• Journal of Digital Convergence
• /
• v.19 no.6
• /
• pp.251-258
• /
• 2021

In this paper, we proposed an encoder-decoder model utilizing residual learning to improve the accuracy of the U-Net-based semantic segmentation method. U-Net is a deep learning-based semantic segmentation method and is mainly used in applications such as autonomous vehicles and medical image analysis. The conventional U-Net occurs loss in feature compression process due to the shallow structure of the encoder. The loss of features causes a lack of context information necessary for classifying objects and has a problem of reducing segmentation accuracy. To improve this, The proposed method efficiently extracted context information through an encoder using residual learning, which is effective in preventing feature loss and gradient vanishing problems in the conventional U-Net. Furthermore, we reduced down-sampling operations in the encoder to reduce the loss of spatial information included in the feature maps. The proposed method showed an improved segmentation result of about 12% compared to the conventional U-Net in the Cityscapes dataset experiment.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.4
• /
• pp.81-87
• /
• 2021

Artificial intelligence technology is developing as it enters the fourth industrial revolution. Active researches are going on; visual-based models using CNNs. U-net is one of the visual-based models. It has shown strong performance for semantic segmentation. Although various U-net studies have been conducted, studies on tracking objects with unclear outlines such as gases and smokes are still insufficient. We conducted a U-net study to tackle this limitation. In this paper, we describe how 3D cameras are used to collect data. The data are organized into learning and test sets. This paper also describes how U-net is applied and how the results is validated.

• Journal of Korean Society for Geospatial Information Science
• /
• v.20 no.4
• /
• pp.55-65
• /
• 2012

The purpose of this study is to construct the System Dynamics Model that can analyze urban spatial and temporal change and suggest the policy directions applicable to U-City Planning in Busan based on the SD model. It reviews previous literatures to elicit U-City issues and performs the case study to simulate urban spatial and temporal changes in Busan. The elicited results are connected into the policy directions of U-City planning. It emphasizes the necessity of business model suggestion based on U-City technology and industry not a tool, the U-City model construction that linkages and integrates the existing cities and new cities, and the excavation of U-City service model reflecting social and demographic changes.

• Spatial Information Research
• /
• v.18 no.2
• /
• pp.45-55
• /
• 2010

Place based intervention has become an important strategy for the ubiquitous city initiative. However, the role of the ubiquitous built environment in determining urban quality of life has not investigated fully. Using place as a relational space where people access u-infrastructure, u-health and u-services, this paper examines the relationship between spatial variations in the provision of ICTs and the spatial reconfiguration of quality of life operating at different geographical scales across Australia. Based on a case study of the state of Queensland in Australia, we emphasize the need for a place based approach to ubiquitous technologies and infrastructure provision in different socio economic hierarchies of space and place.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.7 no.1
• /
• pp.19-29
• /
• 2011

The u-Healthcare system, a new paradigm, provides healthcare and medical service anytime, anywhere in daily life using wired and wireless networks. It only doesn't reach u-Hospital at home, to manage efficient personal health in fitness space, it is essential to feedback process through measuring and analyzing a personal vital signs. MBAN(Medical Body Area Network) is a core of this technology. MBAN, a new paradigm of the u-Healthcare system, can provide healthcare and medical service anytime, anywhere on real time in daily life using u-sensor networks. In this paper, an ontology-based context-awareness in MBAN proposed system development methodology. Accordingly, ontology-based context awareness system on MBAN to Elderly/severe patients/aged/, with measured respiratory rate/temperature/pulse and vital signs having small variables through u-sensor network in real-time, discovered abnormal signs and emergency situations which may happen to people at sleep or activity, alarmed and connected with members of a family or medical emergency alarm(Emergency Call) and 119 system to avoid sudden accidents for early detection. Therefore, We have proposed that accuracy of biological signal sensing and the confidence of ontology should be inspected.

• Journal of Internet Computing and Services
• /
• v.11 no.2
• /
• pp.41-48
• /
• 2010

It is essential to guarantee a smooth communication and data exchange in a PHD(Personal Healthcare Device) network for applications providing U-health services. In spite of that, most of PHDs are heterogeneous, so the heterogeneity of their protocols makes it difficult to develop an integrated gateway sending sensed healthcare data to U-health service providers. To solve this problem, we suggest the design and implementation of a device adapter model based on dynamic managed module in this paper. Our model were implemented to work on the OSGi-based gateway middleware and to have interoperability in connection with the HL7 system that is the standard of the Healthcare Information systems. In addition, our model has an architecture supporting a communication based on the object serialization in order to provide extensibility in the functional aspect of applications. Through the experiment on a test-bed which is an implementation of the device adapter module for electrocardiogram and blood-pressure/blood-sugar device having one channel, we have confirmed the accuracy of sensing and sending data.

• Journal of Service Research and Studies
• /
• v.2 no.2
• /
• pp.45-51
• /
• 2012

U-healthcare is real-time monitoring of personal biometric information using by portable devices, home network and information and communication technology based healthcare systems, and fused together automatically to overcome the constraints of time and space are connected with hospitals and doctors. As u-healthcare gives health service in anytime and anywhere, it becomes to be a new type of medical services in patients management and disease prevention. In this paper, recent changes in prevention-oriented care is analyzed in becoming early response for Healthcare Information System by requirements analysis for technology development trend. According to the healthcare system, PACS, OCS, EMR and emergency medical system, U-healthcare is presenting the design of a patient-centered integrated client system. As the relationship between the meaning of the terms is used in the ontology, information models in the system is providing a common vocabulary with various levels of formality. In this paper, we propose an ontology-based system for patient-centered services, including the concept of clustering to clustering the data to define the relationship between these ontologies for more systematic data.

• Journal of Intelligence and Information Systems
• /
• v.13 no.1
• /
• pp.49-58
• /
• 2007

MDPDPTW (Multi-Depot Pickup and Delivery Problem with Time Windows) is a typical model among the optimization models based on the pickup and delivery flow in supply chains. It is based on multi-vehicles in multi-depots and does not consider moving vehicles near pickup and delivery locations. In ubiquitous environments, it is possible to obtain information on moving vehicles and their baggage. Providing the proper context from the perspective of moving vehicles and their baggage allows for more effective vehicle routings. This study proposes Integer Programming-based MDPDPTW including the information on moving vehicles and their baggage in a ubiquitous environment: u-MDPDPTW, and shows the viability and effectiveness of u-MDPDPTW through comparative experiments of MDPDPTW and u-MDPDPTW.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.36 no.4
• /
• pp.45-58
• /
• 2013

Korean local governments have been planning for u-City construction with great efforts. Such efforts are needed in order to reflect the urban characteristics of each city, to promote local economic growth, and to have a sustainable operation model. Thus it is critical at an earlier stage to set a strategic direction based on urban environment analysis, which will lead to a feasible implementation of u-City. This paper derives issues and suggests improvement methods based on a case study on the USPs (u-City Strategy Planning's) of ten local governments. It is expected that the improvement methods will greatly reduce risks involved in u-City construction and contribute to better provided local-specific u-services.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.1
• /
• pp.57-63
• /
• 1994

The logic function synthesis using ULM U$_h$ is constructed based on canonic Reed-Muller expansion coefficient for a given function. This paper proposes the fast synthesis algorithm using ULM U$_h$ for ternary function. By using circuit cost and synthesis method of proposed in this paper, order of control input variable minimum number of ULM U$_h$ can be decided in the synthesis of n-variable ternary function. Accordingly, this method enables to optimum circuit realization for ternary function synthesis using ULM ULM U$_h$ and can be applied to ternary function synthesis using ULM U$_h$. The complexity of search for select the order of all control input variables is (n+2)(n-1)/2.