• Journal of Intelligence and Information Systems
• /
• v.7 no.2
• /
• pp.153-177
• /
• 2001

Nowadays, product recommendation is one of the important issues regarding both CRM and Internet shopping mall. Generally, a recommendation system tracks past actions of a group of users to make a recommendation to individual members of the group. The computer-mediated marketing and commerce have grown rapidly and thereby automatic recommendation methodologies have got great attentions. But the researches and commercial tools for product recommendation so far, still have many aspects that merit further considerations. To supplement those aspects, we devise a recommendation methodology by which we can get further recommendation effectiveness when applied to Internet shopping mall. The suggested methodology is based on web log information, product taxonomy, association rule mining, and decision tree learning. To implement this we also design and intelligent Internet shopping mall support system based on agent technology and develop it as a prototype system. We applied this methodology and the prototype system to a leading Korean Internet shopping mall and provide some experimental results. Through the experiment, we found that the suggested methodology can perform recommendation tasks both effectively and efficiently in real world problems. Its systematic validity issues are also discussed.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.11
• /
• pp.277-286
• /
• 2020

In this paper, we propose a new educational approach to help learners form concepts by identifying the properties of programming concepts targeting a group of experts in programming education. Therefore, we confirmed the typical properties of concepts by programming education experts for programming learning elements through conceptual metaphor analysis, which is a qualitative research method, and confirmed the validity through the delphi method. As a result of this study, we identified 17 typical properties of programming concepts that learners should form in programming education. The conclusions of this study are that need to compose the educational content more specifically for the conceptualization of learners' programming as follows: 1)the concept of a variable is to understand how to store data, how to set a name, what an address has, how to change a value, various types of variables, and the meaning of the size of a variable, 2)the concept of operator is to understand how to operate the four rules, how to deal with it logically, how to connect according to priority, meaning of operation symbols, and how to compare, 3)the concept of the control structure is to understand how to control the execution flow, how to make a logical judgment, how to set an execution rule, meaning of sequential execution, and how to repeat executing.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2002.11a
• /
• pp.345-352
• /
• 2002

무선 인터넷을 이용하는 사용자는 정보의 양의 따른 시간적 통신비용의 증가 문제로 개인화 에이전트가 사용자의 관심에 따라 서비스를 제공하는 기능과 맞춤화된 정보를 제공하는 기능, 지식 기반 방식으로 정보를 예측하는 기능을 가지기를 바라고 있다. 본 논문에서는 이와 같이 무선 인터넷을 사용하는 사용자를 위한 PDA 개인화 에이전트 시스템을 구축하고자 한다. PDA 개인화 에이전트 시스템 구축을 위해 프로파일 기반의 에이전트 엔진과 사용자 프로파일을 이용한 지식기반 방식을 사용한다. 사용자가 웹페이지에서 행하는 행위들을 모니터링하여 사용자가 관심 가지는 문서를 파악하고 정보 검색을 통해 얻어진 문서를 분석하여 사용자 각각의 관심 문서로 나누어 서비스하게 된다. 모니터링 되어진 문서를 효과적으로 분석하기 위해 unsupervised clustering 기계학습 방식인 Cobweb을 이용한다. unsupervised 기계 학습은 conceptual 방식을 이용하여 검색되어진 정보를 사용자의 관심 분야별로 clustering한다. 클러스터링을 통해 얻어진 결과를 다시 기계학습을 통해 사용자 관심문서에 대한 프로파일을 생성하게 된다. 이렇게 만들어진 프로파일을 룰(Rule)로 만들어 이를 기반으로 사용자에게 서비스하게 된다. 이러한 룰은 사용자의 모니터링 결과로 얻어지기 때문에 주기적으로 업데이트하게 된다. 제안하는 시스템은 인터넷신문이나 웹진 등에서 사용자들에게 뉴스를 전달하기 위한 목적으로 생성하는 뉴스문서를 특정 대상으로 선정하였고 사용자 정보를 이용한 검색을 실시하고 결과로 얻어진 정보를 정보 분류를 통해 PDA나 휴대폰을 통해 사용자에게 제공한다. 상품을 검색하기 위한 검색노력을 줄이고, 검색된 대안들로부터 구매자와 시스템이 웹상에서 서로 상호작용(interactivity) 하여 해를 찾고, 제약조건과 규칙들에 의해 적합한 해를 찾아가는 방법을 제시한다. 본 논문은 구성기반 예로서 컴퓨터 부품조립을 사용해서 Template-based reasoning 예를 보인다 본 방법론은 검색노력을 줄이고, 검색에 있어 Feasibility와 Admissibility를 보장한다.매김할 수 있는 중요한 계기가 될 것이다.재무/비재무적 지표를 고려한 인공신경망기법의 예측적중률이 높은 것으로 나타났다. 즉, 로지스틱회귀 분석의 재무적 지표모형은 훈련, 시험용이 84.45%, 85.10%인 반면, 재무/비재무적 지표모형은 84.45%, 85.08%로서 거의 동일한 예측적중률을 가졌으나 인공신경망기법 분석에서는 재무적 지표모형이 92.23%, 85.10%인 반면, 재무/비재무적 지표모형에서는 91.12%, 88.06%로서 향상된 예측적중률을 나타내었다.ting LMS according to increasing the step-size parameter $\mu$ in the experimentally computed. learning curve. Also we find that convergence speed of proposed algorithm is increased by (B+1) time proportional to B which B is the number of recycled data buffer without complexity of compu

• Korean Journal of Social Welfare
• /
• v.59 no.4
• /
• pp.137-162
• /
• 2007

In democracy basic rights such as political equality and participation through elections have been respected, opportunities of corporation and opposition have been guaranteed, and ability of self-learning and self-correction have been developed. These positive factors give preconditions for the welfare development in the democratic state. Because in this state adults get the suffrage and the open competition for official positions induces political parties use social policies as means to win the election. That is to say, political parties have an incentive to use various social policies to win the election. Democracy, therefore, has affinity with social policy. The affinity between democracy and social policy can be found also in Korea which was democratized in 1987. But, in Korea, the positive relationship between democracy and social policy is very weak due to the problem of constitutional structures. Korean Parliament usually enacts abstract social act and delegates the right to fill concrete contents of the social acts to the executive. Delegation itself has no problem, but excessive delegation is a problem since the executive can overuse its discretion as sacrificing the social rights of the citizen. In addition social consensus could not be achieved in this constitutional structures, which are a obstacle to establishing a political process in the Parliament to promote the welfare development through party competition. Excessive delegation should be reduced, and the Parliament should fill concrete contents of the social acts as exercising its legislative power more. Then a mechanism of welfare development can be launched in Korea.

• Journal of Families and Better Life
• /
• v.2 no.1
• /
• pp.131-150
• /
• 1984

The purpose of this study is to explore the family as an interaction system, concentrating on the mutual influences between communication and family development; (1) how Communication patterns affect family relationships, and (2) how relationships among family members affect communication. In order to do this Galvin, Brommel used the following frame work; family is a system in which communication regulates cohesion and adaptability by a flow of message patterns through a defined network of evolving interdependent relationships. A family system consists of members, the relationships among them, the family attributes, the members attributes and an environment in which family functions. Within the framework of common cultural communication patterns, each family has the capacity to develop its own communication code based on the experiences of individual members and the collective family experience. Most of us develop our communication skills within the family context learning both the general cultural language and the specific familial communication code. Communication may be viewed as a symbolic, transactional process as the process of creating and sharing meanings. To say that communication is a process implies a continuous interaction of an indefinite large numbers of variables with a concomitant,. continuous change in the values taken by these variables. Finally the process implies change, Family functions include the primary functions of cohesion and adaptability, and supporting functions of family images, themes, boundaries, and biosocial issues. The primary functions reveal concepts integrated family interaction and supporting function, along with those of cohesion and adaptability, give shape to family life. the characteristics of developed relationships of richness, uniqueness efficiency, substitutability, pacing , openness spontaneity, and evaluation are reflected in the verbal and nonverbal behaviors with which family members negotiated a set of common meanings and develop thier own unique message system. The message system is the major element of communication process and influences both the form and the content of thier relationship and in create and share meanings. Family systems need to provide order and predictability for thier members, specifically focusing on communication rules and the networks by which messages are transmitted. Most rules emerge as a result of multiful interactions. There are basic rules and rules about rules, or metarules. Perceiving the rules of family system is very difficult because often family members don't think about the basic rules, much less the metarules. Breaking the rule may result in the creation of a new set because the system may recalibrate itself to accept more variety of behavior. Families develop communication networks to deal with the general issue. Family adaptability may be seen through the degree of flexibility in forming and reforming networks and networks become a vital part of the decision- making process and relate to the power dynamics operating within the family. Networks also play an integral part in maintaining the roles and rules operating with the family system. Thus networks and rules have mutual influence. The family -of -origin issues influence all aspects of family communication and account for many of the communication patterns, rules and networks and the role of the family -of-origin influences as a primary force for communication on behavior of newly forming systems. Each family system develops its own communication meanings. There is not one right way to communicate within a family but may be indefinitly large change of family life and communication behavior. Study on functional family communication helps to gain a better understanding of dynamics of family communication and ability of a new insight into the family.

• (The)Study of the Eastern Classic
• /
• no.62
• /
• pp.9-35
• /
• 2016

This study examined Songgye Na-sik's(松桂懶湜, 1684~1765) literary world based on Priest Songgye's Anthology(松桂大禪師文集). In consideration of the insufficiencies of the only previous study on Songgye's literature, this study was focused on his ideological character and its historicity, the trend of literary exchange in the Buddhist circle, and the literary geographical aspect of his literature. Priest Songgye was the head of the Bonghwa-sa Temple in Andong during the years under the rule of Kings Sukjong and Yeongjo, and learned from Hwanseong Ji-ahn(喚醒志安, 1664~1729) and Nakam Eui-nul(落巖義訥, 1666~1737). The priest did not have many students under him nor leave numerous writings. In the process of the development of the Buddhist doctrines in the late Joseon Dynasty, however, he completed the scripture learning courses faithfully and laid the ground of his philosophy. In addition, the afterword of Hwaeomgyeongchilcheogupumhoipummok (華嚴經七處九會品目跋) shows that he compiled the book under his teacher's instruction. What is more, he is known to have devoted himself to belief in the Pure Land in his late years. Given these backgrounds, the priest's life, writings, and ideological tendencies pursued all of Zen, Hwaeom, and the Pure Land together, and at the same time, reflected the characteristics of Korean Buddhism in the 18th century. The priest steadily cultivated himself in poetry and established his own literary world, and all the outcomes were fully reflected in his anthology. Priest Songgye walked the road of a learner throughout his lifetime but, on the other hand, he established his identity as a literary man in the specific time and space of Andong, Yeongnam in the late Joseon Dynasty.

• Journal of the Korean Chemical Society
• /
• v.66 no.5
• /
• pp.362-375
• /
• 2022

In this study, science teachers' NOS lessons were observed and the characteristics of the lessons were analyzed. Three science teachers who taught NOS in the 'Science Inquiry Experiment' developed under the 2015 revised curriculum participated in the study. Their NOS lessons were observed and interviews were conducted before and after lessons. The collected data were analyzed using analytical induction and constant comparative method. The analyses of the result revealed the teachers' naive views on NOS were also revealed during the lessons. There were some cases where they showed naive views during the lessons even if they showed informed views in the interviews. Although the domains of NOS taught by them were diverse, all of them taught 'tentativeness' and considered this an important goal. They tended to teach NOS with content related with their major, and teaching NOS was found to be deeply related to their major. In the activity where students learn NOS by inferring the unknown object, teachers disclosed the unknown object, which is unlike the rule of the activity. They thought that could help students' learning. At last, although they emphasized teaching NOS, they either did not assess NOS or assessed NOS in a limited way. Based on the results, some directions for teacher education and follow-up study are suggested.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.125-132
• /
• 2022

Sentence compression is a natural language processing task that generates concise sentences that preserves the important meaning of the original sentence. For grammatically appropriate sentence compression, early studies utilized human-defined linguistic rules. Furthermore, while the sequence-to-sequence models perform well on various natural language processing tasks, such as machine translation, there have been studies that utilize it for sentence compression. However, for the linguistic rule-based studies, all rules have to be defined by human, and for the sequence-to-sequence model based studies require a large amount of parallel data for model training. In order to address these challenges, Deleter, a sentence compression model that leverages a pre-trained language model BERT, is proposed. Because the Deleter utilizes perplexity based score computed over BERT to compress sentences, any linguistic rules and parallel dataset is not required for sentence compression. However, because Deleter compresses sentences only considering perplexity, it does not compress sentences by reflecting the linguistic information of the words in the sentences. Furthermore, since the dataset used for pre-learning BERT are far from compressed sentences, there is a problem that this can lad to incorrect sentence compression. In order to address these problems, this paper proposes a method to quantify the importance of linguistic information and reflect it in perplexity-based sentence scoring. Furthermore, by fine-tuning BERT with a corpus of news articles that often contain proper nouns and often omit the unnecessary modifiers, we allow BERT to measure the perplexity appropriate for sentence compression. The evaluations on the English and Korean dataset confirm that the sentence compression performance of sentence-scoring based models can be improved by utilizing the proposed method.

• The Journal of Bigdata
• /
• v.8 no.1
• /
• pp.99-109
• /
• 2023

Recently, not only in Korea but also around the world, we have been experiencing constant disasters such as typhoons, wildfires, and heavy rains. The property damage caused by typhoons and heavy rain in South Korea alone has exceeded 1 trillion won. These disasters have resulted in significant loss of life and property damage, and the recovery process will also take a considerable amount of time. In addition, the government's contingency funds are insufficient for the current situation. To prevent and effectively respond to these issues, it is necessary to collect and analyze accurate data in real-time. However, delays and data loss can occur depending on the environment where the sensors are located, the status of the communication network, and the receiving servers. In this paper, we propose a two-stage hybrid situation analysis and prediction algorithm that can accurately analyze even in such communication network conditions. In the first step, data on river and stream levels are collected, filtered, and refined from diverse sensors of different types and stored in a bigdata. An AI rule-based inference algorithm is applied to analyze the crisis alert levels. If the rainfall exceeds a certain threshold, but it remains below the desired level of interest, the second step of deep learning image analysis is performed to determine the final crisis alert level.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.4
• /
• pp.21-29
• /
• 2023

In this paper, we propose an AI-based system for automatically classifying industry and occupation codes in the population census. The accurate classification of industry and occupation codes is crucial for informing policy decisions, allocating resources, and conducting research. However, this task has traditionally been performed by human coders, which is time-consuming, resource-intensive, and prone to errors. Our system represents a significant improvement over the existing rule-based system used by the statistics agency, which relies on user-entered data for code classification. In this paper, we trained and evaluated several models, and developed an ensemble model that achieved an 86.76% match accuracy in industry and 81.84% in occupation, outperforming the best individual model. Additionally, we propose process improvement work based on the classification probability results of the model. Our proposed method utilizes an ensemble model that combines transfer learning techniques with pre-trained models. In this paper, we demonstrate the potential for AI-based systems to improve the accuracy and efficiency of population census data classification. By automating this process with AI, we can achieve more accurate and consistent results while reducing the workload on agency staff.