• 산업과 과학
• /
• 1권1호
• /
• pp.28-34
• /
• 2022

소프트웨어 품질평가에 대해서는 많은 연구가 진행되어왔다. 최근에 인공지능 관련 소프트웨어들이 많이 개발되어지면서 기존 소프트웨어에 인공지능 기능을 평가하기 위한 방안에 대한 연구가 진행되어지고 있다. 소프트웨어 평가는 기능적합성(Functional suitability), 신뢰성(Reliability), 사용성(Usability), 유지보수성(Maintainability), 효율성(Performance efficiency), 이식성(Portability), 상호운영성(Compatibility), 보안성(Security)이란 8가지 품질 특성을 기반으로 평가 되어왔으나 인공지능 기능을 가지고 있는 소프트웨어의 경우는 8가지 품질 특성뿐만 아니라 인공지능 부분의 기능에 대해서 평가를 통해서 확인해야 하는 부분에 대한 연구가 진행되고 있다. 본 연구는 이 부분에서 평가 방안에 대한 내용을 소개하려 한다. 기존에 소프트웨어 품질 평가 방안과 인공지능 부분에서 고려해야 하는 부분에 대한 제시를 통해서 인공지능 소프트웨어의 품질 평가 방안을 제시하려 한다.

• Architectural research
• /
• 제24권1호
• /
• pp.1-11
• /
• 2022

As the occurrence of a crime is dependent on different factors, their correlations are beyond the ordinary cognitive range. Owing to this limitation, systems face difficulty in correlating various factors, thereby requiring the assistance of artificial intelligence (AI) to overcome such limitations. Therefore, AI has become indispensable for crime prediction. Crimes can cause severe and irrevocable damage to a society. Recently, big data has been introduced for developing highly accurate models for crime prediction. Prediction of night crimes should be given significant consideration, because crimes primarily occur during nights, when the spatiotemporal characteristics become vulnerable to crimes. Many environmental factors that influence crime rate are applied for crime prediction, and their influence on crime rate may differ based on temporal characteristics and the nature of crime. This study aims to identify the environmental factors that influence sex and theft crimes occurring at night and proposes an artificial neural network (ANN) model to predict sex and theft crimes at night in random areas. The crime data of A district in Seoul for 12 years (2004-2015) was used, and environmental factors that influence sex and theft crimes were derived through multiple regression analysis. Two types of crime prediction models were developed: Type A using all environmental factors as input data; Type B with only the significant factors (obtained from regression analysis) as input data. The Type B model exhibited a greater accuracy than Type A, by 3.26 and 9.47 % higher for theft and sex crimes, respectively.

• Journal of Information Technology Applications and Management
• /
• 제29권1호
• /
• pp.59-70
• /
• 2022

Recently, in platforms such as YouTube and Instagram, virtual characters resembling human life become the main characters, produce various contents, breathe with the public, and create the era of virtual humans. For example, existing game characters appear as virtual characters with unique AUs, or AI characters created by reflecting the public's preferences are actively communicating with the public through advertisements and SNS activities. As the consumption of video content through smart devices increases significantly in the post-corona era, virtual influencers are being used as all-round entertainers because there is little risk of personality controversy or production cost. there is a trend In this study, we investigated the characteristics of the case of being active as an influencer among the activities of a virtual character, and how the interactive aspect of the influencer appears by identifying the current situation through major cases. Combining this, based on the analysis of the influence of virtual influencers, the parts that producers should recognize are derived, and the differentiated characteristics of interactive virtual influencers are summarized. In addition, the difficulties of virtual influencers were investigated and problems were identified, and for the development of the content industry, a more favorable method for interaction was presented and suggestions were made to secure inner sincerity.

• 한국가축번식학회지
• /
• 제25권2호
• /
• pp.119-124
• /
• 2001

본 연구는 한우 난포발달에 있어서 난포액 및 inhibin의 생리적 역할을 검토하기 위해 수행되었다. Anti-inhibin serum(AI)생산을 위해 사용된 항원은 porcine inhibin-$\alpha$-subunit 19~32의 peptide를 사용하여 adjuvant 용액을 혼합, 앙고라종 토끼 5두(체중 2.5kg)에게 주 2회 간격으로 면역 실시 후 52일째의 토끼로부터 항혈청을 생산하였다. 과립막 세포의 체외배양을 위해 D-MEM(10% FCS와 antibiotics를 첨가)을 배양액으로 하여 1$\times$$10^{6}$ cells/$m\ell$로 조절하였으며, 호르몬은 RIA 및 ELISA법으로 분석하였다. Western blotting법에 의해 과립막 세포 및 황체조직의 각 세포질을 SDS-PAGE로 분리하여 nitro cellulose membrane에 transfer하여 검토한 결과, 직경 1.0 cm의 성숙 난포의 granulosa cell의 세포질에서 특이하게 Inhibin이 존재하고 있음이 확인되었으나, 황체조직 및 성숙 난포에서는 검출되지 않았다. 난포 크기별 난포액의 progesterone 및 estradiol-17$\beta$을 농도를 분석한 결과, estradiol-17$\beta$농도는 난포 크기가 직경 2.0 cm부터 유의적으로 높았으나 난포 크기가 적을수록 감소되었다. 이에 반해, Progesterone 농도는 직경 2.0 cm 난포에서 가장 높았으며 난포 크기가 적을수록 낮았다. 과립막 세포의 48시간 체외배양에서 bFF 5% 처리구와 bFF 5%+AI 5% 처리구에서는 progesterone은 대조구보다 유의적으로 억제되었으나, AI 5% 단독 처리구에서는 대조구와 큰 차이가 없었다. 또한, estradiol-17$\beta$농도는 5% AI구와 5% AI+5% bFF 처리구에서는 대조구에 비해 증가하였다. 그러나, 5% bFF 단독처리구에서는 대조구와 큰 차이가 없었다. 이상의 결과로, 한우에 있어서 성숙난포에 존재하는 Inhibin은 AI처리에 의해 내인성 Inhibin의 기능이 약하되어 FSH분비를 조절하는 역할을 함으로써 난포발달 및 난포세포의 스테로이드호르몬합성에 중요하게 관여하고 있는 것으로 사료된다.

• 대한용접접합학회:학술대회논문집
• /
• 대한용접접합학회 2003년도 춘계학술발표대회 개요집
• /
• pp.114-116
• /
• 2003

The multi function sprayed coating is used for direct-heating, wear resistance and high bonding strength. The merits of surface direct-heating coatings are short warming time, low power consumption and better wear resistance that can be used in many organization parts. In this study, the surface direct-heating and wear resistance can be improved by spraying the proper materials on the surface $Al_2$O$_3$40%TiO$_2$ powder and Ni-20%Cr powder that had the properties of conduction and high wear resistivity are used in order to improve wear resistance, electrical properties and bonding strength.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2002년도 봄 학술발표회 논문집
• /
• pp.759-766
• /
• 2002

In the paper the authors describe the development of ITIS(Intelligent Tunneling Information System) for the Purpose of applying the 3D visualization technique, GIS, AI(Artificial Intelligence) to tunnel design and construction. VR(Virtual Reality) and 3D visualization techniques are applied in order to develope the 3D model of characteristics and structures of ground and rock mass. Database for all the materials related to site investigation and tunnel construction is developed using GIS technique. AI technique such as fuzzy theory and neural network is applied to predict ground settlement, decide tunnel support method and estimate ground and rock mass properties according to tunnel excavation steps. ITIS can help to inform various necessary tunnel information to engineers quickly and manage tunnel using acquired information based on D/B.

• 대한원격탐사학회지
• /
• 제18권5호
• /
• pp.263-271
• /
• 2002

Recently, spatial information technologies using remotely sensed imagery and functionality of GIS (Geographic Information Systems) have been widely utilized to various types of transportation-related applications. In this study, extraction programs of some practical indices, to be effectively used in transportation reference planning problem, were designed and implemented as prototyped extensions in GIS development environment: traffic flow estimation (TFL/TFB), urban rural index (URI), and accessibility index (AI). In TFL/TFB, user can obtain quantitative results on traffic flow estimation at link/block using high-resolution satellite imagery. Whereas, URI extension provides urban-rural characteristics related to road system, being considered one of important factors in transportation planning. Lastly, AI extension helps to obtain accessibility index between nodes of road segments and surrounding district areas touched or intersected with the road network system, and it also provides useful information for transportation planning problems. This approach is regarded as one of RS-T (Remote Sensing in Transportation), and it is expected to expand as new application of remotely sensed imagery.

• Journal of Information Processing Systems
• /
• 제17권3호
• /
• pp.505-517
• /
• 2021

This research presented an implementation of autostereoscopic virtual three-dimensional (3D) button device as non-contact style. The proposed device has several characteristics about visible feature, non-contact use and artificial intelligence (AI) engine. The device was designed to be contactless to prevent virus contamination and consists of 3D buttons in a virtual stereoscopic view. To specify the button pressed virtually by fingertip pointing, a simple deep learning network having two stages without convolution filters was designed. As confirmed in the experiment, if the input data composition is clearly designed, the deep learning network does not need to be configured so complexly. As the results of testing and evaluation by the certification institute, the proposed button device shows high reliability and stability.

• 한국정보시스템학회지:정보시스템연구
• /
• 제31권2호
• /
• pp.137-158
• /
• 2022

Purpose As artificial intelligence voice agents (AIVA) have been widely adopted in services, diverse forms of their voices, which are the main interface with users, have been experimented. The purpose of this study is to examine how users evaluate vocal characteristics (gender, voice pitch, and voice pace) of AIVA, depending on prior research on human voice attractiveness. Design/methodology/approach This study employed an experimental survey which 516 participated in. Each participant was randomly assigned into one of eight situations (e.g., male - higher pitch - faster pace) and listened a AIVA voice sample, which introduce weather information. Next, a participant answered three consequence factors (attractiveness, trust, and anthropomorphism). Findings The results reveal that female voices of AIVA were perceived as more attractive and trustworthy than male voices. As far as voice pitch goes, while lower-pitch voices were preferred in female voices, higher-pitch voices were preferred in male voices. Finally, faster voices of AIVA were more attractive than slower voices.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 춘계학술발표대회
• /
• pp.362-365
• /
• 2022

최근 노동 집약적인 성격의 섬유 산업에서는 AI를 통해 공정에 들어가는 시간과 비용을 줄이고 품질을 최적화 하려는 시도를 하고 있다. 그러나 섬유 방사 공정은 데이터 수집에 필요한 비용이 크고 체계적인 데이터 처리 시스템이 부족하여 축적된 데이터양이 적다. 또 방사 목적에 따라 특정 변수 위주의 조합에 대한 데이터만을 우선적으로 수집하여 데이터 불균형이 발생하며, 물성 측정환경 차이로 인해 동일 방사조건에서 수집된 샘플 간에도 오차가 존재한다. 이러한 데이터 특성들을 고려하지 않고 AI 모델에 활용할 경우 과적합과 성능 저하 등의 문제가 발생할 수 있다. 따라서 본 논문에서는 물성 단위 및 허용오차를 고려한 이상치 처리 기법과 데이터 불균형 정도 및 물성과의 상관성을 고려한 오버샘플링 기법을 물성 예측 모델에 적용한다. 두 기법들을 모델에 적용한 결과 그렇지 않은 모델에 비해 물성 예측 오차와 방사 공정 데이터에 대한 모델의 적합도가 개선됨을 보인다.