• Nuclear Engineering and Technology
• /
• v.55 no.1
• /
• pp.285-294
• /
• 2023

Autonomous radiation source detection has long been studied for radiation emergencies. Compared to conventional data-driven or path planning methods, deep reinforcement learning shows a strong capacity in source detection while still lacking the generalized ability to the geometry in unknown environments. In this work, the detection task is decomposed into two subtasks: exploration and localization. A hierarchical control policy (HC) is proposed to perform the subtasks at different stages. The low-level controller learns how to execute the individual subtasks by deep reinforcement learning, and the high-level controller determines which subtasks should be executed at the current stage. In experimental tests under different geometrical conditions, HC achieves the best performance among the autonomous decision policies. The robustness and generalized ability of the hierarchy have been demonstrated.

• Journal of Electrical Engineering and Technology
• /
• v.11 no.6
• /
• pp.1812-1824
• /
• 2016

The neural dynamics underlying the causal network during motor planning or imagery in the human brain are not well understood. The lack of signal processing tools suitable for the analysis of nonlinear and nonstationary electroencephalographic (EEG) hinders such analyses. In this study, noise-assisted multivariate empirical mode decomposition (NA-MEMD) is used to estimate the causal inference in the frequency domain, i.e., partial directed coherence (PDC). Natural and intrinsic oscillations corresponding to the motor imagery tasks can be extracted due to the data-driven approach of NA-MEMD, which does not employ predefined basis functions. Simulations based on synthetic data with a time delay between two signals demonstrated that NA-MEMD was the optimal method for estimating the delay between two signals. Furthermore, classification analysis of the motor imagery responses of 29 subjects revealed that NA-MEMD is a prerequisite process for estimating the causal network across multichannel EEG data during mental tasks.

• The Journal of Korean Academy of Prosthodontics
• /
• v.57 no.3
• /
• pp.312-320
• /
• 2019

One of the fastest growing segments of implant dentistry is the utilization of computed tomography (CT) scan data and treatment planning software in conjunction with guided surgery for implant reconstruction cases. Computer assisted planning systems and associated surgical templates have established a predictable, esthetic, functional technique for placing and restoring implants. Especially, a philosophy of restoratively driven implant placement has been generally adopted. Recently, a variety of commercial dental fields have released their scanning and fabricating protocols and methods for restorations. This process is still being investigated and developed for the most precise and predictable outcome. This case report describes a female patient who wanted dental implants in fully edentulous areas. Restoratively driven implant placements were performed with surgical guide and the patient was fully satisfied with the clinical results, and at 5-year post restorative follow-up assessment, both implant and prosthesis were proved clinical success.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2006.05a
• /
• pp.333-337
• /
• 2006

The purpose of this paper is to present a strategic approach to selecting prior areas of soil erosion to be examined for effective soil conservation planning and management, in conjunction with remote sensing data and GIS skill for surface characteristics. To do this, two basins are selected: Andong and Imha basin. Geographically one is in the vicinity of the other but turbidity in the main reservoir of each basin is quite different. it is important to clarify general behavior of soil erosion driven by rainfall event for both basins for further understanding and effective soil conservation planning and management. Also, Both basins are divided into several sub-basins and the severity of soil loss is intensively investigated to identify areas with high erosion potential for each sub-basin so that the efficiency of soil conservation program may increase. Especially, this study analyzed soil erodibility factor(K), topographic factor(LS), cover management factor(C) and soil erosion; 3 sub-basins for Andong basin (up-, mid-, downstream) and 6 sub-basins for Imha basin (up-, mid-, and downstream for two tributaries) because Imha basin consists of two tributaries (Banyeon and Yongjeon river). The approach suggested herein will provide a guideline for choosing prior areas to be examined and managed for soil conservation planning.

• Journal of Korean Society of Rural Planning
• /
• v.22 no.2
• /
• pp.31-43
• /
• 2016

In existing method, research for landscape resource is driven by professional (or with the participation of local people at Tokenism level), and usually hinder local residents from reflecting their appreciations on the landscape resources in their own ways and eventually ends up with indistinguishable landscape planning. To avoid this, a profound understanding of what landscape they experience in their daily life and how they perceive it should be empirically analysed carefully. The purpose of this study is to apply walking behavior as a method to examine local residents' subjective perceptions and consider its usability. The researcher walked the site(Sucheongri) with the residents, carrying a GPS device, taking photographs of the landscape objects they described, and recording the relevant explanations. After gathering photographs and explanations which represent the research participants' individual subjective perception, the researcher analysed the explanation using open coding, based on grounded theory. By the analysis, 117 landscape objectives are identified and 18 reason factors for landscape perception were deduced from the explanation. Those factors could be classified as 'positive feeling inducing' and 'negative feeling inducing', and also as 'personal emotion based' and 'community based emotion'. By comparison between feeling map by conventional method and feeing map by new method, usability of new method was empirically reveled. Walking behavior makes it easier for researcher to get more abundant data in quantitative aspect and profound understanding with affection of respondent by allowing them to 'go beyond' the perceptions they remember. Finally new method with walking gives professionals a contextual understanding of a place and more resident-oriented plans and management on sites.

• Geophysics and Geophysical Exploration
• /
• v.23 no.3
• /
• pp.168-177
• /
• 2020

Seabed multiple reflections (seabed multiples) are the main cause of misinterpretations of primary reflections in both shot gathers and stack sections. Accordingly, seabed multiples need to be suppressed throughout data processing. Conventional model-driven methods, such as prediction-error deconvolution, Radon filtering, and data-driven methods, such as the surface-related multiple elimination technique, have been used to attenuate multiple reflections. However, the vast majority of processing workflows require time-consuming steps when testing and selecting the processing parameters in addition to computational power and skilled data-processing techniques. To attenuate seabed multiples in seismic reflection data, input gathers with seabed multiples and label gathers without seabed multiples were generated via numerical modeling using the Marmousi2 velocity structure. The training data consisted of normal-moveout-corrected common midpoint gathers fed into a U-Net neural network. The well-trained model was found to effectively attenuate the seabed multiples according to the image similarity between the prediction result and the target data, and demonstrated good applicability to field data.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.6_2
• /
• pp.1017-1027
• /
• 2022

Development of social overhead capital (SOC) requires huge national finance, and performance issues such as cost-efficiency, safety, and environment have been constantly raised. However, currently each construction client has limited access to its own projects' performance without analytic methodology for industry-level comparisons and benchmarking for improvement. To overcome this problem, this study proposes a comprehensive performance analysis framework for post-evaluation of large-scale construction projects. To this end, this study performed a case study of advanced countries (the U.S., the U.K. and Japan) and consultation with related experts to develop a tailored performance analysis framework for the Post- Construction Evaluation and Management system in Korea. The developed framework covers three categories (project performance, project efficiency, and ripple effect), nine areas (cost, schedule, change, safety, quality, demand, benefit-cost ratio, civil complaint, and defect), and 31 detailed metrics. Using industry-level project performance database and statistical techniques, the proposed framework can be used not only to diagnose excellent and unsatisfactory performance areas for completed construction projects, but also to provide reference data for future similar projects. This study can contribute to the improvement of clients' performance management practices and effectiveness of construction projects.

• Korean Journal of Agricultural Science
• /
• v.46 no.2
• /
• pp.381-393
• /
• 2019

A smart farm is a system that combines information and communication technology (ICT), internet of things (IoT), and agricultural technology that enable a farm to operate with minimal labor and to automatically control of a greenhouse environment. Machine learning based on recently data-driven techniques has emerged with big data technologies and high-performance computing to create opportunities to quantify data intensive processes in agricultural operational environments. This paper presents research on the application of machine learning technology to diagnose the growth status of crops and predicting the harvest time of strawberries in a greenhouse according to image processing techniques. To classify the growth stages of the strawberries, we used object inference and detection with machine learning model based on deep learning neural networks and TensorFlow. The classification accuracy was compared based on the training data volume and training epoch. As a result, it was able to classify with an accuracy of over 90% with 200 training images and 8,000 training steps. The detection and classification of the strawberry maturities could be identified with an accuracy of over 90% at the mature and over mature stages of the strawberries. Concurrently, the experimental results are promising, and they show that this approach can be applied to develop a machine learning model for predicting the strawberry harvesting time and can be used to provide key decision support information to both farmers and policy makers about optimal harvest times and harvest planning.

• Spatial Information Research
• /
• v.9 no.1
• /
• pp.73-89
• /
• 2001

In the recent rapidly changing technology environment the computerization of administration business using GIS is driven or will be driven to give improved information services for the people by local government or central government with huge budget. Development of GIS for local governments is investigated with huge budge. Development of GIS for local governments is investigated to prevent local government from investing redundant money and to reuse the existing investment at this time. The purpose of this study is finding the development method of Land Management Information System (LMIS) to give service and share data in various computing environment of local governments. To do this, we have to develop LMIS as open system with interoperability and we explain it with a focus to framework of Open LMIS. According to recent trend of technology we developed Open LMIS for convenient maintenance with nationwide LMIS expansion at hand. This system was developed at the $\ulcorner$Land Management Information System Development$\lrcorner$project which was managed by Ministry of Construction and Transportation (MOCT). GIS application was based on OpenGIS CORBA specification for development of standard interface and RUP(Rational Unified Process) for development method and LML(Unified Modeling Language) for system design. Developed systems were land administration system for local government, spatial planning support system for regional government, and land policy support system for MOCT.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.9
• /
• pp.458-465
• /
• 2020

Technological advances in artificial intelligence are affecting many industries, such as telecommunications, logistics, security, and healthcare, and research and development related to economic, efficiency, linkage with commercial technologies are the current focus. Predicting the changes in the future battlefield environment and ways of conducting war from a strategic point of view, as well as designing/planning the direction of military development for a leading response is not only a basic element to prepare for comprehensive future threats but also an indispensable factor that can produce an optimal effect over a limited budget/time. From this perspective, this study was conducted as part of a technology-driven plan to discover potential future technologies with high potential for use in the defense field and apply them to R&D. In this study, based on research data collected in a defense future technology investigation, the future new technology that requires further research was predicted by considering the redundancy with existing defense research projects and the feasibility of technology. In addition, an empirical study was conducted to verify the significance between the future new defense technology and the evaluation indicators in the AI field.