• 한국농공학회논문집
• /
• 제62권1호
• /
• pp.51-60
• /
• 2020

The purpose of this study is to determine the spatial and temporal resolutions that can represent land surface characteristics comprised of various land use using Landsat/AMSR2-based soil moisture data. We estimated the Landsat (30 m×30 m)-based soil moisture values using the soil moisture regression model. Then, the Landsat (30 m×30 m)-based soil moisture (reference values) were resampled to the relatively coarse resolutions from 1 km to 4 km, respectively. Comparing the reference values to the resampled soil moisture values, we confirmed that uncertainties were increased with the spatial resolutions of 2 km~4 km indicating that the spatial resolution of 1 km×1 km is required to represent the complicated land surface. Also, the AMSR2 soil moisture values have less uncertainties compared to SMAP data with the temporal resolution of 1~2 days. Thus, our findings can be useful for various areas such as agriculture, hydrology, forest, etc.

• Smart Structures and Systems
• /
• 제30권6호
• /
• pp.601-612
• /
• 2022

The prediction of structural mechanical behaviors is vital important to early perceive the abnormal conditions and avoid the occurrence of disasters. Especially for underground engineering, complex geological conditions make the structure more prone to disasters. Aiming at solving the problems existing in previous studies, such as incomplete consideration factors and can only predict the continuous performance, the deep attention fused temporal convolution network (DATCN) is proposed in this paper to predict the spatial mechanical behaviors of structure, which integrates both the temporal effect and spatial effect and realize the cross-time prediction. The temporal convolution network (TCN) and self-attention mechanism are employed to learn the temporal correlation of each monitoring point and the spatial correlation among different points, respectively. Then, the predicted result obtained from DATCN is compared with that obtained from some classical baselines, including SVR, LR, MLP, and RNNs. Also, the parameters involved in DATCN are discussed to optimize the prediction ability. The prediction result demonstrates that the proposed DATCN model outperforms the state-of-the-art baselines. The prediction accuracy of DATCN model after 24 hours reaches 90 percent. Also, the performance in last 14 hours plays a domain role to predict the short-term behaviors of the structure. As a study case, the proposed model is applied in an underwater shield tunnel to predict the stress variation of concrete segments in space.

• 대한공간정보학회지
• /
• 제24권4호
• /
• pp.75-81
• /
• 2016

본 연구에서는 아파트 실거래가와 이에 영향을 미치는 변인들의 공간적 이질성을 시공간적인 측면에서 탐색하는데 초점을 두었다. 아파트 실거래가에 영향을 미칠 것으로 사료되는 독립변수로서 교통 및 지역적 특성과 교육여건, 인구 경제적 특성을 고려하였다. 따라서 전역적인 측면과 국지적인 측면에서 독립변수의 영향력과 공간상의 분포패턴을 분석하였으며, 종속변수인 아파트 실거래가의 시공간적인 변화패턴을 살펴보았다. 먼저, 분석모형 구축을 위해 일반최소제곱분석과 지리가중회귀분석을 수행하여 보다 효율적이고 적합한 모형을 채택하였다. 2010년과 2013년의 모형 분석결과는 유사한 패턴을 보이며, 두 시기 모두 지리가중회귀모형이 일반최소제곱모형보다 더 설명력이 있는 모형인 것으로 분석되었다. 둘째, 채택된 지리가중회귀모형을 이용하여 독립변수의 시공간적 이질성을 파악하기 위해 Local $R^2$를 이용하여 국지적 분석을 수행하였다. Local $R^2$값은 지역별로 상이하게 나타났으며 이는 공간상의 이질성이 존재함을 보여주는 것으로 판단할 수 있다. 셋째, 지리가중회귀분석 시 종속변수로 사용했던 아파트 실거래가의 시기별/전용면적별 공간분포를 살펴보기 위해 크리깅분석을 실시하였다. 이를 통해 아파트 실거래가와 같은 공간데이터에 영향을 미치는 외부적 환경도 지역별 이질성이 크기 때문에 공간적 편차가 있는 것으로 나타났다. 따라서 이러한 결과를 바탕으로 보다 미시적인 주택하위시장분석을 수행할 수 있고, 부동산정책을 수립하는데 근간이 될 수 있을 것으로 사료된다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(4)
• /
• pp.29-32
• /
• 2001

Visual speech information improves the performance of speech recognition, especially in noisy environment. We have tested the various spatial-temporal features for the Korean lipreading and evaluated the performance by using a hidden Markov model based classifier. The results have shown that the direction as well as the magnitude of the movement of the lip contour over time is useful features for the lipreading.

• 한국수산과학회지
• /
• 제46권1호
• /
• pp.59-69
• /
• 2013

Temporal and spatial variation in the freshwater region, created by river runoff, of a small bay, caused by the passage of typhoons was examined using a three-dimensional primitive equation model (the Princeton Ocean Model, POM). Numerical experiments were implemented focusing on temporal evolution in the freshwater region in association with typhoon tracks. The model domain covered most of the estuary around the Nakdong River, including Noksan Bay, where river water is periodically released from upstream (Noksan dam). The model showed that the extension of the freshwater region outside of the bay depended strongly on the tracks of typhoons, specifically the associated wind directions and inner flow fields that are accompanied by new clockwise eddies. The model also showed that entrainment from typhoon passage frequently creates salt wedges in the estuary, indicating that organisms in the bay are biologically and chemically influenced with variation in the freshwater region.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.473-475
• /
• 2003

To overcome the limitation that traditional GISs lose much information for the real world, 4-dimensional GIS has the additional reference systems including object's height and temporal dimension. This paper describes the 4-dimensional geometric object model and components. The prototype for 4-dimensional GIS consists of the data provider, manager, and renderer components. We show the virtual city that its database contains topographic maps, buildings, roads and temporal history data. This provides spatial, temporal operations and analysis functions.

• ETRI Journal
• /
• 제43권2호
• /
• pp.272-287
• /
• 2021

This article presents a multi-dimensional spatial pattern analysis of crime events in San Francisco. Our analysis includes the impact of spatial resolution on hotspot identification, temporal effects in crime spatial patterns, and relationships between various crime categories. In this work, crime prediction is viewed as a classification problem. When predictions for a particular category are made, a binary classification-based model is framed, and when all categories are considered for analysis, a multiclass model is formulated. The proposed crime-prediction model (HotBlock) utilizes spatiotemporal analysis for predicting crime in a fixed spatial region over a period of time. It is robust under variation of model parameters. HotBlock's results are compared with baseline real-world crime datasets. It is found that the proposed model outperforms the standard DeepCrime model in most cases.

• International Journal of Contents
• /
• 제17권3호
• /
• pp.1-14
• /
• 2021

Since the outbreak of the coronavirus disease 2019 (COVID-19) pandemic, a lot of efforts have been made in the field of data science to help combat against this disease. Among them, forecasting the number of cases of infection is a crucial problem to predict the development of the pandemic. Many deep learning-based models can be applied to solve this type of time series problem. In this research, we would like to take a step forward to incorporate spatial data (geography) with time series data to forecast the cases of region-level infection simultaneously. Specifically, we model a single spatio-temporal graph, in which nodes represent the geographic regions, spatial edges represent the distance between each pair of regions, and temporal edges indicate the node features through time. We evaluate this approach in COVID-19 in a Korean dataset, and we show a decrease of approximately 10% in both RMSE and MAE, and a significant boost to the training speed compared to the baseline models. Moreover, the training efficiency allows this approach to be extended for a large-scale spatio-temporal dataset.

• 제어로봇시스템학회논문지
• /
• 제7권7호
• /
• pp.632-639
• /
• 2001

This paper proposes an improved architecture of web-based monitoring systems for monitor of processes in plants from the soft real-time point of view. The suggested model is designed to be able to guarantee the temporal and spatial consistency and transmit the monitoring data periodically via the intranet and the Internet. The model generates one thread for monitoring management, one DB thread, one common memory, and corresponding monitoring threads to clients. The monitoring thread is executed during the smaller time than the execution time of the process used in the conventional methods such as CGI and servlet method. The Java API for the server API, VRML, EAI(External Authoring Interface) and Java Applets for efficient dimensional WEB monitoring are used. The proposed model is implemented and tested for a FMS plant, Some examples show that the proposed model is useful one.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2007년도 추계종합학술대회
• /
• pp.457-461
• /
• 2007

In many applications, received signal strength indicator is used for location tracking and sensor nodes localization. For location finding, the distances between sensor nodes can be estimated by converting received signal's power into distance using path loss prediction model. Many researches have done the analysis of power-distance relationship for radio channel characterization. In indoor environment, the general conclusion is the non-linear variation of RSSI values as distance varied linearly. This has been one of the difficulties for indoor localization. This paper presents works on indoor RSSI characterization based on statistical methods to find the overall trend of RSSI variation at different places and times within the same room From experiments, it has been shown that the variation of RSSI values can be determined by both spatial and temporal factors. This two factors are directly indicated by the two main parameters of path loss prediction model. The results show that all sensor nodes which are located at different places share the same characterization value for the temporal parameter whereas different values for the spatial parameters. Using this relationship, the characterization for location estimation can be more efficient and accurate.