• Journal of the Society of Disaster Information
• /
• v.20 no.2
• /
• pp.302-314
• /
• 2024

Purpose: This study proposes a fall detection model based on a top-down deep learning pose estimation model to automatically determine falls of multiple workers in an underground utility tunnel, and evaluates the performance of the proposed model. Method: A model is presented that combines fall discrimination rules with the results inferred from YOLOv8-pose, one of the top-down pose estimation models, and metrics of the model are evaluated for images of standing and falling two or fewer workers in the tunnel. The same process is also conducted for a bottom-up type of pose estimation model (OpenPose). In addition, due to dependency of the falling interference of the models on worker detection by YOLOv8-pose and OpenPose, metrics of the models for fall was not only investigated, but also for person. Result: For worker detection, both YOLOv8-pose and OpenPose models have F1-score of 0.88 and 0.71, respectively. However, for fall detection, the metrics were deteriorated to 0.71 and 0.23. The results of the OpenPose based model were due to partially detected worker body, and detected workers but fail to part them correctly. Conclusion: Use of top-down type of pose estimation models would be more effective way to detect fall of workers in the underground utility tunnel, with respect to joint recognition and partition between workers.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2002.11a
• /
• pp.160-166
• /
• 2002

본 연구의 목적은 비디오/오디오 프로토콜 분석 방식을 이용해서 텍스타일 디자인 프로세스 중 모티브 개발 단계에서 디지털 나염(DTP : Digital Textile Printing) 전용 캐드(CAD)와 같은 디자인 저작도구를 설계할 때 어떤 요소에 중점을 두고 개발 할 것인지에 대한 향상된 지침을 마련하는데 있다. 텍스타일 디자인 프로세스에 대한 프로토콜 분석을 위해 선행 연구를 고찰하여 디자인 행동 범주의 틀을 하향식(top-down)방식으로 설정하고 실제 행동 프로토콜 (action protocol) 분석을 통해 상향식(bottom-up)방식으로 세부 디자인 행동을 도출하였다. 텍스타일 디자인은 선행연구의 건축디자인과는 다른 특징을 지니기 때문에 프로토콜 분석에서도 새로운 디자인 행동 범주(action category)가 필요하게 되었다. 이를 위하여 모델 휴먼 프로세서(Model Human Processor)이론을 근거로 디자인 행동을 모터 행동(motor action), 지각 행동(perceptual action), 인지 행동(cognitive action)의 세 가지 범주[4]로 나누었으며 텍스타일 디자인 프로세스에 적합한 코딩 스킴(coding scheme)을 개발하였다. 본 연구에서는 이 새로운 코딩 스킴을 토대로 디자인 저작도구에 대한 디자이너의 인지적 모형(Cognitive Model)을 개발하였다. 이렇게 개발된 디자이너의 인지적 모형은 디지털 나염을 기반으로 하는 모티브 개발 단계에서 스케치와 렌더링에 대한 디자인 저작 도구의 향상된 설계지침 뿐만 아니라 방향도 시사하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.6
• /
• pp.1110-1115
• /
• 2001

Virtual Reality technology is divided two parts Panorama technology to embody VR on space and Object technology to embody VR of things. About Object VR technology until present, they provided a cube access way, then observer can see object up, down, left, right side and zoom-in, zoom-out, but there is a fact that up-and-down expression is distorted or shows shortcoming that is not expressed by limited situation of manufacture way in Panorama VR's expression. Therefore, in this research, we examine the shortcoming that do not become top-and-bottom expression through basic concept of Panorama and Panorama VR manufacture process and do to propose cube type of new data format that permit up-and-down expression as a real world and compose Panorama VR space.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2001.10a
• /
• pp.177-180
• /
• 2001

Virtual Reality technology is divided two parts Panorama technology to imbody VR on space and Object technology to embody VR of things. About Object VR technology until present, they provided a cube access way, then observer can see object up, down, left, right side and zoom-in, zoom-out, but there is a fact that up-and-down expression is distorted or shows shortcoming that is not expressed by limited situation of manufacture way in Panorama VR's expression. Therefore, in this research, we examine the shortcoming that do not become top-and-bottom expression through basic concept of Panorama and Panorama VR manufacture process and do to propose cube type of new data format that permit up-and-down expression as a real world and compose Panorama VR space.

• Korean Journal of Construction Engineering and Management
• /
• v.16 no.1
• /
• pp.119-128
• /
• 2015

Domestic dominant method in subcontract cost estimate for comprehensive program management is estimation by referencing similar cases or relying on the experience and expertise of the engaged. However, this method is not reliable due to lack of accuracy, making it harder for clients to plan and budget the program. Since budget itself is roughly estimated, it becomes a source of cost rise in the course of management due to design modifications. Therefore, the client and service providers shall calculate more accurate service cost by applying objective and scientific method in order to minimize cost rise and cost related dispute. Traditional cases, in estimating program management cost, took Top-Down approach based on precedents and experience. On the contrary, this study will categorize management structure into phases and activities, issue WBS for each phase to estimated schedule and cost for each code, and take Bottom-UP approach. By taking this approach named ICEP (Integrated Cost Estimate based on Project), Set project typical model will be developed for service cost estimating, calculate cost by applying project-specific factors. Also, by analyzing progress data and allocated management cost to complement them, more efficient construction management will take shape based on program management cost standards which reflect project-specific features.

• Journal of Internet Computing and Services
• /
• v.6 no.6
• /
• pp.107-115
• /
• 2005

A workflow procedure has recently become more complicated and large scaled. In this paper, we propose an advanced workflow modeling methodology, called a fragment driven cooperative workflow modeling methodology. which enables several real workflow designers to cooperatively define a workflow model. The methodology is a Bottom-Up approach in terms of integrating a set of fragment ICNs to compose a complete workflow model. Each fragment ICN is defined by each participant in the cooperative modeling session, We also use the ICN based formal description and the ICN based graphical notation as well. Finally, we prove the feasibility of the methodology by implementing a cooperative workflow modeling system.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.28 no.1
• /
• pp.79-83
• /
• 2015

This paper presents a numerical study on the alignment of ridge-like surface structures evolving on silicon-germanium thin films under localized modulation of surface diffusivity. A situation is considered in which the surface diffusion of film material is selectively promoted such that its morphology is perturbed to periodic patterns. To simulate the growth behavior, a governing equation is formulated taking the surface chemical potential into account, and its solution is numerically sought using a finite-difference method. Results show that an initially planar surface coalesces upon the diffusivity modulation, and the surface structures can be aligned by changing the frequency of modulation condition. This research suggests a bottom-up fabrication technique that can manage the regularity of surface structures for thin film devices.

• Journal of Advanced Navigation Technology
• /
• v.21 no.6
• /
• pp.521-528
• /
• 2017

Research on AI is essential to build a system with collective intelligence that allows a large number of UAVs to maintain their flight while carrying out various missions. A typical approach of AI includes 'top-down' approach, which is a rule-based logic reasoning method including expert system, and 'bottom-up approach' in which overall behavior is determined through partial interaction between simple objects such as artificial neural network and Flocking Algorithm. In the same study as the existing Flocking Algorithm, individuals can not perform individual tasks. In addition, studies such as UAV formation flight can not flexibly cope with problems caused by partial flight defects. In this paper, we propose organic integration between top - down approach and bottom - up approach through multi - agent system, and suggest a flight flight algorithm which can perform flexible mission through it.

• Journal of Digital Convergence
• /
• v.15 no.7
• /
• pp.55-64
• /
• 2017

The purpose of this study is to identify the difficulties of learners who started programming after entering college and to search an effective software education method as university liber arts for non-science major students. In order to do this, we analyzed the difficulties of learners in Python programming classes composed of students from various majors at H University through questioning and taught them using flipped class model with pre-questions. The questions that students submit are collected online before class every time, the data on the degree of the difficulty of feeling and the understanding of feeling were obtained through the questionnaire. As a result, for learners who are new to programming, the learners should allocate the process of making the problem into a logical abstraction at the beginning of the curriculum before learning the basic concept of computer language, each lesson should be practiced through the bottom-up problems enough to provide a logical understanding before actual coding. In addition, detailed curriculum should be developed according to characteristics of learner's major, contents and conducting level.

• Journal of the Korean Society for Library and Information Science
• /
• v.49 no.3
• /
• pp.81-107
• /
• 2015

This study describes the Bottom-up method for implementation of an ontology system from the RDB. The STNet, a structured terminology glossary based on RDB, was served as a test bed for converting to RDF ontology, for generating the inference rules, and for evaluating the results of the semantic search. We have used protege editor of the ontology developing tool to design ontologies with test data. We also tested the designed ontology with the Inference Engine (Pellet) of protege editor. The generated reference rules were tested by TBox and SPARQL queries through STNet ontology. The results of test show that the generated reference rules were verified as true and STNet ontology were also evaluated to be useful for searching the complex combination of semantic relation.