• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.26-27
• /
• 2021

본 논문에서는 자막방송 제공을 위해 방송콘텐츠를 이해하는 방법으로 잔차 합성곱 순환신경망 기반 음향 사건 분류 기법을 제안한다. 제안된 기법은 잔차 합성곱 신경망과 순환 신경망을 연결한 구조를 갖는다. 신경망의 입력 특징으로는 멜-필터벵크 특징을 활용하고, 잔차 합성곱 신경망은 하나의 스템 블록과 5개의 잔차 합성곱 신경망으로 구성된다. 잔차 합성곱 신경망은 잔차 학습으로 구성된 합성곱 신경망과 기존의 합성곱 신경망 대비 특징맵의 표현 능력 향상을 위해 합성곱 블록 주의 모듈로 구성한다. 추출된 특징맵은 순환 신경망에 연결되고, 최종적으로 음향 사건 종류와 시간정보를 추출하는 완전연결층으로 연결되는 구조를 활용한다. 제안된 모델 훈련을 위해 라벨링되지 않는 데이터 활용이 가능한 평균 교사 모델을 기반으로 훈련하였다. 제안된 모델의 성능평가를 위해 DCASE 2020 챌린지 Task 4 데이터 셋을 활용하였으며, 성능 평가 결과 46.8%의 이벤트 단위의 F1-score를 얻을 수 있었다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.4
• /
• pp.71-76
• /
• 2024

In this paper, we propose a platform for learning deboning technology of Korean beef through vr-based experiential learning. The Korean beef deboning process is not only a food ingredient that has represented Korea for a long time, but also an object with high traditional cultural value. However, due to the hard and dangerous work envrionment of the deboning field, the number of skilled dobiners is gradually decreasing. This study proposes a platform that can train these deboning technicians in virtual reality and covers applied technologies used. In particular, we discussed how processes such as bending, opening, and cutting are implemented during meat cutting, which is a very important part of deboning work. In the experiment, cutting work was performed based on actual meat modeling, and complete cutting was tested.

• The KIPS Transactions:PartB
• /
• v.10B no.3
• /
• pp.281-286
• /
• 2003

A large number of features are collected for problem solving in real life, but to utilize ail the features collected would be difficult. It is not so easy to collect of correct data about all features. In case it takes advantage of all collected data to learn, complicated learning model is created and good performance result can't get. Also exist interrelationships or hierarchical relations among the features. We can reduce feature's number analyzing relation among the features using heuristic knowledge or statistical method. Heuristic technique refers to learning through repetitive trial and errors and experience. Experts can approach to relevant problem domain through opinion collection process by experience. These properties can be utilized to reduce the number of feature used in learning. Experts generate a new feature (highly abstract) using raw data. This paper describes machine learning model that reduce the number of features used in learning using heuristic function and use abstracted feature by neural network's input value. We have applied this model to the win/lose prediction in pro-baseball games. The result shows the model mixing two techniques not only reduces the complexity of the neural network model but also significantly improves the classification accuracy than when neural network and heuristic model are used separately.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.3
• /
• pp.199-208
• /
• 2019

As the number of available satellites increases and technology advances, image information outputs are becoming increasingly diverse and a large amount of data is accumulating. In this study, we propose a change detection method for high-resolution satellite images that uses transfer learning and a deep learning network to overcome the limit caused by insufficient training data via the use of pre-trained information. The deep learning network used in this study comprises convolutional layers to extract the spatial and spectral information and convolutional long-short term memory layers to analyze the time series information. To use the learned information, the two initial convolutional layers of the change detection network are designed to use learned values from 40,000 patches of the ISPRS (International Society for Photogrammertry and Remote Sensing) dataset as initial values. In addition, 2D (2-Dimensional) and 3D (3-dimensional) kernels were used to find the optimized structure for the high-resolution satellite images. The experimental results for the KOMPSAT-3A (KOrean Multi-Purpose SATllite-3A) satellite images show that this change detection method can effectively extract changed/unchanged pixels but is less sensitive to changes due to shadow and relief displacements. In addition, the change detection accuracy of two sites was improved by using 3D kernels. This is because a 3D kernel can consider not only the spatial information but also the spectral information. This study indicates that we can effectively detect changes in high-resolution satellite images using the constructed image information and deep learning network. In future work, a pre-trained change detection network will be applied to newly obtained images to extend the scope of the application.

• Journal of Korean Society of Transportation
• /
• v.19 no.5
• /
• pp.119-134
• /
• 2001

This paper proposed a dynamic transit vehicle simulation model and a dynamic transit passengers simulation model, which can simultaneously simulate the transit vehicles and passengers traveling on a transit network, and also developed an algorithm of dynamic departure time choice model based on individual passenger. The proposed model assumes that each passenger's behavior is heterogeneous based on stochastic process by relaxing the assumption of homogeneity among passengers and travelers have imperfect information and bounded rationality to more actually represent and to simulate each passenger's behavior. The proposed model integrated a inference and preference reforming procedure into the learning and decision making process in order to describe and to analyze the departure time choices of transit passengers. To analyze and evaluate the model an example transit line heading for work place was used. Numerical results indicated that in the model based on heterogeneous passengers the travelers' preference influenced more seriously on the departure time choice behavior, while in the model based on homogeneous passengers it does not. The results based on homogeneous passengers seemed to be unrealistic in the view of rational behavior. These results imply that the aggregated travel demand models such as the traditional network assignment models based on user equilibrium, assuming perfect information on the network, homogeneity and rationality, might be different from the real dynamic travel demand patterns occurred on actual network.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.8
• /
• pp.1-8
• /
• 2020

Air ducts installed for ventilation inside buildings accumulate contaminants during their service life. Robots are installed to clean the air duct at low cost, but they are still not fully automated and depend on manpower. In this study, an intersection detection algorithm for autonomous driving was applied to an air duct cleaning robot. Autonomous driving of the robot was achieved by calculating the distance and angle between the extracted point and the center point through the intersection detection algorithm from the camera image mounted on the robot. The training data consisted of CAD images of the duct interior as well as the cross-point coordinates and angles between the two boundary lines. The deep learning-based CNN model was applied as a detection algorithm. For training, the cross-point coordinates were obtained from CAD images. The accuracy was determined based on the differences in the actual and predicted areas and distances. A cleaning robot prototype was designed, consisting of a frame, a Raspberry Pi computer, a control unit and a drive unit. The algorithm was validated by video imagery of the robot in operation. The algorithm can be applied to vehicles operating in similar environments.

• Journal of The Korean Association For Science Education
• /
• v.19 no.3
• /
• pp.355-366
• /
• 1999

In this study, the characteristics of science inquiry problem solving were analyzed in the interactions between science process skills and science concepts by each related its category. Nine types of problem solving, which were based on two elements and the thinking aloud were found largely by protocol analysis, but six types when integrated similar thinking processes. There were quite differences in the representative types between students who succeeded and failed when science inquiry items were solved in the abilities of recognizing problems and generating hypotheses or those of drawing conclusions and evaluating. But there were not complete differences in those types between students who succeeded and failed when they were solved in the abilities of designing and performing experiments or those of interpreting and analyzing data. The data were divided into independent variables: $D_1,\;D_2,\;D_3,\;D_4,\;D$ and $C_1,\;C_2,\;C_3,\;C_4,\;C$ and dependant variables; $E_1,\;E_2,\;E_3,\;E_4,\;E$. The former consisted of the content-free science process skill achievement levels by each category of science inquiry skill and the science concept achievement levels, the latter the science inquiry problem achievement levels by each category of science inquiry skill. The regression equations were acquired within the 0.05 significant level by regression analysis: $E_1=0.03+0.16D_1+0.29C_1,\;E_2=-0.203+0.21D_2+0.45C_2,\;E_3=-0.32+0.13D_3+0.47C_3,\;E_4=0.61+0.09D_4+0.29C_4,\;E=-1.41+0.13D+0.47C$(E : the achievement of science problems, D : the achievement of science process skills, C : the achievement of science concepts).

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.4
• /
• pp.193-205
• /
• 2003

There has been so many research activities about robot soccer system in the many research fields, for example, intelligent control, communication, computer technology, sensor technology, image processing, mechatronics. Especially researchers research strategy for attacking in the field of strategy, and develop intelligent strategy. Then, soccer robots cannot defense completely and efficiently by using simple defense strategy. Therefore, intention extraction of attacker is needed for efficient defense. In this thesis, intention extractor of soccer robots is designed and developed based on FMMNN(Fuzzy Min-Max Neural networks ). First, intention for soccer robot system is defined, and intention extraction for soccer robot system is explained.. Next, FMMNN based intention extractor for soccer robot system is determined. FMMNN is one of the pattern classification method and have several advantages: on-line adaptation, short training time, soft decision. Therefore, FMMNN is suitable for soccer robot system having dynamic environment. Observer extracts attack intention of opponents by using this intention exactor, and this intention extractor is also used for analyzing strategy of opponent team. The capability of developed intention extractor is verified by simulation of 3 vs. 3 robot succor simulator. It was confirmed that the rates of intention extraction each experiment increase.

• Korean Journal of Culture and Social Issue
• /
• v.18 no.3
• /
• pp.329-347
• /
• 2012

Criminal media such as dramas and movies are growing in popularity. However, the effects of criminal media as well as its psychological mechanism are not clearly examined. Based on social learning theory (Bandura, 1978), past studies showed that arrest and punishment to the criminal in media have a suppressing effect. The present research examined the ironic possibility that media coverage of punishment could increase the audience's criminal intention and proposed the mediating role of counterfactual thinking in the effect. We hypothesized that when punishment was depicted as accidental rather than unavoidable in media coverage, perceived high mutability and counterfactuals focusing on the accidental factors could clarify the ways to commit the crime without being caught and subsequently increase future criminal intention. In this study, 95 college students read a story of plagiarizing either no, accidental, or inevitable punishment, and later asked to report their intention to plagiarize. An ANCOVA with participants' own history of plagiarism as a covariate found that the intention of plagiarism in future was significantly different. The results showed that the intention of plagiarism in the accidental punishment condition was higher than that in the inevitable punishment condition. Further, the intention of plagiarism in the accidental punishment condition was the same level with non-punishment condition. The findings suggest that whether criminals are caught or not is not enough to reduce criminal intentions of audience, but how criminals are caught matters.

• Journal of Chest Surgery
• /
• v.34 no.1
• /
• pp.45-50
• /
• 2001

배경: 관상동맥우회술은 허혈성 심질환 환자에서 증상을 완화하고 급사를 방지할 수 있는 효과적인 치료방법으로 확립되었다. 그러나 80년대에 들어와 지금까지 사용되었던 대복재정맥편에 비해 동맥이식편의 장기개통율이 월등함이 알려지면서 좌내유동맥과 함께 사용할 수 있는 동맥이식편에 대한 관심이 증가하였다. 본원에서는 1998년부터 다동맥이식편을 이용하여 관상동맥 우회술을 시행하고 있으며, 조기성적에 대해 대복재정맥을 사용한 경우와 비교하고자 하였다. 대상 및 방법: 1998년 6월부터 1999년 5월까지 본원에서 관상동맥우회술을 시행받았던 355명의 환자중 심정지액을 이용하여 시행했던 153명을 대상으로 하였다. 76명의 단일 동맥편을 사용한 환자를 I군, 두 개 이상의 다동맥편을 사용한 77명의 환자를 II군으로 분류하여 수술전후 임상기록, 심초음파 및 관상동맥 조영술 소견등을 후향적으로 분석하였다. 결과: 술전 양군간에는 II군의 환자가 I군의 환자에 비해 더 젊고 흡연자가 많다는 것 이외에는 통계학적으로 차이는 없었다. 술후 조기사망은 각 군에서 1례씩 있었고 환자당 문합갯수에 통계학적으로 차이가 있는 것 이외에는 수술과정 및 술후 결과에서 차이는 없었다. 결론: 다동맥편을 이용한 관상동맥우회술을 시행한 결과 본원에서 학습기(learning period)임에도 불구하고 조기성적에 있어 대복재정맥을 이용한 경우와 차이가 없었다. 물론 중기 및 장기성적에 대한 지속적인 추적관찰이 필요하겠으나 이러한 조기성적은 동맥이식편을 이용한 관상동맥우회술이 환자의 장기생존에 도움을 줄 수 있으리라 사료된다. 또한 이러한 결과를 토대로 완전 동맥이식편 관상동맥우회술로의 전환이 이루어질 수 있으리라 생각된다.