• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.479-480
• /
• 2024

본 논문에서는 원자력 안전조치 용어를 미세조정(fine tuning) 알고리즘을 활용해 추가 학습한 공개 거대 언어모델(Large Language Model, LLM)이 안전조치 관련 질문에 대해 답변한 결과를 정성적으로 평가하였다. 평가 결과, 학습 데이터 범위 내 질문에 대해 학습 모델은 기반 모델 답변에 추가 학습 데이터를 활용한 낮은 수준의 추론을 수행한 답변을 출력하였다. 평가 결과를 통해 추가 학습 개선 방향을 도출하였으며 저비용 전문 분야 언어 모델 구축에 활용할 수 있을 것으로 보인다.

• The KIPS Transactions:PartD
• /
• v.16D no.3
• /
• pp.395-406
• /
• 2009

Korean government has operated EA by the act on efficient introduction of information system and operation, etc. But the evaluation system for EA and the criteria don't prepare well. Particularly, There is no model for EA performance measurement and the way is insufficient. In this study, we derived 8 areas and 17 criteria for the performance evaluation based on the Performance Reference Model of U.S FEA and Korea. And we also derived 8 areas and 10 criteria for it based on the OMB EA Assessment Framework and the EA maturity model in Korea. We propose the performance evaluation model of the five areas that consists of the business performance, customer performance, process, human resource and the technology for EA performance evaluation. To verify the model, we applied the model to three organizations and evaluated EA performance. In addition, we compared the performance result with the performance evaluation area of EA maturity model of Korea to verify the result. We also analyzed the criteria of the proposed performance evaluation model with the current EA maturity model and Performance Reference Model of Korea. As a result of the evaluation, we verified of the proposed performance evaluation model, too.

• Journal of Software Assessment and Valuation
• /
• v.15 no.2
• /
• pp.73-83
• /
• 2019

Voice Recognition has recently been improved with AI(Artificial Intelligence) and has greatly improved the false recognition rate and provides an effective and efficient Human Machine Interface (HMI). This trend has also been applied in the defense industry, particularly in the aviation, F-35. However, for the quality evaluation of Voice Recognition, the defense industry, especially the aircraft, requires measurable quantitative models. In this paper, the quantitative evaluation model is proposed for applying Voice Recognition to aircraft. For the proposal, the evaluation items are identified from the Voice Recognition technology and ISO/IEC 25000(SQuaRE) quality attributes. Using these two perspectives, the quantitative evaluation model is proposed under aircraft operation condition and confirms the evaluation results.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.04a
• /
• pp.344-348
• /
• 2005

이 논문에서는 개체에 대한 신뢰도를 계산하기 위해 여러 가지의 평가기준을 이용하고, 또한 다른 개체들로부터의 추천정보를 이용하는 신뢰모델에 대해서 제안한다. 제안한 모델에서는 개체의 신뢰도를 개체가 주어진 상황에서 만족스러운 결과를 낼 기대값으로 정의한다. 다른 개체와 상호작용이 일어날 때마다 각 평가기준에 따른 평가결과가 얻어진다고 전제하는 상황에서 적용되는 신뢰 모델이다. 제안된 모델에서는 신뢰정보가 요구될 때 우선 결과확률 분포(outcome probability distribution)와 개체의 평가결과에 대한 선호도를 고려하여 각 평가기준에 대한 만족정도를 계산한다. 이렇게 계산된 만족정도 값들은 각 평가기준의 중요도를 반영하여 하나의 신뢰값으로 결합된다. 이때 추천 정보도 신뢰값에 함께 결합되는 모델이다.

• The Safety technology
• /
• no.34
• /
• pp.8-14
• /
• 2000

얼마 전부터 안전보건경영체제의 시행여부와 관련하여 최근 위험성 평가(Risk Assessme nt)가 각 방면에서 주목을 받고 있다. 우리나라에서는 위험성 평가가 96년부터 공정안전관리(PSM : Process Safety Management nt)가 시행되면서 특히 화학업종을 중심으로 해당 사업장에 적용되어 실시해왔으나 안전보건경영체제에서는 일반업종에도 위험성 평가를 요구하고 있다. 이러한 위험성 쳥가에 관한 국제적인 표준이 ISO 14121 등 여러 가지가 있는데 일본에서는 이미 위험성 평가에 대한 표준 모델을 발표하고 있다. 본 자료에서는 일반 기계기구업종에서의 위험성 평가에 대한 표준모델로서 영국규격 BS8800 부속서D를 일본에서 발표된 모델을 소개 하고자 한다.

• 한국IT서비스학회:학술대회논문집
• /
• 2009.05a
• /
• pp.13-17
• /
• 2009

초기 사업자들에 의해 일방적으로 정보가 제공되던 인터넷 GIS 사이트는 Web 2.0의 패러다임과 함께 사용자들에 의해서 정보가 생산되고, 평가되는 형태로 변화하였다. 기존의 일반적인 웹사이트의 평가모델과 GIS 사이트 평가 모델에 대해서 살펴보고, Web 2.0을 고려하여 보완된 GIS 2.0 사이트 평가모델의 기준점을 활용하여 유비쿼터스 사업 특성을 고려한 평가 모델을 제시하고자 한다.

• Journal of the Korean Society for information Management
• /
• v.40 no.3
• /
• pp.77-98
• /
• 2023

Large Language Models (LLMs) are becoming the major trend in the natural language processing field. These models were built based on research data, but information such as types, limitations, and risks of using research data are unknown. This research would present how to analyze and evaluate the LLMs that were built with research data: LLaMA or LLaMA base models such as Alpaca of Stanford, Vicuna of the large model systems organization, and ChatGPT from OpenAI from the perspective of research data. This quality evaluation focuses on the validity, functionality, and reliability of Data Quality Management (DQM). Furthermore, we adopted the Holistic Evaluation of Language Models (HELM) to understand its evaluation criteria and then discussed its limitations. This study presents quality evaluation criteria for LLMs using research data and future development directions.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.13 no.5
• /
• pp.57-67
• /
• 2003

Security Policy Model is a structured representation using informal, semiformal or formal method of security policy to be enforced by TOE. It provides TOE to get an assurance to mitigate security flaws resulted from inconsistency between security functional requirements and functional specifications. Therefore, Security Policy Model has been required under an hish evaluation assurance level on an evaluation criteria such as ISO/IEC 15408(Common Criteria, CC). In this paper, we present an evaluation method for security policy model based on assurance requirements for security policy model in Common Criteria through an analysis of concepts, related researches and assurance requirements for security policy model.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.9
• /
• pp.269-274
• /
• 2016

In this paper We focuses on suggestion to quality model for IoT infrastructure services for Internet of Things. Quality model is suggested on security set out in ISO25000 quality factors and assessment of the existing traditional software application of ISO 9126 quality model. We validated that the proposed model can be realized it was applied to evaluate the 4 elements and related security in Metrics.

• Fire Science and Engineering
• /
• v.10 no.4
• /
• pp.29-36
• /
• 1996

The hazard assessment in which the potential hazard factors in the buildings are investigated and the scale of the hazard is analyzed should be performed first in order to prevent personal and material damages due to building fire. In this study, the building fire hazard are assessed using 822-item checklist, for the qualitative evaluation of which the main factors are classified into 10 items, yielding 100 scale points with some weighting. It is shown that present model is applicable for the assessment of all general buildings through the examination of the suitability of assessment model by actual assessment of existing building. Also, the checklist is prepared in itemized questionnaire form for easy assessment of building fire hazard. Therefore, the present model will be helpful for those working in fire prevention, who are suffering from the lack of manifest evaluation model for the fire prevention assessment so far in Korea.