• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.6
• /
• pp.802-808
• /
• 2009

Recently many researches have been presented to improve the clustering performance of gene expression data by incorporating Gene Ontology into the process of clustering. In particular, Kustra et al. showed higher performance improvement by exploiting Biological Process Ontology compared to the typical expression-based clustering. This paper extends the work of Kustra et al. by performing extensive experiments on the way of incorporating GO structures. To this end, we used three ontological distance measures (Lin's, Resnik's, Jiang's) and three GO structures (BP, CC, MF) for the yeast expression data. From all test cases, We found that clustering performances were remarkably improved by incorporating GO; especially, Resnik's distance measure based on Biological Process Ontology was the best.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.2
• /
• pp.212-217
• /
• 2009

There are rule-based learning method and statistic based learning method and so on which represent learning method for hierarchy relation between domain term. In this paper, we propose to leveling and similarity measure using the extended AHP of fuzzy term in Information system. In the proposed method, we extract fuzzy term in document and categorize ontology structure about it and level priority of fuzzy term using the extended AHP for specificity of fuzzy term. the extended AHP integrates multiple decision-maker for weighted value and relative importance of fuzzy term. and compute semantic similarity of fuzzy term using min operation of fuzzy set, dice's coefficient and Min+dice's coefficient method. and determine final alternative fuzzy term. after that compare with three similarity measure. we can see the fact that the proposed method is more definite than classification performance of the conventional methods and will apply in Natural language processing field.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.3
• /
• pp.259-259
• /
• 2003

Genetic algorithms using a Process of genetic evolution of an organism are appropriate for hard problems that have not been solved by any deterministic method. Up to now, the controller design method has been made with the frequency dependent specification but the design method with the time specification has gotten little progress. In this paper, we study the controller design to satisfy the performance of a plant using the generalized Manabe standard form. When dealing with a controller design in the case of two parameter configurations, there are some situations that neither a known pseudo inverse technique nor the inverse method can be applicable. In this case, we propose two methods of designing a controller by the gradient algorithm and the new pseudo inverse method so that the desired closed polynomials are either equalized to or approximated to the designed polynomial. Design methods of the proposed controller are implemented in Java.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.6
• /
• pp.735-740
• /
• 2012

In this paper, we introduce design methodologies of polynomial radial basis function neural network classifier with the aid of Principal Component Analysis(PCA) and Linear Discriminant Analysis(LDA). By minimizing the information loss of given data, Feature data is obtained through preprocessing of PCA and LDA and then this data is used as input data of RBFNNs. The hidden layer of RBFNNs is built up by Fuzzy C-Mean(FCM) clustering algorithm instead of receptive fields and linear polynomial function is used as connection weights between hidden and output layer. In order to design optimized classifier, the structural and parametric values such as the number of eigenvectors of PCA and LDA, and fuzzification coefficient of FCM algorithm are optimized by Artificial Bee Colony(ABC) optimization algorithm. The proposed classifier is applied to some machine learning datasets and its result is compared with some other classifiers.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.5
• /
• pp.55-64
• /
• 2018

In this paper, we propose fully convolutional neural networks based automatic detection of a pothole that directly causes driver's safety accidents and the vehicle damage. First, the training DB is collected through the camera installed in the vehicle while driving on the road, and the model is trained in the form of a semantic segmentation using the fully convolutional neural networks. In order to generate robust performance in a dark environment, we augmented the training DB according to brightness, and finally generated a total of 30,000 training images. In addition, a total of 450 evaluation DB was created to verify the performance of the proposed automatic pothole detection, and a total of four experts evaluated each image. As a result, the proposed pothole detection showed robust performance for missing.

• Proceedings of the Korea Technology Innovation Society Conference
• /
• 2005.10a
• /
• pp.619-636
• /
• 2005

기술의 복합성이 증가하고 제품의 존속 수명주기가 불확실해지면서 기술개발자가 의도하는 바와는 관계없이 사업 영역과 기술기반의 변하고 있다. 이러한 환경 속에서 산업 내 기술의 특성을 분석하는 이른바 산업기술분석 역할은 매우 중요하다. 그러나 그 범위가 매우 광범위하고 그 중 기술개발에 있어 관련된 산업기술분석의 프레임이 구체적으로 적용된 사례를 제한적이다. 따라서 다양한 산업을 지원하는 정부 기술개발 기회의 경우, 반도체에 적용되는 모듈러 기반 기술개발 틀과 성과분석이 항공기, 지능형 로봇과 같은 복합 시스템 산업에 그대로 적용해왔던 것이 현실이다. 이는 기술을 제품화함에 있어 필수적인 개발시스템의 기술적 속성이 산업기술 분석 방법론에 효과적으로 체화되지 못했기 때문이다 본 연구는 시스템과 서브 부품으로 구성되는 제품설계 특성을 구조화한 제품 아키텍쳐 이론을 소개하고 이를 기술개발체계에 적용하는 실증적 연구를 수행한다. 실증적 분석을 위해 항공기 개발 전 과정을 분해하고 아키텍쳐 분석방법을 실제 적용하였다. 아키텍쳐는 대표적으로 모듈 형(Module)과 인테그랄 형(Integral)으로 구분한다. 실제로 한 가지의 제품 안에도 모듈형 부품과 인테그랄 형 부품이 복합적으로 혼합되어 있는 경우가 많다. 또한, 제품을 어느 레벨까지 분해할 지에 따라 모듈화의 정도도 달라 질 수 있다. 본 연구는 아키텍쳐 중 Integral 속성의 정도를 파악하여 아키텍쳐 정도를 파악하였다. 측정 기준으로 첫째, 타 부품과의 기능적인 상호연관성과 둘째, 체계종합 설계와의 상호의존성 두 가지를 설정하였다. 이러한 두 가지 아키텍쳐 기준을 547개의 항공우주 부품 및 기술을 적용해 본 결과, 항공기 개발과정은 총 $65\%$의 인테그럴 속성을 가지고 있으며 기술분야 별로 아키텍쳐 정도가 다르게 나타나고 있었다(전자 부품은 분야는 오히려 모듈형에 가까웠음). 비단 항공기 개발과정 뿐만 아니라 다른 산업, 제품에도 적용될 수 있는 틀을 마련함으로써, 기존 연구개발기회에서 산업기술 분석을 통한 체계적 기획으로 전환할 수 있는 새로운 대안을 제시한다. 결과적으로 산업기술의 특성과 구조를 반영한 기술개발 방법론으로 아키텍쳐 이론을 적용할 수 있는 단초를 마련했으며, 이것은 본 논문이 기대하는 바이기도 하다.

• Journal of Intelligence and Information Systems
• /
• v.22 no.4
• /
• pp.87-107
• /
• 2016

Understanding market convergence has became essential for small and mid-size enterprises. Identifying convergence items among heterogeneous markets could lead to product innovation and successful market introduction. Previous researches have two limitations. First, traditional researches focusing on patent databases are suitable for detecting technology convergence, however, they have failed to recognize market demands. Second, most researches concentrate on identifying the relationship between existing products or technology. This study presents a platform to identify the opportunity of market convergence by using product databases from a global B2B marketplace. We also attempt to identify convergence opportunity in different industries by applying Structural Hole theory. This paper shows the mechanisms for market convergence: attributes extraction of products and services using text mining and association analysis among attributes, and network analysis based on structural hole. In order to discover market demand, we analyzed 240,002 e-catalog from January 2013 to July 2016.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.253-266
• /
• 2018

This paper proposes a methodology applying sequence tagging methodology to improve the performance of NER(Named Entity Recognition) used in QA system. In order to retrieve the correct answers stored in the database, it is necessary to switch the user's query into a language of the database such as SQL(Structured Query Language). Then, the computer can recognize the language of the user. This is the process of identifying the class or data name contained in the database. The method of retrieving the words contained in the query in the existing database and recognizing the object does not identify the homophone and the word phrases because it does not consider the context of the user's query. If there are multiple search results, all of them are returned as a result, so there can be many interpretations on the query and the time complexity for the calculation becomes large. To overcome these, this study aims to solve this problem by reflecting the contextual meaning of the query using Bidirectional LSTM-CRF. Also we tried to solve the disadvantages of the neural network model which can't identify the untrained words by using ontology knowledge based feature. Experiments were conducted on the ontology knowledge base of music domain and the performance was evaluated. In order to accurately evaluate the performance of the L-Bidirectional LSTM-CRF proposed in this study, we experimented with converting the words included in the learned query into untrained words in order to test whether the words were included in the database but correctly identified the untrained words. As a result, it was possible to recognize objects considering the context and can recognize the untrained words without re-training the L-Bidirectional LSTM-CRF mode, and it is confirmed that the performance of the object recognition as a whole is improved.

• Informatization Policy
• /
• v.20 no.2
• /
• pp.39-59
• /
• 2013

Majority of knowledge management(KM) studies in e-government have been confined to facilitate KM within an organization. But due to citizen-centric(citizen-driven) paradigm shift and advance of web 2.0 communication in recent years, KM between governments and citizen in e-government portals is becoming an important consideration. So a series of studies on knowledge enhanced e-government portal get under way by considering that it is necessary to enhance knowledge of e-government portal and assuming it improves the usability of portal. While the topics of knowledge enhancement and e-government(portal) are widely discussed in their own domains there is a paucity of studies that address these constructs in a joint context. This paper aims to propose conceptual framework of knowledge enhanced e-government portal through structuralization of theoretical discussion with holistic approach. This framework presents an evolutional path of knowledge enhanced e-government portal that consists of three phases and it will be used for realizing the knowledge enhanced portal project as a basic reference model.

• Journal of Digital Convergence
• /
• v.19 no.10
• /
• pp.253-263
• /
• 2021

Machine learning is the process of constructing a cost function using learning data used for learning and an artificial neural network to predict the data, and finding parameters that minimize the cost function. Parameters are changed by using the gradient-based method of the cost function. The more complex the digital signal and the more complex the problem to be learned, the more complex and deeper the structure of the artificial neural network. Such a complex and deep neural network structure can cause over-fitting problems. In order to avoid over-fitting, a weight decay regularization method of parameters is used. We additionally use the value of the cost function in this method. In this way, the accuracy of machine learning is improved, and the superiority is confirmed through numerical experiments. These results derive accurate values for a wide range of artificial intelligence data through machine learning.