• Journal of KIISE:Software and Applications
• /
• v.29 no.3
• /
• pp.145-155
• /
• 2002

In content-based image retrieval (CBIR), most conventional approaches assume a linear relationship between different features and require users themselves to assign the appropriate weights to each feature. However, the linear relationship assumed between the features is too restricted to accurately represent high-level concepts and the intricacies of human perception. In this paper, a neural network-based image retrieval (NNIR) model is proposed. It has been developed based on a human-computer interaction approach to CBIR using a radial basis function network (RBFN). By using the RBFN, this approach determines the nonlinear relationship between features and it allows the user to select an initial query image and search incrementally the target images via relevance feedback so that more accurate similarity comparison between images can be supported. The experiment was performed to calculate the level of recall and precision based on a database that contains 1,015 images and consists of 145 classes. The experimental results showed that the recall and level of the proposed approach were 93.45% and 80.61% respectively, which is superior than precision the existing approaches such as the linearly combining approach, the rank-based method, and the backpropagation algorithm-based method.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.19 no.12
• /
• pp.1356-1363
• /
• 2009

The aim of this research is to construct eigenfrequency optimization codes for plates with Arbitrary Rank Microstructures. From among noise factors, resonance sound is main reason for floor's solid noise. But, Resonance-elusion design codes are not fixed so far. Besides, The prediction of composite material's capability and an resonance elusion by controlling natural frequency of plate depend on designer's experiences. In this paper, First, using computer program with arbitrary rank microstructure, variation on composite material properties is studied, and then natural frequency control is performed by plate topology optimization method. The results of this study are as followed. 1) Programs that calculate material properties along it's microstructure composition and control natural frequency on composite material plate are coded by Homogenization and Topology Optimization method. and it is examined by example problem. 2) Equivalent material properties, calculated by program, are examined for natural frequency. In this paper, Suggested programs are coded using $Matlab^{TM}$, Feapmax and Feap Library with Homogenization and Topology Optimization method. and Adequacy of them is reviewed by performing the maximization or minimization of natural frequency for plates with isotropic or anisotropic materials. Since the programs has been designed for widely use. If the mechanism between composite material and other structural member is identified, extension application may be possible in field of structure maintenance, reinforcement etc. through application of composite material.

• Journal of The Korean Association of Information Education
• /
• v.13 no.1
• /
• pp.69-76
• /
• 2009

This paper proposes a teaching plan of programming language class for university of education students amusingly with LEGO Mindstorms NXT robot. The goal of class is not fragmentary knowledge acquirement but problem-solving of maze. This robot communicates with GUI named NXT-G installed in computer via USB. GUI is not text-based but icon-based programming tool. This paper designs a semester with 3 steps such as beginner, intermediate, high-rank. Beginner step is consists of learning of basic functions such as GUI usage and several sensors of robot. Intermediate step is consists of solving of maze problem with low complexity. High-rank step is consists of solving maze problem with medium and high complexity. All maze problem-solving have 3 process with algorithm, flowchart, and programming with stack.

• Journal of Information Technology and Architecture
• /
• v.9 no.4
• /
• pp.413-422
• /
• 2012

Many researchers have been studied to reveal human natural language to let machine understand its meaning by text based, page rank based or more. Particularly, it has been considered that URL and HTML Tag information in web documents are attracting people' attention again to analyze huge amount of web document automatically. In this paper, we propose a STW (Semantic Term Weight) approach based on syntactic and linguistic structure of web documents in order to classify what genres are. For the evaluation, we analyzed more than 1,000 documents from 20-Genre-collection corpus for training the documents based on SVM algorithm. Afterwards, we tested KI-04 corpus to evaluate performance of our proposed method. This paper measured their accuracy by classifying them into an experiment using STW and one without u sing STW. As the results, the proposed STW based approach showed approximately 10.2% which Is higher than one without use of STW.

• Journal of KIISE:Software and Applications
• /
• v.32 no.7
• /
• pp.636-649
• /
• 2005

Field-associated Terms itself have field Information. So, they determine field of document just like when human being perceives field. In case of Korean, we organized and experimented them by collecting approximately IS,999 document banks that are classified into 180 fields. We obtained high precision of extraction that 88,782 single field-associated terms are contracted into 8,405 ones thus recording compression rate as approximately 9$\%$ and recall as above 0.77 (average 0.85), precision as above 0.90 (average 0.94). By applying established field-associated terms to initial determination for document classification and comparing it with filed determination by human being, we got correct answers above approximately 90$\%$. We can use results of research as fundamental research for initial stage and apply it document retrieval between multilingual environment thus utilizing it as fundamental research for multilingual information retrieval.

• The Journal of the Korea Contents Association
• /
• v.21 no.1
• /
• pp.24-38
• /
• 2021

This study aims to measure Korea's global competitiveness in intelligent information technology, which is the core technology of the 4th industrial revolution. For analysis, we collect patents of each field and prior patents cited by them, which are applied at the U.S. Patent Office (USPTO) between 2010 and 2018 from PATSTAT Online. A global knowledge transfer network was established by grouping citing- and cited-relationships at a national level. The in-degree centrality is used to evaluate technology acceptance, which indicates the process of absorbing existing technological knowledge to create new knowledge in each field. Second, to evaluate the impact of existing technological knowledge on the creation of new one, the out-degree centrality is investigated. Third, we apply the PageRank algorithm to qualitatively and quantitatively investigate the importance of the relationships between countries. As a result, it is confirmed through all the indicators that the AI sector is currently the least competitive.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.39-46
• /
• 2021

This study is about a method of extracting a summary from a news article in consideration of the importance of each sentence constituting the article. We propose a method of calculating sentence importance by extracting the probabilities of topic sentence, similarity with article title and other sentences, and sentence position as characteristics that affect sentence importance. At this time, a hypothesis is established that the Topic Sentence will have a characteristic distinct from the general sentence, and a deep learning-based classification model is trained to obtain a topic sentence probability value for the input sentence. Also, using the pre-learned ELMo language model, the similarity between sentences is calculated based on the sentence vector value reflecting the context information and extracted as sentence characteristics. The topic sentence classification performance of the LSTM and BERT models was 93% accurate, 96.22% recall, and 89.5% precision, resulting in high analysis results. As a result of calculating the importance of each sentence by combining the extracted sentence characteristics, it was confirmed that the performance of extracting the topic sentence was improved by about 10% compared to the existing TextRank algorithm.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.2
• /
• pp.176-182
• /
• 2023

With about 80% of the global economy expected to shift to the global market by 2030, exports of reverse direct purchase products, in which foreign consumers purchase products from online shopping malls in Korea, are growing 55% annually. As of 2021, sales of reverse direct purchases in South Korea increased 50.6% from the previous year, surpassing 40 million. In order for domestic SMEs(Small and medium sized enterprises) to enter overseas markets, it is important to come up with export strategies based on various market analysis information, but for domestic small and medium-sized sellers, entry barriers are high, such as lack of information on overseas markets and difficulty in selecting local preferred products and determining competitive sales prices. This study develops an AI-based product recommendation and sales price estimation model to collect and analyze global shopping malls and product trends to provide marketing information that presents promising and appropriate product sales prices to small and medium-sized sellers who have difficulty collecting global market information. The product recommendation model is based on the LTR (Learning To Rank) methodology. As a result of comparing performance with nDCG, the Pair-wise-based XGBoost-LambdaMART Model was measured to be excellent. The sales price estimation model uses a regression algorithm. According to the R-Squared value, the Light Gradient Boosting Machine performs best in this model.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11a
• /
• pp.595-597
• /
• 2005

청소로봇은 대부분 랜덤방식 또는 바둑판식의 청소알고리즘으로 운용된다. 랜덤 알고리즘은 전체 청소 시간이 오래 걸린다는 단점을 가지고 있다. 랜덤 알고리즘의 문제를 해결하기 위한 바둑판식 알고리즘은 현재까지 가장 좋은 알고리즘으로 알려져 있으나 장애물이 복잡한 공간에서는 청소시간이 길어지는 단점을 가지고 있다. 이런 문제점을 해결하기 위하여 본 논문에서는 Group-k 라는 새로운 청소 알고리즘을 제안한다. Group-k 알고리즘은 청소시간을 단축시키는 목적보다는 청소시간은 같더라도 복잡한 구역일수록 나중에 청소함으로써 가능한 빠른 시간 내에 가장 많은 면적을 청소하는 것을 목표로 한다. 즉 인접한 복잡한 장애물들을 하나의 그룹으로 구성하고 그룹의 복잡성을 계산하여 복잡성이 낮은 그룹부터 먼저 청소하는 방식이다. 시뮬레이션에 기반한 실험을 통해 Group-k 알고리즘이 복잡한 장애물 구역을 그룹화하여 복잡한 공간을 효율적으로 청소함을 보여준다.

• Journal of Information Technology Applications and Management
• /
• v.11 no.4
• /
• pp.49-60
• /
• 2004

While the World-Wide Web offers an incredibly rich base of information, organized as a hypertext it does not provide a uniform and efficient way to retrieve specific information. Therefore, it is needed to develop an efficient web crawler for gathering useful information in acceptable amount of time. In this paper, we studied the order in which the web crawler visit URLs to rapidly obtain more important web pages. We also developed an internet agent for efficient web crawling using hyperlink structure and fitness of hypertext documents. As a result of experiment on a website. it is shown that proposed agent outperforms other web crawlers using BackLink and PageRank algorithm.