• The Journal of the Acoustical Society of Korea
• /
• v.28 no.5
• /
• pp.441-446
• /
• 2009

This paper proposes an automatic indexing algorithm of golf video using audio information. In the proposed algorithm, the input audio stream is demultiplexed into the stream of video and audio. By means of Adaboost-cascade classifier, the continuous audio stream is classified into announcer's speech segment recorded in studio, music segment accompanied with players' names on TV screen, reaction segment of audience according to the play, reporter's speech segment with field background, filed noise segment like wind or waves. And golf swing sound including drive shot, iron shot, and putting shot is detected by the method of impulse onset detection and modulation spectrum verification. The detected swing and applause are used effectively to index action or highlight unit. Compared with video based semantic analysis, main advantage of the proposed system is its small computation requirement so that it facilitates to apply the technology to embedded consumer electronic devices for fast browsing.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.105-111
• /
• 2021

한국어 사실 확인 과제는 학습 자료의 부재로 인해 연구에 어려움을 겪고 있다. 본 논문은 수작업으로 구성된 학습 자료를 토대로 자연어 생성 모델을 이용하여 한국어 사실 확인 자료를 구축하는 방법을 제안한다. 본 연구는 임의의 근거를 기반으로 하는 주장을 생성하는 방법 (E2C)과 임의의 주장을 기반으로 근거를 생성하는 방법 (C2E)을 모두 실험해보았다. 이때 기존 학습 자료에 위 두 학습 자료를 각각 추가하여 학습한 사실 확인 분류기가 기존의 학습 자료나 영문 사실 확인 자료 FEVER를 국문으로 기계 번역한 학습 자료를 토대로 구성된 분류기보다 평가 자료에 대해 높은 성능을 기록하였다. 또한, C2E 방법의 경우 수작업으로 구성된 자료 없이 기존의 자연어 추론 과제 자료와 HyperCLOVA Few Shot 예제만으로도 높은 성능을 기록하여, 비지도 학습 방식으로 사실 확인 자료를 구축할 수 있는 가능성 역시 확인하였다.

• Progress in Medical Physics
• /
• v.18 no.2
• /
• pp.65-72
• /
• 2007

An echo planar imaging (EPI)-based spin-echo sequence Is often used to obtain diffusion tensor imaging (DTI) data on most of the clinical MRI systems, However, this sequence is confounded with the susceptibility artifacts, especially on the temporal lobe in the human brain. Therefore, the objective of this study was to design a pulse sequence that relatively immunizes the susceptibility artifacts, but can map diffusion tensor components in a single-shot mode. A multi-slice multi-echo pulsed-gradient spin-echo (MePGSE) sequence with eight echoes wasdeveloped with selective refocusing pulses for all slices to map the full tensor. The first seven echoes in the train were diffusion-weighted allowing for the observation of diffusion in several different directions in a single experiment and the last echo was for crusher of the residual magnetization. All components of diffusion tensor were measured by a single shot experiment. The sequence was applied in diffusive phantoms. The preliminary experimental verification of the sequence was illustrated by measuring the apparent diffusion coefficient (ADC) for tap water and by measuring diffusion tensor components for watermelon. The ADC values in the series of the water phantom were reliable. The MePGSE sequence, therefore, may be useful in human brain studies.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.22 no.6
• /
• pp.806-814
• /
• 2019

One of the future weapon systems is the individual smart weapon which has a structure mounted on the forearm of soldiers. The structure may cause injuries or affect the accuracy of fire due to its impact on joints when shooting. This paper proposes human-impact interaction modeling and a verification methodology in order to estimate the impact of fire applied to the forearm. For this purpose, a human musculoskeletal model was constructed and the joints' behavior in various shooting positions was simulated. In order to verify the simulation results, an impact testing device substituting the smart weapon was made and the experiment was performed on a real human body. This paper compares the simulation results performed under various impact conditions and the experimental values in terms of accuracy and introduces methods to complement them. The results of the study are expected to be a basis for a reliable human-impact interaction modeling, and smart individual weapon development.

• Journal of the Korean Society of Radiology
• /
• v.11 no.1
• /
• pp.9-17
• /
• 2017

A high degree of precision and accuracy in Gamma Knife Radiosurgery(GKRS) is a fundamental requirement for therapeutical success. Elaborate radiation delivery and dose gradients with the steep fall-off of radiation are clinically applied thus necessitating a dedicated Quality Assurance(QA) program in order to guarantee dosimetric and geometric accuracy and reduce all the risk factors that can occur in GKRS. In this study, as a part of QA we verified the accuracy of single-shot dose profiles used in the algorithm of Gamma Knife Perfexion(PFX) treatment planning system employing Variable Ellipsoid Modeling Technique(VEMT). We evaluated the dose distributions of single-shots in a spherical ABC phantom with diameter 160 mm on Gamma Knife PFX. The single-shots were directed to the center of ABC phantom. Collimating configurations of 4, 8, and 16 mm sizes along x, y, and z axes were studied. Gamma Knife PFX treatment planning system being used in GKRS is called Leksell GammaPlan(LGP) ver 10.1.1. From the verification like this, the accuracy of GKRS will be doubled. Then the clinical application must be finally performed based on precision and accuracy of GKRS. Specifically the width at the 50% isodose level, that is, Full-Width-of-Half-Maximum(FWHM) was verified under such conditions that a patient's head is simulated as a sphere with diameter 160mm. All the data about dose profiles along x, y, and z axes predicted through VEMT were excellently consistent with dose profiles from LGP within specifications(${\leq}1mm$ at 50% isodose level) except for a little difference of FWHM and PENUMBRA(isodose level: 20%~80%) along z axis for 4 mm and 8mm collimating configurations. The maximum discrepancy of FWHM was less than 2.3% at all collimating configurations. The maximum discrepancy of PENUMBRA was given for the 8 mm collimator along z axis. The difference of FWHM and PENUMBRA in the dose distributions obtained with VEMT and LGP is too small to give the clinical significance in GKRS. The results of this study are considered as a reference for medical physicists involved in GKRS in the whole world. Therefore we can work to confirm the validity of dose distributions for all collimating configurations determined through the regular preventative maintenance program using the independent verification method VEMT for the results of LGP and clinically assure the perfect treatment for patients of GKRS. Thus the use of VEMT is expected that it will be a part of QA that can verify and operate the system safely.