• Journal of Auto-vehicle Safety Association
• /
• v.9 no.3
• /
• pp.24-30
• /
• 2017

This paper presents the development of laser scanner based static obstacle detection algorithm for vehicle localization on lane lost section. On urban autonomous driving, vehicle localization is based on lane information, GPS and digital map is required to ensure. However, in actual urban roads, the lane data may not come in due to traffic jams, intersections, weather conditions, faint lanes and so on. For lane lost section, lane based localization is limited or impossible. The proposed algorithm is designed to determine the lane existence by using reliability of front vision data and can be utilized on lane lost section. For the localization, the laser scanner is used to distinguish the static object through estimation and fusion process based on the speed information on radar data. Then, the laser scanner data are clustered to determine if the object is a static obstacle such as a fence, pole, curb and traffic light. The road boundary is extracted and localization is performed to determine the location of the ego vehicle by comparing with digital map by detection algorithm. It is shown that the localization using the proposed algorithm can contribute effectively to safe autonomous driving.

• Journal of the Society of Disaster Information
• /
• v.4 no.2
• /
• pp.138-154
• /
• 2008

The conventional non-dig underground structure building method which made an appearance to reduce the social and environmental costs and maximize the efficiency of the social overhead capital facilities could not help being uneconomical because of many problems such as unnecessary excessive excavation, water leakage, obstacle interference, difficulty of curvilinear application and connection complexity between propelled and injected bodies due to indiscriminate application of small and large circular steel pipes without consideration of the site conditions. The T.S.T.M, in which a protruded square tube is applied as a propulsion and injection body in a design that considered site conditions such as ground condition, depth of soil and live load, was able to be economical as it solved the problems of water resistance, minimization of obstacle interference and curvilinearity, and we can see that it can be applied to all grounds by utilizing or complementing the target ground in terms of engineering. Also in configuring the transverse section, it is possible to not only secure excellent structural safety but also implement all of the above engineering characteristics not only in the square cross section but also in the arch cross section, so it was possible to build structures on any section or ground, and we could confirm the LCC reduction effect and the VE effect.

• Journal of the Korean Society for Library and Information Science
• /
• v.12
• /
• pp.201-224
• /
• 1985

The traditional oriental materials are very important to study on Oriental or Korean studies. Every reseacher that study on this field is familier to Four Category Classification Scheme (四部分類法) as it is based on the traditional knowledge of Orient. Then, when all materials of libraries will he computerized, it will be the first condition that will has to understand about the classification of division and section of oriental knowledge, because not only ancient literature but also many dissertation of this subject will be classified. Therefore, Four Category Classification Scheme has been valuable until now. This paper is intended to help librarians to classify the traditional oriental materials or the dissertation concerned with that, to serve researched user that literatures which have been filed among various traditional bibliographies. The outline of this study are as follows: :1 Examining closely origins, developing process and characteristics of classification of Confacian Classics Part (經部) of Four Category Classification Scheme. (2) Explaning the content of division and section of Confucian Classics Part (經部). (3) Coordinating relation of division and section of Confucian Classics Part as well as those of other parts of the classification scheme. (4) Clearing up the limitation of classification related to other division. (5) Attempting to give basic knowledge on practical classification as concrete examples beloging to each division and section of classification.

• ETRI Journal
• /
• v.45 no.1
• /
• pp.18-27
• /
• 2023

We present an English-Korean speech translation corpus, named EnKoST-C. End-to-end model training for speech translation tasks often suffers from a lack of parallel data, such as speech data in the source language and equivalent text data in the target language. Most available public speech translation corpora were developed for European languages, and there is currently no public corpus for English-Korean end-to-end speech translation. Thus, we created an EnKoST-C centered on TED Talks. In this process, we enhance the sentence alignment approach using the subtitle time information and bilingual sentence embedding information. As a result, we built a 559-h English-Korean speech translation corpus. The proposed sentence alignment approach showed excellent performance of 0.96 f-measure score. We also show the baseline performance of an English-Korean speech translation model trained with EnKoST-C. The EnKoST-C is freely available on a Korean government open data hub site.

• Journal of Biomedical Engineering Research
• /
• v.37 no.1
• /
• pp.1-6
• /
• 2016

The biomedical information (heart rate, HRV, $SpO_2$ etc) from the Photoplethysmography (PPG) signal section can be estimated without the motion artifacts if the PPG signal section in the motion artifacts is detected accurately. But the PPG signal is easily exposed to the motion artifacts by the decrease of the medical instrument size and applying as portable or wearable. Besides, it is difficult to completely eliminate the motion artifacts from the PPG signal without distortion and ensure reliability as well. In this paper, the method was suggested to determine the motion artifacts or not on the PPG signal of the section divided into intervals of constant length. By comparing the spectrum of each section, it can be determined whether the motion artifacts are or not after obtaining the spectrum of each section by the Goertzel algorithm. Moreover, an amount of computation while maintaining a high detection rate can be reduced by using the Goertzel algorithm.

• Journal of Institute of Control, Robotics and Systems
• /
• v.6 no.12
• /
• pp.1106-1112
• /
• 2000

In this paper, we present a vision system which measures the cross-section of a hot wire-rod in the steel plant. We developed a mobile vision system capable of accurate measurement, which is strong to vibration and jolt when moving. Our system uses green laser light sources and CCD cameras as a sensor, where laser sheet beams form a cross-section contour on the surface of the hot wire-rod and the reflected light from the wire-rode is imaged on the CCD cameras. We use four lasers and four cameras to obtain the image with the complete cross-section contour without an occlusion region. We also perform camera calibrations to obtain each cameras physical parameters by using a single calibration pattern sheet. In our measuring algorithm, distorted four-camera images are corrected by using the camera calibration information and added to generate an image with the complete cross-section contour of the wire-rod. Then, from this image, the cross-section contour of the wire-rod is extracted by preprocessing and segmentation, and its height, width and area are measured.

• Journal of the Korean Home Economics Association
• /
• v.44 no.5 s.219
• /
• pp.109-118
• /
• 2006

The purpose of the study is to analyze web-site content for activating internet apparel shopping malls. With a view to improving the transaction experience and efficiency for both shopping-mall managers and customers. According to RANKEY(rankey.com) and 100 HOT RANHNC(100hot.co.kr), 5 big internet apparel shopping malls were chosen, divided into 3 web-site criteria of Users' Interface Section, Informational Section, and Customer Satisfaction Section, and analyzed. The results of our analysis of the web-site contents are as follows: 1) Concerning Users' Interface Section, the structure of the first screen is complicated and confusing. 2) Concerning Informational Section, the specific image of shopping man is ambiguous to understand and differentiated product information is not properly given. 3) Concerning Customer Satisfaction Section, the customers are not encouraged to show any interest in the shopping mall. These three problems are easily observed in most of the internet apparel shopping malls. To develop the internet apparel shopping mall, the following methods to activate them need to be implemented.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.52 no.10
• /
• pp.602-609
• /
• 2003

This paper describes the fault location calculation using neuro-fuzzy systems in combined transmission lines with underground power cables. Neuro-fuzzy systems used in this paper are composed of two parts for fault section and fault location. First, neuro-fuzzy system discriminates the fault section between overhead and underground with normalized detail coefficient obtained by wavelet transform. Normalized detail coefficients of voltage and current in half cycle information are used for the inputs of neuro-fuzzy system. As the result of neuro-fuzzy system for fault section, impedance of selected fault section is calculated and it is used as the inputs of the neuro-fuzzy systems for fault location. Neuro-fuzzy systems for fault location also consist of two parts. One calculates the fault location of overhead, and the other does for underground. Fault section is completely classified and neuro-fuzzy system for fault location calculates the distance from the relaying point. Neuro-fuzzy systems proposed in this paper shows the excellent results of fault section and fault location.

• ETRI Journal
• /
• v.45 no.1
• /
• pp.75-92
• /
• 2023

Level 3 autonomous vehicles require conditional autonomous driving in which autonomous and manual driving are alternately performed; whether the driver can resume manual driving within a limited time should be examined. This study investigates whether the demographics and subjective driving tendencies of drivers affect the take-over performance. We measured and analyzed the reengagement and stabilization time after a take-over request from the autonomous driving system to manual driving using a vehicle simulator that supports the driver's take-over mechanism. We discovered that the driver's reengagement and stabilization time correlated with the speeding and wild driving tendency as well as driving workload questionnaires. To verify the efficiency of subjective questionnaire information, we tested whether the driver with slow or fast reengagement and stabilization time can be detected based on machine learning techniques and obtained results. We expect to apply these results to training programs for autonomous vehicles' users and personalized human-vehicle interfaces for future autonomous vehicles.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 1995.02a
• /
• pp.255-260
• /
• 1995