• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.8
• /
• pp.3021-3027
• /
• 2010

Example-based chatBot generates a response to user's utterance by searching the most similar utterance in a collection of dialogue examples. Though finding an appropriate example is very important as it is closely related to a response quality, few studies have reported regarding what features should be considered and how to use the features for similar utterance searching. In this paper, we propose a machine learning framework which uses various linguistic features. Experimental results show that simultaneously using both semantic features and lexical features significantly improves the performance, compared to conventional approaches, in terms of 1) the utilization of example database, 2) precision of example matching, and 3) the quality of responses.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.4
• /
• pp.851-867
• /
• 1999

Numerous proposals for extending the relational data model as well as conceptual and object-oriented data models have been suggested. However, there has been relatively less research in the area of defining segmented storage structure and data migration strategies for temporal data. This paper presents the segmented storage structure in order to increment search performance and the two data migration strategies for segmented storage structure. this paper presents the two data migration strategies : the migration strategy by Time granularity, the migration strategy by LST-GET. In the migration strategy by Time Granularity, the dividing time point to assign the entity versions to the past segment, the current segment, and future segment is defined and the searching and moving process for data validity at a granularity level are described. In the migration strategy by LST-GET, we describe the process how to compute the value of dividing criterion. searching and moving processes are described for migration on the future segment and the current segment and entity versions 새 assign on each segment are defined. We simulate the search performance of the segmented storage structure in order to compare it with conventional storage structure in relational database system. And extensive simulation studies are performed in order to compare the search performance of the migration strategies with the segmented storage structure.

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.9
• /
• pp.833-839
• /
• 2004

This paper proposes a method that minimizes the consumed energy by searching the optimal locations of the mass centers of links composing of a biped robot using Real-Coded Genetic Algorithm. Generally, in order to utilize optimization algorithms, the system model and design variables must be defined. Firstly, the proposed model is a 6-DOF biped robot composed of seven links, since many of the essential characteristics of the human walking motion can be captured with a seven-link planar biped walking in the saggital plane. Next, Fourth order polynomials are used for basis functions to approximate the walking gait. The coefficients of the fourth order polynomials are defined as design variables. In order to use the method generating the optimal gait trajectory by searching the locations of mass centers of links, three variables are added to the total number of design variables. Real-Coded GA is used for optimization algorithm by reason of many advantages. Simulations and the comparison of three methods to generate gait trajectories including the GCIPM were performed. They show that the proposed method can decrease the consumed energy remarkably and be applied during the design phase of a robot actually.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.7 no.1
• /
• pp.319-351
• /
• 1994

This rearch is a case study for the newspaper libraries in Seoul and the primary purpose of the this study are to investigate its document delivery capability. To achieve the above-mentioned purpose, representative rsers visited seven the newspaper library and checked their searching time. Document delivery capability was checked by units of hour, minute, second(searching time). Retrieval effectiveness was tested through the recall ratio and the precision ratio. The major findings of the study are summarized as follows： 1) Most of the newspaper libraries excellent to the document delivery capability； 6 newspaper libraries deliverived the data related subject. 2) The newspaper libraries were came out 50.1% the mean recall ratio and 84.8% the mean precision ratio about the all materials. 3) Concerned their own articles, the newspaper libraries showed 71.4% the recall ratio and 90.0% the precision ratio. That moaned their own articles were more effectived than others. 4) The Kookmin Ilbo library had the most excellent system, and the precision ratio of The Dong-A Ilbo library prior to the recall ratio. The Han Kyoreh Shinmun library had a excellent arragement in own articles, but The Segye Times library had problem in every parties.

• The Korean Journal of Community Living Science
• /
• v.17 no.4
• /
• pp.15-27
• /
• 2006

Most countries recognize traditional knowledge as an economical resource in recent years, and so are actively participating in WIPO discussions for making sure of their intellectual property rights. In this study, the definition of traditional knowledge was discussed for making clear its categories and relative subjects. A tool for Korean Traditional Knowledge Resource Classification(KTKRC) was developed for putting the data of the resources in order, and was indispensable for searching for and examining cultural artifacts within the system of international intellectual property rights. KTKRC covers comprehensively our various traditional knowledge resources and has a similar structure to IPC for international searching, examining, and information exchange. KTKRC consists of a section of traditional knowledge(A), and three subsections: production technology(A0), living technology(A2) and creative technology(A4). The subsections include 8 classes, 28 subclasses, 105 groups, and a great number of subgroups.

• Journal of the Semiconductor & Display Technology
• /
• v.14 no.2
• /
• pp.53-59
• /
• 2015

Since the amount of digital image continues to grow in usage, users feel increased difficulty in finding specific images from the image collection. This paper proposes a novel image searching scheme that extracts the image feature using combination of Advanced SURF (Speed-Up Robust Feature) and DCD (Dominant Color Descriptor). The key point of this research is to provide a new feature extraction algorithm to improve the existing SURF method with removal of unnecessary feature in image retrieval, which can be adaptable to mobile system and efficiently run on the mobile environments. To evaluate the proposed scheme, we assessed the performance of simulation in term of average precision and F-score on two databases, commonly used in the field of image retrieval. The experimental results revealed that the proposed algorithm exhibited a significant improvement of over 14.4% in retrieval effectiveness, compared to OpenSURF. The main contribution of this paper is that the proposed approach achieves high accuracy and stability by using ASURF and DCD in searching for natural image on mobile platform.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.33 no.3
• /
• pp.130-136
• /
• 2010

In this study, we propose a new method for generating candidate solutions based on both the Cauchy and the Gaussian probability distributions in order to use the merit of the solutions generated by these distributions. The Cauchy probability distribution has larger probability in the tail region than the Gaussian distribution. Thus, the Cauchy distribution can yield higher probabilities of generating candidate solutions of large-varied variables, which in turn has an advantage of searching wider area of variable space. On the contrary, the Gaussian distribution can yield higher probabilities of generating candidate solutions of small-varied variables, which in turn has an advantage of searching deeply smaller area of variable space. In order to compare and analyze the performance of the proposed method against the conventional method, we carried out experiments using benchmarking problems of real valued functions. From the result of the experiment, we found that the proposed method based on the Cauchy and the Gaussian distributions outperformed the conventional one for most of benchmarking problems, and verified its superiority by the statistical hypothesis test.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.1B
• /
• pp.148-155
• /
• 2000

In image coding applications such as web browsing and image database searching, it is very useful to quickly view a small portion of the image with higher quality. Region of interest (ROI) coding technique provides the capability to reconstruct the ROI in advance of decompressing the rest of the image, with a smaller number of transmitted bits compared to the case where the entire image is treated with the same priority. In this paper, a progressive ROI coding method using the enbedded coder is presented, and an efficient transmission method for the ROI information. Experimental results show that the proposed progressive ROI coding technique can be effectively used for image coding applications such as web browsing and image database searching system.

• Journal of Broadcast Engineering
• /
• v.5 no.1
• /
• pp.41-49
• /
• 2000

In this paper, we propose a new method of indexing and searching based on object-specific features at different semantic levels for video retrieval. A moving trajectory model is used as an indexing key for accessing the individual object in the semantic level. By tracking individual objects with segmented data, we can generate motion trajectories and set model parameters using polynomial curve fitting. The proposed searching scheme supports various types of queries including query by example, query by sketch, and query on weighting parameters for event-based video retrieval. When retrieving the interested video clip, the system returns the best matching event in the similarity order.

• The Journal of Society for e-Business Studies
• /
• v.17 no.2
• /
• pp.73-85
• /
• 2012

Recently, as Social Network Services(SNS), such as Twitter, Facebook, are becoming more popular, much research has been doing actively. However, since SNS has been launched recently, related researches are also infant level. Especially, search engines serviced in web potals simply show the postings in order of upload time. Searching the postings in Twitter should be different from web search, which is based on traditional TF-IDF. In this paper, we present the new method of searching and ranking the interesting postings in Twitter. In proposed method, we utilize the frequency of retweets as a major factor for estimating the quality of postings. It can be an important criteria since users tend to retweet the valuable postings. Experimental results show that proposed method can be applied successfully in Twitter search system.