• 디지털산업정보학회논문지
• /
• 제19권4호
• /
• pp.45-52
• /
• 2023

With the advent of deep learning, Artificial Intelligence (AI) technology has experienced rapid advancements, extending its application across various industrial sectors. However, the focus has shifted from the independent use of AI technology to its dispersion and proliferation through the open AI ecosystem. This shift signifies the transition from a phase of research and development to an era where AI technology is becoming widely accessible to the general public. However, as this dispersion continues, there is an increasing demand for the verification of outcomes derived from AI technologies. Causal AI applies the traditional concept of causal inference to AI, allowing not only the analysis of data correlations but also the derivation of the causes of the results, thereby obtaining the optimal output values. Causal AI technology addresses these limitations by applying the theory of causal inference to machine learning and deep learning to derive the basis of the analysis results. This paper analyzes recent cases of causal AI technology and presents the major tasks and directions of causal AI, extracting patterns between data using the correlation between them and presenting the results of the analysis.

• 농업과학연구
• /
• 제42권1호
• /
• pp.15-22
• /
• 2015

본 실험은 imazosulfuron+fentrazamide 혼합제가 벼의 생육에 미치는 영향을 알아보고자 수행하였다. Imazosulfuron+fentrazamide SC 처리 시 벼의 이앙심도는 3 cm 이상, 사질양토나 식양토를 이용하는 것이 바람직하다. 담수직파 재배의 경우 imazosulfuron+fentrazamide SC의 파종 전처리는 25+100 g ai/ha로 적어도 파종 10일 전에 처리하며, 파종후 처리에서는 약량이 증가하여도 파종 15일 이후에 처리하면 약해를 나타내지 않을 것으로 판단된다. 기계이앙 재배의 경우 imazosulfuron+fentrazamide GR의 약량에 따른 약해는 보이지 않으나 이앙 5일 후 처리하여야 벼 생육에 안전할 것으로 판단된다. 체계처리의 경우 파종 3일 전 25+100 g ai/ha이나 50+200 g ai/ha으로 처리한 후 이앙 15일 또는 20일에 75+300 g ai/ha로 처리할 경우 잡초방제의 효과를 높이고 벼 생육에는 안전한 방법으로 사료된다.

• 한국잡초학회지
• /
• 제18권2호
• /
• pp.106-115
• /
• 1998

담수표면산파재배시 파종 7~10일전에 oxadiazon, molinate, thiobencarb를 처리하여 앵미와 피에 대한 방제 효과 및 재배벼에 대한 영향을 조사하였다. oxadiazon 처리구 중에 특히 72g ai/10a이상의 고약량구에서는 환경조건에 따라 초기 입모지연 등의 약해증상이 나타날 수도 있으나, 이는 경시적으로 회복되어 그후의 생육에는 지장이 없었다. 따라서 약해에 대한 안전성면에서 60g ai/10a 이하가 적정량으로 생각된다. Molinate와 thiobencarb 처리구는 각각 225~400, 210~420g ai/10a 약량수준으로 처리하였는데 거의 약해가 없었다. 앵미에 대한 효과는 제초제의 종류 및 약량에 따라 차이가 있었는데, oxadiazon의 경우는 처리량이 60g ai/10a이상에서 비교적 우수한 방제율을 나타냈다. Molinate와 thiobencarb는 약량이 증가되면서 앵미의 방제효과는 증가되었으며, 두 약제 모두 300g ai/10a이상의 약량에서 비교적 양호한 방제율을 나타냈다. 피에 대한 효과는 공시 제초제 모두 90~100% 범위의 우수한 효과를 보였다. 실험을 실시한 모든 포장에서 공시한 3가지의 파종전 제초제를 처리하여 약해로 인한 수량감소를 보인 포장은 한군데도 없었다. 폿트실험에서 파종 1일 후 배수한 경우가 착근할 때까지 계속 담수상태를 유지한 경우보다 약해도 적고 입모수도 많았으며 초기생육도 양호하였다.

• 패션비즈니스
• /
• 제26권2호
• /
• pp.28-47
• /
• 2022

Rapid development of information and communication technology is leading the digital transformation (hereinafter, DT) of various industries. At this point in rapid online transition, fashion manufacturers operating offline-oriented businesses have become highly interested in DT and artificial intelligence (hereinafter AI), which leads DT. The purpose of this study is to examine the development status and application case of AI-based digital technology developed for the fashion industry, and to examine the DT stage and AI application status of domestic fashion manufacturers. Hence, in-depth interviews were conducted with five domestic IT companies developing AI technology for the fashion industry and six domestic fashion manufacturers applying AI technology. After analyzing interviews, study results were as follows: The seven major AI technologies leading the DT of the fashion industry were fashion image recognition, trend analysis, prediction & visualization, automated fashion design generation, demand forecast & optimizing inventory, optimizing logistics, curation, and ad-tech. It was found that domestic fashion manufacturers were striving for innovative changes through DT although the DT stage varied from company to company. This study is of academic significance as it organized technologies specialized in fashion business by analyzing AI-based digitization element technologies that lead DT in the fashion industry. It is also expected to serve as basic study when DT and AI technology development are applied to the fashion field so that traditional domestic fashion manufacturers showing low growth can rise again.

• 대한의생명과학회지
• /
• 제29권2호
• /
• pp.53-57
• /
• 2023

The main objective of pathologists is to achieve accurate lesion diagnoses, which has become increasingly challenging due to the growing number of pathological slides that need to be examined. However, using digital technology has made it easier to complete this task compared to older methods. Digital pathology is a specialized field that manages data from digitized specimen slides, utilizing image processing technology to automate and improve analysis. It aims to enhance the precision, reproducibility, and standardization of pathology-based researches, preclinical, and clinical trials through the sophisticated techniques it employs. The advent of whole slide imaging (WSI) technology is revolutionizing the pathology field by replacing glass slides as the primary method of pathology evaluation. Image processing technology that utilizes WSI is being implemented to automate and enhance analysis. Artificial intelligence (AI) algorithms are being developed to assist pathologic diagnosis and detection and segmentation of specific objects. Application of AI-based digital pathology in biomedical researches is classified into four areas: diagnosis and rapid peer review, quantification, prognosis prediction, and education. AI-based digital pathology can result in a higher accuracy rate for lesion diagnosis than using either a pathologist or AI alone. Combining AI with pathologists can enhance and standardize pathology-based investigations, reducing the time and cost required for pathologists to screen tissue slides for abnormalities. And AI-based digital pathology can identify and quantify structures in tissues. Lastly, it can help predict and monitor disease progression and response to therapy, contributing to personalized medicine.

• 시스템엔지니어링학술지
• /
• 제18권1호
• /
• pp.90-98
• /
• 2022

On February 12, 2019, the U.S. Department of Defense newly established and announced the "Defense AI Strategy" to accelerate the use of artificial intelligence (AI) technology for military purposes. As China and Russia invested heavily in AI for military purposes, the U.S. was concerned that it could eventually lose its advantage in AI technology to China and Russia. In response, China and Russia, which are hostile countries, and especially China, are speeding up the development of new military theories related to the overall construction and operation of the Chinese military based on AI. With the rapid development of AI technology, major advanced countries such as the U.S. and China are actively researching the application of AI technology, but most existing studies do not address the special topic of defense. Fortunately, the "Future Defense 2030 Technology Strategy" classified AI technology fields from a defense perspective and analyzed advanced overseas cases to present a roadmap in detail, but it has limitations in comparing private technology-oriented benchmarking and AI technology's maturity level. Therefore, this study tried to overcome the limitations of the "Future Defense 2030 Technology Strategy" by comparing and analyzing Chinese and U.S. military research cases and evaluating the maturity level of military use of AI technology, not AI technology itself.

• 한국응용곤충학회지
• /
• 제12권2호
• /
• pp.63-70
• /
• 1973

수도에 대하여 본질적으로 근부흡수선택성 또는 안전성이 있다고 생각되는 몇 가지 약제들에 대하여 MO 모내기 후 처리를 대조로 SiCL 토양조건에서 시용약량, 혼화심도, 처리시기를 달리하여 모내기 전 토양혼화처리 (Ronstar, Saturn, TOK, Saturn-S)와 모내기 전 토양표면처리(Machete, PCP, MON-0385)를 실시하였던 바 그 결과를 요약하면 다음과 같다. 1. 제초효과 1차 조사결과(모내기 27일후 조사) 처리구 모두 $90-99.7\%$의 우수한 제초효과를 나타냈다. 2차 조사시(모내기 73일후)까지 $90\%$ 이상의 제초효과를 유지한 plot는 Ronstar 전 처리구 및 Saturn-S 3-4kg prod./10a 구였다. 다소 제초효과가 저조한 구는 MON-0385 175g ai/10a구와 TOK 280g ai/10a 혼화구였다. 2. 초기약해 및 생육관계 PCP 1,000g ai/10a의 모내기 전 토양표면처리구가 눈에 뛸 정도로 약해를 내었으나 처리 50여일 후 까지는 회복이 되었다. Saturn-S 4kg prod./10a구에서 초기 국부적으로 미해가 있었으나 곧 회복이 되었고 그 이외의 처리구에 있어서는 거의 약해를 인정할 수 없었다. 3.수량 방임구가 $11.4\%$ 수량감소를 나타낸 이외에는 관행구에 비하여 통계적으로 유의차를 나타낸 Plot는 없었다. 특히 관행구보다 증수된 plot는 Machete 210g ai/10a 1DBT 및 2DBT, Ronstar 60g ai/10a 2.5cm 혼화구 및 12cm 혼화구, Saturn-S 3kg prod./10a 혼화구 그리고 MON-0385 175g ai/10a 1DBT구 등이었다.

• 지능정보연구
• /
• 제29권4호
• /
• pp.129-164
• /
• 2023

최근 생성형 AI 기술의 발전으로 인해 대형 언어 모델(Large Language Model, LLM)의 활용 및 도입이 확대되고 있는 상황에서 기존 연구들은 기업내부 데이터의 활용에 대한 실제 적용사례나 구현방법을 찾아보기 힘들다. 이에 따라 본 연구에서는 가장 많이 이용되고 있는 LangChain 프레임워크를 이용한 LLM 애플리케이션 아키텍처를 활용하여 생성형 AI 서비스를 구현하는 방법을 제시한다. 이를 위해 LLM의 활용을 중심으로, 정보 부족 문제를 극복하는 다양한 방법을 검토하고 구체적인 해결책을 제시하였다. 이를 위해 파인튜닝이나 직접 문서 정보를 활용하는 방법을 분석하며, 이러한 문제를 해결하기 위한 RAG 모델을 활용한 정보 저장 및 검색 방법에 대해 주요단계에 대해 자세하게 살펴본다. 특히, RAG 모델을 활용하여 정보를 벡터저장소에 저장하고 검색하기 위한 방법으로 유사문맥 추천 및 QA시스템을 활용하였다. 또한 구체적인 작동 방식과 주요한 구현 단계 및 사례를 구현소스 및 사용자 인터페이스까지 제시하여 생성형 AI 기술에 대한 이해를 높였다. 이를 통해 LLM을 활용한 기업내 서비스 구현에 적극적으로 활용할 수 있도록 하는데 의미와 가치가 있다.

• International journal of advanced smart convergence
• /
• 제12권3호
• /
• pp.186-191
• /
• 2023

This study would investigate the generative AIs currently in service in the era of hyperscale AIs and explore measures for the use of generative AIs, focusing on 'ChatGPT,' which has received attention as a leader of generative AIs. Among the various generative AIs, this study selected ChatGPT, which has rich application cases to conduct research, investigation, and use. This study investigated the concept, learning principle, and features of ChatGPT, identified the algorithm of conversational AI as one of the specific cases and checked how it is used. In addition, by comparing various cases of the application of conversational AIs such as Google's Bard and MS's NewBing, this study sought efficient ways to utilize them through the collected cases and conducted research on the limitations of conversational AI and precautions for its use. If connected to city-related databases, it can provide information on city infrastructure, transportation systems, and public services, so residents can easily get the information they need. We want to apply this research to enrich the lives of our citizens.

• Journal of Digestive Cancer Research
• /
• 제12권1호
• /
• 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.