• 한국멀티미디어학회논문지
• /
• 제20권2호
• /
• pp.179-187
• /
• 2017

The fourth industrial revolution is a phenomenon where productivity is improved in each field by the convergence of IT technology and existing industries. In the dental treatment process, prosthetic treatment time is drastically shortened through AI and expert software. Oral imaging, prosthesis design, and prosthesis manufacturing are performed continuously, so the treatment can be completed in a few hours. In this paper, we introduce the research trend of multimedia technology in the prosthetic process. We also propose a new method for accelerating the fusion of surface data during the optical impression. Proposed method enables high-speed optical impression and accelerates the overall automated production process of dental prosthesis.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2017년도 추계학술발표대회
• /
• pp.571-574
• /
• 2017

본 논문에서는 최근 들어서 계속 반복되고 있는 조류독감의 확산을 예방하기 위해서 방역시스템을 IT 기술과 결합하였다. 먼저 각국의 조류독감 방역시스템에 대해서 설명하고, 조류독감 예방을 위한 BioSecurity에 대해서 알아본다. BioSecurity에 근거한 요구분석사항을 도출해 보고, 다양한 ICT 기술을 결합, 여러가지 센서들을 사용한 자동화된 시스템을 제안한다. 전체 방역시스템에 투입되는 리소스들과 그 역할 등을 구분하고 시스템작동 시나리오를 예상해본다. 향후 AI 발생시 자동화된 시스템의 선제적인 대응으로 조류독감의 확산을 예방하고자 한다.

• International Journal of Advanced Culture Technology
• /
• 제7권4호
• /
• pp.295-301
• /
• 2019

Since the third artificial intelligence boom was triggered by deep learning, it has been 10 years. It is time to analyze and discuss the research trends of deep learning for the stable development of AI. In this regard, this study systematically analyzes the trends of research on deep learning over the past 10 years. We collected research literature on deep learning and performed LDA based topic modeling analysis. We analyzed trends by topic over 10 years. We have also identified differences among the major research countries, China, the United States, South Korea, and United Kingdom. The results of this study will provide insights into research direction on deep learning in the future, and provide implications for the stable development strategy of deep learning.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제27권1호
• /
• pp.33-40
• /
• 2000

자동공정계획은 CAD 모델을 자동적으로 해석하여 CAM을 구동시키는 것을 목표로 하는데, 이를 위해서는 우선 CAD 모델로부터 특징형상을 인식하여야 한다. 특징형상 인식에 관한 연구는 근 20년간의 역사를 가지고 있지만, 그 연구 성과는 실용화되지 못하고 있다. 그 이유 중 하나는, 특징형상 인식과 자동공정계획 연구가 분리되어 진행되어왔기 때문이다. 본 연구에서는 인공지능 기법을 토대로 이 두 분야를 통합하여, 제조가능한 특징형상을 인식하고, 셋업을 최소화하며, 특징형상 간의 의존 관계를 설정하고, 최적의 가공 순서를 결정하였다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2014년도 추계학술발표대회
• /
• pp.894-897
• /
• 2014

The speed of processes and the extremely large amount of data to be used in Intelligence Transportations System (ITS) cannot be handling by humans without considerable automation. However, it is difficult to develop software with conventional fixed algorithms (hard-wired logic on decision making level) for effectively manipulate dynamically evolving real time transportation environment. This situation can be resolved by applying methods of artificial intelligence and data mining that provide flexibility and learning capability. This paper presents a brief introduction of data mining and artificial intelligence (AI) applications in Intelligence Transportation System (ITS), analyzing the prospects of enhancing the capabilities by means of knowledge discovery and accumulating intelligence to support in decision making.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2018년도 춘계학술발표대회
• /
• pp.139-141
• /
• 2018

최근 IoT, SNS 등이 확대 되면서 대규모의 빅데이터가 생산되고 있고, 이러한 빅데이터는 AI 등 지능형 기술과 결합하여 다양한 분야의 예측과 의사결정을 지원하며 새로운 가치를 창출하고 있다. 그러나, 이러한 활용에 있어 가장 걸림돌이 되는 것은 빅데이터에 내제되어 있는 개인정보에 대한 위협이다. 본연구에서는 빅데이터에 내제되어 있는 개인정보를 보호하면서도 빅데이터의 효과적인 분석과 활용을 가능하게 할 수 있는 동형암호(homomorphic encryption)을 살펴보고 빅데이터의 프라이버시 강화 방안과 이를 통한 빅데이터의 활용방안에 대해 연구하고 향 후 과제 등에 대해 고찰해 보도록 한다.

• 한국멀티미디어학회논문지
• /
• 제22권2호
• /
• pp.250-259
• /
• 2019

Big data processing technology and artificial intelligence (AI) are increasingly attracting attention. Natural language processing is an important research area of artificial intelligence. In this paper, we use Korean news articles to extract topic distributions in documents and word distribution vectors in topics through LDA-based Topic Modeling. Then, we use Word2vec to vector words, and generate a weight matrix to derive the relevance SCORE considering the semantic relationship between the words. We propose a way to recommend documents in order of high score.

• 한국멀티미디어학회논문지
• /
• 제24권5호
• /
• pp.651-658
• /
• 2021

In this paper, we propose methods for character recognition and classification for table items through deep learning. First, table areas are detected in a document image through CNN. After that, table areas are separated by separators such as vertical lines. The text in document is recognized through a neural network combined with CNN and RNN. To correct errors in the character recognition, multiple candidates for the recognized result are provided for a sentence which has low recognition accuracy.

• International journal of advanced smart convergence
• /
• 제10권2호
• /
• pp.1-9
• /
• 2021

In the Internet-of-Things (IoT) and artificial intelligence (AI), complete implementations are dependent largely on the speed of the fifth generation (5G) networks. However, successive interference cancellation (SIC) in non-orthogonal multiple access (NOMA) of the 5G mobile networks can be still decoding latency and receiver complexity in the conventional SIC NOMA scheme. Thus, in order to reduce latency and complexity of inherent SIC in conventional SIC NOMA schemes, we propose a rate-lossless non-SIC NOMA scheme. First, we derive the closed-form expression for the achievable data rate of the asymmetric 2PAM non-SIC NOMA, i.e., without SIC. Second, the exact achievable power allocation interval of this rate-lossless non-SIC NOMA scheme is also derived. Then it is shown that over the derived achievable power allocation interval of user-fairness, rate-lossless non-SIC NOMA can be implemented. As a result, the asymmetric 2PAM could be a promising modulation scheme for rate-lossless non-SIC NOMA of 5G networks, under user-fairness.

• 반도체디스플레이기술학회지
• /
• 제21권3호
• /
• pp.92-97
• /
• 2022

Plastics are classified into 7 types such as PET (PETE), HDPE, PVC, LDPE, PP, PS, and Other for separation and recycling. Recently, large corporations advocating ESG management are replacing them with bioplastics. Incineration and landfill of disposal of plastic waste are responsible for air pollution and destruction of the ecosystem. Because it is not easy to accurately classify plastic materials with the naked eye, automated system-based screening studies using various sensor technologies and AI-based software technologies have been conducted. In this paper, NIR scanning devices considering the NIR wavelength characteristics that appear differently for each plastic material and a system that can identify the type of plastic by learning the NIR spectrum data collected through it. The accuracy of plastic material identification was evaluated through a decision tree-based SVM model for multiclass classification on NIR spectral datasets for 8 types of plastic samples including biodegradable plastic.