• Journal of Information Processing Systems
• /
• 제19권4호
• /
• pp.439-449
• /
• 2023

This paper deals with a resource efficient artificial intelligence (AI) service architecture for multi-channel video streams. As an AI service, we consider the object detection model, which is the most representative for video applications. Since most object detection models are basically designed for a single channel video stream, the utilization of the additional resource for multi-channel video stream processing is inevitable. Therefore, we propose a resource efficient AI service framework, which can be associated with various AI service models. Our framework is designed based on the modular architecture, which consists of adaptive frame control (AFC) Manager, multiplexer (MUX), adaptive channel selector (ACS), and YOLO interface units. In order to run only a single YOLO process without regard to the number of channels, we propose a novel approach efficiently dealing with multi-channel input streams. Through the experiment, it is shown that the framework is capable of performing object detection service with minimum resource utilization even in the circumstance of multi-channel streams. In addition, each service can be guaranteed within a deadline.

• Bulletin of the Korean Chemical Society
• /
• 제34권4호
• /
• pp.1243-1246
• /
• 2013

• The Journal of Advanced Prosthodontics
• /
• 제9권4호
• /
• pp.239-243
• /
• 2017

PURPOSE. The purpose of this study is to compare single and three-unit metal frameworks that are produced by micro-stereolithography. MATERIALS AND METHODS. Silicone impressions of a selected molar and a premolar were used to make master abutments that were scanned into a stereolithography file. The file was processed with computer aided design software to create single and three-unit designs from which resin frameworks were created using micro-stereolithography. These resin frameworks were subjected to investment, burnout, and casting to fabricate single and three-unit metal ones that were measured under a digital microscope by using the silicone replica technique. The measurements were verified by means of the Mann-Whitney U test (${\alpha}=.05$). RESULTS. The marginal gap was $101.9{\pm}53.4{\mu}m$ for SM group and $104.3{\pm}62.9{\mu}m$ for TUM group. The measurement of non-pontics in a single metal framework was $93.6{\pm}43.9{\mu}m$, and that of non-pontics in a three-unit metal framework was $64.9{\pm}46.5{\mu}m$. The dimension of pontics in a single metal framework was $110.2{\pm}61.4{\mu}m$, and that of pontics in a three-unit metal framework was $143.7{\pm}51.8{\mu}m$. CONCLUSION. The marginal gap was smaller for the single metal framework than for the three-unit one, which requires further improvement before it can be used for clinical purposes.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.268-271
• /
• 2003

In this paper, we propose a new framework based on negotiatory mobile multi agent system, and implement a mobile multi agent environment based on DECAF(Distributed Environment-Centered Agent Framework) which is one of the distributed agent development toolkit so as to implement a new PDS(Personal Digital Library System). The new framework has some optimality and higher performance in distributed environments.

• 한국CDE학회논문집
• /
• 제5권1호
• /
• pp.50-60
• /
• 2000

XML and CORBA have vast potential to improve software interoperability and to facilitate data exchange across applications and people from various disciplines and vendors. This Paper describes a framework for the integration and validity evaluation of injection mold design problems in a network-oriented design environment, based on In and CORBA. An overview of the framework is provided and an application to a design phase of injection mold is illustrated. The example illustrates how design validities are notified and design directions are provided to the designer during design process.

• 시스템엔지니어링학술지
• /
• 제6권2호
• /
• pp.21-27
• /
• 2010

As system is larger, and technology evolves, the system gets complicated due to its integration and heterogeneity of system components. To address its complexity and to accomplish efficient system development, various methodologies have been developed. MBSE using Models and tools is one of methodologies. MBSE methodologies and its products are differently applied according to the organization and project. It is proper that unique methodology is applied in a development of single system. But what if a variety of methodologies are applied in the same domain or SoS development, it will cause a confusion of communication and waste of engineering efforts. As a way to resolve this, it can be considered that MBSE using architecture framework that clearly define products. In other words, by taking advantage of that an architecture framework provides the type, representation and meta-model of products, the reusability and universality of MBSE products can be improved.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권2호
• /
• pp.536-564
• /
• 2019

Soft faults are inherent in wireless sensor networks (WSNs) due to external and internal errors. The failure of processes in a protocol stack are caused by errors on various layers. In this work, impact of errors and channel misbehavior on process execution is investigated to provide an error classification mechanism. Considering implementation of WSN protocol stack, inter-process correlations of stacked and peer layer processes are modeled. The proposed model is realized through local and global decision trees for fault diagnosis. A hybrid framework is proposed to implement local decision tree on sensor nodes and global decision tree on diagnostic cluster head. Local decision tree is employed to diagnose critical failures due to errors in stacked processes at node level. Global decision tree, diagnoses critical failures due to errors in peer layer processes at network level. The proposed model has been analyzed using fault tree analysis. The framework implementation has been done in Castalia. Simulation results validate the inter-process correlation model-based fault diagnosis. The hybrid framework distributes processing load on sensor nodes and diagnostic cluster head in a decentralized way, reducing communication overhead.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2009년도 추계학술대회
• /
• pp.237-240
• /
• 2009

본 논문에서는 HIS(병원 정보 시스템) 환경에서 의료 및 주변 기기들의 다양한 솔루션과 미들웨어를 통합할 수 있는 프레임워크 기반에서 환자 기초, 의료 정보의 전달 구조를 정의하였다. OSGi 번들 형태로 HL7(Health Level 7) 기반의 메시지 전달 구조의 설계하고 다른 장치 제어 번들과의 효율적인 상호 운용을 보이고자 한다.

• Wind and Structures
• /
• 제32권4호
• /
• pp.283-292
• /
• 2021

Performance-based seismic design (PBSD) is currently used for retrofitting of older buildings and the design of new buildings. Whereas, application of performance-based design for wind load is still under development. The tendency has been in the codes to increase wind hazard based on recent recorded events. Since tall buildings are highly susceptible to wind load, necessity for developing a framework for performance-based wind design (PBWD) has intensified. Only a few guidelines such as ASCE (2019) provide information on using PBWD as an alternative for code prescriptive wind design. Though wind hazards, performance objectives, analysis techniques, and acceptance criteria are explained, no recommendations are provided for several aspects like how to select a proper level of wind hazard for each target performance criterion. This paper is an attempt to explain current design philosophy for wind and seismic loads and inherent connection between the components of PBSD for development of a framework for PBWD of tall buildings. Recognizing this connection, a framework for PBWD based on limits set for serviceability and strength is also proposed. Also, the potential for carrying out PBWD in line with ASCE 7-16 is investigated and proposed in this paper.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.1202-1208
• /
• 2022

Techniques based on computer vision are becoming increasingly important in construction safety monitoring. Using AI algorithms can automatically identify conceivable hazards and give feedback to stakeholders. However, the construction site remains various potential hazard situations during the project. Due to the site complexity, many visual devices simultaneously participate in the monitoring process. Therefore, it challenges developing and operating corresponding AI detection algorithms. Safety information resulting from computer vision needs to organize before delivering it to safety managers. This study proposes a framework for computer vision-aided construction safety monitoring using collaborative 4D BIM information to address this issue, called CSM4D. The suggested framework consists of two-module: (1) collaborative BIM information extraction module (CBIE) extracts the spatial-temporal information and potential hazard scenario of a specific activity; through that, Computer Vision-aid Safety Monitoring Module (CVSM) can apply accurate algorithms at the right workplace during the project. The proposed framework is expected to aid safety monitoring using computer vision and 4D BIM.