• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.6
• /
• pp.1319-1326
• /
• 2024

Accurate crowd density prediction is crucial for applications such as crowd management, public safety, and urban planning. Traditional methods often struggle with capturing temporal dependencies and dynamic changes in video sequences, leading to less reliable forecasts. Dense and dynamic crowds present additional challenges, including occlusions, motion blur, and varied perspectives, which complicate accurate density estimation. To address these issues, we propose a novel approach that integrates convolutional Long Short-Term Memory (convLSTM) networks with Multi-Head Attention mechanisms. This combined model improves prediction accuracy by effectively capturing temporal patterns and spatial relationships, even in complex scenarios. Extensive experiments show that our method significantly outperforms traditional techniques, offering a robust solution for precise crowd density prediction in real-world applications.

• Journal of Cadastre & Land InformatiX
• /
• v.54 no.2
• /
• pp.5-18
• /
• 2024

To produce seamless cadastral maps through coordinate transformation, a correction that minimizes the boundary difference between neighboring zones or maps is required. In coordinate transformation, a technology that emphasizes specific common points in cadastral surveying was developed, and the usefulness of the perspective projection is presented as a technology to eliminate the coordinate difference between the adjacent four map points that occurs as a result of the coordinate transformation. The correction of the displacement of the vertice points and the map matching entail changes in the boundary line of the parcel, which changes the shape of the parcel and causes changes in the area of the parcel. Therefore, in order to ultimately ensure the consistency of the registered area and the coordinate area, the introduction of a numerical calculation method by the least square method is presented as a working method that can fine-tune the boundary points. The method of utilizing the Affine transformation, perspective projection, and boundary point refinement in conjunction improves the quality of the maps, which has been managed as an individual maps, and enables them to be created as a continuous map over the area.

• Korean Journal of Construction Engineering and Management
• /
• v.9 no.1
• /
• pp.187-198
• /
• 2008

There are usually plenty of material inventories in a construction site. More inventories can meet unexpected demands, and also they may have an economical advantage by avoiding a probable escalation of raw material costs. On the other hand, these inventories also cause negative aspects to increase costs for storing redundant inventory as well as decreasing construction productivity. Therefore, a proper method of deciding an optimal level of material inventories while considering dynamic variations of resources under uncertainty is very crucial for the economical efficiency of construction projects. This research presents a stochastic modelling method for construction operations, particularly targeting a work process involving on-site fabrication of raw materials like iron-rebar process (delivery, cut and assembly, and placement). To develop the model, we apply the concept of factory physics to depict the overall components of a system. Then, an optimal inventory management model is devised to support purchase decisions where users can make timely actions on how much to order and when to buy raw materials. Also, optimal time lag, which minimizes the storage time for pre-assembled materials, is obtained. To verify this method, a real case is applied to elicit an optimal amount of inventory and time lag. It is found that average values as well as variability of inventory level decreased significantly so as to minimize economic costs related to inventory management under uncertain project condition.

• Journal of Korea Water Resources Association
• /
• v.38 no.7 s.156
• /
• pp.517-526
• /
• 2005

In Korea, the methods of estimating groundwater recharge can categorized into two groups. One is baseflow separation method by means of groundurater recession curve, the other is water level fluctuation method by using the data from groundwater monitoring wells. Baseflow separation method is based on annual recharge and lumped concept, and water-table fluctuation method is largely dependent on monitoring wells rather than water budget in watershed. However, groundwater recharge rate shows the spatial-temporal variability due to climatic condition, land use and hydrogeological heterogeneity, these methods have various limits to deal with these characteristics. For this purpose, the method of estimating daily recharge rate with spatial variability based on distributed rainfall-runoff model is suggested in this study. Instead of representative recharge rate of large watershed, the subdivided recharge rate with heterogeneous characteristics can be computed in daily base. The estimated daily recharge rate is an advanced quantity reflecting the heterogeneity of hydrogeology, climatic condition, land use as well as physical behaviour of water in soil layers. Therefore, the newly suggested method could be expected to enhance existing methods.

• Journal of Korea Water Resources Association
• /
• v.46 no.11
• /
• pp.1041-1052
• /
• 2013

In this study, we estimate parameters of a distributed hydrologic model, GRM (grid based rainfall-runoff model), using a model-independent parameter estimation tool, PEST. We implement auto calibration of model parameters such as initial soil moisture, multipliers of overland roughness and soil hydraulic conductivity in the Geumho River Catchment and the Gamcheon Catchment using radar rainfall estimates and ground-observed rainfall represented by Thiessen interpolation. Automatic calibration is performed by GRM-MP (multiple projects), a modified version of GRM without GUI (graphic user interface) implementation, and "Parallel PEST" to improve estimation efficiency. Although ground rainfall shows similar or higher cumulative amount compared to radar rainfall in the areal average, high spatial variation is found only in radar rainfall. In terms of accuracy of hydrologic simulations, radar rainfall is equivalent or superior to ground rainfall. In the case of radar rainfall, the estimated multiplier of soil hydraulic conductivity is lower than 1, which may be affected by high rainfall intensity of radar rainfall. Other parameters such as initial soil moisture and the multiplier of overland roughness do not show consistent trends in the calibration results. Overall, calibrated parameters show different patterns in radar and ground rainfall, which should be carefully considered in the rainfall-runoff modelling applications using radar rainfall.

• Korean Journal of Construction Engineering and Management
• /
• v.10 no.5
• /
• pp.123-134
• /
• 2009

Since 1970s, urethane waterproofing method is broadly used in rooftops, underground spaces, and sports stadium for its outstanding ultraviolet blockage, watertightness, and elasticity. However, development of slippage-resistance and endurance, improvement of function considering convenience and visually pleasing of users, urethane waterproofing method is necessary, since rooftops and underground spaces have slippage and external force risks. Therefore, many improved waterproofing methods are being developed and, recently, embo-thane waterproofing method, which applies embo-spray coating system, has been developed. This paper explains exposure, nonexposure, and floor-material of embo-thane waterproofing method, and then perform experimental study for comparison with urethane waterproofing method about tensile strength, coefficient of expansion, performance of bond, anti-abrasion, and slippage-resistance. In addition, the performance index was presented for the superiority of embo-thane waterproofing method compared to urethane by setting up evaluation criteria considering not only physical performance but also design side of embo-thane waterproofing method, and Value Analysis applying AHP. Also for an assessment considering uncertain result, Monte Carlo Simulation Method was used to operate reliability analysis through statistic approach method.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.6
• /
• pp.583-590
• /
• 2021

This paper is a study on the digitization of an analog 3D pen. The term digital implies features such as homeostasis, transformability, combinability, reproducibility, and convenience of storage. One device that produces a combination of these digital characteristics is a 3D printer, but its industrial use is limited due to low productivity and limitations with materials and physical characteristics. In particular, improvements are required to use 3D printers, such as better user accessibility owing to expertise and skills in modeling software and printers. Complementing this fact is the 3D pen, which is excellent in portability and ease of use, but has a limitation in that it cannot be digitized. Therefore, in order to secure a digitalization capability and ease of use, and to secure the safety of printing materials that pose controversial hazards during the printing process, research problems and alternatives have been derived by combining food, and digitization was demonstrated with a newly developed 3D pen. In order to digitize the 3D pen, a sensor in a structured device detects the motion of an analog 3D pen, and this motion is converted into 3D data (X-Y-Z coordinate values) through a spatial analysis algorithm. To prove this method, the similarity was confirmed by visualization using MeshLab version 1.3.4. It is expected that this food pen can be used in youth education and senior healthcare programs in the future.

• Journal of Plant Biotechnology
• /
• v.48 no.3
• /
• pp.179-185
• /
• 2021

Indoor gardening includes wall greening, terrariums, and flower arrangements. Among these types of indoor gardens, the terrarium is easy to access for the general public, but in Korea, because of the focus on esthetics, the original purpose of creating terrariums, which was to grow plants sustainably in an enclosed space, has been lost. In addition, miniaturization of plants is required to grow plants in an enclosed space. Since the available plant species suitable for a terrarium are limited, only plants such as succulents, cacti, and moss have been used. In this study, Bronze (X Graptosedum) was used, and these problems were solved using the following three methods: placement and growth of virus-free plants in the terrarium; extending the diversity of plants with minimal size that can be planted in terrariums; and reducing the price of in vitro plants with minimal size by achieving large-scale production. In particular, tissue-cultured succulents were developed into a Vivorium by replacing the tissue culture container and renewing the composition of the plant. This paper suggests a new indoor horticultural field, Vivorium, that can improve the current limitations of terrariums and make them more accessible to the general public. The introduction and popularization of new indoor gardening fields with the increase in single-person households and indoor activities in the Pandemic era can also improve psychological stability among people and in the society.

• 한국노년학
• /
• v.38 no.4
• /
• pp.1057-1081
• /
• 2018

This study analyzed the case of elderly care cluster in Gwangjin-gu to explore the possibilities of social economy as a provider of community-based social services. Community-based means the approach by which community organizations build a voluntary and collaborative network to enhance collective problem-solving abilities. Therefore, it is very likely that the social economy that emphasizes people, labor, community, and democratic principles can contribute to community-based social services. This study analyzed social economic network by using four characteristics of social economy suggested by OECD community economy and employment program as an analysis framework. The results of this study are as follows: First, it is found that social economy would hardly supply community-based social services through network cooperation because of a large variation in community identity, investment to new product, and labor protection. Second, community users are not the consumers of the social economy and the products of the social economy stay in market products only for the organizations in social economy. In order to create good services that meet the needs of residents, community development approaches are required at the same time. The importance of community space where local residents and social economy meet is derived. Third, public support such as purchasing support has weakened the ecosystem of social economy by making the distinction between public economy and social economy more obscure. On the other hand, public investment in community infrastructure is an indirect aid to social economy to communicate with residents and to promote good supply and consumption. In the end, community-based social services need a platform where the social economy and the people meet. This type of public investment can create the ecosystem of the social economy.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.2
• /
• pp.38-46
• /
• 2011

3D motion analysis system which is currently widely used for walking analysis has limitations due to both necessity of wide space for many cameras for measurement, high cost, and complicated preparation procedure, which results in low accessability in use and application for clinical diagnosis. To resolve this problem, we developed 3-dimensional wireless ambulatory measurement system based on inertial sensor which can be easily applicable for clinical diagnosis for lower extremity deformity and developed system was evaluated by applying for 10 elderly people with diabetes mellitus. Developed system was composed of wireless ambulatory measurement module that consists of inertial measurement unit (IMU) which measures the gait characteristics, microcontroller which collects and precesses the inertial data, bluetooth device which transfers the measured data to PC and Window's application for storing and processing and analyzing received data. This system will utilize not only to measure lower extremity (foot) problem conveniently in clinical medicine but also to analyze 3D motion of human in other areas as sports science, rehabilitation.