• Korean Journal of Construction Engineering and Management
• /
• v.24 no.5
• /
• pp.73-82
• /
• 2023

Optimization of Construction Site Layout Planning (CSLP) heavily relies on workers' travel paths. However, traditional path generation approaches predominantly focus on the shortest path, often neglecting critical variables such as individual wayfinding tendencies, the spatial arrangement of site objects, and potential hazards. These oversights can lead to compromised path simulations, resulting in less reliable site layout plans. While Deep Reinforcement Learning (DRL) has been proposed as a potential alternative to address these issues, it has shown limitations. Despite presenting more realistic travel paths by considering these variables, DRL often struggles with efficiency in complex environments, leading to extended learning times and potential failures. To overcome these challenges, this study introduces a refined model that enhances spatial navigation capabilities and learning performance by integrating workers' visibility into the reward functions. The proposed model demonstrated a 12.47% increase in the pathfinding success rate and notable improvements in the other two performance measures compared to the existing DRL framework. The adoption of this model could greatly enhance the reliability of the results, ultimately improving site operational efficiency and safety management such as by reducing site congestion and accidents. Future research could expand this study by simulating travel paths in dynamic, multi-agent environments that represent different stages of construction.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.227-229
• /
• 2021

The modern society is advancing from the analog era to the digital imaging era, and in line with the trend of this era, various imaging devices such as exploration robots, medical equipment, and CCTV are helping our daily life a lot. However, noises caused by various causes in digital images not only cause image deterioration, but also deteriorate and deteriorate image quality. A typical noise is AWGN, and types of filters to remove it include an average filter, a median filter, and an alpha-trimmed average filter, but these filters have a disadvantage in that they show somewhat inadequate noise reduction performance in the high frequency region. Therefore, in this paper, a modified spatial division average filter based on standard deviation is proposed to effectively reduce AWGN existing in the high frequency region of the image.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.11 no.1
• /
• pp.155-166
• /
• 2008

The quantitative bivariate spatial pattern analysis was applied for the water quality and nutrients data of Masan Bay, and for this analysis Pearson's r as aspatial correlation measurement, Moran's I as spatial association measurement and L index as integration of aspatial and spatial measurement methods were used. To understand the aspatial and spatial characteristics implicated in L index, Pearson's r as well as Moran's I were classified into 3 types respectively, and Pearson's r and Moran's I were combined with 9 types, and also quantile of L index value was used for each of those 9 types. Finally, these types were defined as 5 groups having not overlapped L index range. According to the application result of L index groups, bivariate water quality and nutrients showed no aspatial correlation regardless of spatial association in February and July, but they showed aspatial correlation having clustered spatial pattern in May and November. The result of this study providing the guideline for the interpretation of aspatial correlation and spatial association using L index is expected to be helpful for the marine environment pattern analysis using quantitative index for further study.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.17 no.4
• /
• pp.101-111
• /
• 2014

Spatial events are predictable using data mining classification algorithms. Decision trees have been used as one of representative classification algorithms. And they were normally used in the classification tasks that have label class values. However since using rule ranking methods, spatial prediction have been applied in the spatial prediction problems. This paper compared rule ranking methods for the spatial prediction application using a decision tree. For the comparison experiment, C4.5 decision tree algorithm, and rule ranking methods such as Laplace, M-estimate and m-branch were implemented. As a spatial prediction case study, landslide which is one of representative spatial event occurs in the natural environment was applied. Among the rule ranking methods, in the results of accuracy evaluation, m-branch showed the better accuracy than other methods. However in case of m-brach and M-estimate required additional time-consuming procedure for searching optimal parameter values. Thus according to the application areas, the methods can be selectively used. The spatial prediction using a decision tree can be used not only for spatial predictions, but also for causal analysis in the specific event occurrence location.

• Journal of Korea Spatial Information System Society
• /
• v.8 no.2 s.17
• /
• pp.13-38
• /
• 2006

Range query is one of the most important operations for spatial objects, it retrieves all spatial objects that overlap a given query region in multi-dimensional space. The DOT(DOuble Transformation) is known as an efficient indexing methods, it transforms the MBR of a spatial object into a single numeric value using a space filling curve, and stores the value in a $B^+$-tree. The DOT index is possible to be employed as a primary index for spatial objects. However, the range query processing based on the DOT index requires much overhead for spatial transformations to get the query region in the final space. Also, the detailed range query processing method for 2-dimensional spatial objects has not been studied yet in this paper, we propose an efficient multi-dimensional range query processing technique based on the DOT index. The proposed technique exploits the regularities in the moving patterns of space filling curves to divide a query region into a set of maximal sub-legions within which space filling curves traverse without interruption. Such division reduces the number of spatial transformations required to perform the range query and thus improves the performance of range query processing. A visual simulator is developed to show the evaluation method and the performance of our technique.

• Journal of Environmental Science International
• /
• v.13 no.5
• /
• pp.479-488
• /
• 2004

Five sediment cores from the tidal flat of artificial Lake Shihwa are analyzed in terms of sedimentology and geochemistry to evaluate the heavy metal contamination and redox condition of surficial sediment following the Shihwa seawall construction. The variability of concentrations of various elements depends on the depositional environment, and reflects the various redox conditions and sediment provenances. The amounts of Ti and Al and their ratio of Ti/ Al with respect to Li clearly indicate that there is an anthropogenic contribution to the surficial sediment. The high concentrations of heavy metals suggest an anthropogenic contribution at ST. 34 and ST. 22. Concentrations of most elements (Cr, Cu, Zn and Pb) are higher near the Shihwa-Banwol industrial complex than in the central part of Lake Shihwa. Concentrations of heavy metal in surficial sediment near the Shihwa-Banwol industrial complex are two to eight times higher than in the center of Lake Shihwa. Enrichment factors (EF), which are normalized by the unpolluted shale, suggests a significant metallic contamination near the Shihwa-Banwol industrial complex (SBIC). The redox condition is divided into two anoxic and mixed oxi $c_oxic zones based on the carbon:sulfur (C/S) ratios of organic matter and elemental relationships. Correlations among geochemical elements Mn, U and Mo are significantly different from site to site, and may therefore be an indicator of the spatial redox condition. Controlling factors for switching anoxic/oxic conditions are thought to be water depth and the differences in industrial effluent supply. The variations of the Cu/Mn ratio in the sediments confirms above mentioned spatial differences of a redox condition in part, and therefore shows a location-dependence redox condition in sediments at four other sites. The redox condition of the surficial sediment characteristics of the Shihwa Lake are controlled by its geographic location and water depth.th.

• The Korean Journal of Physiology and Pharmacology
• /
• v.13 no.4
• /
• pp.315-319
• /
• 2009

Astragalus Membranaceus (AM) is a useful Korean herb that has been clinically prescribed for stress-related illness. The objective of the present study was to examine the anti-stress effects of AM on repeated stress-induced alterations of anxiety, learning and memory in rats. Restraint stress was administered for 14 days (2h/day) and AM (400mg/kg) given by oral administration, in the AM group, for the same period. Starting on the eighth day, the rats were tested for spatial memory on the Morris water maze test (MW) and for anxiety on the elevated plus maze (EPM). Changes of expression on immunohistochemistry were studied for cholineacetyl transferase (ChAT) and tyrosine hydroxylase (TH) in the brain. The results showed that the rats treated with AM had significantly reduced stress-induced deficits on learning and memory on the spatial memory tasks. In addition, the ChAT immunoreactivities were increased. In the EPM, treatment with AM increased the time spent in the open arms (p<0.001) compared to the control group. In addition, AM treatment also normalized increases of TH expression in the LC (p<0.001). In conclusion, administration of AM improved spatial learning and memory and reduced stress-induced anxiety. Thus, the present results suggest that AM is able to recover behavioral and neurochemical impairments induced by stress.

• Journal of the Economic Geographical Society of Korea
• /
• v.2 no.1_2
• /
• pp.27-45
• /
• 1999

Recently, the changes of industrial location can be explained as the concentration of small and medium manufacturing firms or high technology industries by industrial restructuring in Seoul metropolitan area, and the dispersion of large companies'branch plant into the peripheral region in Korea. Particularly deindustrialization is progressing in the inner city and manufacturing firms disperse into the outer city in Seoul metropolitan area. This study reviews on the structural perspectives for the changing industrial location factors. The development of capitalism organizes economic spacial structures and Its characteristics can be reasons which can raise changes in industrial location. Korean economy rapidly grew in the movement process of international capital. And capital accumulation by continuous economic growth is raising the spatial division of labor or the spatial difference and inequality on land price, wages. the base of labor reproduction. Therefore, these factors are the most reasons to raise the changes of industrial location in Korea. Hereafter the study on these factors, that is, in relation to sociocultural structure and land use structure have to be progress more concretely.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.18 no.4
• /
• pp.15-27
• /
• 2015

The objectives of this study are to analyze the quantitative ecological principal components of Korean Peninsula using the multivariate spatial environmental datasets and to compare the ecological difference between South and North Korea. Ecological maps with GIS(Geographical Information System) are constructed by PCA(Principal Component Analysis) based on seventeen raster(cell based) variables at 1km resolution. Ecological differences between South and North Korea are extracted by Factor Analysis using ecosystem maps masked from Korean ones. Spatial data include SRTM(Shuttle Radar Topography Mission), Temperature, Precipitation, SWC(Soil Water Content), fPAR(Fraction of Photosynthetically Active Radiation) representing for a productivity, and SR(Solar Radiation), which all cover Korean peninsula. When it performed PCA, the first three scores were assigned to red, green, and blue color. This color triplet indicates the relative mixture of the seventeen environmental conditions inside each ecological region. The first red one represents for 'physiographic conditions' worked by high elevation and solar radiation and low temperature. The second green one stands for 'seasonality' caused by seasonal variations of temperature, precipitation, and productivity. The third blue one means 'wetness condition' worked by high value such as precipitation and soil water contents. FA extraction shows that South Korea has relatively warm and humid ecosystem affected by high temperature, precipitation, and soil water contents whereas North Korea has relatively cold and dry ecosystem due to the high elevation, low temperature and precipitation. Results would be useful at environmental planning on inaccessible land of North Korea.

• Korean Journal of Optics and Photonics
• /
• v.16 no.4
• /
• pp.334-339
• /
• 2005

We studied the spatial filtering characteristics of a multi-phase hologram optical low-pass filter(HOLF). Using the Monte-Carlo based hologram generation program, we designed holograms whose diffraction patterns are circular shaped 21 beams and calculated the diffraction efficiencies and MTFs. 4-phase HOLF have the same diffraction efficiency as that of 2-phase HOLF. The MTF graphs of the two are also nearly alike. But 8-phase HOLF shows higher efficiency than those previously discussed and has larger MTF values in the low frequency region. 16-phase HOLF has just a little better characteristics than 8-phase. Considering the errors which can arise in the process of making holograms, 8-phase HOLF fits the goal of improving the resolution of spatial filter. We also fabricated 8-phase HOLF and .measured MTF The experimental results agree well with the theoretical expectations.