• 한국컴퓨터정보학회논문지
• /
• 제29권3호
• /
• pp.227-235
• /
• 2024

정보 혁명 시대를 맞이하여 전 세계적인 변화의 흐름 속에서 인공지능 융합 교육의 필요성이 더욱 대두되고 있다. 이에 본 논문에서는 인공지능을 융합한 피지컬 컴퓨팅 프로그래밍 교육 방법을 개발 및 적용하였다. 통제집단에는 인공지능을 융합하지 않은 피지컬 컴퓨팅 프로그래밍 교육을 실시하였으며, 실험집단에는 인공지능을 융합한 피지컬 컴퓨팅 프로그래밍 교육 방법을 개발하여 적용한 후 초등학생의 컴퓨팅 사고력에 미치는 영향을 분석하였다. 그 결과, 인공지능을 융합한 피지컬 컴퓨팅 프로그래밍 교육이 인공지능을 융합하지 않은 피지컬 컴퓨팅 프로그래밍 교육과 비교하여 초등학생의 컴퓨팅 사고력 신장에 더욱 긍정적인 효과를 나타내었음에 대한 통계적으로 유의미한 결과를 확인할 수 있었다.

• 한국전자통신학회논문지
• /
• 제12권1호
• /
• pp.139-146
• /
• 2017

알파고로 촉발된 인공지능에 대한 국민의 관심이 고조되고 있다. 아직 국내에는 인공지능 분야에 대한 기술융합 맵 및 국가 프로파일에 대한 연구가 미진한 실정이다. 본 연구는 특허와 논문을 통해 인공지능 분야의 기술융합 현상을 밝히고, 인공지능 분야의 국가 프로파일을 분석하고자 하였다. 특허와 논문에서 인공지능 분야 데이터를 추출한 후 기술융합 맵을 작성하였다. KISTI가 보유한 SCOPUS 데이터를 이용해 국가 프로파일 분석에 필요한 지표를 구했다. 기술적 측면에서 인공지능 분야의 기술은 금융가격결정, 이미지분석, 수술 등 분야와 기술융합이 활발하게 나타났다. 학문적 측면에서 보면 인공지능 분야는 컴퓨터 과학 하위 분야에서 주로 연구되고 있지만 전기전자공학, 바이오 공학, 의학 등 분야와 융합이 활발하게 나타났다. 우리나라는 인공지능 분야에 대한 연구 성장도가 세계 평균인 것으로 나타났으며, 국가집중도, 영향력 등 측면에서는 주요국과 격차가 큰 것으로 나타났다.

• 한국인공지능학회지
• /
• 제10권2호
• /
• pp.13-18
• /
• 2022

The role of artificial medical intelligence through medical big data has been focused on data-based medical device business and medical service technology development in the field of diagnostic examination of the patient's current condition, clinical decision support, and patient monitoring and management. Recently, with the 4th Industrial Revolution, the medical field changed the medical treatment paradigm from the method of treatment based on the knowledge and experience of doctors in the past to the form of receiving the help of high-precision medical intelligence based on medical data. In addition, due to the spread of non-face-to-face treatment due to the COVID-19 pandemic, it is expected that the era of telemedicine, in which patients will be treated by doctors at home rather than hospitals, will soon come. It can be said that artificial medical intelligence plays a big role at the center of this paradigm shift in prevention-centered treatment rather than treatment. Based on big data, this paper analyzes the current status of artificial intelligence technology for chronic disease patients, market trends, and domestic and foreign company trends to predict the expected effect and future development direction of artificial intelligence technology for chronic disease patients. In addition, it is intended to present the necessity of developing digital therapeutics that can provide various medical services to chronically ill patients and serve as medical support to clinicians.

• 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 2021년도 추계학술발표대회
• /
• pp.95-98
• /
• 2021

최근 비정상적인 네트워크 활동 감지 및 네트워크 서비스 프로비저닝과 같은 다양한 분야에서 응용되는 네트워크 트래픽 예측 기술이 네트워크 통신 문제에 의한 트래픽의 결측 및 네트워크 유저의 불규칙한 활동에 의한 비선형 특성 때문에 발생하는 성능 저하를 극복하기 위해 딥러닝 신경망에 대한 연구가 활성화되고 있다. 이 딥러닝 신경망 중 시계열 딥러닝 신경망은 단기 네트워크 트래픽 볼륨을 예측할 때 낮은 오류율을 보인다. 하지만, 시계열 딥러닝 신경망은 기울기 소멸 및 폭발과 같은 비선형성, 다중 계절성 및 장기적 의존성 문제와 같은 한계를 보여준다. 이 논문에서는 계절성 임베딩을 고려한 주의 신경망 기반 트래픽 예측 기법을 제안한다. 제안하는 기법은 STL 분해 기법을 통해 분해된 트래픽 트랜드, 계절성, 잔차를 이용하여 일별 및 주별 계절성을 임베딩하고 이를 주의 신경망을 기반으로 향후 트래픽을 예측한다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 춘계학술발표대회
• /
• pp.510-512
• /
• 2023

In order to enhance a model's capability for detecting facial expressions, this research suggests a pipeline that makes use of the GradCAM component. The patching module and the pseudo-labeling module make up the pipeline. The patching component takes the original face image and divides it into four equal parts. These parts are then each input into a 2Dconvolutional layer to produce a feature vector. Each picture segment is assigned a weight token using GradCAM in the pseudo-labeling module, and this token is then merged with the feature vector using principal component analysis. A convolutional neural network based on transfer learning technique is then utilized to extract the deep features. This technique applied on a public dataset MMI and achieved a validation accuracy of 96.06% which is showing the effectiveness of our method.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.540-542
• /
• 2023

Due to the serious issues posed by facial manipulation technologies, many researchers are becoming increasingly interested in the identification of face forgeries. The majority of existing face forgery detection methods leverage powerful data adaptation ability of neural network to derive distinguishing traits. These deep learning-based detection methods frequently treat the detection of fake faces as a binary classification problem and employ softmax loss to track CNN network training. However, acquired traits observed by softmax loss are insufficient for discriminating. To get over these limitations, in this study, we introduce a novel discriminative feature learning based on Vision Transformer architecture. Additionally, a separation-center loss is created to simply compress intra-class variation of original faces while enhancing inter-class differences in the embedding space.

• 한국산업융합학회 논문집
• /
• 제24권5호
• /
• pp.531-536
• /
• 2021

As artificial intelligence technology advances, it is being applied to various application fields. Artificial intelligence is performing well in the field of image recognition and classification. Chip design specialized in this field is also actively being studied. Artificial intelligence-specific chips are designed to provide optimal performance for the applications. At the design task, memory component optimization is becoming an important issue. In this study, the optimal algorithm for the memory size exploration is presented, and the optimal memory size is becoming as a important factor in providing a proper design that meets the requirements of performance, cost, and power consumption.

• 전자통신동향분석
• /
• 제36권6호
• /
• pp.88-95
• /
• 2021

Korea will face difficult social problems including population decline and climate change in the future. Artificial intelligence (AI)-powered ICT convergence services are expected to greatly help in overcoming these social challenges. Accordingly, we have derived key promising services (AI+x) in terms of individuals, industries, and countries and identified expectations and threats perceived by the general public. These findings provide policies and research directions for promising AI-based ICT convergence services for social goods.

• 한국멀티미디어학회논문지
• /
• 제25권8호
• /
• pp.1224-1232
• /
• 2022

Whole body bone scan is the most frequently performed nuclear medicine imaging to evaluate bone metastasis in cancer patients. We evaluated the performance of a VGG16-based transfer learning classifier for bone scan images in which metastatic bone lesion was present. A total of 1,000 bone scans in 1,000 cancer patients (500 patients with bone metastasis, 500 patients without bone metastasis) were evaluated. Bone scans were labeled with abnormal/normal for bone metastasis using medical reports and image review. Subsequently, gradient-weighted class activation maps (Grad-CAMs) were generated for explainable AI. The proposed model showed AUROC 0.96 and F1-Score 0.90, indicating that it outperforms to VGG16, ResNet50, Xception, DenseNet121 and InceptionV3. Grad-CAM visualized that the proposed model focuses on hot uptakes, which are indicating active bone lesions, for classification of whole body bone scan images with bone metastases.