• Journal of information and communication convergence engineering
• /
• v.16 no.3
• /
• pp.148-152
• /
• 2018

Adversarial attacks on artificial intelligence (AI) systems use adversarial examples to achieve the attack objective. Adversarial examples consist of slightly changed test data, causing AI systems to make false decisions on these examples. When used as a tool for attacking AI systems, this can lead to disastrous results. In this paper, we propose an ensemble of degraded convolutional neural network (CNN) modules, which is more robust to adversarial attacks than conventional CNNs. Each module is trained on degraded images. During testing, images are degraded using various degradation methods, and a final decision is made utilizing a one-hot encoding vector that is obtained by summing up all the output vectors of the modules. Experimental results show that the proposed ensemble network is more resilient to adversarial attacks than conventional networks, while the accuracies for normal images are similar.

• Journal of Korean Society for Quality Management
• /
• v.19 no.1
• /
• pp.151-162
• /
• 1991

The purpose of this study is to propose a facility layout design algorithm based on artificial intelligence concept, and then to develop a computer program which is more practical than any other conventional facility layout design systems. The algorithm is composed of five step layout procedures; knowledge and data input, knowledge interpretation, priority determination, inference of layout design, and evaluation, In the step of priority determination, the algorithm is divided into single row and multi row layout problem. In the step of inference of layout design, alternatives are generated by constraints-directed reasoning and depth first search method based on artificial intelligence concept. Alternatives are evaluated by the moving cost and relationship value by interactive man-machine interface in the step of evaluation. As a case study, analytical considerations over conventional programs such as CRAFT and CORELAP was investigated and compared with algorithm propsed in this study. The proposed algorithm in this study will give useful practical tool for layout planner. The computer progran was written in C language for IBM PC-AT.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1997.06a
• /
• pp.89-94
• /
• 1997

In this paper, we present a VR-based interface method which provides users more natural, realistic, and interactive communication and collaboration tool. Since most services in the communication systems matches with the services in the real world, the best understanding would be achieved when the communication services are represented in accordance with the services in the real world. However, conventional text-based interface and 2D GUI cannot provide such reality to the users. In this paper, we discuss VR-based interface to overcome such difficulty and introduce one instance of communication system using the VR-based realistic, what we call Virtual Village, which we are currently developing. This application might be applied to education in virtual space, desktop conferencing system, and entertainment such as MUD or the games in the distributed environment, etc.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.491-496
• /
• 2022

최근 멀티-세션 데이터로 장기간 페르소나와 대화 일관성을 유지하며 인터넷에서 대화와 관련된 지식을 활용하는 대화모델 연구가 활발히 진행되고 있다. 하지만 이를 위한 한국어 멀티-세션 오픈 도메인 지식 기반 대화 데이터는 공개되지 않아 한국어 대화모델 연구에 어려움이 있다. 따라서 본 논문에서는 한국어 멀티-세션 오픈 도메인 지식 기반 데이터의 필요성을 시사하고, 데이터 수집을 위한 툴을 제안한다. 제안하는 수집 툴은 양질의 데이터 수집을 위해 작업자들이 사용하기 편하도록 UI/UX를 구성하였으며, 대화 생성 시 텍스트뿐만 아니라 정보가 밀집된 테이블도 대화에 활용할 지식으로 참조할 수 있도록 구현하였다. 제안하는 수집 툴은 웹 랜덤채팅 시스템에 기반을 두어 작업자가 여러 다른 작업자와 같은 확률로 매칭되게 구현되었으며, 일정 확률로 기존 대화로부터 대화를 시작하도록 함으로써 멀티-세션 대화 수집이 가능하도록 하였다.

• Electronics and Telecommunications Trends
• /
• v.38 no.3
• /
• pp.38-46
• /
• 2023

The value of living a long and healthy life without suffering has increased owing to aging populations, transition to welfare societies, and global interest in health deriving from the novel coronavirus disease pandemic. New drug development has gained attention as both a tool to improve the quality of life and high-value market, with blockbuster drugs potentially generating over 10 billion dollars in annual revenue. However, for newly discovered substances to be used as drugs, various properties must be verified over a long period in a time-consuming and costly process. Recently, the development of artificial intelligence technologies, such as deep and reinforcement learning, has led to significant changes in drug development by enabling the effective identification of drug candidates that satisfy desired properties. We explore and discuss trends in artificial intelligence for de novo drug design.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.407-408
• /
• 2022

본 논문에서는 AIoT를 위한 비주얼 블록 코딩 도구를 설계하였다. AI 블록 코딩이 가능한 EduB 플랫폼에 피지컬 컴퓨팅을 가능하게 하는 모듈을 추가함으로써 블록을 사용한 쉬운 피지컬컴퓨팅 코딩과 AIoT 코딩이 가능하다. 도구는 WebSocket과 Wifi를 사용해 EduB와 타겟보드인 RaspberryPi의 무선 통신을 하며, 블록으로 생성된 코드를 RaspberryPi 내부에서 실행하여 GPIO와 SenseHAT을 제어할 수 있게 하였다. 따라서, 코딩 결과를 콘솔 출력이나 그래프로만 확인할 수 있어 정적이던 AI 교육을 LED나 모터를 제어해 동적으로 결과를 확인할 수 있게 하여 흥미와 관심을 유발할 수 있도록 한다.

• Journal of Digestive Cancer Research
• /
• v.12 no.1
• /
• pp.31-37
• /
• 2024

Pancreatic cancer is a highly fatal malignancy with a 5-year survival rate of < 10%. Endoscopic ultrasound (EUS) is a useful noninvasive tool for differential diagnosis of pancreatic malignancy and treatment decision-making. However, the performance of EUS is suboptimal, and its accuracy for differentiating pancreatic malignancy has increased interest in the application of artificial intelligence (AI). Recent studies have reported that EUS-based AI models can facilitate early and more accurate diagnosis than other preexisting methods. This article provides a review of the literature on EUS-based AI studies of pancreatic malignancies.

• Clinical Endoscopy
• /
• v.57 no.1
• /
• pp.24-35
• /
• 2024

The field of artificial intelligence is rapidly evolving, and there has been an interest in its use to predict the risk of lymph node metastasis in T1 colorectal cancer. Accurately predicting lymph node invasion may result in fewer patients undergoing unnecessary surgeries; conversely, inadequate assessments will result in suboptimal oncological outcomes. This narrative review aims to summarize the current literature on deep learning for predicting the probability of lymph node metastasis in T1 colorectal cancer, highlighting areas of potential application and barriers that may limit its generalizability and clinical utility.

• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.33 no.3
• /
• pp.142-155
• /
• 2022

Diagnosis using voice is non-invasive and can be implemented through various voice recording devices; therefore, it can be used as a screening or diagnostic assistant tool for laryngeal voice disease to help clinicians. The development of artificial intelligence algorithms, such as machine learning, led by the latest deep learning technology, began with a binary classification that distinguishes normal and pathological voices; consequently, it has contributed in improving the accuracy of multi-classification to classify various types of pathological voices. However, no conclusions that can be applied in the clinical field have yet been achieved. Most studies on pathological speech classification using speech have used the continuous short vowel /ah/, which is relatively easier than using continuous or running speech. However, continuous speech has the potential to derive more accurate results as additional information can be obtained from the change in the voice signal over time. In this review, explanations of terms related to artificial intelligence research, and the latest trends in machine learning and deep learning algorithms are reviewed; furthermore, the latest research results and limitations are introduced to provide future directions for researchers.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.8
• /
• 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.