• Speech Sciences
• /
• v.11 no.2
• /
• pp.217-226
• /
• 2004

An automatic pronunciation correction system provides users with correction guidelines for each pronunciation error. For this purpose, we develop a speech recognition system which automatically classifies pronunciation errors when Koreans speak a foreign language. In this paper, we propose a machine scoring method for automatic assessment of pronunciation quality by the speech recognizer. Scores obtained from an expert human listener are used as the reference to evaluate the different machine scores and to provide targets when training some of algorithms. We use a log-likelihood score and a normalized log-likelihood score as machine scoring methods. Experimental results show that the normalized log-likelihood score had higher correlation with human scores than that obtained using the log-likelihood score.

• Journal of the Korean Society of Safety
• /
• v.9 no.4
• /
• pp.125-131
• /
• 1994

This paper proposes a dynamic recursive model with the effect analysis of machine state considering human factor(human skillfulness) In a single lot man-machine production system. This model obtained using Kalman Filtering Algorithm Is based on input state, output state, machine state. For sensitivity analysis, this model constructed is examined according to the impact of human skillfulness with computer simulation. The model studied in this paper has a great advance from the point of view a combination of three factors( human engineering, dynamic control theory, quality control ) and can also be extended in several applications.

• Proceedings of the Korean Nuclear Society Conference
• /
• 1997.05a
• /
• pp.437-443
• /
• 1997

DYLAM and its related applications are reviewed in detail and found to have many favorable characteristics. Concerning human factor analysis, the study demonstrates that DYLAM methodology represents an appropriate tool to study man-machine behavior provided that DYLAM is used to model machine behavior and an appropriate operator interface human factor model is included. A hybrid model which is a synthesis of the DYLAM model, a system thermodynamic simulation model and a neural network predicative model, is implemented and used to analyze dynamically the CANDU pressurizer system.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.5 no.6
• /
• pp.33-39
• /
• 1982

In the design of some systems, the circumstance may require a determination as to whether a giver information input or processing function can best be performed by an individual or by some physical components of a system. In the consideration of human factors, also, in the design of equipment, facilities, and other physical items that people use, there are certain basic stages or processes that typically have to be carried out. The main purpose of this paper is study fundamental man-machine system assumptions in Human Factors Engineering. Therefore, this paper will deal with certain human factors that may be relevant to the design consideration that relate to human information - receiving and processing functions.

• Journal of Biosystems Engineering
• /
• v.22 no.2
• /
• pp.210-216
• /
• 1997

A study to select ground colors of Fuji apple for maturity index which are needed to standardize grading of the apples is presented. Two extreme colors of immature and fully mature Fuji and Zonagold apples produced in Korea were determined. Various ground colors of Fuji apple between the two extreme colors were collected and classified by human vision and colors of Fuji apple for maturity index were selected from the classification. Coordinates of the selected colors in xy chromaticity diagram were determined by spectrophotometers to define them in a standard coordinate system. Coordinates of the colors in r-g chromaticity diagram using a color machine vision system were also determined to use the colors in apple grading by the machine vision system. Grading Fuji apples using the machine vision system was performed and result of the grading was compared with Ending results of human vision and colorimeter. The comparison was performed with the same Fuji apple samples and showed 65% md 75% of same grades, respectively, as the grades determined by the machine vision system. Differences of fading performance between the compared three grading methods were explained as mainly because of the differences of observation area of the grading methods.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.118-121
• /
• 2003

Human support systems, such as computers and robots, are required to be changed to a machine equipment independently operates and communicate with human, rather than non-sensitivity and obedient machine equipment Therefore, we notice nonverbal language that human recognizes naturally. In addition, we show the validity and constitution of mechanism that recognizes an intention of human using those several information to judge independently.

• Convergence Security Journal
• /
• v.14 no.6_2
• /
• pp.45-52
• /
• 2014

Up to now, the security system in Korea has been developed from the human security system to more efficient mechanical security system. The mechanical security system has its advantages over the human security system in terms of economy and operation. However, as there are weaknesses in the use of mechanical security equipment such as erroneous alarm sounds, the studies have been done to improve them. This paper tries to suggest how to improve the mechanical security system based on the results of the study on the weakness of the mechanical security obtained through AHP technique.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.7
• /
• pp.633-640
• /
• 2001

In this paper we examine the machine learning issues raised by the domain of the Intrusion Detection Systems(IDS), which have difficulty successfully classifying intruders. There systems also require a significant amount of computational overhead making it difficult to create robust real-time IDS. Machine learning techniques can reduce the human effort required to build these systems and can improve their performance. Genetic algorithms are used to improve the performance of search problems, while data mining has been used for data analysis. Data Mining is the exploration and analysis of large quantities of data to discover meaningful patterns and rules. Among the tasks for data mining, we concentrate the classification task. Since classification is the basic element of human way of thinking, it is a well-studied problem in a wide variety of application. In this paper, we propose a classifier system based on genetic algorithm, and the proposed system is evaluated by applying it to IDS problem related to classification task in data mining. We report our experiments in using these method on KDD audit data.

• Proceedings of the Korea Society of Design Studies Conference
• /
• 2001.10a
• /
• pp.27.1-27
• /
• 2001

The purpose of rhis research is proposing rhe sysrem which does information supporr as for a truck driver, and verifying the validity. First, it investigated by visiting the Transporr Company and interview for the present situation and the opinion on computerization from the operation administrator and truck drivers. Consequently, the problem of computerization could be found out to the present system. Next, the present system was considered. As for present machine system, human's "Choosing a function", srarts processing. Then this system is called "Function-Oriented-System". And three problems were extracted from this sysrem. As a solution of those problems, the Purpose-Oriented-System was proposed. In order to attain user's purpose, Agent that situation is perceived and works a function autonomously assumed that this system was inherent. 3D-Sceanrio-Expression was proposed as the description method of rhe task process. It consists of "Machine and Functional-Item axis", "Time axis", and "Situation-Item axis". And, the task execution process of Function-Oriented-System and Purpose-Oriented-System was compared using 3D-Sceanrio-Expression supposing the scene of truck business. As a resulr, rhe following two things could be found out. (1) The concepr of Purpose-Oriented-System that Agent is inherent is effective as siruarion correspondence machine. (2) A solid scenario can express the interaction rhar cannor be seen, in the relarion of rhe conventional Human and Machine.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.795-798
• /
• 1997