• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.446-450
• /
• 2020

딥러닝 기반의 영상 분석 방법들은 많은 양의 학습 데이터가 필요하며, 학습 데이터 구축에는 많은 시간과 노력이 소요된다. 특히 객체 검출 분야의 경우 영상 내 객체의 위치, 크기, 범주 등의 정보가 모두 필요하여 학습 데이터 구축에 더 많은 어려움이 있으며, 이를 해결하기 위해 최근 이미지 합성기반 데이터 증강에 관한 연구가 활발히 진행되고 있다. 이미지 합성기반 데이터 증강 방법은 배경 영상에 객체를 합성할 때 객체와 배경 영상이 접한 영역에서 아티팩트(Artifact)가 발생하며, 이는 객체 검출 모델이 아티팩트를 객체의 특징으로 모델링하여 검출 성능이 저하되는 원인이 된다. 이러한 문제를 해결하기 위하여 본 논문에서는 양방향 필터 기반의 이미지 합성 방법을 제안하고, 단일 단계 검출의 대표적인 방법인 RetinaNet을 이용하여 이미지 합성기반 데이터 증강 방법의 성능을 분석하였다. 공개 데이터셋에 대한 실험 결과 본 논문에서 사용한 단일 검출 방법 및 데이터 증강 기법을 사용하면 더 적은 양의 증강 데이터로 기존 방법과 동일한 성능을 보여주는 것을 확인하였다.

• Korean Journal of Cognitive Science
• /
• v.13 no.1
• /
• pp.23-40
• /
• 2002

This study is to examine brain regions that are involved in picture encoding in normal adults using fMRI methods. In Scan 1, the picture encoding was studied during a semantic categorization task in comparison with word. In Scan 2 task type effects were studied both during a picture naming task and during a semantic categorization task with pictures. Subjects were asked to make decision either by pressing a mouse button (Scan 1) or by responding subvocally (naming or saying yes/no) (Scan 2). Regardless of stimulus type, left prefrontal, bilateral occipital, and parietal activations were observed during semantic processing in comparison with fixation baseline. Processing of word stimulus relative to picture resulted in activations in prefrontal and parieto-temporal regions in the left side while that of picture stimulus relative to word resultd in activations in bilateral extrastriatal visual cortices and parahippocampal regions. In spite of the same task demands, stimulus-specific information processings were involved and mediated by different neural substrates; the word encoding was associated with more semantic/lexical processings than pictures and the picture processing associated with more perceptual and novelty related information processings than word. Activations of dorsal part of inferior prefrontal region, i.e., Broca's areas were found both during the picture naming and during the semantic tasks subvocally performed Especially, during the picture naming task, greater occipital activations were found bilaterally relative to the semantic categorization task. indicating a possibility that greater and higher visual processing was involved in retrieving the name referred by picture stimuli.

• Journal of Digital Convergence
• /
• v.18 no.9
• /
• pp.379-389
• /
• 2020

This is a qualitative study about Google 'Nest Hub Max' that displays proactive intelligent personal assistant. Following the step of grounded theory, an in-depth interview for 6 users who had used this device for a month was taken. 186 concepts were discovered, categorized as 11 top-categories and 24 sub-categories. Paradigm diagram, considering axis-coding, was made and it have been narrowed down to 'Usage patterns' of proactive IPA, considering selective coding aspects. 'Usage patterns' were divided to passive and active user. Thus, neither passive user nor active user was satisfied about device and proactive IPA. This study is meaningful that it constructed basic data about the user experience of proactive IPA on this device. It will support the device or service that consists proactive IPA in the future.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.2
• /
• pp.447-463
• /
• 2022

Artificial Intelligence (AI) technology is a major technology that develops smart ships into autonomous ships in the marine industry. Autonomous ships recognize a situation with the information collected without human judgment which allow them to operate on their own. Existing ship systems, like control systems on land, are not designed for security against cyberattacks. As a result, there are infringements on numerous data collected inside and outside the ship and potential cyber threats to AI technology to be applied to the ship. For the safety of autonomous ships, it is necessary to focus not only on the cybersecurity of the ship system, but also on the cybersecurity of AI technology. In this paper, we analyzed potential cyber threats that could arise in AI technologies to be applied to existing ship systems and autonomous ships, and derived categories that require security risks and the security of autonomous ships. Based on the derived results, it presents future directions for cybersecurity research on autonomous ships and contributes to improving cybersecurity.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.729-732
• /
• 2018

모바일 게임 산업의 발달로 많은 사용자들이 게임을 이용하면서, 그들의 만족감을 사용리뷰를 통해 드러낸다. 실제로 각 리뷰의 범주가 모두 다르지만 현재 구글 플레이 앱스토어(Google Play App Store)의 게임 리뷰 범주는 3가지로 매우 제한적이다. 따라서 본 연구에서는 빠르고 정확한 고객의 요구를 필요로 하는 게임 소프트웨어의 특성을 고려하여 게임 리뷰를 입력했을 때, 게임의 운영 및 시스템에 맞도록 리뷰의 카테고리를 세분화하고 만족도를 분석하는 시스템을 개발한다. 제안 시스템은 인공신경망 모델인 CNN을 평점을 기반으로 훈련시켜 리뷰에 대한 만족도를 도출한다. 또한 Word2Vec을 이용해 단어들 간의 유사도를 구하고, 이를 활용한 단어 배열을 이용하여 가장 스코어가 높은 카테고리로 배정한다. 본 논문은 제안한 리뷰 만족도 및 카테고리 분류 시스템이 실제 효과적으로 리뷰를 보다 의미 있는 정보로써 제공할 수 있음을 보인다.

• Journal of Science Education
• /
• v.45 no.1
• /
• pp.105-117
• /
• 2021

The purpose of this study is to analyze the gender differences of elementary, junior high, and high school students in the artificial intelligence ethics awareness (hereinafter referred to as AIEA). This is a study to investigate whether there is a gender difference in the AIEA, and if so, when the gender difference will occur. This study was conducted with 198 elementary school students (98 female students, 100 male students), 265 middle school students (166 female students, 99 male students), and 114 high school students (58 female students and 56 male students) in I Metropolitan City. The results are as follows: First, a gender difference in the AIEA between all boys and girls was confirmed. Second, the gender difference in the AIEA tended to be solidified as the school age increased from elementary school to middle school and high school. Third, female students at all stages of elementary school, junior high school, and high school are not yet very reliable in artificial intelligence, and there is a greater concern about non-discrimination than boys. It turns out that they have a negative position on permission to enter the territory. Fourth, the interaction effects of school age and gender have been identified in 'stability and reliability,' and in 'permit and limit' categories. Taken together, these results show that an educational strategy that approaches the gender equality perspective of the educational program is necessary so that there will be no gender difference in the AIEA during artificial intelligence education activities.

• The Journal of the Korea Contents Association
• /
• v.21 no.10
• /
• pp.630-644
• /
• 2021

This study was conducted to develop evidence-based nursing practice guideline for the prevention of VAP. This is a methodological study to develop guideline and verify the effectiveness according to the hybrid method of the NECA. Topics and key questions were derived through literature review and interviews, and recommendations were converged and developed through guidelines review and SR and meta-analysis. This was verified through the RAND and evaluated through AGREEII. The clinical feasibility of the nursing practice guideline, consisting of 44 recommendations in 9 categories, was evaluated by 122 ICU nurses. Conclusively this evidence-based nursing practice guideline for the prevention of VAP was confirmed methodological quality and content validity and was suitable for our nursing practice environment.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.11
• /
• pp.1720-1728
• /
• 2022

The industrial 4.0 era has been opened with the development of artificial intelligence technology, and the realization of smart farms incorporating ICT technology is receiving great attention in the livestock industry. Among them, the quality management technology of livestock products and livestock operations incorporating computer vision-based artificial intelligence technology represent key technologies. However, the insufficient number of livestock image data for artificial intelligence model training and the severely unbalanced ratio of labels for recognizing a specific defective state are major obstacles to the related research and technology development. To overcome these problems, in this study, combining oversampling and adversarial case generation techniques is proposed as a method necessary to effectively utilizing small data labels for successful defect detection. In addition, experiments comparing performance and time cost of the applicable techniques were conducted. Through experiments, we confirm the validity of the proposed methods and draw utilization strategies from the study results.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.45 no.9
• /
• pp.794-806
• /
• 2017

It is essential to protect the national space assets and space environment safely as a space development country from the continuously increasing space debris. And Active Debris Removal(ADR) is the most active way to solve this problem. In this paper, we studied the Artificial Neural Network(ANN) for a stable recognition model of vision-based space debris tracking system. We obtained the simulated image of the space environment by the KARICAT which is the ground-based space debris clearing satellite testbed developed by the Korea Aerospace Research Institute, and created the vector which encodes structure and color-based features of each object after image segmentation by depth discontinuity. The Feature Vector consists of 3D surface area, principle vector of point cloud, 2D shape and color information. We designed artificial neural network model based on the separated Feature Vector. In order to improve the performance of the artificial neural network, the model is divided according to the categories of the input feature vectors, and the ensemble technique is applied to each model. As a result, we confirmed the performance improvement of recognition model by ensemble technique.

• Korean Chemical Engineering Research
• /
• v.61 no.1
• /
• pp.123-141
• /
• 2023

A sufficient amount of data with quality is needed for training artificial neural networks (ANNs). However, developing ANN models with a small amount of data often appears in engineering fields. This paper presented an ANN model to improve prediction performance of the ammonia emission amount with 83 data. The ammonia emission rate included eleven inputs and two outputs (maximum ammonia loss, N_max and time to reach half of N_max, K_m). Categorical input variables were transformed into multi-dimensional equal-distance variables, and 13 data were added into 66 training data using a generative adversarial network. Hyperparameters (number of layers, number of neurons, and activation function) of ANN were optimized using Gaussian process. Using 17 test data, the previous ANN model (Lim et al., 2007) showed the mean absolute error (MAE) of K_m and N_max to 0.0668 and 0.1860, respectively. The present ANN outperformed the previous model, reducing MAE by 38% and 56%.