• Journal of Korea Multimedia Society
• /
• v.25 no.11
• /
• pp.1643-1652
• /
• 2022

Most of the existing machine reading research has used Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN) algorithms as networks. Among them, RNN was slow in training, and Question Answering Network (QANet) was announced to improve training speed. QANet is a model composed of CNN and self-attention. CNN extracts semantic and syntactic information well from the local corpus, but there is a limit to extracting the corresponding information from the global corpus. Graph Convolutional Networks (GCN) extracts semantic and syntactic information relatively well from the global corpus. In this paper, to take advantage of this strength of GCN, we propose I-QANet, which changed the CNN of QANet to GCN. The proposed model performed 1.2 times faster than the baseline in the Stanford Question Answering Dataset (SQuAD) dataset and showed 0.2% higher performance in Exact Match (EM) and 0.7% higher in F1. Furthermore, in the Korean Question Answering Dataset (KorQuAD) dataset consisting only of Korean, the learning time was 1.1 times faster than the baseline, and the EM and F1 performance were also 0.9% and 0.7% higher, respectively.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.501-503
• /
• 2022

초해상이란 해상도가 낮은 영상을 해상도가 높은 영상으로 합성하는 기술이다. 딥러닝은 영상의 해상도를 높이는 초해상 기술에도 응용되며 실현은 2아4년에 발표된 SRCNN(Super Resolution Convolutional Neural Network) 모델로부터 시작됐다. 이후 오토인코더 (Autoencoders) 구조로는 SRCAE(Super Resolution Convolutional Autoencoders), 합성된 영상을 실제 영상과 통계적으로 구분되지 않도록 강제하는 GAN (Generative Adversarial Networks) 구조로는 SRGAN(Super Resolution Generative Adversarial Networks) 모델이 발표됐다. 모두 SRCNN의 성능을 웃도는 모델들이나 그중 가장 높은 성능을 끌어내는 SRGAN 조차 아직 완벽한 성능을 내진 못한다. 본 논문에서는 SRGAN의 성능을 개선하기 위해 사전 훈련된 특징 추출기(Pre-trained Feature Extractor) VGG(Visual Geometry Group)-19 모델을 변경하고, 기존 모델과 성능을 비교한다. 실험 결과, VGG-19 모델보다 윤곽이 뚜렷하고, 실제 영상과 더 가까운 영상을 합성할 수 있는 모델을 발견할 수 있을 것으로 기대된다.

• Korean Journal of Environmental Agriculture
• /
• v.41 no.4
• /
• pp.252-260
• /
• 2022

BACKGROUND: The number of biomass power plants is increasing around the world and the amount of wastes from power plants is expected to increase. But the bottom ash (BA) is not recycled and has been dumped in landfill. This study was conducted to find out functional groups of BA and adsorption rate of heavy metals on BA. METHODS AND RESULTS: The BA was dried in oven at 105℃ for 24 hours, and characterized by analyzing the chemistry, functional group, and surface area. The adsorption rates of heavy metals on BA were evaluated by different concentration, time, and pH. As a result, the adsorption amount of the heavy metals was high in the order of Zn> Cu> Cd> Ni and the removal rates of Zn, Cu, Cd, and Ni by BA was 49.75, 30.20, 32.46, and 36.10%, respectively. Also, the maximum adsorption capacity of BA was different by the heavy metal in the environmental conditions, and it was suggested that the isotherms for Zn, Ni, Cd, and Cu were adequate to Langmuir model. CONCLUSION(S): It is suggested that it would be effective to remove heavy metals in aqueous solution by using BA from biomass power plants in South Korea.

• The Journal of the Korea Contents Association
• /
• v.18 no.5
• /
• pp.539-544
• /
• 2018

Interdisciplinary, or convergence, research has been a priority for the National Research Foundation of Korea (NRF) and many scholars in Korea have proposed interdisciplinary projects. Of the 4,930 proposals for the submitted in 2017, 2,575 (52.2%) of these proposals could be considered interdisciplinary projects. However, interdisciplinary projects had an acceptance rate of 35.0%, compared to an acceptance rate of 42.1% for single-discipline proposals. According to the study, despite the large share of research projects that appear to be interdisciplinary research, the characteristics of interdisciplinary studies was not reflected properly in the evaluation. I would suggest that it is required to prepare the criteria for classification of interdisciplinary studies in the classification system of research fields so that the characteristics of interdisciplinary research projects may be duly considered.

• Journal of Korean Elementary Science Education
• /
• v.37 no.2
• /
• pp.188-205
• /
• 2018

For STEM education science teachers usually choose topics which are related to both science and other disciplinary contents. Nevertheless it is not clear for the teachers to adopt what kind of criteria for their choices. Interdisciplinary teaching is not a mixture of science content with another one from different disciplines as resources for the content teaching. Instead the criteria and perspectives for the integration need to be clearly defined. In this study we investigated how to integrate science and other disciplines in terms of interdisciplinary teaching. Family resemblance approach by Wittgenstein, recently revised by Erduran and Dagher, was applied to comparative analysis of science, math, and physical education curriculum documents in Korea. Aim and value, methodological rules and methods, knowledge, and activities in each discipline were compared and analyzed with the view of FRA. Results of the study described alternative criteria of how to find appropriate topics for interdisciplinary teaching.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.04a
• /
• pp.846-849
• /
• 2012

대부분의 시간을 실내에서 보내는 사람들이 점점 많아짐에 따라서 안전한 실내 생활환경에 대한 관심이 높아지고 있고, 특히 실내 오염원을 감지하여 사전 조치를 취할 수 있는 측정 시스템에 대한 필요성이 점차 증대되고 있다. 이와 관련하여 본 논문에서는 다양한 환경 센서를 활용하여 가정이나 특정 실내공간의 환경정보를 측정하고 실내공기를 관리할 수 있는 '실내 환경정보 모니터링시스템'을 설계하고 구현하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.485-487
• /
• 2023

컴퓨터 비전의 하위 태스크(Task)인 의미론적 분할(Semantic Segmentation)은 자율주행, 해상에서 선박찾기 등 다양한 분야에서 연구되고 있다. 기존 FCN(Fully Conovlutional Networks) 기반 의미론적 분할 모델은 다운샘플링(Dowsnsampling)과정에서 공간정보의 손실이 발생하여 정확도가 하락했다. 본 논문에서는 공간정보 손실을 완화하고자 PSA(Polarized Self-attention)의 공간정보 강조 모듈을 HRNet(High-resolution Networks)의 합성곱 블록 사이에 추가한다. 실험결과 파라미터는 3.1M, GFLOPs는 3.2G 증가했으나 mIoU는 0.26% 증가했다. 공간정보가 의미론적 분할 정확도에 영향이 미치는 것을 확인했다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.520-523
• /
• 2022

일본 우주항공연구개발기구(Japan Aerospace Exploration Agency, JAXA)는 2007년부터 2017년까지 달 탐사선 셀레네(Selenological and Engineering Explorer, SelEnE)가 관측한 데이터를 수집하고, 연구했다. JAXA는 지구 상층 대기에 존재하는 산소가 자기장의 꼬리 부분에 실려 달로 이동한다는 사실을 발견했다. 하지만 이 연구는 아직 진행 중이며 달의 산화 과정 규명에 추가 연구가 필요하다. 본 논문에서는 생성적 적대 신경망(Generative Adversarial Networks, GAN)으로 달 분화구의 영구 그림자 영역을 제거하고, 물과 얼음을 발견하여 선행 연구의 완성도를 향상하고자 한다. 실험에 사용할 모델은 CIPS(Conditionally Independent Pixel Synthesis)다. CIPS는 실제 같은 영상을 고해상도로 합성한다. 합성할 데이터의 최적인 가중치 초기화 및 파라미터 갱신 방법, 활성 함수 조합은 실험을 통해 확인한다. 필요에 따라 앙상블 학습을 할 수도 있다. 성능평가는 FID(Frechet Inception Distance), 정밀도, 재현율을 사용한다. 제안한 방법은 진행 중인 연구의 시간과 비용을 절약하고, 인과관계를 더욱 명확히 밝히는 데 도움 될 수 있다고 사료된다.

• Korean Journal of Environmental Agriculture
• /
• v.41 no.4
• /
• pp.310-317
• /
• 2022

BACKGROUND: The salt in soil interrupts crop growth. Therefore, water resources are used to remove any salt found in the soil. However, water resources have been reduced by global warming; thus, a new study is required into reducing the salt in soil. Recently, the bottom ash (BA) of a biomass power plant was found to be similar to biochar. Hence, it can be used to remove heavy metals and wastewater through the adsorption characteristics of BA. The objective of this study was to evaluate the improvement effects on crop growth in saline soil containing the BA from biomass power plants. METHODS AND RESULTS: The effect on crop growth in the saline soil supplemented with BA was studied with the crop-planted pots, which were packed by reclaimed greenhouse soils collected from Byolyang, Suncheon. The BA application level was 25, 50, 100, 200, and 400 kg/10a (referred as BA25, BA50, BA100, BA200, and BA400, respectively). The BA increased the fresh weights of the leaf and root, while nitrogen uptake increased by approximately 24-102% and 54-77%, respectively for the lead and root. The phosphorous uptake increased by 38%, although only in the leaf of the lettuce. In the case of soil, BA increased water content, pH, EC, CEC, and NH₄⁺ and the SAR of the soil decreased by 5-15%. The bottom ash increased the contents of Ca²⁺ and Mg²⁺, and fixed the amount of Na⁺. CONCLUSION(S): It was confirmed the bottom ash of a biomass power plant, based on wood pellets, improved crop growth, and increased the nutrient uptake of crops in saline soil. In addition, bottom ash, which has a wide range of porosity and high values of pH and EC, improved properties of the saline soil. However, the BA has a large amount of B, As, and heavy metals. Finally, it may require a study on the safety and contamination of heavy metals contained in the bottom ash, which would be applied in soil for a long time.

• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.246-259
• /
• 2023

This study explores the evolving landscape of consumer experiences in the context of pop-up stores, considering the shifts from product economy to service economy and now the experience economy. It investigates the factors influencing consumer word-of-mouth intentions by examining the interplay of pop-up store experiences, brand equity, brand charisma, and verbal intent. Using Schmitt's strategic experience modules and the Aaker brand equity model, the study employs quantitative methods and data analysis to uncover the relationships among these variables. Surprisingly, it finds limited associations between the aspects of the pop-up store experience and brand equity. However, it highlights the direct impact of brand equity on brand charisma, which subsequently influences consumers' intentions to share brand-related information. This research contributes to our understanding of word-of-mouth marketing for pop-up stores, filling a knowledge gap and offering valuable insights for academics and businesses navigating the evolving marketing landscape. It also emphasizes the significance of brand charisma in the context of transient in-store experiences and evolving consumer preferences.