• Journal of Digital Convergence
• /
• v.15 no.2
• /
• pp.173-181
• /
• 2017

In this paper, we have studied tracking as a training stage of considering the position and the scale of a person given its previous position, scale, as well as next and forward image fraction. Unlike other learning methods, CNN is thereby learning combines both time and spatial features from the image for the two consecutive frames. We introduce multiple path ways in CNN to better fuse local and global information. A creative shift-variant CNN architecture is designed so as to alleviate the drift problem when the distracting objects are similar to the target in cluttered environment. Furthermore, we employ CNNs to estimate the scale through the accurate localization of some key points. These techniques are object-independent so that the proposed method can be applied to track other types of object. The capability of the tracker of handling complex situations is demonstrated in many testing sequences. The accuracy of the SVM classifier using the features learnt by the CNN is equivalent to the accuracy of the CNN. This fact confirms the importance of automatically optimized features. However, the computation time for the classification of a person using the convolutional neural network classifier is less than approximately 1/40 of the SVM computation time, regardless of the type of the used features.

• Journal of Digital Convergence
• /
• v.18 no.4
• /
• pp.201-209
• /
• 2020

In this paper, we perform a case study of children's emotional care program that analyzes the emotional status through the drawings of children based on web system. In order to overcome spatial and temporal environment constraints, we have developed based on web system that performs to support the whole process from the request of analysis of children 's drawings to the feedback of the final result step by step. The online platform is designed to conduct observations for the purpose of primary screening using a smartphone, and then proceed to the offline secondary care linkage process based on the results. Then according to the results of the analysis, children and parents who need deep examination are figured out and professional institutions are linked to them for help. Parental stress had been analyzed to improve the accuracy of the test and to figure out the cause of the problem. The study was conducted on 2,532 children and their parents between the ages of 3 and 5 years attending a day care center. As a result, 564 children and 223 parents were figured out to be in need of secondary institutional care, and 311 parents were educated and counseled from the professional institutions.

• Journal of Cadastre & Land InformatiX
• /
• v.50 no.1
• /
• pp.215-229
• /
• 2020

In response to the recent 4th industrial revolution, the demand for 3D object models in the latest fields of digital twin, autonomous driving, and VR/AR, as well as the existing fields such as city, construction, transportation, and energy has increased significantly. It is expected that the demand for 3D object models with various precision from LOD1 to LOD4 will increase more and more in various industry fields. However, the Ministry of Land, Infrastructure and Transport, and the local government and the private sector have partially built 3D object models of different precisions for some specific regions because of the huge cost. Therefore, this study proposes a feasible plan that can solve the cost problem in generating 3D object models for the whole territory. For our purpose, we first analyzed usage, demand, generation technology and generation cost for 3D object models. Afterwards, we proposed LOD3 model generation plan for all territory using automatic 3D object model generation technology based on image matching. Additionally, we supplemented the proposed plan by using LOD4 generation plan for landmarks and LOD2 generation plan non-urban area. In the near future, we expect this would be a great help in establishing a feasible and effective 3D object model generation plan for the whole country.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.9 no.1
• /
• pp.82-89
• /
• 2016

And by entering into an aging society with economic growth "beautiful and healthy desire to live', aesthetics industry as promote interest in 'Anti-aging' is emerging as a promising business increased significantly the skin care market. However, the management of the hospital or the temporal order to receive professional care providers, spatial, and cost constraints caused many companies to solve this problem began to approach the Home Care Area. Global trends in personal skin care market has been activated, the domestic has been activated at low cost, private market due to the recession. We have performed this test in order to develop a skin care device for home in order to compensate for this point.In this paper, we develop a low-level laser to create a personal skin care products and sought to incorporate them into the skin cosmetic.Expand the pores by using the low-level laser to the skin by to the dermal layer of the skin was penetrated aim experiment the ampoule, and by a comparison of the medical low-level laser reliability and determine the effectiveness or absence of the performance and efforts to commercialize.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.8
• /
• pp.55-63
• /
• 2017

Due to spatial problems and system size,conventional measurement methods used to acquire the information needed for existing electrical energy and management have been limited to new buildings or areas where replacement is possible. This electric load management method is problematic when applying it to energy and safety management of vulnerable areas or existing homes or offices. The problem with installing a measurement module in every branch is that the system is too large. Even if the measurement module is installed, the type of load is not recognized, and efficient management is not performed. In particular, it is very difficult to apply it to traditional markets and backward facilities in Korea. In this paper, we apply NIALM technology and arc detection technology to solve these problems and verify the feasibility of NIALM for normal arc generation. Also, based on the verification results, we propose a new smart home safety management system that can effectively manage electrical safety and that can be applied to conventional market and existing home safety management systems. The proposed system conducts a comparative performance test with an existing safety management system. In addition, it achieves 95% or more load recognition for four loads, which is impossible in 40% of the existing systems, and the arc detection function was confirmed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.2
• /
• pp.357-363
• /
• 2014

The development of information technology grows the society and allows the user to generate more information and the requirements. According to recent growing interest in digital convergence technologies, digital convergence can be utilized by a variety of methods as a new study. Electronic culture atlas would be digitized cultural information that represents a particular area on the map. In detail, spatial data like as point, line, and area can be used to represent the culture information. Using electronic culture atlas, also, it is possible to provide and utilize information which is associated with time, space(map) and subject(culture). Thus, electronic culture atlas could be used as a method for the humanities or area studies and spread research results by displaying on the culture atlas. In general, existing electronic culture atlas used bitmap image mostly as a base map. Using bitmap image, it is difficult to represent to provide three-dimensional information of specific area. Also, it happens problem such as breakage occurs during zoom-in operation. To solve this problems, we design and implement electronic culture atlas based on Google Earth which is three-dimensional map service.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.5
• /
• pp.3518-3524
• /
• 2015

Spatial and time variation of the precipitation in Korea is high, therefore, more than 2/3 of the annual precipitation is concentrated during the rainy season. Climate change also causes the intensive rainfall in the area of dense population, thus the occurrence frequency of the heavy flood in the impervious area has been increased. Therefore, the structural food mitigation measures such as the construction of the higher design frequency stormwater pipes, pumping stations, and/or detention ponds. The flood bypass tunnel or retention storage is also one of the efficient structures to mitigate flood damage in the urban area. However, the economic feasibility has been controversial because the flood bypass tunnel might be used once or twice a year. To solve the problem, the multi-functional tunnel for the urban traffic and flooding bypass has been considered. In this study, the design criteria of the road and water tunnel has been analysed and the composite design criteria is proposed for the multi-functional tunnel which is expected to be constructed.

• Journal of Korea Water Resources Association
• /
• v.43 no.8
• /
• pp.721-731
• /
• 2010

The rainfall-runoff relationship is very difficult to predict because it is complicate factor affected by many temporal and spatial parameters of the basin. In recent, models which is based on artificial intelligent such as neural network, genetic algorithm fuzzy etc., are frequently used to predict discharge while stochastic or deterministic or empirical models are used in the past. However, the discharge data which are generally used for prediction as training and validation set are often estimated from rating curve which has potential error in its estimation that makes a problem in reliability. Therefore, in this study, water stage is predicted from antecedent rainfall and water stage data for short term using three models of neural network which trained by error back propagation algorithm and optimized by genetic algorithm and training error back propagation after it is optimized by genetic algorithm respectively. As the result, the model optimized by Genetic Algorithm gives the best forecasting ability which is not much decreased as the forecasting time increase. Moreover, the models using stage data only as the input data give better results than the models using precipitation data with stage data.

• Journal of Korea Water Resources Association
• /
• v.38 no.8 s.157
• /
• pp.631-643
• /
• 2005

The objective of this study is to perform hydraulic and numerical model experiments of the flows in circulation-water-pump(CWP) chambers of combined cycle power plants (CCPP) to be built and to suggest improvement plans if the flows might cause a serious problem on the operation of CWPs. Hydraulic model was constructed in a scale of 1 to 20 using acrylic sheets and a two dimensional numerical model used was RMA2. To evaluate results of Hydraulic and numerical model experiments, evaluation criteria of flow conditions in the intake canal and CWP chambers were determined. Vertical vorticities obtained from numerical simulations for the initial plan of CCPPs were qualitatively compared with results of hydraulic model experiments and the formation possibility of a large scale vortex, one of the flow evaluation criteria, was evaluated. The initial plan was found not to satisfy the flow evaluation. Nine improvement plans were devised and numerically simulated. Four alternative plans among nine improvement plans were selected and hydraulically experimented. On the ground of the results of hydraulic model experiments, a final improvement plan, one of four improvement plants, was suggested. When CWP chambers and intake canals were designed with spatial constraints, flow separating wall and guide walls were found to improve flow conditions in CWP chambers.

• Journal of Wetlands Research
• /
• v.20 no.1
• /
• pp.94-104
• /
• 2018

In general, the rainfall-runoff simulation is performed using rainfall data from meteorological and observational rain gauge stations. However, if we only use rainfall data from meteorological and observational rain gauge stations for runoff simulation of a large watershed, the problem in the reliability of the simulated runoff can be occurred. Therefore, this study examined the influence of the rainfall data on the simulated runoff volume by a Semi-distributed model. For this, we used rainfall data from meteorological stations, meteorological and observational stations, and a spatially distributed rainfall data from hypothetical stations obtained by kriging method. And, we estimated the areal rainfall of each sub-basin. Also the estimated areal rainfall and the observed rainfall were compared and we compared the simulated runoff volumes using SWAT model by the rainfall data from meteorological and observational rain gauge stations and runoff volume from the estimated areal rainfall by Kriging method were analyzed. This study was performed to examine the accuracy of calculated runoff volume by spatially distributed areal rainfall. The analysis result of this study showed that runoff volume using areal rainfall is similar to observed runoff volume than runoff volume using the rainfall data of weather and rain gauging station. this means that spatially distributed rainfall reflect the real rainfall pattern.