• 한국IT서비스학회지
• /
• 제20권4호
• /
• pp.113-128
• /
• 2021

In the rapidly developing 4th industrial revolution. RPA is increasing in use at home and abroad due to its advantages of simplifying workflow and providing flexibility and scalability at the same time. Thus, this paper conducted an empirical study on companies using RPA to determine which factors affect the intention to use the services provided by RPA systems. As system characteristics, exogenous variables were selected as information quality, system quality, and service quality of the information system success model. The endogenous variables were selected as the system acceptance factors for the performance and effort expectancy of the integrated technology acceptance model, and the perceived economic values and functional values were additionally selected. For the purpose of this study, a structured questionnaire was used for empirical analysis and the proposed hypothesis was verified through the path analysis of structural equations. As a result of the study, there was no significant relationship between service quality and effort expectancy, between service quality and economic value, and it was verified that the relationship between other factors was positively significant.

• 한국정보통신학회논문지
• /
• 제23권8호
• /
• pp.930-935
• /
• 2019

우리의 제안시스템인 mobiAutoBot은 모바일 장치를 지원 가능한 인지 자동화 수준의 로보틱스 프로세스 자동화 소프트웨어의 개념모델이다. mobiAutoBot은 mobiAutoBot controller와 mobiAutoBot runner의 두 부분으로 구성되어 있다. mobiAutoBot controller는 모바일기기에 Job을 지시하고 모니터링 및 연동작업을 수행하며, 모바일기기에 설치된 mobiAutoBot runner는 명령내린 작업을 수행한다. 우리가 제안한 mobiAutoBot을 통하여 모바일기기에 대한 자동화 기능을 중소기업에 제공한다면, 고가의 정보기반 인프라가 없더라도 단순 스마트폰과 같은 모바일기기만으로 기존 정보시스템과 연계 가능한 로보틱스 프로세스 자동화 기능을 저비용으로 구축할 수 있다. 우리의 제안은 모든 정보시스템 인프라를 갖추기는 어려운 중소기업이나 개인 사용자에게도 로보틱스 프로세스 자동화를 확산하는 계기가 될 것으로 기대한다.

• 스마트미디어저널
• /
• 제10권1호
• /
• pp.99-107
• /
• 2021

4차 산업혁명, Industry 4.0 과 더불어 최근 ICT 분야의 메가트렌드는 빅데이터, IoT, 클라우드 컴퓨팅, 그리고 인공지능이라고 할 수 있다. 따라서, 4차 산업혁명 시대에 알맞은 AI 서비스들의 기술 개발과 다양한 산업 영역에서 ICT 분야의 융합에 따른 BI (Business Intelligence), IA (Intelligent Analytics, BI + AI), AIoT (Artificial Intelligence of Things), AIOPS (Artificial Intelligence for IT Operations), RPA 2.0 (Robotic Process Automation + AI) 등의 세분화된 기술 발전으로 급속한 디지털 전환 (Digital Transformation)이 진행되고 있는 추세이다. 본 연구에서는 이러한 기술적 상황에 따른 대용량 분산 Abyss 스토리지 기반으로 인프라 측면의 GPU, CDA (Connected Data Architecture) 프레임워크, 그리고 AI의 다양한 머신러닝 서비스들을 통합 및 고도화를 목표로 하며, AI 비즈니스의 수익 모델을 다양한 산업 영역에 활용하고자 한다.

• International Journal of Advanced Culture Technology
• /
• 제12권3호
• /
• pp.434-440
• /
• 2024

SIZE KOREA updates body measurement data every five years, providing essential information for the fashion industry. This anthropometric data is widely used to diagnose consumer body shapes and develop optimal clothing sizes. Artificial intelligence, particularly machine learning, excels in predicting such body shape classifications. This study seeks to enhance the suitability of clothing design by applying the new analytical methodology of machine learning techniques to better capture and classify the unique body shapes of Korean women. In this study, machine learning techniques such as K-means clustering, Silhouette analysis, and Decision Tree analysis were used to classify the lower body shapes of Korean women in their twenties and identify standard body shapes useful for slacks design. The results showed that the lower body of the age group could be classified into three categories: 'small stature' (the majority), 'tall with an average lower body volume,' and 'medium height with a fuller lower body' (the smallest share). The three-cluster approach is validated through Silhouette analysis, which minimizes misclassification. Decision Tree analysis then further defines the criteria for these clusters, highlighting waist height and hip depth as the most significant factors, achieving a classification accuracy of 90.6%. While this study is not directly related to Robotic Process Automation, its detailed analysis of body shapes for slacks patterns can aid RPA in clothing production. Future research should continue integrating machine learning in human body and fashion design studies.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.1249-1249
• /
• 2022

The facade, an exterior material of a building, is one of the crucial factors that determine its morphological identity and its functional levels, such as energy performance, earthquake and fire resistance. However, regardless of the type of exterior materials, huge property and human casualties are continuing due to frequent exterior materials dropout accidents. The quality of the building envelope depends on the detailed design and is closely related to the back frames that support the exterior material. Detailed design means the creation of a shop drawing, which is the stage of developing the basic design to a level where construction is possible by specifying the exact necessary details. However, due to chronic problems in the construction industry, such as reducing working hours and the lack of design personnel, detailed design is not being appropriately implemented. Considering these characteristics, it is necessary to develop the detailed design process of exterior materials and works based on the domain-expert knowledge of the construction industry using artificial intelligence (AI). Therefore, this study aims to establish a detailed design automation algorithm for AI-based condition-responsive exterior wall panels and their back frames. The scope of the study is limited to "detailed design" performed based on the working drawings during the exterior work process and "stone panels" among exterior materials. First, working-level data on stone works is collected to analyze the existing detailed design process. After that, design parameters are derived by analyzing factors that affect the design of the building's exterior wall and back frames, such as structure, floor height, wind load, lift limit, and transportation elements. The relational expression between the derived parameters is derived, and it is algorithmized to implement a rule-based AI design. These algorithms can be applied to detailed designs based on 3D BIM to automatically calculate quantity and unit price. The next goal is to derive the iterative elements that occur in the process and implement a robotic process automation (RPA)-based system to link the entire "Detailed design-Quality calculation-Order process." This study is significant because it expands the design automation research, which has been rather limited to basic and implemented design, to the detailed design area at the beginning of the construction execution and increases the productivity by using AI. In addition, it can help fundamentally improve the working environment of the construction industry through the development of direct and applicable technologies to practice.