• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.532-535
• /
• 2021

다양한 SNS 플랫폼이 등장하고, 이용자 수가 급증함에 따라 온라인에서 얻을 수 있는 정보의 활용 가치가 높아지고 있다. 문장은 자연어 처리 시스템의 기본적인 단위이므로 주어진 문서로부터 문장의 경계를 인식하는 작업이 필수적이다. 공개된 문장 경계 인식기는 SNS 문서에서 좋은 성능을 보이지 않는다. 본 논문에서는 문어체로 구성된 일반 문서뿐 아니라 SNS 문서에서 사용할 수 있는 문장 경계 인식기를 제안한다. 본 논문에서는 SNS 문서에 적용하기 위해 다음과 같은 두 가지를 개선한다. 1) 학습 말뭉치를 일반문서와 SNS 문서 두 영역으로 확장하고, 2) 이모티콘을 사용하는 SNS 문서의 특징을 반영하는 어절의 유형을 자질로 추가하여 성능을 개선한다. 실험을 통해서 추가된 자질의 기여도를 분석하고, 또한 기존의 한국어 문장 경계 인식기와 제안한 모델의 성능을 비교·분석하였다. 개선된 모델은 일반 문서에서 99.1%의 재현율을 보이며, SNS 문서에서 88.4%의 재현율을 보였다. 두 영역 모두에서 문장 경계 인식이 잘 이루어지는 것을 확인할 수 있었다.

• Korean Journal of Cleft Lip And Palate
• /
• v.2 no.1_2
• /
• pp.15-22
• /
• 1999

It is well known that the postoperative skeletal instability after Le Fort I osteotomy for advancement of maxilla in the cleft patients is one of the major surgical problems. So we had tried to compare the amount of relapse after Le Fort I advancement surgery in the horizontal and vertical positional change, angular change of reference points between cleft patients and non-cleft patients. Longitudinal records of 10 consecutive cleft patients (test group) and 20 non-cleft patients (control group) were analyzed. Lateral cephalograms were taken preoperatively, immediately postoperatively, and 2, 6, 12 months postoperatively. We measured horizontal and vertical changes (ANS, PNS, AI) and angular change (SNA) of the reference points and lines. In the test group, horizontal relapse of ANS, PNS, AI point are 36.4%, 37.5%, 32.0% respectively at 12 months postoperatively. The vertical relapse of ANS, PNS, AI are 25.3%, 32.3%, 39.1% respectively at 12 months postoperatively. The angular change of SNA is 33.6% at 12 months postoperatively. In the control group, horizontal relapse of ANS, PNS, AI point are 23.8%, 30.2%, 21.7% respectively at 12 months postoperatively. The vertical relapse of ANS, PNS, AI are 22.7%, 27.3%, 25.1% respectively at 12 months postoperatively. The angular change of SNA is 22.2% at 12 months postoperatively. The cleft patients have a larger tendency of skeletal and dental relapse compared with non-cleft patients after Le Fort I surgery. So the oral and maxillofacial surgeons must keep in mind these facts in order to minimize the relapse phenomenon from the beginning of surgical planning to postoperative care.

• Tunnel and Underground Space
• /
• v.31 no.1
• /
• pp.25-40
• /
• 2021

As the era of Industry 4.0 arrives, the researches using artificial intelligence in the field of rock engineering as well have increased. For a better understanding and availability of AI, this paper analyzed the types of algorithms and how to apply them to the research papers where AI is applied among domestic and international studies related to tunnels, blasting and mines that are major objects in which rock engineering techniques are applied. The analysis results show that the main specific fields in which AI is applied are rock mass classification and prediction of TBM advance rate as well as geological condition ahead of TBM in a tunnel field, prediction of fragmentation and flyrock in a blasting field, and the evaluation of subsidence risk in abandoned mines. Of various AI algorithms, an artificial neural network is overwhelmingly applied among investigated fields. To enhance the credibility and accuracy of a study result, an accurate and thorough understanding on AI algorithms that a researcher wants to use is essential, and it is expected that to solve various problems in the rock engineering fields which have difficulty in approaching or analyzing at present, research ideas using not only machine learning but also deep learning such as CNN or RNN will increase.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.8
• /
• pp.1013-1018
• /
• 2021

Due to the recent accident caused by the automated vehicle, discussions on the ethical aspects of AI have been actively underway. This paper confirms that AI is inevitably connected to ethical components through the concepts and techniques related to robots-AI, and argues that ethical aspects are built-in, not post facto. Furthermore, this devises a solution to the trolley dilemma that can serve as a clue to ethical problems associated with automated vehicles. Preferentially, that process contains writing Bayesian networks. Next, only important and influential data are left after the pre-processing stage, and crowd-sourcing & extrapolation is used to calculate the exact figures of the networks. Through this process, this argues that humans' subjects are certainly included in implementing algorithms and models and discusses the necessity and direction of engineering liberal arts, especially education of ethics that distinguished from major education to prevent distortions and biases abouts AI systems.

• Smart Media Journal
• /
• v.11 no.9
• /
• pp.56-63
• /
• 2022

Recently, the frequency and range of algae occurrence in major rivers and lakes are increasing due to the increase in water temperature due to climate change, the inflow of excessive nutrients, and changes in the river environment. Abnormal algae include green algae and red algae. Green algae is a phenomenon in which blue-green algae such as chlorophyll (Chl-a) in the water grow excessively and the color of the water changes to dark green. In this study, a 3D virtual world of digital twin was built to monitor and control water quality information measured in ecological rivers and lakes in the living environment in real time from a remote location, and a sensor measuring device for water quality information based on the Internet of Things (IOT) sensor. We propose to build a smart water environment service platform that can provide algae warning and water quality forecasting by predicting the causes and spread patterns of water pollution such as algae based on AI machine learning-based collected data analysis.

• Genomics & Informatics
• /
• v.21 no.2
• /
• pp.20.1-20.10
• /
• 2023

Aromatase inhibitors (AI) are drugs that are widely used in treating estrogen receptor (ER)-positive breast cancer patients. Drug resistance is a major obstacle to aromatase inhibition therapy. There are diverse reasons behind acquired AI resistance. This study aims at identifying the plausible cause of acquired AI resistance in patients administered with non-steroidal AIs (anastrozole and letrozole). We used genomic, transcriptomic, epigenetic, and mutation data of breast invasive carcinoma from The Cancer Genomic Atlas database. The data was then separated into sensitive and resistant sets based on patients' responsiveness to the non-steroidal AIs. A sensitive set of 150 patients and a resistant set of 172 patients were included for the study. These data were collectively analyzed to probe into the factors that might be responsible for AI resistance. We identified 17 differentially regulated genes (DEGs) among the two groups. Then, methylation, mutation, miRNA, copy number variation, and pathway analyses were performed for these DEGs. The top mutated genes (FGFR3, CDKN2A, RNF208, MAPK4, MAPK15, HSD3B1, CRYBB2, CDC20B, TP53TG5, and MAPK8IP3) were predicted. We also identified a key miRNA - hsa-mir-1264 regulating the expression of CDC20B. Pathway analysis revealed HSD3B1 to be involved in estrogen biosynthesis. This study reveals the involvement of key genes that might be associated with the development of AI resistance in ER-positive breast cancers and hence may act as a potential prognostic and diagnostic biomarker for these patients.

• Korean Journal of Community Nutrition
• /
• v.29 no.2
• /
• pp.144-155
• /
• 2024

Objectives: This study evaluated dietary intake and food sources of essential fatty acids in Korean adolescents. Methods: This study was comprised of 3,932 adolescents (9-18 years) who participated in the 2016-2021 Korea National Health and Nutrition Examination Surveys. Dietary intake and food sources of essential fatty acids, including alpha-linolenic acid (ALA), eicosapentaenoic acid (EPA), docosahexaenoic acid (DHA), and linoleic acid (LA) were evaluated using data obtained from one-day 24-hour dietary recall. The proportions of adolescents consuming ALA, EPA + DHA, and LA above or below the adequate intake (AI) of the 2020 Dietary Reference Intakes for Koreans were calculated. All statistical analyses accounted for the complex sampling design effect and appropriate sample weights. Results: The mean intakes of ALA, EPA, DHA, and LA among Korean adolescents were 1.29 g/day, 69.6 mg/day, 166.0 mg/day, and 11.1 g/day, respectively. Boys had higher intakes of all essential fatty acids compared to girls. By age group, adolescents aged 15-18 years showed lower intakes of EPA and DHA compared to adolescents in younger age groups. The 9-11-year-old adolescents had lower intakes of ALA and LA than older adolescents. The proportions of adolescents who consumed more than AI were 35.7% for ALA, 30.4% for EPA + DHA, and 41.5% for LA. Adherence to the AI for ALA did not differ by sex or age group, although boys showed a lower adherence to the AI for EPA + DHA than girls. Major food sources for ALA and LA were plant-based oils, mayonnaise, pork, and eggs. Mackerel was the most significant contributor to EPA and DHA intake (EPA, 22.6%; DHA, 22.2%), followed by laver, squid, and anchovy. Conclusions: The proportion of Korean adolescents who consumed EPA + DHA more than AI was low. Our findings highlight that nutrition education emphasizing an intake of essential fatty acids from healthy food sources is needed among Korean adolescents.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.4
• /
• pp.771-780
• /
• 2024

In this study, we implemented a real-time pest detection and prediction system for a strawberry farm using a computer vision model based on the YOLOv5 architecture and an Isolation Forest Classifier. The model performance evaluation showed that the YOLOv5 model achieved a mean average precision (mAP 0.5) of 78.7%, an accuracy of 92.8%, a recall of 90.0%, and an F1-score of 76%, indicating high predictive performance. This system was designed to be applicable not only to strawberry farms but also to other crops and various environments. Based on data collected from a tomato farm, a new AI model was trained, resulting in a prediction accuracy of over 85% for major diseases such as late blight and yellow leaf curl virus. Compared to the previous model, this represented an improvement of more than 10% in prediction accuracy.

• Journal of Digital Convergence
• /
• v.18 no.5
• /
• pp.75-87
• /
• 2020

The present study determined new value that can be created through the convergence between artificial intelligence technology (AIT) and all industries by deriving and thoroughly analyzing major issues related to artificial intelligence (AI). This study analyzes domestic articles related to AI using topic modeling method based on LDA algorithm. Keywords were extracted from 3,889 articles of eleven metropolitan newspapers, eight business newspapers and major broadcasting companies; articles were selected by searching for the keyword "artificial intelligence". Keywords were extracted by optimizing the relevance parameter λ to improve the measure of pointwise mutual information (PMI), which shows the association among the keywords of each topic, and topic names were inferred from keywords based on valid evidence. The extracted topics widely showed changes occurring throughout society, economy, industries, culture, and the support policy and vision of the government.

• Journal of Industrial Convergence
• /
• v.20 no.5
• /
• pp.83-92
• /
• 2022

As cases of social and ethical problems caused by artificial intelligence technology have occurred, artificial intelligence ethics are drawing attention along with social interest in the risks and side effects of artificial intelligence. Artificial intelligence ethics should not just be known and felt, but should be actionable and practiced. Therefore, this study proposes an artificial intelligence ethics education model to strengthen the practical ability of artificial intelligence ethics. The artificial intelligence ethics education model derived educational goals and problem-solving processes using artificial intelligence through existing research analysis, applied teaching and learning methods to strengthen practical skills, and compared and analyzed the existing artificial intelligence education model. The artificial intelligence ethics education model proposed in this paper aims to cultivate computing thinking skills and strengthen the practical ability of artificial intelligence ethics. To this end, the problem-solving process using artificial intelligence was presented in six stages, and artificial intelligence ethical factors reflecting the characteristics of artificial intelligence were derived and applied to the problem-solving process. In addition, it was designed to unconsciously check the ethical standards of artificial intelligence through preand post-evaluation of artificial intelligence ethics and apply learner-centered education and learning methods to make learners' ethical practices a habit. The artificial intelligence ethics education model developed through this study is expected to be artificial intelligence education that leads to practice by developing computing thinking skills.