• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.2078-2093
• /
• 2019

Visual smoke recognition is a challenging task due to large variations in shape, texture and color of smoke. To improve performance, we propose a novel smoke recognition method by combining dual-encoded features that are extracted from both spatial and Curvelet domains. A Curvelet transform is used to filter an image to generate fifty sub-images of Curvelet coefficients. Then we extract Local Binary Pattern (LBP) maps from these coefficient maps and aggregate histograms of these LBP maps to produce a histogram map. Afterwards, we encode the histogram map again to generate Dual-encoded Local Binary Patterns (Dual-LBP). Histograms of Dual-LBPs from Curvelet domain and Completed Local Binary Patterns (CLBP) from spatial domain are concatenated to form the feature for smoke recognition. Finally, we adopt Gaussian Kernel Optimization (GKO) algorithm to search the optimal kernel parameters of Support Vector Machine (SVM) for further improvement of classification accuracy. Experimental results demonstrate that our method can extract effective and reasonable features of smoke images, and achieve good classification accuracy.

• Journal of the Korean Geographical Society
• /
• v.45 no.4
• /
• pp.521-539
• /
• 2010

Recently many local governments have carried out dong merger and abolition process to cope with rapidly changing administrative demand and environment. This administrative effort impacts substantially the locational characteristics of the existing dong offices which directly involve in the quality of local community life. In this paper, we attempt to analyze the location pattern of current dong community service centers (formerly, 'dong office') and suggest the optimal locations maximizing spatial accessibility. As an application, we examine the location pattern of the existing dong community service centers in Mapo-gu, Seoul. Moreover, we compare current spatial configurations with the optimally selected locations such as, a Median maximizing spatial efficiency, a Center maximizing spatial equity, and a Centdian exploring compromising solutions regarding the tradeoff between efficiency and equity. The analytical results present that each of dong community service centers was systematically evaluated in terms of spatial efficiency and equity and in general the community service center locations are not spatially optimized with respect to efficiency and equity, compared with the optimal locations.

• Journal of Korean Society of Forest Science
• /
• v.96 no.6
• /
• pp.730-736
• /
• 2007

The heterogeneity of forest environment plays an important role in the structure and dynamics of tree population, the composition of forest community, and the maintenance of species diversity. Based upon the research data of the nine hectare permanent plot in the typical mixed broadleaved-Korean pine forest, this study was conducted to analyze the characteristics of spatial pattern of Acer tegmentosum population for seedlings, saplings, and living and dead trees so as to evaluate the effect of micro-topography on spatial pattern of the species. The results noted that A. tegmentosum preferred to gentle slopes. There was no difference in density of seedlings by the variation of aspect, but the density of saplings, and living and dead trees was high on the western and southeastern slopes. Living trees of A. tegmentosum showed the clumped pattern for all scales within 150 m and highest at the scale of 30 m. Dead stems of the species indicated the clumped pattern within 111 m, highest at the scale of 72 m, and random pattern beyond the scale of 111 m (P < 0.01 ). The similarity of occurrence by developmental stages of A. tegmentosum showed that seedlings vs. saplings, saplings vs. living trees, and living trees vs. dead stems had highly positive correlation to each other, respectively (P < 0.01 ), indicating that the occurrence of previous developmental stages was positively correlated to following stages.

• Journal of Biomedical Engineering Research
• /
• v.13 no.1
• /
• pp.1-8
• /
• 1992

In the field of prosthesis arm control, the pattern classification of the EMG signal is a required basis process and also the estimation of force from collected EMG data is another necessary duty. But unfortunately, what we've got is not real force but an EMG signal which contains the information of force. This is the reason why we estimate the force from the EMG data. In this paper, when we handle the EMG signal to estimate the force, spatial prewhitening process is applied from which the spatial correlation between the channels are removed. And after the orthogonal transformation which is used in the force estimation process, the transformed signal Is inputed into the probabilistic model for pattern classification. To verify the different results of the multiple channels, SNR(signal to noise ratio) function is introduced.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06a
• /
• pp.142-145
• /
• 2011

뇌전도 기반 뇌-컴퓨터 인터페이스 기술은 신체 움직임이 불가능하거나 불편한 사람에게 새로운 의사전달 수단이 될 수 있으며 일반인에게도 상상만으로 컴퓨터 혹은 기계에 명령을 내릴 수 있게 하는 기술이다. 본 논문에서는 뇌-컴퓨터 인터페이스 연구 분야에 잘 알려진 Common Spatial Pattern (CSP), Invariant Common Spatial Pattern (iCSP) 그리고 Common Spatio-Spectral Pattern (CSSP) 알고리즘들의 성능을 비교 분석하였고, CSSP에 불변성(invariant)을 고려한 iCSSP를 제안하였다. 9명의 피험자로부터 상상움직임 실험을 통해 18셋의 뇌전도 데이터를 측정하였고, 4가지 알고리즘들을 성능 면에서 비교하였다. 그 결과 CSSP의 성능과 차이가 크지는 않지만, 본 연구에서 제안한 노이즈를 고려하여 최적의 필터를 구성하는 iCSSP에 대하여 더 나은 성능을 보여주는 결과들을 확인할 수 있었다.

• Geophysics and Geophysical Exploration
• /
• v.5 no.2
• /
• pp.71-77
• /
• 2002

We developed a modeling and visualization software that can analyze 3-dimensional seismic data. The software divides 3 dimensional space into a series of vertical and horizontal polygons, and allows the various seismic attributes and other spatial information to be stored on these polygons. The program can pick a particular pattern in semi-automatic mode, and store the pattern in the spatial DB. The pattern can be modeled and visualized in 3 dimensional space.

• Journal of Environmental Impact Assessment
• /
• v.29 no.2
• /
• pp.122-131
• /
• 2020

Marine Spatial Planning is an emerging strategy that promoting sustainable development at coastal and marine areas based on the concept of ecosystem services. Regarding its methodology, usage rate of resources and its impact should be considered in the process of spatial planning. Particularly, considering the rapid increase of coastal tourism, visitation pattern is required to be identified across coastal areas. However, actions to quantify visitation pattern have been limited due to its required high cost and labor for conducting extensive field-study. In this regard, this study aimed to pose the usage of social big data in Marine Spatial Planning to identify spatial visitation density and critical management zone throughout coastal areas. We suggested the usage of GPS information from Flickr and Twitter, and evaluated the critical management zone by applying spatial statistics and density analysis. This study's results clearly showed the coastal areas having relatively high visitors in the southern sea of South Korea. Applied Flickr and Twitter information showed high correlation with field data, when proxy excluding over-estimation was applied and appropriate grid-scale was identified in assessment approach. Overall, this study offers insights to use social big data in Marine Spatial Planning for reflecting size and usage rate of coastal tourism, which can be used to designate conservation area and critical zones forintensive management to promote constant supply of cultural services.

• Journal of Korean Association for Spatial Structures
• /
• v.17 no.1
• /
• pp.11-18
• /
• 2017

• Proceedings of the Korean Society of Applied Entomolohy Conference
• /
• 2000.05a
• /
• pp.60-60
• /
• 2000

• Journal of Advanced Navigation Technology
• /
• v.12 no.6
• /
• pp.659-665
• /
• 2008

We demonstrate experimentally that the method of Two-pupil optical scanning technique with PAL-spatial light modulator is capable of performing real-time joint transform correlation(JTC) optical system. Optical addressing is achieved by the use of a photosensitive layer of $\alpha$ - Si which controls the electric field across the liquid crystal The demonstrated technique is based on two-pupil optical heterodyne scanning. The method is independent of a spatial light modulator (SLM) in the Fourier plane. We develop the theory of the technique and evaluate a performance of the method by experimentally estimating the correlation between the target image and the reference image.