• Journal of Information Processing Systems
• /
• 제17권1호
• /
• pp.178-190
• /
• 2021

Alzheimer's disease (AD) is an insidious and degenerative neurological disease. It is a new topic for AD patients to use magnetic resonance imaging (MRI) and computer technology and is gradually explored at present. Preprocessing and correlation analysis on MRI data are firstly made in this paper. Then kernel principal component analysis (KPCA) is used to extract features of brain gray matter images. Finally supervised classification schemes such as AdaBoost algorithm and support vector machine algorithm are used to classify the above features. Experimental results by means of AD program Alzheimer's Disease Neuroimaging Initiative (ADNI) database which contains brain structural MRI (sMRI) of 116 AD patients, 116 patients with mild cognitive impairment, and 117 normal controls show that the proposed method can effectively assist the diagnosis and analysis of AD. Compared with principal component analysis (PCA) method, all classification results on KPCA are improved by 2%-6% among which the best result can reach 84%. It indicates that KPCA algorithm for feature extraction is more abundant and complete than PCA.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 춘계학술발표대회
• /
• pp.496-498
• /
• 2023

Brain tumor segmentation problem has challenges in the tumor diversity of location, imbalance, and morphology. Attention mechanisms have recently been used widely to tackle medical segmentation problems efficiently by focusing on essential regions. In contrast, the fusion approaches enhance performance by merging mutual benefits from many models. In this study, we proposed a 3D dual fusion attention network to combine the advantages of fusion approaches and attention mechanisms by residual self-attention and local blocks. Compared to fusion approaches and related works, our proposed method has shown promising results on the BraTS 2018 dataset.

• 전자통신동향분석
• /
• 제35권5호
• /
• pp.92-101
• /
• 2020

Artificial intelligence (AI) has become the hottest topic in information and communications technology (ICT) in recent years. Along with the advancement of AI technology, technologies such as big data, cloud, and high-speed wired and wireless communication are being applied to existing media areas in earnest, affecting all parts of the media value chain from content production to consumption. AI technology is now spreading across the media industry faster than any other industry. In the future, the gap between those with and without AI technology will widen, further deepening the polarization of the media ecosystem. Media intelligence, which combines media and AI technologies, is now perceived as essential, not optional. In this paper, we examine the current status of technology development and standardization by major domestic and foreign institutions on how AI is being utilized in the media industry. In addition, we discuss what technology should be developed to lead media intelligence.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2019년도 춘계학술대회
• /
• pp.169-170
• /
• 2019

인공지능이 글로벌 경쟁력 원천 기술로 부각되면서 정부도 자율주행차, 드론, 로봇 등 미래 신산업의 기반 기술이 되는 인공지능을 전략적으로 육성하고 있다. 국내 인공지능 연구 및 서비스는 네이버와 카카오를 중심으로 출시되었으나 해외에 비하면 규모나 수준이 미약한 편이다. 최근, 딥러닝 (deep learning)은 최근 음성인식과 영상인식을 비롯한 다양한 패턴인식 분야에서 혁신적인 성능을 기록하면서 많은 연구가 진행되고 있다. 그 뿐만 아니라 딥러닝은 초창기부터 산업계의 큰 관심을 끌어 구글이나 마이크로소프트, 삼성전자 등 글로벌 정보기술 회사에서 상용제품에 딥러닝 기술을 성공적으로 적용하고 있고 계속 연구개발을 진행하고 있어 대중매체에서도 관심을 가지고 주목하고 있다. 이러한 선행연구를 바탕으로 주목 받고 있는 인공지능에 대해 살펴보도록 하겠다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권8호
• /
• pp.2241-2258
• /
• 2023

This study developed digital literacy instruments and tested their effectiveness on college students' perceptions of AI technologies. In creating a new digital literacy test tool, we reviewed the concept and scale of digital literacy based on previous studies that identified the characteristics and measurement of AI literacy. We developed 23 preliminary questions for our research instrument and used a quantitative approach to survey 318 undergraduates. After conducting exploratory and confirmatory factor analysis, we found that digital literacy in the age of AI had four ability sub-factors: critical understanding, artificial intelligence social impact recognition, artificial intelligence technology utilization, and ethical behavior. Then we tested the sub-factors' predictive powers on the perception of AI's usefulness and ease of use. The regression result shows that the most common powerful predictor of the usefulness and ease of use of AI technology was the ability to use AI technology. This finding implies that for college students, the ability to use various tools based on AI technology is an essential competency in the AI era.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2023년도 제68차 하계학술대회논문집 31권2호
• /
• pp.7-10
• /
• 2023

최근 기후 변화가 심각해짐에 따라 수소 에너지에 대한 관심이 집중되고 있으며 이를 안전하게 운송/보관할 수 있는 용기에 대한 연구도 활발히 진행되고 있다. 특히 고압 가스를 저장하는 TypeIII 용기의 노후화 및 안전과 관련되어 결함을 인지하는 연구가 활발하다. 그러나 이 용기의 외각층을 이루는 CFRP 소재는 탄소 섬유와 에폭시가 복잡한 구조로 구성되어 결함별 탐지가 매우 어렵다. 본 논문에서는 음향방출시험과 딥러닝을 활용하여 CFRP 결함 데이터셋을 구축하고 이를 분류할 수 있는 모델을 제안한다. 특히 CFRP 시편을 직접 제작하여 AE 센서를 부착하고 파괴하여 파형 데이터를 수집하였다. 이후 표현 학습을 통해 데이터의 특징을 압축/추출하고 유사도를 비교해 결함별 데이터를 판별하는 알고리즘을 개발하였다. 구축된 데이터셋의 실루엣 계수는 0.86으로 높은 군집도를 보였다. 마지막으로 구축된 데이터셋을 실시간으로 분류할 수 있는 1D-CNN 딥러닝 모델을 개발하였으며 99.33%의 높은 분류 정확도를 보였다.

• Journal of Information Science Theory and Practice
• /
• 제10권spc호
• /
• pp.12-24
• /
• 2022

This study attempted to investigate changes in collaboration structure for each stage of national Research and Development (R&D) in the artificial intelligence (AI) field through analysis of a co-author network for papers written under national R&D projects. For this, author information was extracted from national R&D outcomes in AI from 2014 to 2019. For such R&D outcomes, NTIS (National Science & Technology Information Service) information from the KISTI (Korea Institute of Science and Technology Information) was utilized. In research collaboration in AI, power function structure, in which research efforts are led by some influential researchers, is found. In other words, less than 30 percent is linked to the largest cluster, and a segmented network pattern in which small groups are primarily developed is observed. This means a large research group with high connectivity and a small group are connected with each other, and a sporadic link is found. However, the largest cluster grew larger and denser over time, which means that as research became more intensified, new researchers joined a mainstream network, expanding a scope of collaboration. Such research intensification has expanded the scale of a collaborative researcher group and increased the number of large studies. Instead of maintaining conventional collaborative relationships, in addition, the number of new researchers has risen, forming new relationships over time.

• 한국시스템다이내믹스연구
• /
• 제7권1호
• /
• pp.5-26
• /
• 2006

Ever increasing dependence of organization on information technology stimulates interactions between individuals and groups in the process of knowledge creation, which overall impies that a reciprocal mechanism lies within the structure of the growth of group intelligence. Individual's intelligence may affect the group intelligence, and vise versa. However, the level of group intelligence is not necessarily determined by the sum of individual's intelligence but the quality of the interactions among the individuals. This study thus aims to conceptually identify the dynamic structure of interactions among the factors influencing the group intelligence level, which is believed to be used as a tool to measure the difference of intelligence between groups. To achieve this goal several attempts were made. First, determinants of intelligence at indiviual level and group level and similarities and differences between individual's and group intelligence were identified from the previous research. Second, causal loop diagrams were developed, which show how individual's intelligence influences group intelligence and vise versa. Third, it was attempted to identify and interpret which feedback loops are most influential in either improving or hapering group intelligence as a whole. Since this study remains only at exploratory level, a more detailed and workable model for field applications has to be developed in the future.

• 한국언어정보학회:학술대회논문집
• /
• 한국언어정보학회 2007년도 정기학술대회
• /
• pp.481-488
• /
• 2007

In this paper, we propose a method to classify movie review documents into positive or negative opinions. There are several approaches to classify documents. The previous studies, however, used only a single classifier for the classification task. We describe a multiple classifier for the review document classification task. The method consists of three classifiers based on SVMs, ME and score calculation. We apply two voting methods and SVMs to the integration process of single classifiers. The integrated methods improved the accuracy as compared with the three single classifiers. The experimental results show the effectiveness of our method.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2019년도 춘계학술대회
• /
• pp.385-388
• /
• 2019

In recent years, China has faced unprecedented intelligent reforms. Artificial intelligence has become a hot topic in society. The deep learning framework is the core of artificial intelligence industrialization, and it has also attracted the attention of all parties. Among them, deep learning has been applied in the fields of computer vision, speech recognition, and language technology processing. This paper will introduce China's development status and future challenges in technology, talent, and market applications.