the spherical k-means vector space model and concept vector and fuzzy ART vigilance parameter. The new algorithm not only supports incremental clustering and automatically sets the appropriate number of clusters, but also solves the current problems of overfitting caused by outlier and noise. Additionally, concerning the objective function value, which measures the cluster's coherence that is used to evaluate the quality of produced clusters, tests on the CLASSIC3 data set showed that the newly suggested algorithm works better than the spherical k-means by 8.04% in average.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.264-266
• /
• 2022

In order to apply the RNN model to the radio fingerprint-based indoor path generation technology, the data set must be continuous and sequential. However, Wi-Fi radio fingerprint data is not suitable as RNN data because continuity is not guaranteed as characteristic information about a specific location at the time of collection. Therefore, continuity information of sequential positions should be given. For this purpose, clustering is possible through classification of each region based on signal data. At this time, the continuity information between the clusters does not contain information on whether actual movement is possible due to the limitation of radio signals. Therefore, correlation information on whether movement between adjacent clusters is possible is required. In this paper, a deep learning network, a recurrent neural network (RNN) model, is used to predict the path of a moving object, and it reduces errors that may occur when predicting the path of an object by generating continuous location information for path generation in an indoor environment. We propose a method of giving correlation between clustering for generating an improved moving path that can avoid erroneous path prediction that cannot move on the predicted path.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2009.01a
• /
• pp.31-34
• /
• 2009

ART2 알고리즘은 신경 회로망 모델로서 실시간 학습이 가능하여 저속 및 고속을 지원할 뿐만 아니라 지역 최소화(local minima) 문제가 발생하지 않는 장점을 갖는다. 그러나 ART2 알고리즘은 경계 변수 설정에 따라 클러스터의 수가 달라지며, 이러한 경계 변수 설정은 패턴의 분류와 인식 성능을 좌우한다. 따라서 본 논문에서는 ART2 알고리즘에서 효율적으로 경계 변수를 설정하기 위해 패턴셋 설정을 통한 경계 변수 설정 방법을 제안한다. 제안된 경계 변수 설정 방법의 성능을 평가하기 위해 숫자 및 영문 패턴을 대상으로 실험한 결과, 패턴 분류의 성능이 기존의 방식 보다 개선된 것을 확인하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2009.01a
• /
• pp.35-40
• /
• 2009

FCM 알고리즘은 입력 벡터와 각 클러스터의 유클리드 거리를 이용하여 구해진 소속도만를 비교하여 데이터를 분류하기 때문에 클러스터링 된 공간에서의 데이터들의 분포에 따라 바람직하지 못한 클러스터링 결과를 보일 수 있다. 이러한 문제점을 개선하기 위해 대칭적 성질을 이용하는 대칭성 측도에 퍼지 이론을 적용하여 군집간의 거리에 따른 변화와 군집 중심의 위치, 그리고 군집 형태에 따라 영향을 덜 받는 개선된 FCM이 제안되었다. 본 논문에서는 효과적으로 패턴을 분류하기 위해 개선된 FCM 알고리즘을 적용한 개선된 하이브리드 네트워크를 제안한다. 제안된 하이브리드 네트워크는 개선된 FCM 알고리즘을 입력층과 중간층의 학습구조 적용하고 중간층과 출력층의 학습구조는 일반화된 델타학습법을 적용한다. 제안된 방법의 인식성능을 평가하기 위해 2차원 좌표평면 상의 데이터를 기존의 Max_Min 신경망을 이용한 FCM 기반 RBF 네트워크와 FCM 기반 RBF 네트워크, HCM 기반 네트워크와 제안된 방법 간의 학습 및 인식 성능을 비교 및 분석하였다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1996.10a
• /
• pp.239-242
• /
• 1996

본 논문에서는 BP(Back Propagation)에 비해서 빠른 학습시간과 다른 경쟁학습 신경회로망 알고리즘에 비해서 비교적 우수한 성능으로 패턴인식 등에 많이 이용되고 있는 LVQ(Learning Vector Quantization) 알고리즘의 성능을 향상시키기 위한 방법을 논의하고자 한다. 일반적으로 LVQ는 음(negative)의 학습을 하기 때문에 초기 가중치가 제대로 설정되지 않으면 발산할 수 있다는 단점이 있으며, 경쟁학습 계열의 신경망이기 때문에 출력 층의 뉴런 수에 따라 성능에 큰 영향을 받는다고 알려져 있다.[1]. 지도학습 형태를 지닌 LVQ의 경우에 학습패턴이 n개의 클래스를 가지고, 각 클래스 별로 학습패턴의 수가 같은 경우에 일반적으로 전체 출력뉴런에 대해서 (출력뉴런수/n)개의 뉴런을 각 클래스의 목표(desired) 클러스터로 할당하여 학습을 수행하는데, 본 논문에서는 각 클래스에 동일한 수의 출력뉴런을 할당하지 않고, 학습데이터에서 각 클래스의 분산을 추정하여 각 클래스의 분산을 추정분산에 비례하게 목표 출력뉴런을 할당하고, 초기 가중치도 추정분산에 비례하게 각 클래스의 초기 임의 위치 입력백터를 사용하여 학습을 수행하는 방법을 제안한다. 본 논문에서 제안하는 방법은 분류하고자 하는 데이터에 대해서 필요한 최적의 출력뉴런 수를 찾는 것이 아니라 이미 결정되어 있는 출력뉴런 수에 대해서 각 클래스에 할당할 출력 뉴런 수를 데이터의 추정분산에 의해서 결정하는 것으로, 추정분산이 크면 상대적으로 많은 출력 뉴런을 할당하고 작으면 상대적으로 적은 출력뉴런을 할당하고 초기 가중치도 마찬가지 방법으로 결정하며, 이렇게 하면 정해진 출력뉴런 개수 안에서 각 클래스 별로 분류의 어려움에 따라서 출력뉴런을 할당하기 때문에 미학습 뉴런이 줄어들게 되어 성능의 향상을 기대할 수 있으며, 실험적으로 제안된 방법이 더 나은 성능을 보임을 확인했다.initially they expected a more practical program about planting than programs that teach community design. Many people are active in their own towns to create better environments and communities. The network system "Alpha Green-Net" is functional to support graduates of the course. In the future these educational programs for citizens will becomes very important. Other cities are starting to have their own progrms, but they are still very short term. "Alpha Green-Net" is in the process of growing. Many members are very keen to develop their own abilities. In the future these NPOs should become independent. To help these NPOs become independent and active the educational programs should consider and teach about how to do this more in the future.단하였는데 그 결과, 좌측 촉각엽에서 제4형의 신경연접이 퇴행성 변화를 나타내었다. 그러므로 촉각의 지각신경세포는 뇌의 같은 족 촉각엽에 뻗어와 제4형 신경연접을 형성한다고 결론되었다.$/ 값이 210 $\mu\textrm{g}$/$m\ell$로서 효과적인 저해 활성을 나타내었다 따라서, 본 연구에서 빈