• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.275-284
• /
• 2023

Gene expression data can be utilized in various studies, including the prediction of disease prognosis. However, there are challenges associated with collecting enough data due to cost constraints. In this paper, we propose a gene expression data generation model based on Conditional Variational Autoencoder. Our results demonstrate that the proposed model generates synthetic data with superior quality compared to two other state-of-the-art models for gene expression data generation, namely the Wasserstein Generative Adversarial Network with Gradient Penalty based model and the structured data generation models CTGAN and TVAE.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.124-130
• /
• 2021

기계요약의 사실 불일치는 생성된 요약이 원문과 다른 사실 정보를 전달하는 현상이며, 특히 개체명이 잘못 사용되었을 때 기계요약의 신뢰성을 크게 훼손한다. 개체명의 수정을 위해서는 두 가지 작업을 수행해야한다. 먼저 요약 내 각 개체명이 올바르게 쓰였는지 판별을 해야하며, 이후 잘못된 개체명을 맞게 고치는 작업이 필요하다. 본 논문에서는 두 가지 작업 모두 각 개체명을 문맥적으로 이해함으로써 해결할 수 있다고 가정하고, 이에 따라 두 작업에 대한 다중 작업 학습 방법을 제안한다. 제안한 방법을 통해 학습한 모델은 생성된 기계요약에 대한 후처리 교정을 수행할 수 있다. 제안 모델을 평가하기 위해 강제적으로 개체명을 훼손시킨 요약데이터와 기계 요약 데이터에 대해서 성능을 평가 하였으며, 다른 개체명 수정 모델과 비교하였다. 제안모델은 개체명 수준에서 92.9%의 교정 정확도를 달성했으며, KoBART 요약모델이 만든 기계요약의 사실 정확도 4.88% 포인트 향상시켰다.

• Annual Conference of KIPS
• /
• 2021.11a
• /
• pp.887-890
• /
• 2021

최근 AI 를 활용한 의료 진단 솔루션 시장이 크게 성장함에 따라 의료 인공지능 기술에 대한 대학 교육에 대한 수요가 증가하고 있지만, 개인정보 유출의 위험성 등으로 인하여 의료 데이터를 대학 교육에 활용하기 어려운 실정이다. 본 논문에서는 실제 의료 데이터 대신 생성적 적대 신경망(GAN)으로 합성된 흉부 X-ray 영상을 활용한 의료 인공지능 교육 모델의 사례를 제시한다. 프로메디우스(주)에 의해 제공받은 흉부 X-ray 합성영상을 사용하여, VGG-16 모델을 훈련하고 성능을 검증 및 평가하며 미세조정을 통해 성능을 개선하는 교육 모델을 구성하였다. 또한 교육모델이 의료 인공지능에 대한 학생들의 이해력 향상에 기여한 효과를 정량적으로 평가하였다.

• Communications of Mathematical Education
• /
• v.38 no.1
• /
• pp.49-67
• /
• 2024

Recent interest in the diverse applications of artificial intelligence (AI) language models has highlighted the need to explore didactical uses in mathematics education. AI language models, capable of natural language processing, show promise in solving mathematical word problems. This study tested the capability of ChatGPT, an AI language model, to solve word problems from elementary school textbooks, and analyzed both the solutions and errors made. The results showed that the AI language model achieved an accuracy rate of 81.08%, with errors in problem comprehension, equation formulation, and calculation. Based on this analysis of solution processes and error types, the study suggests implications for the didactical application of AI language models in education.

• Annual Conference of KIPS
• /
• 2024.05a
• /
• pp.768-771
• /
• 2024

인간의 산업 활동으로 인하여 동물들의 생존이 위협받으면서, 동물의 서식 분포를 효과적으로 파악할 수 있는 자동 야생동물 모니터링 기술의 필요성이 점점 더 커지고 있다. 그중에서도 동물 소리 분류 기술은 시각적으로 식별이 어려운 동물에게도 효과적으로 적용할 수 있는 장점으로 인하여 널리 사용되고 있다. 최근 심층학습 기반의 분류 모델들이 좋은 판별 성능을 보여주고 있어 동물 소리 분류에 많이 사용되고 있지만, 희귀종과 같이 개체 수가 적어 데이터가 부족한 경우에는 학습이 제대로 이루어지지 않을 수 있다. 또한, 이러한 모델들은 모델 내부에서 일어나는 추론 과정을 알 수 없어 결과를 완전히 신뢰하고 사용하는 데 제약이 따른다. 이에 본 논문에서는 전이 학습을 통해 데이터 부족 문제를 고려하고, SHAP을 이용하여 분류 모델의 추론 과정을 해석하는 설명가능한 동물 소리 분류 기법을 제안한다. 실험 결과, 제안하는 기법은 지도 학습을 한 경우보다 분류 성능이 향상됨을 확인하였으며, SHAP 분석을 통해 모델의 분류 근거를 이해할 수 있었다.

• Journal of Digital Convergence
• /
• v.12 no.9
• /
• pp.123-131
• /
• 2014

The demand of the real-time data was promoted by significant development of network and IT technology. In particular, the entry of an aging society and income growth increase the demand for personal health related data which attempt to provide various and evolutional healthcare services by several healthcare institutions. Especially the presentation of the medical examination result is the most basic healthcare services which should be expressed to maximize understanding in personal health records for their own health. However according to absence of systematic visualization framework and visualization model, intuitive understanding of healthcare related data is difficult. Cosequently In this study, customized visualization representation based on the results of medical examination was provided to aviod consistent format for health examinee and establish a variety of data representations.

• Journal of The Korean Association of Information Education
• /
• v.19 no.1
• /
• pp.21-30
• /
• 2015

Information and knowledge society in the 21st century computer education is very important. Computer programming education in computer education is very important. There are very few teaching and learning model of computer programming education. In this paper, we develop a self-regulated learning model for students to be self-regulated learning. In this study, we propose self-regulated learning elements, a self-regulated learning steps and self-regulated learning modele. Self-regulated learning elements are task level, generalized level, and efficiency level. Self-regulated learning phases are problem understanding, design, and coding, testing, and maintenance. Self-regulated learning models are to copy, to modify, create, and to challenge. The results of this study are as follows. At Correlations between learning elements and achievement, generalized level, and efficiency level are higher than the task level. At Correlations between learning and achievement, Understanding and design stages are higher than the other stages. At Correlations between learning model and achievement, to transform, to create, and to challenge are higher than to copy.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.2
• /
• pp.858-867
• /
• 2013

Hardware and software field are developed by environment of MPSOC. Also it is still working with economic world and academic world. This study focus on software side and try to classify from parallel programming design world. It can be divided by three; Data, Tasks, and Data flow model. Then we used Petri Net to CUDA and HOPES programmer and found how much they understand parallel programming for each side. We focus on two sides and what is different between their experience. Petri Net is easy to descript parallel program or parallel design pattern for Task, Data, and Hybird. This research can explain how they know and how much they know about parallel programming.

• The KIPS Transactions:PartD
• /
• v.8D no.2
• /
• pp.166-174
• /
• 2001

Lately computing environment is changing into integrating open system. This paper proposes Integrated Management Model to improve productivity about new software development. The model is divided by Management Model to deal with the rapidly changing environment effectively into three layers: the first layer classifies and displays information to users, the users, the second layer controls function, the integration and management layer, and the last layer manages data, the objects management storage layer. So it designs of Efficient Object Management Repository Using Integration Management Model. This might support afterward prototyping in maximizing the reuse of software, which is advantage to the integration of the system, and in promoting its productivity.

• Journal of KIISE
• /
• v.42 no.3
• /
• pp.341-360
• /
• 2015

While architectural patterns provide software development solutions by providing schemas for structural organizations of software systems based on empirical knowledge, Jackson's problem frames provide a method of analyzing software problems. Problem frames are useful to understanding the software development problem, by putting emphasis on the problem domain, rather than on the solution space. Research exists that relates problem frames and software architecture, but most of this research uses problem frames only to understand given problems. Moreover, none of the existing research derives architectural patterns by considering both problem frames and quality attributes. In this paper, we propose a software architecture design method for pattern-based architecture design, by matching problem frames and architectural patterns. To that end, our approach first develops the problem model based on the problem frames approach, and then uses it to match with candidate architectural patterns, from the perspectives of both functionality, and quality attributes. Functional matching uses the problem frame diagram to match the problem model of an architectural pattern. We conduct a case study to show that our approach can systematically decide the right architectural patterns, and provide a basis for fine-grained software architecture design.