• Journal of the Korea Convergence Society
• /
• v.12 no.12
• /
• pp.31-37
• /
• 2021

In this paper proposed a feature fusion and spatial attention-based modified YOLOv4S for small and occluded detection. Conventional YOLOv4S is a lightweight network and lacks feature extraction capability compared to the method of the deep network. The proposed method first combines feature maps of different scales with feature fusion to enhance semantic and low-level information. In addition expanding the receptive field with dilated convolution, the detection accuracy for small and occluded objects was improved. Second by improving the conventional spatial information with spatial attention, the detection accuracy of objects classified and occluded between objects was improved. PASCAL VOC and COCO datasets were used for quantitative evaluation of the proposed method. The proposed method improved mAP by 2.7% in the PASCAL VOC dataset and 1.8% in the COCO dataset compared to the Conventional YOLOv4S.

• Journal of Internet of Things and Convergence
• /
• v.8 no.2
• /
• pp.79-84
• /
• 2022

This paper presents an enhancement method of document restoration capability which is robust for security, loss, and contamination, It is based on two methods, that is, encryption and DnCNN(DeNoise Convolution Neural Network). In order to implement this encryption method, a mathematical model is applied as a spatial frequency transfer function used in optics of 2D image information. Then a method is proposed with optical interference patterns as encryption using spatial frequency transfer functions and using mathematical variables of spatial frequency transfer functions as ciphers. In addition, by applying the DnCNN method which is bsed on deep learning technique, the restoration capability is enhanced by removing noise. With an experimental evaluation, with 65% information loss, by applying Pre-Training DnCNN Deep Learning, the peak signal-to-noise ratio (PSNR) shows 11% or more superior in compared to that of the spatial frequency transfer function only. In addition, it is confirmed that the characteristic of CC(Correlation Coefficient) is enhanced by 16% or more.

• Journal of Information Processing Systems
• /
• v.20 no.1
• /
• pp.131-147
• /
• 2024

A routing strategy based on traffic prediction and dynamic cache allocation for satellite nodes is proposed to address the issues of high propagation delay and overall delay of inter-satellite and satellite-to-ground links in low Earth orbit (LEO) satellite systems. The spatial and temporal correlations of satellite network traffic were analyzed, and the relevant traffic through the target satellite was extracted as raw input for traffic prediction. An improved gradient boosting regression tree algorithm was used for traffic prediction. Based on the traffic prediction results, a dynamic cache allocation routing strategy is proposed. The satellite nodes periodically monitor the traffic load on inter-satellite links (ISLs) and dynamically allocate cache resources for each ISL with neighboring nodes. Simulation results demonstrate that the proposed routing strategy effectively reduces packet loss rate and average end-to-end delay and improves the distribution of services across the entire network.

• The Korean Journal of Health Service Management
• /
• v.13 no.1
• /
• pp.15-30
• /
• 2019

Objectives: This study aimed to analyze people's accessibility to medical institutions providing national gastric cancer screening services in Gangwon-do using a geographic information system(GIS). Methods: To assess the spatial accessibility, network analysis was applied. Two types of network analysis-Service area analysis and origin-destination cost matrix(OD-cost matrix)-were applied to create network dataset. Results: The results of the analysis of the service area revealed that it took more than 60 minutes each to reach tertiary hospitals and general hospitals from 74.4% and 9.6% of Gangwon-do areas, respectively. Similarly, it took more than 60 minutes each to reach hospitals and clinics from 4.2% and 3.4% of Gangwon-do areas, respectively. The results of the OD-cost revealed that there were large regional variations in distance and time taken to reach the medical institutions. Conclusions: there were regional variations of spatial accessibility between Si and Gun in Gangwon-do.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.1
• /
• pp.277-282
• /
• 2006

It is well known that Kalman filtering is an optimal real-time data fusion method for GPS/INS integration. However, it has some limitations in terms of stability, adaptability and observability. A Kalman filter can perform optimally only when its dynamic model is correctly defined and the noise statistics for the measurement and process are completely known. It is found that estimated Kalman filter states could be influenced by several factors, including vehicle dynamic variations, filter tuning results, and environment changes, etc., which are difficult to model. Neural networks can map input-output relationships without apriori knowledge about them; hence a proper designed neural network is capable of learning and extracting these complex relationships with enough training. This paper presents a GPS/INS integrated system that combines Kalman filtering and neural network algorithms to improve navigation solutions during GPS outages. An Extended Kalman filter estimates INS measurement errors, plus position, velocity and attitude errors etc. Kalman filter states, and gives precise navigation solutions while GPS signals are available. At the same time, a multi-layer neural network is trained to map the vehicle dynamics with corresponding Kalman filter states, at the same rate of measurement update. After the output of the neural network meets a similarity threshold, it can be used to correct INS measurements when no GPS measurements are available. Selecting suitable inputs and outputs of the neural network is critical for this hybrid method. Detailed analysis unveils that some Kalman filter states are highly correlated with vehicle dynamic variations. The filter states that heavily impact system navigation solutions are selected as the neural network outputs. The principle of this hybrid method and the neural network design are presented. Field test data are processed to evaluate the performance of the proposed method.

• Journal of the Korean association of regional geographers
• /
• v.18 no.3
• /
• pp.298-309
• /
• 2012

This paper studies the characteristics of the network of the Zhongguancun Cluster, the most representative innovative cluster of the high-tech industry in China at present. For this study, Zhongguancun Cluster was the first high-tech cluster created in China in 1988, the current Zhongguancun Cluster plays a leading role in the development of the high-tech industry in China. In addition, the Zhongguancun Cluster has attracted global attention and helped elevate China as a key region in terms of research development in relation to the high-tech industry. With regard to the spatial characteristics of the network belonging to the companies in Zhongguancun Cluster, purchase and producer services and information and R&D network have a strong tendency to be local, while on the other hand the product sales network has a strong tendency to be non-local. It is because the political support supplied by the government, institutional base that provides high-tech companies, producer services and information regarding producer services is relatively well prepared and managed in Zhongguancun Cluster. The spatial characteristics of the R&D network have a very strong local character is due to the location of the Zhongguancun Cluster where companies, universities and research centers with outstanding research development capacity as well as various support organizations for technology innovation within the cluster are included. On the other hand, because the high-tech products produced in this area are sold all across China as well as in foreign countries, the product sales network has a strong non-local character. Strengthening the local network in terms of the main agents of the cluster is the most important aspect in order to develop a certain industrial cluster into an innovative cluster. In this respect, if the Zhongguancun Cluster is seen from the perspective of a network, it has a basic network foundation. However, to strengthen international competitiveness, not only the local network but also the international network should be strengthened.

• Journal of Contemporary Eastern Asia
• /
• v.15 no.1
• /
• pp.64-77
• /
• 2016

This case study takes a look at the hyperlink networks extracted from the websites of 367 international non-governmental organizations (NGOs) with datasets from 2010, 2012 and 2014. The first level of evaluation focuses on connections between the NGOs, identifying important nodes, groups and their relations. The second level takes into account the broad range of networked websites from the World Wide Web delivering insights into general networking patterns. The third level explores the underlying spatial configurations of the network which offers a great variety of geographic insights on information flows between and within continents, countries and cities. The most interesting findings of this study are a low level of interconnectedness between the NGOs and at the same time a strong spatial concentration of all embedded network actors.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_2
• /
• pp.961-973
• /
• 2020

In this manuscript, a new pansharpening model based on Convolutional Neural Network (CNN) was developed. Dilated convolution, which is one of the representative convolution technologies in CNN, was applied to the model by making it deep and complex to improve the performance of the deep learning architecture. Based on the dilated convolution, the residual network is used to enhance the efficiency of training process. In addition, we consider the spatial correlation coefficient in the loss function with traditional L1 norm. We experimented with Dilated Residual Networks (DRNet), which is applied to the structure using only a panchromatic (PAN) image and using both a PAN and multispectral (MS) image. In the experiments using KOMPSAT-3A, DRNet using both a PAN and MS image tended to overfit the spectral characteristics, and DRNet using only a PAN image showed a spatial resolution improvement over existing CNN-based models.

• Proceedings of the KSRS Conference
• /
• 2002.10a
• /
• pp.256-272
• /
• 2002

The purpose of this study is to develop landslide susceptibility analysis techniques using artificial neural network and to apply the newly developed techniques to the study area of Boun in Korea. Landslide locations were identified in the study area from interpretation of aerial photographs, field survey data, and a spatial database of the topography, soil type, timber cover, geology and land use. The landslide-related factors (slope, aspect, curvature, topographic type, soil texture, soil material, soil drainage, soil effective thickness, timber type, timber age, and timber diameter, timber density, geology and land use) were extracted from the spatial database. Using those factors, landslide susceptibility was analyzed by artificial neural network methods. For this, the weights of each factor were determinated in 3 cases by the backpropagation method, which is a type of artificial neural network method. Then the landslide susceptibility indexes were calculated and the susceptibility maps were made with a GIS program. The results of the landslide susceptibility maps were verified and compared using landslide location data. A GIS was used to efficiently analyze the vast amount of data, and an artificial neural network was turned out be an effective tool to maintain precision and accuracy.

• Journal of Information Processing Systems
• /
• v.2 no.1
• /
• pp.58-65
• /
• 2006

Accurate and efficient monitoring of dynamically changing environments is one of the most important requirements for ubiquitous network environments. Ubiquitous computing provides intelligent environments which are aware of spatial conditions and can provide timely and useful information to users or devices. Also, the growth of embedded systems and wireless communication technology has made it possible for sensor network environments to develop on a large scale and at low-cost. In this paper, we present the design and implementation of a monitoring system that collects, analyzes, and controls the status information of each sensor, following sensor data extracted from each sensor node. The monitoring system adopts Web technology for the implementation of a simple but efficient user interface that allows an operator to visualize any of the processes, elements, or related information in a convenient graphic form.