• 전자공학회논문지B
• /
• 제33B권10호
• /
• pp.130-138
• /
• 1996

In this paper, we propose a neural network which detect edges of different orentation and spatial frequency in arbitrary image data. We constructed the proposed neural network iwth two different types neural network. A diffusion network performs the gaussian operation efficiently by the diffusion process. And the spatial difference network has specially designed connections suitble to detect the contours of a specific oriention. Simulation results showed that the proposed neural network can extract the edges of selected orientation efficiently by applying the neural network to a test pattern and the real image.

• 대한산업공학회지
• /
• 제41권1호
• /
• pp.64-73
• /
• 2015

Recent emergence of spatial big data attracts the attention of various research groups. This paper analyzes the research trend on spatial big data by text mining the related Scopus DB. We apply topic model and network analysis to the extracted abstracts of articles related to spatial big data. It was observed that optics, astronomy, and computer science are the major areas of spatial big data analysis. The major topics discovered from the articles are related to mobile/cloud/smart service of spatial big data in urban setting. Trends of discovered topics are provided over periods along with the results of topic network. We expect that uncovered areas of spatial big data research can be further explored.

• 한국측량학회지
• /
• 제34권2호
• /
• pp.111-120
• /
• 2016

Prior knowledge about the SNS (Social Network Services) datasets is often required to conduct valuable analysis using social media data. Understanding the characteristics of the information extracted from SNS datasets leaves much to be desired in many ways. This paper purposes on analyzing the detail of the target social network services, Twitter, Instagram, and YouTube to establish the spatial informatization process to integrate social media information with existing spatial datasets. In this study, valuable information in SNS datasets have been selected and total 12,938 data have been collected in Seoul via Open API. The dataset has been geo-coded and turned into the point form. We also removed the overlapped values of the dataset to conduct spatial integration with the existing building layers. The resultant of this spatial integration process will be utilized in various industries and become a fundamental resource to further studies related to geospatial integration using social media datasets.

• International Journal of Computer Science & Network Security
• /
• 제21권6호
• /
• pp.207-212
• /
• 2021

Clustering Unlabeled Spatial-datasets to convert them to Labeled Spatial-datasets is a challenging task specially for geographical information systems. In this research study we investigated the NYC Taxi Limousine Commission dataset and discover that all of the spatial-temporal trajectory are unlabeled Spatial-datasets, which is in this case it is not suitable for any data mining tasks, such as classification and regression. Therefore, it is necessary to convert unlabeled Spatial-datasets into labeled Spatial-datasets. In this research study we are going to use the Clustering Technique to do this task for all the Trajectory datasets. A key difficulty for applying machine learning classification algorithms for many applications is that they require a lot of labeled datasets. Labeling a Big-data in many cases is a costly process. In this paper, we show the effectiveness of utilizing a Clustering Technique for labeling spatial data that leads to a high-accuracy classifier.

• Computers and Concrete
• /
• 제26권5호
• /
• pp.411-420
• /
• 2020

Deep Convolution neural network (DCNN) has been widely used in the healthy maintenance of civil infrastructure. Using DCNN to improve crack detection performance has attracted many researchers' attention. In this paper, a light-weight spatial attention network module is proposed to strengthen the representation capability of ResNet and improve the crack detection performance. It utilizes attention mechanism to strengthen the interested objects in global receptive field of ResNet convolution layers. Global average spatial information over all channels are used to construct an attention scalar. The scalar is combined with adaptive weighted sigmoid function to activate the output of each channel's feature maps. Salient objects in feature maps are refined by the attention scalar. The proposed spatial attention module is stacked in ResNet50 to detect crack. Experiments results show that the proposed module can got significant performance improvement in crack detection.

• 한국지리정보학회지
• /
• 제7권2호
• /
• pp.87-96
• /
• 2004

유역의 공간 DB를 DEM을 이용하여 구축할 경우에는 DEM으로부터 유역의 수문학적 지형특성 인자를 손쉽게 추출할 수 있으며, 이들이 자동으로 공간 DB의 속성으로 입력되어 관리될 수 있다. 본 연구에서는 유역정보를 관리하기 위한 기반정보인 프레임워크 공간 DB의 구축방안에 대하여 기술하였다. 이롤 위하여 프레임워크 공간 데이터의 범위를 결정하고, 이들의 상호 연관관계를 정의하였으며 실제 유역을 대상으로 프레임워크 공간 DB률 구축하였다. 한편 본 연구에서는 순수 국내기술로 수자원 공간자료 생성 및 수자원 시스템 개발 모듈인 HyGIS(Hydrological Geographic Information System)를 개발하였다. HyGIS를 이용하여 수문학적 지형특성인자 및 공간자료를 추출하였으며, 이들 자료를 실제 유역의 프레임워크 공간 DB를 구축하는 기본 데이터로 이용하였다. 본 연구에서는 이러한 과정을 통하여 하천 네트워크 기반의 유역관리시스템 개발을 위한 프레임워크 공간 DB의 구축방안을 제시하고자 한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권9호
• /
• pp.2361-2376
• /
• 2023

The electrocardiogram (ECG) signal is commonly used to screen and diagnose cardiovascular diseases. In recent years, deep neural networks have been regarded as an effective way for automatic ECG disease diagnosis. The convolutional neural network is widely used for ECG signal extraction because it can obtain different levels of information. However, most previous studies adopt single scale convolution filters to extract ECG signal features, ignoring the complementarity between ECG signal features of different scales. In the paper, we propose a dual-scale network with convolution filters of different sizes for 12-lead ECG classification. Our model can extract and fuse ECG signal features of different scales. In addition, different spatial and time periods of the feature map obtained from the 12-lead ECG may have different contributions to ECG classification. Therefore, we add a spatial-temporal attention to each scale sub-network to emphasize the representative local spatial and temporal features. Our approach is evaluated on PTB-XL dataset and achieves 0.9307, 0.8152, and 89.11 on macro-averaged ROC-AUC score, a maximum F1 score, and mean accuracy, respectively. The experiment results have proven that our approach outperforms the baselines.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권1호
• /
• pp.60-79
• /
• 2022

The U-Net architecture-based segmentation models attained remarkable performance in numerous medical image segmentation missions like skin lesion segmentation. Nevertheless, the resolution gradually decreases and the loss of spatial information increases with deeper network. The fusion of adjacent layers is not enough to make up for the lost spatial information, thus resulting in errors of segmentation boundary so as to decline the accuracy of segmentation. To tackle the issue, we propose a new deep learning-based segmentation model. In the decoding stage, the feature channels of each decoding unit are concatenated with all the feature channels of the upper coding unit. Which is done in order to ensure the segmentation effect by integrating spatial and semantic information, and promotes the robustness and generalization of our model by combining the atrous spatial pyramid pooling (ASPP) module and channel attention module (CAM). Extensive experiments on ISIC2016 and ISIC2017 common datasets proved that our model implements well and outperforms compared segmentation models for skin lesion segmentation.

• 한국컴퓨터정보학회논문지
• /
• 제24권8호
• /
• pp.137-142
• /
• 2019

This paper proposed bitmap based spatial data transmission scheme in need of rapid transmission through network in mobile environment that use and creation of data are frequently happen. Former researches that used clustering algorithms, focused on providing service using spatial data can cause delay since it doesn't consider the transmission speed. This paper guaranteed rapid service for user by convert spatial data to bit, leads to more transmission of bit of MTU, the maximum transmission unit. In the experiment, we compared arithmetically default data composed of 16 byte and spatial data converted to bitmap and for simulation, we created virtual data and compared its network transmission speed and conversion time. Virtual data created as standard normal distribution and skewed distribution to compare difference of reading time. The experiment showed that converted bitmap and network transmission are 2.5 and 8 times faster for each.

• 한국수자원학회논문집
• /
• 제52권8호
• /
• pp.515-529
• /
• 2019

하천망과 유역 등 하천 네트워크 관련 공간자료는 각종 하천관리, 하천계획 및 설계, 수리수문학적 해석 등의 근간을 이루는 기초자료로 활용되고 있다. 기존 RIMGIS 등에서 제공하는 하천정보도 현행화 및 적절한 관리 부족으로 공간정보시스템간 불일치와 실제 하천지형과 이격이 나타나고 있는 실정이다. 또한, 고해상도 수치지형도(DEM)이 국가하천 주변 등 일부 지역에서만 제공되어, 저해상도 DEM으로부터 추출된 하천네트워크 정보의 신뢰도가 낮고 가용한 기수립 하천네트워크 정보와의 불일치는 DEM 기반 다양한 하천정보 추출 및 탄력적 활용을 저하시키고 있는 실정이다. 본 연구에서는 우선 국내 하천공간정보시스템이 제공하는 하천망 정보의 공간정확도, 정보체계간 일치성 등을 평가하고, 낮은 해상도의 DEM에 기수립된 하천망을 DEM에 강제로 각인시키는 방법으로 DEM을 개선하여 추후 하천망 혹은 유역 추출 시 기수립 하천망 혹은 유역대로 재현이 가능하게 하여 하천분야에 DEM의 활용성을 높일 수 있는 방법론과 소프트웨어(Forced river Network Striation and Delineation tool: FNSD)을 개발하고자 하였다. 개발된 FNSD는 ArcGIS의 ModelBuilder에서 순차적으로 관련 모듈을 연계시켜 자동화되도록 설계되었고, 한강수계의 섬강 유역에 시범 적용되었으며 항공사진 정보를 기반으로 수작업을 통해 도출된 하천망을 기수립 하천망으로 간주하여 30 m 저해상도 DEM에 각인시켜 하천망을 재추출한 후 주어진 기수립 하천망과 비교하여 재현 정확도를 검토하였다. 섬강유역에 적용한 결과 FNSD는 기수립 하천망을 정확하게 재현할 수 있음을 확인하였다. 이러한 검증결과는 각인된 DEM이 다양한 차수의 하천망 및 유역을 신뢰성 있게 재현할 수 있어 저해상도 DEM의 하천활용도를 높이는데 기여할 가능성이 있음을 의미한다.