• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.524-528
• /
• 2020

챗봇은 발화에 대해 컴퓨터가 자동으로 응답하는 시스템이다. 현재 챗봇은 전체 주제에 대한 잡담(chit-chat)보다는 특정 주제에 관한 대화를 목적으로 많이 개발되고 있다. 하지만 개개인이 필요로 하는 챗봇 용도에 적합한 학습 데이터는 부족하다. 이러한 상황에서 챗봇 학습을 위해 필요한 주제의 말뭉치를 대량으로 구축하는 것은 시간과 비용이 많이 소모되어 현실적으로 어렵다. 따라서 학습에 필요한 소량의 말뭉치만 사용하더라도 주제에 적합한 응답을 할 수 있는 챗봇이 필요하다. 이에 본 논문은 챗봇의 목적과 관련 없는 대량의 말뭉치와 소량의 주제 기반 말뭉치를 이용하여 높은 성능을 끌어낼 수 있는 주제 임베딩 방법을 제안한다.

• Journal of Auto-vehicle Safety Association
• /
• v.15 no.3
• /
• pp.17-26
• /
• 2023

This paper presents extended state feedback control based on impulse response for lane change of autonomous driving vehicle. The triple characteristic root of path tracking system and longitudinal velocity determine feedback gains. We suggest a resemblance of impulse response curve of the system and lane change trajectory of the vehicle. The root affects the duration of lane change and lateral acceleration. The effect of limited lateral acceleration and saturation of steering angle will be analyzed and discussed. Finally, simulation results will show the trajectory of lane change based on impulse response under limitation of lateral acceleration.

• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.4
• /
• pp.52-57
• /
• 2003

A PID parameter tuning method was presented by the fuzzy singleton inference, based on step response-shaping of plant and experience knowledge of expert. The parameter-tuning has tow levels. The higher level determines modified coefficients for the controller based on operator's tuning know-how for characteristics of plant which can not be modeled. The lower level determines specified coefficients based on characteristics of response by Ziegler-Nickel's bounded sensitivity method. The last level parameters tuning of a PID controller is adjusted which the modified and specified coefficients makes adjustment rule, and is adjusted the proper value to each parameters by fuzzy singleton inference. Moreover, proposed the tuning method can reflex exporter knowledge and operator's tuning know-how and fuzzy singleton inference is rapidly operated.

• Annual Conference on Human and Language Technology
• /
• 2014.10a
• /
• pp.201-205
• /
• 2014

국립국어원의 온라인 가나다 서비스는 한국어에 대한 다양한 질문과 정확한 답변을 제공한다. 만일 새롭게 등록되는 질문에 대해 유사한 질문을 자동으로 찾을 수 있다면, 질문자는 빠른 시간에 답변을 얻을 수 있고 서비스 관리자는 수동 답변 작성의 부담을 덜 수 있다. 본 논문에서는 국립국어원 질의응답게시판의 특성을 분석하여 질문의 주제를 6가지로 분류하고, 주제 분류 정보와 벡터 유사도, 수열 유사도를 결합하여 유사한 질문을 검색하는 시스템을 제안한다. 평가에서는 본 논문에서 제시한 주제 분류 정보를 활용한 결과 1위 정답 검색 정확률이 향상되는 결과를 얻었다. 최종 실험에서는 MRR이 0.62, 정답이 1위, 5위내에 검색될 확률은 각각 54.2%, 78.2%를 보였다.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.18 no.6
• /
• pp.84-90
• /
• 2004

Many control techniques have been proposed in order to improve the control performance in the control system. In the feedback control system the output of controller is generally used as the input of a plant But the undesired noise is included in the output of a controller. Therefore, there is a need to use a precompensator for rejecting the undesired noise and improving the response characteristic of a system. In this paper, the design method of a precompensator is proposed for the model following control in the I-PD control system. The proposed precompensator is implemented with a neural network. The games of a precompensator are adjusted automatically to obtain a desired response of a system when the response characteristic of a system is changed under a condition.

• Journal of The Korean Society For Urban Railway
• /
• v.6 no.4
• /
• pp.243-248
• /
• 2018

The abnormally high temperature of the train part is related to train accidents and monitoring is important for safe operation of trains. In case of KTX an abnormality detecting device that detects the abnormality of the axle and scans the urban railway is installed on the railroad and when there is an abnormal heat generation, a system for automatically informing the control center is installed. The IR sensors module used in this system are depend on quick response. we have conducted a study on the fast response test method through the production of experimental equipments.

• Survey Research
• /
• v.7 no.2
• /
• pp.71-95
• /
• 2006

This article presents strengths of Computer-Assisted Personal Interviewing(CAPI) in social surveys with complicated questionnaires, from examples of a pilot and the first year surveys of the Korean Longitudinal Study of Ageing(KLoSA). This study focuses on how to improve the quality of data by using CAPI and finds five strengths among others. First of all, CAPI can contribute to reducing response errors by structuring the logic and path of questionnaires, setting a response range, and maintaining response consistency. Second, CAPI enhances convenience of interviewing by allowing customized questions and automatic calculation and scoring. It also allows the 'help' function. Third, its random arrangement of questions prevents response order effect and/or questions order effect. Fourth, CAPI can raise the response rate by reducing item non-responses. Fifth, it makes it easy monitoring interviewing, thus helps supervising interviewers and modifying questionnaires when necessary. These merits of CAPI contribute to reducing possible errors in the process of interviewing, therefore improve the data quality.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.43 no.8
• /
• pp.706-711
• /
• 2015

The fighter aircraft uses several different loading configurations for air-to-surface and air-to-air combat missions. To maintain wings-level flight with an asymmetric weapon configuration, a pilot controls a roll trim system. However, it is difficult to apply an accurate roll trim input for wings-level flight in the actual flight under disturbance. The inaccurate roll trim input degrades the performance of the roll autopilot system. In this paper, to solve this problem, an integrator was additionally designed in the command part of the roll autopilot system. The initial transient response was improved by scheduling the limiter to restrict the roll attitude error. As a result of the evaluation of the simulation for the designed flight control law, the roll attitude following performance was found to be improved in the autopilot system operation under the inaccurate roll trim condition.

• Database Research
• /
• v.34 no.3
• /
• pp.3-13
• /
• 2018

Text classification is one of the text mining technologies that classifies a given textual document into its appropriate categories and is used in various fields such as spam email detection, news classification, question answering, emotional analysis, and chat bot. In general, the text classification system utilizes machine learning algorithms, and among a number of algorithms, naïve Bayes and support vector machine, which are suitable for text data, are known to have reasonable performance. Recently, with the development of deep learning technology, several researches on applying deep neural networks such as recurrent neural networks (RNN) and convolutional neural networks (CNN) have been introduced to improve the performance of text classification system. However, the current text classification techniques have not yet reached the perfect level of text classification. This paper focuses on the fact that the text data is expressed as a vector only with the word dimensions, which impairs the semantic information inherent in the text, and proposes a neural network architecture based upon the semantic tensor space model.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.3
• /
• pp.640-646
• /
• 2017

A GEN TEST of the auxiliary power unit of a T-50 series aircraft is performed as part of the operational test of its emergency power system on the ground before flight. At this time, the auxiliary power unit should be automatically turned off via the response signal of the ECU when power is not normally supplied to the emergency power system. If the correct operation of the emergency power system cannot be confirmed on the ground, it is not possible to proceed with the flight. This kind of defect is a major factor causing the operation rate of the aircraft to be decreased. The defect code identified by the ECU was confirmed as a defect in the inverter. However, the same defect was found after replacing the inverter. This report presents an improved method of identifying the cause of the defect by analyzing the response characteristics of the ECU and emergency power system and allows the ECU to be recognized as the cause of the defect if the inverter does not generate a voltage within a certain time. Also, the application of the improved method confirmed that it can satisfy the output request time of the emergency power system and effectively prevent the auto-shutdown of the auxiliary power unit.