• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.769-772
• /
• 1995

This paper presents fuzzy control rules of automatically driving a car. Fuzzy control rules proposed are designed by investigating human experts' experiences and composed of three groups whose functions are different. According to computer simulations which let a model car pass through a curve of S type, we showed validity of fuzzy control rules suggested.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.13 no.6
• /
• pp.104-110
• /
• 2014

This paper presents a non-contact inspection system for automatically measuring the thickness of an aircraft wing rip product. In order to conduct the inspection of the wing rib thickness automatically, a non-contact laser displacement sensor, end-effector, and a robot were selected for use. The non-contact type inspection system was evaluated by measuring the measurement deviation of the rotation direction of a C-type yoke end-effector and the transfer direction of a V-slim end-effector. In addition, the non-contact inspection system for wing rib thickness measurements was validated through thickness measurements of a web, flange, and stiffener.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.18 no.1
• /
• pp.13-21
• /
• 2009

Interactive Graphic Robotics Integrated Programming(IGRIP) can handle various types of robot models and can exchange graphic or numerical data easily with other CAD software. In a cutting process of shape-steels, however. IGRIP is inconvenient because the users must generate all the tag points manually. In this study we developed an automation program module in order to generate the tag points automatically in IGRIP This program can read and analyze the macro data containing the information for cutting processes of shape-steels and can generate automatically the parts, the devices, the tag points and the Graphic Simulation Language(GSL) program files useful in IGRIP.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.6
• /
• pp.69-77
• /
• 2017

The information related to legislation is massive, and it takes much time and effort to manually build the legislation ontology. Thus, studies on machine-based automated building methods are underway. However, the studies to automatically construct such systems focus on using TBox construction, and those based on automated ABox construction, which corresponds to instances, theoretical systems and data building cases, has not yet been sufficiently developed. Therefore, this paper suggests using a semi-automatic ABox construction method based on sentence patterns to automatically build the ontology for the legislation of the Republic of Korea. Precision and Recall experiments were conducted to further discuss the performance of the suggested method. These experiments provide a comparison between the manual classification, and the triples built by the machines of the legal information by assessing the corresponding numerical values.

• Journal of Digital Contents Society
• /
• v.8 no.4
• /
• pp.451-458
• /
• 2007

In this paper, I developed a method whereby spam mail is automatically blocked through the connection to link URL. The blocking system works as follows. First, the system extracts information of URL linked to electronic mail which was delivered from any server on the internet. Next, the system lets itself be connected to the web pages through this URL. Last, the system blocks the electronic mail if those web pages contain any key word which was defined as a clue to spam mail.

• Speech Sciences
• /
• v.10 no.1
• /
• pp.27-39
• /
• 2003

This study attempts to verify the reliability of automatically generated segment labels as compared to those obtained by conventional labelling by hand. First of all, an autolabeller is constructed using the standard HMM speech recognition technique. For evaluation, we compare the automatically generated labels with manually annotated labels for the same speech data. The comparison is performed by calculating the temporal difference between an autolabel boundary and its corresponding hand label boundary. When the mismatched duration between two labels falls within 10 msec, we consider the autolabel as correct. The results suggest that overall 78% of autolabels are correctly obtained. It is found that the boundary of obstruents is better aligned than that of sonorants and vowels. In case of stop sound classes, strong stops in manner-of-articulation wise and velar stops in place-of-articulation wise show better performance in boundary alignment. The result suggests that more phone-specific consideration is necessary to improve autosegmentation performance.

• Korean Journal of Computational Design and Engineering
• /
• v.14 no.4
• /
• pp.261-270
• /
• 2009

We can save a lot of efforts and time to perform various kinds of multibody system dynamics simulations if the equations of motion of the multibody system can be formulated automatically. In general, the equations of motion are formulated based on Newton's $2^{nd}$law. And they can be transformed into the equations composed of independent variables by using velocity transformation matrix. In this paper the velocity transformation matrix is derived based on a topological modeling approach which considers the topology and the joint property of the multibody system. This approach is, then, used to formulate the equations of motion automatically and to implement a multibody system dynamics simulation program. To verify the the efficiency and convenience of the program, it is applied to the lifting simulation of a floating crane.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.6 no.3
• /
• pp.598-625
• /
• 2014

To support the procedure for determining an optimal liquefaction cycle for FLNG FEED, an ontological modeling method which can automatically generate various alternative liquefaction cycles were carried out in this paper. General rules in combining equipment are extracted from existing onshore liquefaction cycles like C3MR and DMR cycle. A generic relational model which represents whole relations of the plant elements has all these rules, and it is expressed by using the system entity structure (SES), an ontological framework that hierarchically represents the elements of a system and their relationships. By using a process called pruning which reduces the SES to a candidate, various alternative relational models of the liquefaction cycles can be automatically generated. These alternatives were provided by XML-based formats, and they can be used for choosing an optimal liquefaction cycle on the basis of the assessments such as process simulation and reliability analysis.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.972-974
• /
• 1993

This paper presents a new method to automatically design fuzzy logic controller(FLC). The main problems of designing FLC are how to optimally and automatically select the control rules and the parameters of membership function (MF). Cell state space algorithms (CSS), differential competitive learning (DCL) and multialyer neural network are combined in this paper to solve the problems. When the dynamical model of a control process is known. CSS can be used to generate a group of optimal input output pairs(X, Y) used by a controller. The(X, Y) then can be used to determine the FLC rules by DCL and to determine the optimal parameters of MF by DCL and to determine the optimal parameters of MF by multilayer neural network trained by BP algorithm.

• Journal of the Korean Society for Library and Information Science
• /
• v.35 no.4
• /
• pp.141-160
• /
• 2001

This study is to develop a new system for conducting the information retrieval automatically. The system in this study is programmed by Delphi 4.0(PASCAL) and consists of automatic indexing, clustering technique, establishing and expressing term hierarchic relation, and automatic information retrieval technique. Thus this browser system can automatically control all the processes of information searching such as representation, generation and extension of queries and construction of searching strategy and feedback searching.