• Journal of the Korea Convergence Society
• /
• v.12 no.10
• /
• pp.27-35
• /
• 2021

Automatic post editing is a research field that aims to automatically correct errors in machine translation results. This research is mainly being focus on high resource language pairs, such as English-German. Recent APE studies are mainly adopting transfer learning based research, where pre-training language models, or translation models generated through self-supervised learning methodologies are utilized. While translation based APE model shows superior performance in recent researches, as such researches are conducted on the high resource languages, the same perspective cannot be directly applied to the low resource languages. In this work, we apply two transfer learning strategies to Korean-English APE studies and show that transfer learning with translation model can significantly improves APE performance.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.9
• /
• pp.421-428
• /
• 2024

Recently, services utilizing large-scale language models (LLMs) such as GPT-4 and LLaMA have been released, garnering significant attention. These models can respond fluently to various user queries, but their insufficient training on Korean data raises concerns about the potential to provide inaccurate information regarding Korean culture and language. In this study, we selected eight major publicly available models that have been trained on Korean data and evaluated their understanding of Korean culture using a dataset composed of five domains (Korean language comprehension and cultural aspects). The results showed that the commercial model HyperClovaX exhibited the best performance across all domains. Among the publicly available models, Bookworm demonstrated superior Korean language proficiency. Additionally, the LDCC-SOLAR model excelled in areas related to understanding Korean culture and language.

• Korean Journal of Materials Research
• /
• v.11 no.7
• /
• pp.615-621
• /
• 2001

We carried out the kinetic model calculations in order to estimate the nucleation rates for two kinds of half-loop dislocations in highly strained hetero-epitaxial growths; $60^{\circ}$dislocations and twinning dislocations. The surface defects and the stress concentration effects were considered in this model, and the remaining elastic strain of the epilayers with increasing film thickness was taken into account by using the modified Matthews' relation. The calculations showed that the stress concentration effect at surface imperfections is very important for describing the defect generation in highly mismatched epitaxial growth. This work also showed that the stress concentration effect determined the type of dislocation nucleating dominantly at early growth stages in accordance with our XTEM (cross-section transmission electron microscopy) defect observation.

• Journal of Convergence for Information Technology
• /
• v.12 no.4
• /
• pp.260-269
• /
• 2022

In this paper, We propose an anomaly detection model using deep neural network to automate the identification of outliers of the national air pollution measurement network data that is previously performed by experts. We generated training data by analyzing missing values and outliers of weather data provided by the Institute of Environmental Research and based on the BeatGAN model of the unsupervised learning method, we propose a new model by changing the kernel structure, adding the convolutional filter layer and the transposed convolutional filter layer to improve anomaly detection performance. In addition, by utilizing the generative features of the proposed model to implement and apply a retraining algorithm that generates new data and uses it for training, it was confirmed that the proposed model had the highest performance compared to the original BeatGAN models and other unsupervised learning model like Iforest and One Class SVM. Through this study, it was possible to suggest a method to improve the anomaly detection performance of proposed model while avoiding overfitting without additional cost in situations where training data are insufficient due to various factors such as sensor abnormalities and inspections in actual industrial sites.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.5
• /
• pp.31-38
• /
• 2024

In this paper, we propose an ASAP(AI-driven Service for Advertisement Production) application that provides a generative AI-based automatic advertising image production service. This application utilizes GPT-3.5 Turbo Instruct to generate suitable background mood and promotional copy based on user-entered keywords. It utilizes OpenAI's DALL·E 3 model and Stability AI's SDXL model to generate background images and text images based on these inputs. Furthermore, OCR technology is employed to improve the accuracy of text images, and all generated outputs are synthesized to create the final advertisement. Additionally, using the PILLOW and OpenCV libraries, text boxes are implemented to insert details such as phone numbers and business hours at the edges of promotional materials. This application offers small business owners who face difficulties in advertising production a simple and cost-effective solution.

• Journal of Platform Technology
• /
• v.11 no.6
• /
• pp.34-46
• /
• 2023

The design of non-pneumatic tires, which are created by filling the space between the wheel and the tread with elastomeric compounds or polygonal spokes, has become an important research topic in the automotive and aerospace industries. In this study, a system was designed for the design of non-pneumatic tires through the implementation of a generative adversarial network. We specifically examined factors that could impact the design, including the type of non-pneumatic tire, its intended usage environment, manufacturing techniques, distinctions from pneumatic tires, and how spoke design affects load distribution. Using OpenCV, various shapes and spoke configurations were generated as images, and a GAN model was trained on the projected GANs to generate shapes and spokes for non-pneumatic tire designs. The designed non-pneumatic tires were labeled as available or not, and a Vision Transformer image classification AI model was trained on these labels for classification purposes. Evaluation of the classification model show convergence to a near-zero loss and a 99% accuracy rate confirming the generation of non-pneumatic tire designs.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.8
• /
• pp.3295-3300
• /
• 2012

Three Dimensional finite element method (FEM) was used to obtain the stress intensity factor for subsurface cracks and surface cracks existing in inhomogeneous materials. A geometry model, i.e. a solid containing one or several 3D cracks is defined. Several distributions of local node density are chosen, and then automatically superposed on one another over the geometry model. Nodes are generated by the bubble packing, and ten-noded quadratic tetrahedral solid elements are generated by the Delaunay triangulation techniques. To examine accuracy and efficiency of the present system, the stress intensity factor for a semi-elliptical surface crack in a plate subjected to uniform tension is calculated, and compared with Raju-Newman's solutions. Then the system is applied to analyze interaction effects of two dissimilar semi-elliptical cracks in a plate subjected to uniform tension.

• Annual Conference of KIPS
• /
• 2000.10a
• /
• pp.27-30
• /
• 2000

최근 전산 환경은 통합되는 개방형 시스템으로 변모하고 있다. 서로 다른 platform을 기반으로 한 client들과의 연동을 위해서, 각 platform에 따른 application이 개발되어야 했다. 이러한 문제점을 극복하기 위해 이 기종간의 시스템을 통합할 수 있는 통합 Middlware의 선정이 필요하다. 따라서, 본 논문에서는 객체지향 소프트웨어 공학 프로세스에 의해 생성되는 산출물을 객체 형태로 통합 관리하고 객체들을 효율적으로 관리해 주는 통합 객체 관리 모델을 제안한다. 이 모델로 기존의 시스템을 재사용하고 급변하는 소프트웨어 산업에 능동적으로 대체와 소프트웨어 개발에 시간을 함으로써 현존하는 다양 DB군들을 최소한의 코드 수정을 통하여 구동할 수 있게 함으로써 경제성을 높이는 것이 본 논문의 목적이다. 따라서 이 모델을 중심으로 자동차 관리 서비스 도구(AutoMobile Customer Service Shop: AMOSS)를 구현한다.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.10
• /
• pp.3064-3074
• /
• 2000

Lately computing environment is changing into integrating open system Some corporations and research institutions are still using old codes and not dealing with the rapid canging environment actively. Also several software developers have difficulties with the problems of productivity and translating old codes. This paper proposes Integration Object Management Model to deal with the rapid changing environment effectively and to improe productivity about new software development. The model is divided into three layers the first layer classifies and displays information to users, the second layer controls function, the integrationand management layer, and the last layer manages data, the object management stroage later. So it designs and implenments F77/J++ Generator system(FORTRAN77/Java code generator) for Integrated Object Management Model. The generator helps to translate old codes into new codes in redesigning the business and promoting productivity. In consists of nine-stage strategies using reengineering. This might support agterward protolyping in maximizing the reuse of software, which is advanlage to the integrationof the system and in pro,oting its productivity.

• Journal of the Korea Convergence Society
• /
• v.12 no.11
• /
• pp.69-80
• /
• 2021

Neural machine translation using deep neural network has emerged as a mainstream research, and an abundance of investment and studies on model structure and parallel language pair have been actively undertaken for the best performance. However, most recent neural machine translation studies pass along decoding strategy to future work, and have insufficient a variety of experiments and specific analysis on it for generating language to maximize quality in the decoding process. In machine translation, decoding strategies optimize navigation paths in the process of generating translation sentences and performance improvement is possible without model modifications or data expansion. This paper compares and analyzes the significant effects of the decoding strategy from classical greedy decoding to the latest Dynamic Beam Allocation (DBA) in neural machine translation using a sequence to sequence model.