• Korean Journal of Radiology
• /
• 제22권8호
• /
• pp.1225-1239
• /
• 2021

During the past decade, researchers have investigated the use of computer-aided mammography interpretation. With the application of deep learning technology, artificial intelligence (AI)-based algorithms for mammography have shown promising results in the quantitative assessment of parenchymal density, detection and diagnosis of breast cancer, and prediction of breast cancer risk, enabling more precise patient management. AI-based algorithms may also enhance the efficiency of the interpretation workflow by reducing both the workload and interpretation time. However, more in-depth investigation is required to conclusively prove the effectiveness of AI-based algorithms. This review article discusses how AI algorithms can be applied to mammography interpretation as well as the current challenges in its implementation in real-world practice.

• 정보교육학회논문지
• /
• 제24권4호
• /
• pp.313-325
• /
• 2020

최근의 혁신적 기술 진보를 배경으로 지능정보사회의 핵심기술인 머신러닝, 딥러닝을 비롯한 인공지능 기술이 비약적으로 발전하면서 인공지능의 교육적 활용에 대한 관심과 필요성이 높아지고 있다. 이에 교육부에서도 인공지능 기술에 기반한 지능정보사회를 대비하여 인공지능 역량 강화 교육을 교육 현장에 도입하는 제 1차 정보교육 종합계획을 발표하였다. 이에 본 연구에서는 인공지능의 교육적 활용 가능성을 탐색하기 위해 Web of Science(WoS)에서 인공지능의 교육적 활용과 관련된 국외 논문 416편의 자료를 수집하였다. 수집한 자료를 대상으로 R 프로그램의 bibliometrix 패키지를 활용하여 국가별 연구현황과 연구 주제, 인용횟수, 저자 등록 키워드 네트워크 분석을 실시하였다. 이를 통해 현재 해외에서 이루어지는 있는 인공지능의 교육적 활용에 대한 연구 동향을 알 수 있었다. 본 연구의 결과를 토대로 인공지능 역량 강화 교육을 위한 정보교육 과정에서 연구되어야 할 주제와 방향성에 대한 시사점 얻을 수 있을 것으로 보인다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권6호
• /
• pp.3121-3143
• /
• 2019

Segmentation plays an important role in the field of image processing and computer vision. Intuitionistic fuzzy C-means (IFCM) clustering algorithm emerged as an effective technique for image segmentation in recent years. However, standard fuzzy C-means (FCM) and IFCM algorithms are sensitive to noise and initial cluster centers, and they ignore the spatial relationship of pixels. In view of these shortcomings, an improved algorithm based on IFCM is proposed in this paper. Firstly, we propose a modified non-membership function to generate intuitionistic fuzzy set and a method of determining initial clustering centers based on grayscale features, they highlight the effect of uncertainty in intuitionistic fuzzy set and improve the robustness to noise. Secondly, an improved nonlinear kernel function is proposed to map data into kernel space to measure the distance between data and the cluster centers more accurately. Thirdly, the local spatial-gray information measure is introduced, which considers membership degree, gray features and spatial position information at the same time. Finally, we propose a new measure of intuitionistic fuzzy entropy, it takes into account fuzziness and intuition of intuitionistic fuzzy set. The experimental results show that compared with other IFCM based algorithms, the proposed algorithm has better segmentation and clustering performance.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2023년도 제67차 동계학술대회논문집 31권1호
• /
• pp.461-463
• /
• 2023

MZ세대를 중심으로 자기관리를 열심히 하는 사람들이 증가함에 따라 화장의 기본이 되는 개인 피부톤(퍼스널 컬러)을 찾는 것이 중요시되고 있다. 현재 대다수 사람은 자신에게 어울리는 퍼스널 컬러를 찾기 위해 높은 비용을 지불하여 전문가를 이용하거나 객관적이고 정량화된 기준 없이 오랜 시간을 투자하여 스스로 퍼스널 컬러를 찾는 등 시간과 비용 측면에서의 한계점을 가지고 있다. 본 논문에서는 이를 보완하기 위해 이미지 기반 인공지능 기술(객체 탐지, 객체 분할, BeautyGAN)을 적용하여 데이터 기반의 정량적인 기준을 생성하고, 퍼스널 컬러에 알맞은 화장품 추천 웹 서비스를 제안한다.

• 한국산업융합학회 논문집
• /
• 제24권6_2호
• /
• pp.861-872
• /
• 2021

An efficient cost management is important for the domestic social overhead capital(SOC) based on a long lifecycle after 30 years since completion. Maintenance in South Korea have had the restrictions of consistency and suitability of decision-making by the establishment of a budget plan based on the company estimate and repair and reinforcement methods determined by the inspection and diagnosis engineers' subjective determination for each facility. To resolve this issue, the Korea Institute of Civil Engineering and Building Technology is currently in development of a methodology to propose an optimum maintenance method according to the damage of components by artificial intelligence. This study has deduced the primary factors by analyzing information generated during bridge maintenance and management as a prior step for the development of technologies, and conducted a preliminary analysis to select the optimum artificial intelligence technology.

• 디지털산업정보학회논문지
• /
• 제18권1호
• /
• pp.65-77
• /
• 2022

The purpose of this study is to develop a competency strengthen program with the aim of training designers who respond to changing national policies in the era of artificial intelligence. To this end, this study was conducted through a total of five steps. First, through literature research and analysis of prior research and literature related to the role of training designers and HRD managers was investigated and analyzed, and based on related prior research, theoretical and academic grounds for training designer competency modeling were prepared. In the second stage, a draft training program was developed to strengthen the competency of training designers based on the needs analysis of stakeholders and advice from education experts. In the third stage, a pilot program was conducted based on the draft training program. In step 4, the effectiveness verification was confuted and the deficiencies of the training program were derived from the pilot program. Finally, the final draft of the training program for strengthening the competency of training designers in the era of artificial intelligence was developed. The final training program consisted of 10 modules and was designed to run for three days. The details of specific training program are presented in the article.

• 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.

• 상하수도학회지
• /
• 제38권1호
• /
• pp.1-15
• /
• 2024

Occurrence of process environment changes, such as influent load variances and process condition changes, can reduce treatment efficiency, increasing effluent water quality. In order to prevent exceeding effluent standards, it is necessary to manage effluent water quality based on process operation data including influent and process condition before exceeding occur. Accordingly, the development of the effluent water quality prediction system and the application of technology to wastewater treatment processes are getting attention. Therefore, in this study, through the multi-channel measuring instruments in the bio-reactor and smart multi-item water quality sensors (location in bio-reactor influent/effluent) were installed in The Seonam water recycling center #2 treatment plant series 3, it was collected water quality data centering around COD, T-N. Using the collected data, the artificial intelligence-based effluent quality prediction model was developed, and relative errors were compared with effluent TMS measurement data. Through relative error comparison, the applicability of the artificial intelligence-based effluent water quality prediction model in wastewater treatment process was reviewed.

• 한국학교ㆍ지역보건교육학회지
• /
• 제15권2호
• /
• pp.77-89
• /
• 2014

Objectives: This study examined the effects of middle school students emotional intelligence on their aggressiveness and interpersonal relationships. Methods: Data were collected by questionnaires from 316 middle school students in Daegu city. To analyze the sample survey data, descriptive statistics, t-test, ANOVA, pearson correlation coefficient and simple regression analysis were performed with SPSS/PC 18.0 program. Results: First, among the general characteristic differences, academic achievement and economic status yielded a significant difference in emotional intelligence. Gender, economic status, and educational background produced a significant difference in aggressiveness, while gender, academic achievement, and economic status showed a significant difference in interpersonal relationships. Second, an examination of the correlation among emotional intelligence, aggressiveness, and interpersonal relationships found that the higher the emotional intelligence, the lower the aggressive, and the higher the interpersonal relationships. Third, general characters and emotional intelligence explain 22% of agressiveness. Gender, age, economic status, and emotional intelligence have a significant influence on agressiveness. Fourth, the general characters and emontional intelligence explain 45,5% of interpersonal relationships. The economic status and emotional intelligence have a significant influence on the interpersonal relationship. Conclusion: Based on the results, the study is of great importance, in that it provides the basis for future studies, which can be used to help school teachers and students' parents understand the importance of adolescents emotional intelligence and promote the students' quality school life.

• 지식경영연구
• /
• 제24권3호
• /
• pp.127-148
• /
• 2023

전통적인 비즈니스 인텔리전스 환경은 빠르게 변하는 시장과 기하급수적으로 증가하는 데이터의 크기와 복잡성에 대처하는 데 한계를 보여왔다. 이에 기업들은 경쟁사 대비 더 빠르고 정확한 의사결정을 위해 사용자 주도 비즈니스 인텔리전스(Self-Service Business Intelligence) 환경으로의 변모를 요구받고 있다. 그러나 실제 기업 현장에서는 사용자 주도 비즈니스 인텔리전스 환경 구축과 운영에 어려움을 겪고 있으며, 참고할 만한 사례를 포함하여 성공적인 사용자 주도 비즈니스 인텔리전스에 관한 연구가 부족하다. 이에 본 연구에서는 비즈니스 인텔리전스 시스템의 핵심성공요인에 관한 기존 연구 방법론을 기반으로, 국내 3사 제조업 및 유통업체의 비즈니스 인텔리전스 개발 과정 및 활용 사례를 상세하고 깊이 있게 분석하였다. 조직-프로세스-기술 측면 7가지 핵심 성공요인에 대해 개발 목적과 구현 전략이 상이한 세가지 국내 사례를 비교 분석함으로써 비즈니스 인텔리전스 성공모델의 국내 기업 적용 가능성과 도입 전략의 시사점을 도출한다. 해당 프로젝트를 주도한 전문가들의 심층 인터뷰와 도입효과 평가를 통한 심층 비교 분석은, 사용자 주도 비즈니스 인텔리전스의 구체적인 개발 과정과 난제, 활용에 대한 풍부한 시사점을 제공하고 기업의 비즈니스 인텔리전스 활성화와 사용자 주도 비즈니스 인텔리전스 고도화에 기여할 것으로 기대된다.