• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06a
• /
• pp.243-246
• /
• 2011

학습자의 감성 상태가 충분히 반영되는 오프라인 수업과 달리 지금까지 대부분의 e-러닝은 학습자의 감성 정보를 수업에 효과적으로 반영하지 못했다. 이러한 한계점은 e-러닝의 학습 효과성을 저해하는 문제 중 하나로 지적되었다. 이 문제를 해결하기 위해 학습자의 뇌파를 통해 감성을 인식하고 감성 상태에 따라 적절한 학습 콘텐츠 타입을 추천하여 학습 효과를 증대 시킬 수 있는 방법론이 주목을 받고 있다. 본 논문에서는 기 수집된 학습자들의 감성(뇌파) 데이터를 분석하여 콘텐츠 타입 선호도를 파악한 후 프로파일 데이터를 활용하여 상관계수 기반 NN-Recommendation 학습 콘텐츠 타입 추천 시스템을 제안 하고자 한다. 이 시스템은 일반적인 추천시스템에서 발생하는 Cold-start 문제를 해결할 수 있으며 특히 본 연구에서는 보다나은 추천 정확도를 위해 프로파일 각 속성에 자동적으로 가중치를 부여하는 기법을 제시하여 향상된 성능을 보이게 됨을 실험을 통해 확인 하였다.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.24 no.4
• /
• pp.512-518
• /
• 2000

A wall fuel-film flow model is developed to predict the effect of a wall-fuel-film on air-fuel ratio in an SI engine in transient conditions. Fuel redistribution in the intake port resulting from charge backflow and a simple liquid fuel behavior in the cylinder are included in this model. Liquid fuel film flow is calculated of every crank angle degree using the instantaneous air flow rate. The model is validated by comparing the calculated results and corresponding engine experiment results of a commercial 4 cylinder DOHC engine. The predicted results match well with the experimental results. To maintain the constant air-fuel ratio during transient operation. the fuel injection rate control can be obtained from the simulation result.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.6
• /
• pp.2310-2332
• /
• 2020

In recent years, deep learning techniques have achieved tremendous successes in natural language processing, speech recognition and image processing. Collaborative filtering(CF) recommendation is one of widely used methods and has significant effects in implementing the new recommendation function, but it also has limitations in dealing with the problem of poor scalability, cold start and data sparsity, etc. Combining the traditional recommendation algorithm with the deep learning model has brought great opportunity for the construction of a new recommender system. In this paper, we propose a novel collaborative recommendation model based on auxiliary stacked denoising autoencoder(ASDAE), the model learns effective the preferences of users from auxiliary information. Firstly, we integrate auxiliary information with rating information. Then, we design a stacked denoising autoencoder based collaborative recommendation model to learn the preferences of users from auxiliary information and rating information. Finally, we conduct comprehensive experiments on three real datasets to compare our proposed model with state-of-the-art methods. Experimental results demonstrate that our proposed model is superior to other recommendation methods.

• Journal of ILASS-Korea
• /
• v.25 no.2
• /
• pp.74-80
• /
• 2020

The jet in crossflow is a spray method used in the various air-breathing engine. In order to understand the spray characteristics in various environments, many prior studies have been conducted. However, there is a lack of understanding of the low-temperature liquid spray characteristics below 273 K. With this in mind, we tried to enhance the knowledge of the low-temperature liquid spray characteristics by identifying the penetration height of low-temperature ethanol. The experiment was conducted under phase pressure, and 273 K of air and 293, 263, and 233 K of ethanol was used. Shadowgraphy was employed to measure the liquid penetration, and Otsu's method was used to analyze the penetration height. The heights tend to decrease as the temperature of the liquid jet decreases. A correlation for the penetration height in the experimental conditions was derived and presented.

• Journal of Ocean Engineering and Technology
• /
• v.22 no.6
• /
• pp.13-19
• /
• 2008

Abnormally large swells that appeared on the coast of the East Sea in October in 2005 and 2006 were simulated using SWAN model to examine the accuracy of the model for future forecasting Seawind data calculated based on the weather chart ant bottom topography were used for input data, and the model was operated more than 20 days before the observed swells to avoid the problems from the cold start of the model. The comparisons with observed wind and wave data were unsatisfactory and neededmore improvement in terms of swell component in the wave model as well as the quality of seawind data. The satellite wind and wave data can be good candidates for future comparison of the wave model results in the East Sea.

• Asian review of World Histories
• /
• v.2 no.1
• /
• pp.1-16
• /
• 2014

This paper examines the historical relationship between the Little Ice Age and the Anthropocene, which has not yet been studied. The Little Ice Age is the coldest multi-century period in the Holocene. The reforestation of huge farmlands, abandoned due to pandemics in the Americas, aggravated the cooling weather of the Little Ice Age. It was in the long and severe cold of the Little Ice Age that the transition from renewable energy to non-renewable energy was completed in Britain in the latter part of the eighteenth century, and when the pattern of linear growth in greenhouse gas concentrations was forged in the ecosystems of the Earth. The Little Ice Age forced humans to depend on fossil fuels while the advent of warmer and more stable climate in the Holocene enabled them to start agriculture in an energy revolution 11,000 years ago, thus making the coming of the Anthropocene possible.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.363-366
• /
• 2016

추천 기법은 개인의 관심사와 상황을 고려한 개인화된 아이템을 제공함으로써 아이템의 소비과정에서 발생하는 부하를 줄여주고 정보 소비의 효율성을 증대시키는데 중요한 역할을 한다. 본 연구에서는 전통적인 추천 기법인 Content-Based(CB)기법과 최근 온라인 소셜 네트워크의 경향을 반영한 Social Network-based(SN)기법을 접목하여 새로운 복합방식의 정보 추천 기법을 제시한다. CB 기법의 대표적인 한계점인 cold start problem과 SN 기법의 추천 아이템의 전문성 문제를 상호 보완하며, 특히 최근 소셜 네트워크의 특징인 비신뢰 (non-trust) 기반의 영향력 있는 정보 확산자가 존재하는 환경에서 기법을 적용할 수 있도록 하였다. 또한 대부분 사람 추천 중심인 기존의 SN 기법들과는 달리 사람에게 제공할 정보의 추천에 초점을 두며, 정보 선정과정에서 개인의 온라인과 현실(real world)에서의 사회 활동 정보를 모두 활용하여 더육 더 개인화된 가치 정보를 제공하고자 한다.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.9 no.4
• /
• pp.112-120
• /
• 2001

Poor fuel vaporization in gasoline engines causes the problem of HC emission during the cold start and warm-up period. This paper presents a strategy to improve fuel atomization during the warm-up phase. In this experiment, the heated fuel-rail system is constructed to investigate the effects of fuel heating on the average size of fuel droplets. The fuel atomization effects are examined by measuring Sauter Mean Diameter (SMD) of the fuel droplets from the three different types (two-hole, pintle, and six-hole) of injectors based upon a returnless heated fuel-rail system. The results show that the six-hole type injector is the most sensitive to fuel heating in terms of SMD among three different types of injectors.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.4 no.4
• /
• pp.140-146
• /
• 1996

A large portion(above 70%) fo the hydrocorbon and NOx emissions for a typical vehicle occur mainly before the conventional underbody catalyst reaches activation temperature. To meet the stringent regulation as EC stage 2, the emissions produced during this period must be reduced. One of alternative techniques is to place CCC(Close-Coupled Catalyst) near the exhaust manifold. In this study, the characteristics of CCC are observed through EEC mode.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.9 no.6
• /
• pp.112-118
• /
• 2001

In this study the leakage current measurement method based on a porous ceramic is applied to check the conductive substance caused by the ionized particles. By using engine and chassis dynamometer and an experiment vehicle, in which the hydrocarbon sensor (HC sensor) was exposed to the exhaust gas to create the electrical signal, the HC sensor in the exhaust line checked the conductive ions in emission gas. Generally the output electrical signal of HC sensor is followed with amount of hydrocarbon in the experiments in cold start and operation. By combining the electrical signal, a measure of conductivity of exhaust gas with hydrocarbon can be provided by OBD (On Board Diagnosis) II and EMS (Engine Management System).