• 대한한의학원전학회지
• /
• 제36권2호
• /
• pp.23-34
• /
• 2023

Objectives : We propose a method to disassemble Traditional East Asian Medicine herbal formulas using machine learning. Methods : After creating a model using Byte Pair Encoding(BPE) and G-Score, the model was trained with training data. Afterwards, the learned model was applied to the test data, of which the results were compared with expert opinion. Results : The results acquired through the model were not significantly different from those of modern expert opinions. However, there were cases where the meaning was partially unclear, while there were cases where new knowledge could be obtained through the disassembling process. Conclusions : It is expected that disassembling herbal formulas through the proposed method in this study will help save resources required to understand complex ones.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2021년도 제33회 한글 및 한국어 정보처리 학술대회
• /
• pp.629-632
• /
• 2021

기계 번역(machine translation)은 자연 언어로 된 텍스트를 다른 언어로 자동 번역 하는 기술로, 최근에는 주로 신경망 기계 번역(Neural Machine Translation) 모델에 대한 연구가 진행되었다. 신경망 기계 번역은 일반적으로 자기회귀(autoregressive) 모델을 이용하며 기계 번역에서 좋은 성능을 보이지만, 병렬화할 수 없어 디코딩 속도가 느린 문제가 있다. 비자기회귀(non-autoregressive) 모델은 단어를 독립적으로 생성하며 병렬 계산이 가능해 자기회귀 모델에 비해 디코딩 속도가 상당히 빠른 장점이 있지만, 멀티모달리티(multimodality) 문제가 발생할 수 있다. 본 논문에서는 단어 정렬(word alignment)을 이용한 비자기회귀 신경망 기계 번역 모델을 제안하고, 제안한 모델을 한국어-영어 기계 번역에 적용하여 단어 정렬 정보가 어순이 다른 언어 간의 번역 성능 개선과 멀티모달리티 문제를 완화하는 데 도움이 됨을 보인다.

• Communications for Statistical Applications and Methods
• /
• 제31권3호
• /
• pp.279-289
• /
• 2024

Familial searching is a useful technique in a forensic investigation. Using genetic information, it is possible to identify individuals, determine familial relationships, and obtain racial/ethnic information. The total number of shared alleles (TNSA) and likelihood ratio (LR) methods have traditionally been used, and novel data-mining classification methods have recently been applied here as well. However, it is difficult to apply these methods to identify familial relationships above the third degree (e.g., uncle-nephew and first cousins). Therefore, we propose to apply a stacking ensemble machine learning algorithm to improve the accuracy of familial relationship identification. Using real data analysis, we obtain superior relationship identification results when applying meta-classifiers with a stacking algorithm rather than applying traditional TNSA or LR methods and data mining techniques.

• Journal of Korea Artificial Intelligence Association
• /
• 제1권1호
• /
• pp.17-21
• /
• 2023

The primary objective of this research is to utilize machine learning models to analyze factors tailored to each dataset for predicting mental health conditions. The study aims to develop appropriate models based on specific datasets, with the goal of accurately predicting mental health states through the analysis of distinct factors present in each dataset. This approach seeks to design more effective strategies for the prevention and intervention of depression, enhancing the quality of mental health services by providing personalized services tailored to individual circumstances. Overall, the research endeavors to advance the development of personalized mental health prediction models through data-driven factor analysis, contributing to the improvement of mental health services on an individualized basis.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.2676-2681
• /
• 2003

The Haptic Exploration Laboratory at The Johns Hopkins University is currently exploring many problems related to haptics (force and tactile information) in human-machine systems. We divide our work into two main areas: virtual environments and robot-assisted manipulation systems. Our interest in virtual environments focuses on reality-based modeling, in which measurements of the static and dynamic properties of actual objects are taken in order to produce realistic virtual environments. Thus, we must develop methods for acquiring data from real objects and populating pre-defined models. We also seek to create systems that can provide active manipulation assistance to the operator through haptic, visual, and audio cues. These systems may be teleoperated systems, which allow human users to operate in environments that would normally be inaccessible due to hazards, distance, or scale. Alternatively, cooperative manipulation systems allow a user and a robot to share a tool, allowing the user to guide or override the robot directly if necessary. Haptics in human-machine systems can have many applications, such as undersea and space operations, training for pilots and surgeons, and manufacturing. We focus much of our work on medical applications.

• Journal of Platform Technology
• /
• 제10권1호
• /
• pp.20-28
• /
• 2022

인공지능기반의 건강 데이터 검증은 임상 연구에 도움을 줄 뿐만 아니라, 새로운 치료법을 개발하는데 필수 요소가 되었다. 미국 식품의약 관리국이 의학진단 분야 중 인공지능을 이용하여 성인 당뇨병 환자의 경증 이상 당뇨병성 망막증을 감지하는 의료기기 마케팅을 승인한 이래, 인공지능을 이용한 테스트가 증가하고 있다. 본 연구에서는 구글에서 지원하는 Teachable Machine 을 이용하여 이미지 분류 기반의 인공지능모델을 생성하고, 학습을 통한 예측 모델을 완성하였다. 이는 현재 만성질환의 환자들 중 발생하는 안구 질환 중 백내장의 조기 발견하는데 용이하게 할 뿐만 아니라, 눈 건강을 위해 헬스케어 프로그램으로 안 질환 예방을 위한 디지털 개인건강 헬스케어 앱을 개발하기 위한 기초 연구로 진행되었다.

• 한국인공지능학회지
• /
• 제10권1호
• /
• pp.1-7
• /
• 2022

In this paper, a study was conducted to predict natural disasters in Afghanistan based on machine learning. Natural disasters need to be prepared not only in Korea but also in other vulnerable countries. Every year in Afghanistan, natural disasters(snow, earthquake, drought, flood) cause property and casualties. We decided to conduct research on this phenomenon because we thought that the damage would be small if we were to prepare for it. The Azure Machine Learning Studio used in the study has the advantage of being more visible and easier to use than other Machine Learning tools. Decision Forest is a model for classifying into decision tree types. Decision forest enables intuitive analysis as a model that is easy to analyze results and presents key variables and separation criteria. Also, since it is a nonparametric model, it is free to assume (normality, independence, equal dispersion) required by the statistical model. Finally, linear/non-linear relationships can be searched considering interactions between variables. Therefore, the study used decision forest. The study found that overall accuracy was 89 percent and average accuracy was 97 percent. Although the results of the experiment showed a little high accuracy, items with low natural disaster frequency were less accurate due to lack of learning. By learning and complementing more data, overall accuracy can be improved, and damage can be reduced by predicting natural disasters.

• International Journal of Computer Science & Network Security
• /
• 제23권11호
• /
• pp.183-189
• /
• 2023

A stroke is a medical disease where a blood vessel in the brain ruptures, causes damage to the brain. If the flow of blood and different nutrients to the brain is intermittent, symptoms may occur. Stroke is other reason for loss of life and widespread disorder. The prevalence of stroke is high in growing countries, with ischemic stroke being the high usual category. Many of the forewarning signs of stroke can be recognized the seriousness of a stroke can be reduced. Most of the earlier stroke detections and prediction models uses image examination tools like CT (Computed Tomography) scan or MRI (Magnetic Resonance Imaging) which are costly and difficult to use for actual-time recognition. Machine learning (ML) is a part of artificial intelligence (AI) that makes software applications to gain the exact accuracy to predict the end results not having to be directly involved to get the work done. In recent times ML algorithms have gained lot of attention due to their accurate results in medical fields. Hence in this work, Stroke disease identification system by using Machine Learning algorithm is presented. The ML algorithm used in this work is Artificial Neural Network (ANN). The result analysis of presented ML algorithm is compared with different ML algorithms. The performance of the presented approach is compared to find the better algorithm for stroke identification.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 신호처리소사이어티 추계학술대회 논문집
• /
• pp.221-224
• /
• 2003

Recently, TFT-LCD is widely used of medicine machine on the display devices. However, the display precision of TFT-LCD is 8 bits instead of 10 bits of CRT display. If the medical image have more than 8 bits, we must requantize the medical image. We propose an efficient method to reduce medical image from 10 bits into 8 bits by employing human visual perception. The proposed method shows good performance for the medical image display.

• 한국의학물리학회지:의학물리
• /
• 제23권4호
• /
• pp.326-332
• /
• 2012

최근 전 세계적인 원자로 시설의 감축으로 인한 수입 치료용 동위원소의 가격 상승으로 인하여 의료기관에서 근접치료기 운영에 문제가 되고 있다. 본 보고서에서는 국내에서 생산한 두 종류 Ir-192 선원(직경 4.5 mm와 1.1 mm)의 개발 과정과 기술 동향 대하여 제시하였다. 이 보고서의 내용이 근접치료기를 운영하는 의료기관에서 정책 수립에 도움이 되기를 바란다.