• Annual Conference of KIPS
• /
• 2023.05a
• /
• pp.698-700
• /
• 2023

본 논문에서는 한국어 데이터와 모델링, 추가 평가 지표를 통해 Text Summarization 분야에서 한국어로 좋은 성능을 내기 위한 방식을 제안한다. KoBART의 크기를 키우고 PEGASUS의 GSG를 사용하는 KoBART-GSG 모델을 제안한다. 이때 ASR 모델을 사용하여 한국어 데이터를 구축하고 추가 학습을 진행한다. 또한, 생성된 요약문과 원문에서 Attention 기법으로 키워드와 핵심 문장을 추출하여 지능형 텍스트를 구성하는 새로운 방식을 제안한다. ASR Open API와 제안한 방식을 사용하여 오디오 파일을 텍스트로 변환하고 요약하는 강의나 회의 등 학계와 산업에서 사용할 수 있는 서비스를 제공한다.

• The KIPS Transactions:PartA
• /
• v.13A no.6 s.103
• /
• pp.533-540
• /
• 2006

This paper describes the design and implementation of a grid system META (Metacomputing Environment using Test-run of Application) which facilitates the execution of a CFD (Computational Fluid Dynamics) analysis program on distributed environment. The grid system META allows the CFD program developers can access the computing resources distributed over the network just like one computer system. The research issues involved in the grid computing include fault-tolerance, computing resource selection, and user-interface design. In this paper, we exploits an automatic resource selection scheme for executing the parallel SPMD (Single Program Multiple Data) application written in MPI (Message Passing Interface). The proposed resource selection scheme is informed from the network latency time and the elapsed time of the kernel loop attained from test-run. The network latency time highly influences the executional performance when a parallel program is distributed and executed over several systems. The elapsed time of the kernel loop can be used as an estimator of the whole execution time of the CFD Program due to a common characteristic of CFD programs. The kernel loop consumes over 90% of the whole execution time of a CFD program.

• Journal of Internet Computing and Services
• /
• v.25 no.3
• /
• pp.27-33
• /
• 2024

The environment of academic research is continuously changing due to the increase of information, which raises the need for an effective way to analyze and organize large amounts of documents. In this paper, we propose Performance Improvement of Topic Modeling using BART(Bidirectional and Auto-Regressive Transformers) based Document Summarization. The proposed method uses BART-based document summary model to extract the core content and improve topic modeling performance using LDA(Latent Dirichlet Allocation) algorithm. We suggest an approach to improve the performance and efficiency of LDA topic modeling through document summarization and validate it through experiments. The experimental results show that the BART-based model for summarizing article data captures the important information of the original articles with F1-Scores of 0.5819, 0.4384, and 0.5038 in Rouge-1, Rouge-2, and Rouge-L performance evaluations, respectively. In addition, topic modeling using summarized documents performs about 8.08% better than topic modeling using full text in the performance comparison using the Perplexity metric. This contributes to the reduction of data throughput and improvement of efficiency in the topic modeling process.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.4
• /
• pp.221-228
• /
• 2024

Predicting insurance claims is a key task for insurance companies to manage risks and maintain financial stability. Accurate insurance claim predictions enable insurers to set appropriate premiums, reduce unexpected losses, and improve the quality of customer service. This study aims to enhance the performance of insurance claim prediction models by applying ensemble learning techniques. The predictive performance of models such as Random Forest, Gradient Boosting Machine (GBM), XGBoost, Stacking, and the proposed Dynamic Weighted Ensemble (DWE) model were compared and analyzed. Model performance was evaluated using Mean Absolute Error (MAE), Mean Squared Error (MSE), and the Coefficient of Determination (R²). Experimental results showed that the DWE model outperformed others in terms of evaluation metrics, achieving optimal predictive performance by combining the prediction results of Random Forest, XGBoost, LR, and LightGBM. This study demonstrates that ensemble learning techniques are effective in improving the accuracy of insurance claim predictions and suggests the potential utilization of AI-based predictive models in the insurance industry.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.3
• /
• pp.48-66
• /
• 2024

According to the three amended Laws of the Data Economy and the Data Industry Act of Korea, systems for pseudonymous data integration and Data Safe Zones have been operated separately by selected agencies, eventually causing a burden of use in SMEs, startups, and general users because of complicated and ineffective procedures. An over-stringent pseudonymization policy to prevent data breaches has also compromised data quality. Such trials should be improved to ensure the convenience of use and data quality. This paper proposes a prototype system of the Integrated Data Safe Zone based on redesigned and optimized pseudonymization workflows. Conventional workflows of pseudonymization were redesigned by applying the amended guidelines and selectively revising existing guidelines for business process redesign. The proposed prototype has been shown quantitatively to outperform the conventional one: 6-fold increase in time efficiency, 1.28-fold in cost reduction, and 1.3-fold improvement in data quality.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.8
• /
• pp.388-394
• /
• 2024

Since recommendation systems play a key role in increasing the revenue of companies, various approaches and models have been studied in the past. However, this diversity also leads to a complexity in the types of recommendation systems, which makes it difficult to select a recommendation model. Therefore, this study aims to solve the difficulty of selecting an appropriate recommendation model for recommendation systems by providing a unified criterion for categorizing various recommendation models and comparing their performance in a unified environment. The experiments utilized MovieLens and Coursera datasets, and the performance of linear models(ADMM-SLIM, EASER, LightGCN) and non-linear models(Caser, BERT4Rec) were evaluated using HR@10 and NDCG@10 metrics. This study will provide researchers and practitioners with useful information for selecting the best model based on dataset characteristics and recommendation context.

• Journal of Korean Society of Disaster and Security
• /
• v.15 no.3
• /
• pp.89-99
• /
• 2022

Bridges are a key infrastructure that underpins economic and social activities. In Korea, bridges began to be built with economic development in the 1970s and were built intensively in the 1980s and 1990s. In recent years, as the number of bridges with a service life of more than 30 years is increasing, continuous maintenance is required to ensure the safety of the bridges. In particular, in order to cope with the aging of bridges, research on technology development such as maintenance using ICT technology, preventive maintenance, life cycle cost reduction, and long life bridge is being actively promoted. This paper presents the results of correlation analysis based on the safety evaluation data of bridges as part of the research on the development of a model for estimating load-carrying capacity of bridges. As a analysis result, indicators highly correlated with the load-carrying capacity of the bridge was derived.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.39 no.6
• /
• pp.575-581
• /
• 2015

The drill bit, which directly transmits percussive forces and torque to the rock, is the core part of a rock drilling machine. For effective drilling, the button arrangement of a drill bit should be optimized because it is the most important design factor in determining drilling efficiency. Furthermore, a quantitative method is necessary to evaluate the button arrangement for the optimization of the drill bit button. Therefore, we propose a new method for the evaluation of the drill bit button arrangement using new evaluation indices, which include the overlapped impact area, blank area, and moment. Moreover, we verify the suitability of the proposed evaluation method by applying it to the conventional button arrangement.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.395-398
• /
• 2021

최근 방대한 양의 텍스트 정보가 인터넷에 유통되면서 정보의 핵심 내용을 파악하기가 더욱 어려워졌으며, 이로 인해 자동으로 텍스트를 요약하려는 연구가 활발하게 이루어지고 있다. 텍스트 자동 요약을 위한 다양한 기법 중 특히 트랜스포머(Transformer) 기반의 모델은 추상 요약(Abstractive Summarization) 과제에서 매우 우수한 성능을 보이며, 해당 분야의 SOTA(State of the Art)를 달성하고 있다. 하지만 트랜스포머 모델은 매우 많은 수의 매개변수들(Parameters)로 구성되어 있어서, 충분한 양의 데이터가 확보되지 않으면 이들 매개변수에 대한 충분한 학습이 이루어지지 않아서 양질의 요약문을 생성하기 어렵다는 한계를 갖는다. 이러한 한계를 극복하기 위해 본 연구는 소량의 데이터가 주어진 환경에서도 양질의 요약문을 생성할 수 있는 문서 요약 방법론을 제안한다. 구체적으로 제안 방법론은 한국어 사전학습 언어 모델인 KoBERT의 임베딩 행렬을 트랜스포머 모델에 적용하는 방식으로 문서 요약을 수행하며, 제안 방법론의 우수성은 Dacon 한국어 문서 생성 요약 데이터셋에 대한 실험을 통해 ROUGE 지표를 기준으로 평가하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.9
• /
• pp.1864-1869
• /
• 2012

We make an interference analysis to obtain a critical ctiteria for coexisting availability of WLAN and WiBro between adjacent channels can be used in TVWS(TV White Space). To meet this analysis, we set the various transmission parameters including the emission and blocking mask, antenna height and gain, transmission power and bandwidth, channel model etc. And, based on these parameters, we analyze on performances according to a variation of guard band, a number of service user and allowable transmit power of the user operating in the adjacent channels. In this paper, we consider a urban environment and apply a Extended Hata-SRD for WLAN and an interference link and Extended Hata model for WiBro, respectively. With these results, we can see how each system can be shared in an adjacent channel.