• ETRI Journal
• /
• v.43 no.2
• /
• 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.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.11
• /
• pp.43-49
• /
• 2018

In this paper, we propose a displacement measurement method based on deep learning using image data obtained from tensile tests of a material specimen. We focus on the fact that the sequential images during the tension are generated and the displacement of the specimen is represented in the image data. So, we designed sample generation model which makes sequential images of specimen. The behavior of generated images are similar to the real specimen images under tensile force. Using generated images, we trained and validated our model. In the deep neural network, sequential images are assigned to a multi-channel input to train the network. The multi-channel images are composed of sequential images obtained along the time domain. As a result, the neural network learns the temporal information as the images express the correlation with each other along the time domain. In order to verify the proposed method, we conducted experiments by comparing the deformation measuring performance of the neural network changing the displacement range of images.

• Korean Journal of Soil Science and Fertilizer
• /
• v.50 no.4
• /
• pp.306-317
• /
• 2017

Unmanned aerial vehicles (UAVs) became popular platforms for the collection of remotely sensed data in the last years. This study deals with the monitoring of multi-temporal onion growth with very high resolution by means of low-cost equipment. The concept of the monitoring was estimation of multi-temporal onion growth using normalized difference vegetation index (NDVI) and meteorological factors. For this study, UAV imagery was taken on the Changnyeong, Hapcheon and Muan regions eight times from early February to late June during the onion growing season. In precision agriculture frequent remote sensing on such scales during the vegetation period provided important spatial information on the crop status. Meanwhile, four plant growth parameters, plant height (P.H.), leaf number (L.N.), plant diameter (P.D.) and fresh weight (F.W.) were measured for about three hundred plants (twenty plants per plot) for each field campaign. Three meteorological factors included average temperature, rainfall and irradiation over an entire onion growth period. The multiple linear regression models were suggested by using stepwise regression in the extraction of independent variables. As a result, $NDVI_{UAV}$ and rainfall in the model explain 88% and 68% of the P.H. and F.W. with a root mean square error (RMSE) of 7.29 cm and 59.47 g, respectively. And $NDVI_{UAV}$ in the model explain 43% of the L.N. with a RMSE of 0.96. These lead to the result that the characteristics of variations in onion growth according to $NDVI_{UAV}$ and other meteorological factors were well reflected in the model.

• Journal of Korean Society for Atmospheric Environment
• /
• v.26 no.2
• /
• pp.190-201
• /
• 2010

Fine particulate matter < $1.8{\mu}m$ was collected as a slurry using the Semicontinuous Elements in Aerosol Sampler with time resolution of 30-min between May 23 and 27, 2002 at the Sydney Supersite, Florida, USA. Concentrations of 11 elements, i.e., Al, As, Cd, Cr, Cu, Fe, Mn, Ni, Pb, Se, and Zn, in the collected slurry samples were determined off-line by simultaneous multi-element graphite furnace atomic absorption spectrometry. Temporal profiles of $SO_2$ and elemental concentrations combined with meteorological parameters such as wind direction and wind speed indicate that some transient events in their concentrations are highly correlated with the periods when the plume from an animal feed supplement processing facility influenced the Sydney sampling site. The peaking concentrations of the elemental species during the transient events varied clearly as the plume intensity varied, but the relative concentrations for As, Cr, Pb, and Zn with respect to Cd showed almost consistent values. During the transient events, metal concentrations increased by factors of >10~100 due to the influence of consistent plumes from an individual stationary source. Also the multi-variate air dispersion receptor model, which was previously developed by Park et al. (2005), was applied to ambient $SO_2$ and 8 elements (Al, As, Cd, Cr, Cu, Fe, Pb, and Zn) measurements between 20:00 May 23 and 09:30 May 24 when winds blew from between 70 and $85^{\circ}$, in which animal feed processing plant is situated, to determine emission and ambient source contributions rates of $SO_2$ and elements from one animal feed processing plant. Agreement between observed and predicted $SO_2$ concentrations was excellent (R of 0.99; and their ratio, $1.09{\pm}0.35$) when one emission source was used in the model. Average ratios of observed and predicted concentrations for As, Cd, Cr, Pb, and Zn varied from $0.83{\pm}0.26$ for Pb to $1.12{\pm}0.53$ for Cd.

• Journal of Environmental Impact Assessment
• /
• v.18 no.3
• /
• pp.171-183
• /
• 2009

This study aims to analyze the sedimentary environment change in mid-channel bar of the lower Geum river basin after the construction of the estuary barrage using multi-temporal satellite data and GIS. The sedimentary environment changes were observed in mid-channel bar areas. The mid-channel bar F was found to have been newly formed for 10 years(1996-2006), whereas the mid-channel bar B located between mid-channel bar A and C has disappeared by erosion during the same periods. When examined by section, the areas of the mid-channel bar in the upper stream section from the Yipo's reference point generally increased due to the prevailing sedimentary environments, and those of the downstream section decreased where corrosive environments are dominant. In ternms of the centroid movement, the mid-channel bars grew up toward the downstream by switching erosion and accumulation, as sedimentation was prevailing in the downstream area of mid-channel bars and corrosion was dominant in the upper stream. Through grain size analysis, the study areas are divided into three sections according to the average grain size. In Section I, the mid-channel bars were formed as a result of sedimentary process of tides in the past. In Section II, the mid-channel bars were formed partly through the sedimentary process of rivers although the sedimentary process of tides is prevailing. In Section III, the mid-channel bars were formed mainly through the sedimentary process of rivers, even if it showed the sedimentary process of tides in the past.

• Korean Journal of Remote Sensing
• /
• v.33 no.1
• /
• pp.37-46
• /
• 2017

Sinabung volcano in Indonesia was formed due to the subduction between the Eurasian and Indo-Australian plates along the Pacific Ring of Fire. After being dormant for about 400 years, Sinabung volcano erupted on the 29th of August, 2010 and most recently on the 1st of November, 2016. We measured the deformation of Sinabung volcano using Advanced Land Observing Satellite/Phased Array type L-band Synthetic Aperture Radar(ALOS/PALSAR) interferometric synthetic aperture radar(InSAR) images acquired from February 2007 to January 2011. Based on multi-temporal InSAR processing, we mapped the ground surface deformation before, during, and after the 2010 eruption with time-series InSAR technique. During the 3 years before the 2010 eruption, the volcano inflated at an average rate of ~1.7 cm/yr with a markedly higher rate of 6.6 cm/yr during the 6 months prior to the 2010 eruption. The inflation was constrained to the top of the volcano. From the 2010 eruption to January 2011,the volcano subsided by approximately 3 cm (~6 cm/yr). We interpreted that the inflation was due to magma accumulation in a shallow reservoir beneath Sinabung. The deflation was attributed to magma withdrawal from the shallow reservoir during the eruption as well as thermo-elastic compaction of erupted material. This result demonstrates once again the utility of InSAR for volcano monitoring.

• Journal of Korean Society for Geospatial Information Science
• /
• v.20 no.2
• /
• pp.47-54
• /
• 2012

Additional high resolution satellite images, other period or site, are essential for efficient city modeling and analysis. However, the same ground objects have a radiometric inconsistency in different satellite images and it debase the quality of image processing and analysis. Moreover, in an urban area, buildings, trees, bridges, and other artificial objects cause shadow effects, which lower the performance of relative radiometric normalization. Therefore, in this study, we exclude shadow areas and suggest the selective histogram matching methods for image based application without supplementary digital elevation model or geometric informations of sun and sensor. We extract the shadow objects first using adjacency informations with the building edge buffer and spatial and spectral attributes derived from the image segmentation. And, Outlier objects like a asphalt roads are removed. Finally, selective histogram matching is performed from the shadow masked multi-temporal Quickbird-2 images.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.10
• /
• pp.47-53
• /
• 2012

Time-reversal (TR) precoding focuses the energy of the effective channel in time and improves receive performance of a single tap receiver. Frequency-domain equal-gain-combining (FD-EGC) TR scheme, which works in linear block precoding fashion, has better temporal focusing performance than the traditional TR. Also, the FD-EGC improves receive performance of minimum mean square error receiver with distributed antenna systems (DAS). The detailed receive performance of the FD-EGC was analyzed in our previous work. In this paper, we focused on capacity analysis of the FD-EGC in DAS. We derived a scaling law which shows how the use of multiple antenna can increase the capacity of the FD-EGC precoding compared with that of no precoding. In addition, we analyze the secrecy rate of the FD-EGC which shows how high-rate messages can be transmitted towards an intended user without being decoded by the other users from the view point of information theoretic security.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.35 no.2
• /
• pp.327-340
• /
• 2015

General Circulation Models (GCMs) are the basic tool used for modelling climate. However, the spatio-temporal discrepancy between GCM and observed value, therefore, the models deliver output that are generally required calibration for applied studies. Which is generally done by Multi-Model Ensemble (MME) approach. Stochastic downscaling methods have been used extensively to generate long-term weather sequences from finite observed records. A primary objective of this study is to develop a forecasting scheme which is able to make use of a MME of different GCMs. This study employed a Nonstationary Hidden Markov Chain Model (NHMM) as a main tool for downscaling seasonal ensemble forecasts over 3 month period, providing daily forecasts. Our results showed that the proposed downscaling scheme can provide the skillful forecasts as inputs for hydrologic modeling, which in turn may improve water resources management. An application to the Nakdong watershed in South Korea illustrates how the proposed approach can lead to potentially reliable information for water resources management.

• Journal of Korean Society for Geospatial Information Science
• /
• v.18 no.2
• /
• pp.87-92
• /
• 2010

Large pressure on the growing population has increased rapid change in the LULC (land use/land cover) patterns in the watershed area. Spatial distribution of LULC information and its changes are desirable for any effective planning, managing and monitoring activities. The aim of the study is to produce the 1,50,000 scaled LULC change map for the sub-watershed, Western Moyar, India using the multi-temporal satellite image dataset of IRS LISS III images for the year 1989, 1999, and 2002. About 9 classes are extracted using onscreen visual interpretation techniques for all the three years. The change detection analysis was performed using matrix method for period I (1989-1999) and period II (1999-2002). The study reveals that the changes noticed in period II (1999-2002) is comparatively more than period I (1989-1999), which is dynamic information to protect the sub-watershed area from the deterioration and paves the way to for the sustainable development.