• Journal of the Korean Geotechnical Society
• /
• v.37 no.9
• /
• pp.25-36
• /
• 2021

Recently, the intelligent compaction technology for quality control of earthworks has brought attention as a quality control standard for earthworks. In this study, intelligent compaction technology and earthwork quality control methods were investigated and earthwork quality control procedures using intelligent compaction technology were considered based on field tests. Through the field compaction test of the silty sand (SM) fill material, it was confirmed that CMV and bearing capcaity index from plate load tests increased as the number of compactions increased. Based on the field test data, the average CMV and quality control target CMV were derived. The target CMV (34.2) was calculated through the correlation with the bearing capacity index of the plate load test, and the target CMV (36.6) was calculated through the analysis of the CMV increase rate. In this paper, the on-site compaction quality management procedure and methodology using intelligent compaction technology were discussed, and an intelligent compaction quality management method was proposed to promote the applicability of the technology.

• Journal of Intelligence and Information Systems
• /
• v.17 no.1
• /
• pp.17-35
• /
• 2011

The collective intelligence is a common-based production by the collaboration and competition of many peer individuals. In other words, it is the aggregation of individual intelligence to lead the wisdom of crowd. Recently, the utilization of the collective intelligence has become one of the emerging research areas, since it has been adopted as an important principle of web 2.0 to aim openness, sharing and participation. This paper introduces an approach to seek the collective intelligence by cognition of the relation and interaction among individual participants. It describes a methodology well-suited to evaluate individual intelligence in information retrieval and classification as an application field. The research investigates how to derive and represent such cognitive intelligence from individuals through the application of fuzzy relational theory to personal construct theory and knowledge grid technique. Crucial to this research is to implement formally and process interpretatively the cognitive knowledge of participants who makes the mutual relation and social interaction. What is needed is a technique to analyze cognitive intelligence structure in the form of Hasse diagram, which is an instantiation of this perceptive intelligence of human beings. The search for the collective intelligence requires a theory of similarity to deal with underlying problems; clustering of social subgroups of individuals through identification of individual intelligence and commonality among intelligence and then elicitation of collective intelligence to aggregate the congruence or sharing of all the participants of the entire group. Unlike standard approaches to similarity based on statistical techniques, the method presented employs a theory of fuzzy relational products with the related computational procedures to cover issues of similarity and dissimilarity.

• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.119-134
• /
• 2018

A knowledge map as the taxonomy used in a knowledge repository should be structured to support and supplement knowledge activities of users who sequentially inquire and select knowledge for problem solving. The conventional knowledge map with a hierarchical structure has the advantage of systematically sorting out types and status of the knowledge to be managed, however it is not only irrelevant to knowledge user's process of cognition and utilization, but also incapable of supporting user's activity of querying and extracting knowledge. This study suggests a methodology for constructing a networked knowledge map that can support and reinforce the referential navigation, searching and selecting related and chained knowledge in term of contents, between knowledge. Regarding a keyword as the semantic information between knowledge, this research's networked knowledge map can be constructed by aggregating each set of knowledge links in an automated manner. Since a keyword has the meaning of representing contents of a document, documents with common keywords have a similarity in content, and therefore the keyword-based document networks plays the role of a map expressing interactions between related knowledge. In order to examine the feasibility of the proposed methodology, 50 research papers were randomly selected, and an exemplified networked knowledge map between them with content relevance was implemented using common keywords.

• Journal of Intelligence and Information Systems
• /
• v.12 no.2
• /
• pp.33-48
• /
• 2006

The Semantic Web and its related technologies have been opening the era of information sharing via the Web. There are, however, several huddles still to overcome in the new era, and one of the major huddles is the issue of information integration, unless a single unified and huge ontology could be built and used which could address everything in the world. Particularly in the e-business area, the problem of information integration is of a great concern for product search and comparison at various Internet shopping sites and e-marketplaces. To overcome this problem, we proposed an ontology-driven mapping algorithm between heterogeneous product classification and description frameworks. We also peformed a comparative evaluation of the proposed mapping algorithm against a well-Down ontology mapping tool, PROMPT.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.165-184
• /
• 2023

Recently, Deep learning analysis of unstructured text data using language models, such as Google's BERT and OpenAI's GPT has shown remarkable results in various applications. Most language models are used to learn generalized linguistic information from pre-training data and then update their weights for downstream tasks through a fine-tuning process. However, some concerns have been raised that privacy may be violated in the process of using these language models, i.e., data privacy may be violated when data owner provides large amounts of data to the model owner to perform fine-tuning of the language model. Conversely, when the model owner discloses the entire model to the data owner, the structure and weights of the model are disclosed, which may violate the privacy of the model. The concept of offsite tuning has been recently proposed to perform fine-tuning of language models while protecting privacy in such situations. But the study has a limitation that it does not provide a concrete way to apply the proposed methodology to text classification models. In this study, we propose a concrete method to apply offsite tuning with an additional classifier to protect the privacy of the model and data when performing multi-classification fine-tuning on Korean documents. To evaluate the performance of the proposed methodology, we conducted experiments on about 200,000 Korean documents from five major fields, ICT, electrical, electronic, mechanical, and medical, provided by AIHub, and found that the proposed plug-in model outperforms the zero-shot model and the offsite model in terms of classification accuracy.

• Cross-Cultural Studies
• /
• v.52
• /
• pp.277-312
• /
• 2018

First-order cybernetics during the 1940s and 1950s aimed for control of an observed system, while second-order cybernetics during the mid-1970s aspired to address the mechanism of an observing system. The former pursues an objective, subjectless, approach to a system, whereas the latter prefers a subjective, personal approach to a system. Second-order observation must be noted since a human observer is a living system that has its unique cognition. Maturana and Varela place the autopoiesis of this biological system at the core of second-order cybernetics. They contend that an autpoietic system maintains, transforms and produces itself. Technoscientific recreation of biological autopoiesis opens up to a new step in cybernetics: what I describe as third-order cybernetics. The formation of technoscientific autopoiesis overlaps with the Fourth Industrial Revolution or what Erik Brynjolfsson and Andrew McAfee call the Second Machine Age. It leads to a radical shift from human centrism to posthumanity whereby humanity is mechanized, and machinery is biologized. In two versions of the novel Demon Seed, American novelist Dean Koontz explores the significance of technoscientific autopoiesis. The 1973 version dramatizes two kinds of observers: the technophobic human observer and the technology-friendly machine observer Proteus. As the story concludes, the former dominates the latter with the result that an anthropocentric position still works. The 1997 version, however, reveals the victory of the techno-friendly narrator Proteus over the anthropocentric narrator. Losing his narrational position, the technophobic human narrator of the story disappears. In the 1997 version, Proteus becomes the subject of desire in luring divorcee Susan. He longs to flaunt his male egomaniac. His achievement of male identity is a sign of technological autopoiesis characteristic of third-order cybernetics. To display self-producing capabilities integral to the autonomy of machinery, Koontz's novel demonstrates that Proteus manipulates Susan's egg to produce a human-machine mixture. Koontz's demon child, problematically enough, implicates the future of eugenics in an era of technological autopoiesis. Proteus creates a crossbreed of humanity and machinery to engineer a perfect body and mind. He fixes incurable or intractable diseases through genetic modifications. Proteus transfers a vast amount of digital information to his offspring's brain, which enables the demon child to achieve state-of-the-art intelligence. His technological editing of human genes and consciousness leads to digital standardization through unanimous spread of the best qualities of humanity. He gathers distinguished human genes and mental status much like collecting luxury brands. Accordingly, Proteus's child-making project ultimately moves towards technologically-controlled eugenics. Pointedly, it disturbs the classical ideal of liberal humanism celebrating a human being as the master of his or her nature.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.22 no.5
• /
• pp.515-528
• /
• 2020

Underground concrete structures are usually designed to be used for decades, but in recent years, many of them are nearing their original life expectancy. As a result, it is necessary to promptly inspect and repair the structure, since it can cause lost of fundamental functions and bring unexpected problems. Therefore, personnel-based inspections and repairs have been underway for maintenance of underground structures, but nowadays, objective inspection technologies have been actively developed through the fusion of deep learning and image process. In particular, various researches have been conducted on developing a concrete crack detection algorithm based on supervised learning. Most of these studies requires a large amount of image data, especially, label images. In order to secure those images, it takes a lot of time and labor in reality. To resolve this problem, we introduce a method to increase the accuracy of crack area detection, improved by 0.25% on average by applying adversarial learning in this paper. The adversarial learning consists of a segmentation neural network and a discriminator neural network, and it is an algorithm that improves recognition performance by generating a virtual label image in a competitive structure. In this study, an efficient deep neural network learning method was proposed using this method, and it is expected to be used for accurate crack detection in the future.

• Journal of KIISE
• /
• v.44 no.1
• /
• pp.51-56
• /
• 2017

The research area for solving question answering (QA) problems using artificial intelligence models is in a methodological transition period, and one such architecture, the dynamic memory network (DMN), is drawing attention for two key attributes: its attention mechanism defined by neural network operations and its modular architecture imitating cognition processes during QA of human. In this paper, we increased accuracy of the inferred answers, by adapting an automatic data augmentation method for lacking amount of training data, and by improving the ability of time perception. The experimental results showed that in the 1K-bAbI tasks, the modified DMN achieves 89.21% accuracy and passes twelve tasks which is 13.58% higher with passing four more tasks, as compared with one implementation of DMN. Additionally, DMN's word embedding vectors form strong clusters after training. Moreover, the number of episodic passes and that of supporting facts shows direct correlation, which affects the performance significantly.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2011.05a
• /
• pp.382-382
• /
• 2011

최근의 극심한 기상이변으로 인하여 발생되는 유출량의 예측에 관한 사항은 치수 이수는 물론 방재의 측면에서도 역시 매우 중요한 관심사로 부각되고 있다. 강우-유출 관계는 유역의 수많은 시 공간적 변수들에 의해 영향을 받기 때문에 매우 복잡하여 예측하기 힘든 요소이며, 과거에는 추계학적 예측모형이나 확정론적 예측모형 혹은 경험적 모형 등을 사용하여 유출량을 예측하였으나 최근에는 인공신경망과 퍼지모형 그리고 유전자 알고리즘과 같은 인공지능기반의 모형들이 많이 사용되고 있다. 하지만 유출량을 예측하고자 할 때 학습자료 및 검정자료로써 사용되는 유출량은 수위-유량 관계곡선식으로부터 구하는 경우가 대부분으로 이는 이렇게 유도된 유출량의 경우 오차가 크기 때문에 그 신뢰성에 문제가 있을 것으로 판단된다. 따라서 본 논문에서는 수위를 직접 예측함으로써 이러한 오차의 문제점을 극복 하고자 한다. Neuro-Fuzzy 모형은 과거자료의 입 출력 패턴에서 정보를 추출하여 지식으로 보유하고, 이를 근거로 새로운 상황에 대한 해답을 제시하도록 하는 인공지능분야의 학습기법으로 인간이 과거의 경험과 훈련으로 지식을 축적하듯이 시스템의 입 출력에 의하여 소속함수를 최적화함으로서 모형의 구조를 스스로 조직화한다. 따라서 수학적 알고리즘의 적용이 어려운 강우와 유출관계를 하천유역이라는 시스템에서 발생된 신호체계의 입 출력패턴으로 간주하고 인간의 사고과정을 근거로 추론과정을 거쳐 수문계의 예측에 적용할 수 있을 것이다. 유전자 알고리즘은 적자생존의 생물학 원리에 바탕을 둔 최적화 기법중의 하나로 자연계의 생명체 중 환경에 잘 적응한 개체가 좀 더 많은 자손을 남길 수 있다는 자연선택 과정과 유전자의 변화를 통해서 좋은 방향으로 발전해 나간다는 자연 진화의 과정인 자연계의 유전자 메커니즘에 바탕을 둔 탐색 알고리즘이다. 즉, 자연계의 유전과 진화 메커니즘을 공학적으로 모델화함으로써 잠재적인 해의 후보들을 모아 군집을 형성한 뒤 서로간의 교배 혹은 변이를 통해서 최적 해를 찾는 계산 모델이다. 이러한 유전자 알고리즘은 전역 샘플링을 중심으로 한 수법으로 해 공간상에서 유전자의 개수만큼 복수의 탐색점을 설정할 뿐만 아니라 교배와 돌연변이 등으로 좁아지는 탐색점 바깥의 영역으로 탐색을 확장할 수 있기 때문에 지역해에 빠질 위험성이 크게 줄어든다. 따라서 예측과 패턴인식에 강한 뉴로퍼지 모형의 해 탐색방법을 유전자 알고리즘을 사용한다면 보다 정확한 해를 찾는 것이 가능할 것으로 판단된다. 따라서 본 논문에서는 선행우량 및 상류의 수위자료로부터 하류의 단시간 수위예측에 관해 연구하였으며, 이를 위해 유전자 알고리즘을 이용항여 소속함수를 최적화 시키는 형태의 Neuro-Fuzzy모형에 대하여 연구하였다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.6
• /
• pp.828-833
• /
• 2009

WWW which is an applicable massive set of document on the Web is a thesaurus of various information for users. However, Search engines spend a lot of time to retrieve necessary information and to filter out unnecessary information for user. In this paper, we propose the EFAM(the Extended Fuzzy AHP Method) model to manage the Web resource efficiently, and to make a decision in the problem of specific domain definitely. The EFAM model is concerned with the emotion analysis based on the domain corpus information, and it composed with systematic common concept grids by the knowledge of multiple experts. Therefore, The proposed the EFAM model can extract the documents by considering on the emotion criteria in the semantic context that is extracted concept from the corpus of specific domain and confirms that our model provides more efficient decision-making through an experiment than the conventional methods such as AHP and Fuzzy AHP which describe as a hierarchical structure elements about decision-making based on the alternatives, evaluation criteria, subjective attribute weight and fuzzy relation between concept and object.