• Journal of Internet of Things and Convergence
• /
• v.6 no.4
• /
• pp.89-92
• /
• 2020

According to the various IoT(Internet of Things) services, there have been lots of task offloading researches for IoT devices. Since there are service response delay and core network load issues in conventional cloud computing based offloadings, fog computing based offloading has been focused whose location is close to the IoT devices. However, even in the fog computing architecture, the load can be concentrated on the for computing node when the number of requests increase. To solve this problem, the opportunistic fog computing concept which offloads task to available computing resources such as cars and drones is introduced. In previous fog and opportunistic fog node researches, the offloading is performed immediately whenever the service request occurs. This means that the service requests can be offloaded to the opportunistic fog nodes only while they are available. However, if the service response delay requirement is satisfied, there is no need to offload the request immediately. In addition, the load can be distributed by making the best use of the opportunistic fog nodes. Therefore, this paper proposes a delayed offloading scheme to satisfy the response delay requirements and offload the request to the opportunistic fog nodes as efficiently as possible.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.419-437
• /
• 2023

As the number of thin filers in Korea surpasses 12 million, there is a growing interest in enhancing the accuracy of assessing their credit default risk to generate additional revenue. Specifically, researchers are actively pursuing the development of default prediction models using machine learning and deep learning algorithms, in contrast to traditional statistical default prediction methods, which struggle to capture nonlinearity. Among these efforts, Graph Neural Network (GNN) architecture is noteworthy for predicting default in situations with limited data on thin filers. This is due to their ability to incorporate network information between borrowers alongside conventional credit-related data. However, prior research employing graph neural networks has faced limitations in effectively handling diverse categorical variables present in credit information. In this study, we introduce the Transformer embedded Graph Convolutional Network (TeGCN), which aims to address these limitations and enable effective default prediction for thin filers. TeGCN combines the TabTransformer, capable of extracting contextual information from categorical variables, with the Graph Convolutional Network, which captures network information between borrowers. Our TeGCN model surpasses the baseline model's performance across both the general borrower dataset and the thin filer dataset. Specially, our model performs outstanding results in thin filer default prediction. This study achieves high default prediction accuracy by a model structure tailored to characteristics of credit information containing numerous categorical variables, especially in the context of thin filers with limited data. Our study can contribute to resolving the financial exclusion issues faced by thin filers and facilitate additional revenue within the financial industry.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.1243-1244
• /
• 2022

In recent years, the growing interest in off-site construction has led to factories scaling up their manufacturing and production processes in the construction sector. Consequently, continuous large-scale site monitoring in low-variability environments, such as prefabricated components production plants (precast concrete production), has gained increasing importance. Although many studies on computer vision-based site monitoring have been conducted, challenges for deploying this technology for large-scale field applications still remain. One of the issues is collecting and transmitting vast amounts of video data. Continuous site monitoring systems are based on real-time video data collection and analysis, which requires excessive computational resources and network traffic. In addition, it is difficult to integrate various object information with different sizes and scales into a single scene. Various sizes and types of objects (e.g., workers, heavy equipment, and materials) exist in a plant production environment, and these objects should be detected simultaneously for effective site monitoring. However, with the existing object detection algorithms, it is difficult to simultaneously detect objects with significant differences in size because collecting and training massive amounts of object image data with various scales is necessary. This study thus developed a large-scale site monitoring system using edge computing and a small-object detection system to solve these problems. Edge computing is a distributed information technology architecture wherein the image or video data is processed near the originating source, not on a centralized server or cloud. By inferring information from the AI computing module equipped with CCTVs and communicating only the processed information with the server, it is possible to reduce excessive network traffic. Small-object detection is an innovative method to detect different-sized objects by cropping the raw image and setting the appropriate number of rows and columns for image splitting based on the target object size. This enables the detection of small objects from cropped and magnified images. The detected small objects can then be expressed in the original image. In the inference process, this study used the YOLO-v5 algorithm, known for its fast processing speed and widely used for real-time object detection. This method could effectively detect large and even small objects that were difficult to detect with the existing object detection algorithms. When the large-scale site monitoring system was tested, it performed well in detecting small objects, such as workers in a large-scale view of construction sites, which were inaccurately detected by the existing algorithms. Our next goal is to incorporate various safety monitoring and risk analysis algorithms into this system, such as collision risk estimation, based on the time-to-collision concept, enabling the optimization of safety routes by accumulating workers' paths and inferring the risky areas based on workers' trajectory patterns. Through such developments, this continuous large-scale site monitoring system can guide a construction plant's safety management system more effectively.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.13 no.6
• /
• pp.7-20
• /
• 2017

The advancement of cloud and big data and the considerable growth of traffic have increased the complexity and problems in the management inefficiency of existing networks. The software-defined networking (SDN) environment has been developed to solve this problem. SDN enables us to control network equipment through programming by separating the transmission and control functions of the equipment. Accordingly, several studies have been conducted to improve the performance of SDN controllers, such as the method of connecting existing legacy equipment with SDN, the packet management method for efficient data communication, and the method of distributing controller load in a centralized architecture. However, there is insufficient research on the control of SDN in terms of the quality of network-using applications. To support the establishment and change of the routing paths that meet the required network service quality, we require a mechanism to identify network requirements based on a contract for application network service quality and to collect information about the current network status and identify the violations of network service quality. This study proposes a method of identifying the quality violations of network paths through ontology to ensure the network service quality of applications and provide efficient services in an SDN environment.

• Korean Journal of Heritage: History & Science
• /
• v.55 no.4
• /
• pp.212-240
• /
• 2022

This study is a multi-layered exploration of 「The Thirty-Six Scenery of Seongdeok Summer Mountain Resort(承德避暑山莊三十六景)」 (The 36th view of Kangxi) recited by Emperor Kangxi of China through literature study, ancient calligraphy diagrams, and field studies. The conclusion of tracing the landscape characteristics and implications contained in 「The 36th view of Kangxi」 through the analysis of the headword(標題語) and the interpretation of the Jeyeong poem(題詠詩) is as follows. 「The 36th view of Kangxi」 is an extension of the outer edge of the Eight Sceneries, and when compared to the existing Eight Sceneries peom and Eight Sceneries painting, it is found that the landscape is centered on the 'viewpoint' rather than the landscape object. In particular, it aimed to create a structured landscape centered on nine types of buildings represented by 'Jeon(殿)' and 'Jeong(亭)' was given. In particular, Yeouiju, located in Lake district, is a scenic country endowed with the character of a gardens in Garden, which is composed by collecting famous representative Chinese landscapes and landscapes of Sansu-si and Sanshu Painting. As a result of headword analysis to understand the characteristics of landscape components, 14 landscapes (38.9%) related to water elements and 13 landscapes(36.1%) related to mountain elements, the elements related to architecture and civil engineering were classified in the order of 3 cases(8.3%), and the elements related to the skylight were classified in the order of 2 cases(5.6%). However, in Jeyeong-si, the mention of landscape vocabulary for climate elements was overwhelming. In other words, in the poems of 「The 36th Scenery of Kangxi」, scenery vocabulary symbolizing 'coolness' such as 雲(cloud), 水(water), 泉(spring), 清(clear), 波(wave), 流(wave), 風(wind) and 無暑(without heat), etc. It is not a coincidence that it appears, and it is strongly attached to the sense of place of Summer Mountain Resort in Rehe(熱河). Among the 23 landscapes whose seasonal background was confirmed, the fact that the lower landscape is portrayed as the majority and the climate elements of the resort area are portrayed in three-dimensional and multi-dimensional ways are closely related to the period of enjoying the gardens of Kangxi, the main subject of the landscape. In addition, many animal and plant landscapes appearing in Jeyeong-si appear to be in the same context as the spatial attributes of not only recreation, but also contemplation and hunting. On the other hand, in Jeyeongsi, there are 33 wonders(91.7%) citing famous people and famous books through ancient poems, old stories, and ancient stories tends to be prominent. It is inferred that this was based on Kangxi's understanding and pride in traditional Chinese culture. In 「The 36th view of Kangxi」, not only a book-writing description of the feelings of being entrusted to the family sutras, but also the spirit of patriotism, love, self-discipline and respect for mother and filial piety are strongly implied. Ultimately, 「The 36th view of Kangxi」 shows the real scene of the resort, as well as the spiritual dimension, in a multi-faceted and three-dimensional way, and the spirit of an emperor based on the dignity of the royal family and the sentiments of a writer it deserves to be called a collection of imperial records that were intended to reveal.

• Korean Journal of Environment and Ecology
• /
• v.32 no.3
• /
• pp.342-350
• /
• 2018

The purpose of this study was to identify the environmental factors that affect the beginning and end of calling by Hyalessa fuscata and Cryptotympana atrata, which are dominant cicada species in the central urban areas of Korea. The study area was Banpo Apartments in Seoul. The research period included two months, being from the end of July to the end of August 2015. We analyzed the start and end time of cicada calling, and on average H. fuscata started calling at 5:21 am and C. atrata started at 7:40 am. The average end time of calling was 6:31 pm for H. fuscata and 7:51 pm for C. atrata. From the scatter plot and box plot results, H. fuscata started calling at 05:00 am, whereas C. atrata consistently stopped calling at 20:00 pm compared to H. fuscata. Multiple regression analysis of the start and end time of cicada calling showed that sunrise time was a factor affecting the start of H. fuscata calling. The end time of H. fuscata calling was affected by sunset time and total cloud cover. The starting time of C. atrata calling was mostly affected by temperature and sunrise time. The effect of temperature was greater than that of sunrise time. The end time of C. atrata calling was strongly affected by sunset time, whereas peak temperature was also shown to affect the end time. From the above results, sunrise and sunset are thought to be the critical factor affecting the start and end time of H. fuscata calling. Therefore, H. fuscata started calling with sunrise, and the end time was also affected by sunset. Temperature was the factor most affecting the start of C. atrata calling and sunset was identified as the factor affecting the end time. Therefore, the start time of C. atrata calling shows variation with daily temperature changes, and C. atrata stop calling simultaneously with sunset.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.21 no.4
• /
• pp.64-80
• /
• 2018

In Korea, citizens can only know general information about crime. Thus it is difficult to know how much they are exposed to crime. If the police can predict the crime risky area, it will be possible to cope with the crime efficiently even though insufficient police and enforcement resources. However, there is no prediction system in Korea and the related researches are very much poor. From these backgrounds, the final goal of this study is to develop an automated crime prediction system. However, for the first step, we build a big data set which consists of local real crime information and urban physical or non-physical data. Then, we developed a crime prediction model through machine learning method. Finally, we assumed several possible scenarios and calculated the probability of crime and visualized the results in a map so as to increase the people's understanding. Among the factors affecting the crime occurrence revealed in previous and case studies, data was processed in the form of a big data for machine learning: real crime information, weather information (temperature, rainfall, wind speed, humidity, sunshine, insolation, snowfall, cloud cover) and local information (average building coverage, average floor area ratio, average building height, number of buildings, average appraised land value, average area of residential building, average number of ground floor). Among the supervised machine learning algorithms, the decision tree model, the random forest model, and the SVM model, which are known to be powerful and accurate in various fields were utilized to construct crime prevention model. As a result, decision tree model with the lowest RMSE was selected as an optimal prediction model. Based on this model, several scenarios were set for theft and violence cases which are the most frequent in the case city J, and the probability of crime was estimated by $250{\times}250m$ grid. As a result, we could find that the high crime risky area is occurring in three patterns in case city J. The probability of crime was divided into three classes and visualized in map by $250{\times}250m$ grid. Finally, we could develop a crime prediction model using machine learning algorithm and visualized the crime risky areas in a map which can recalculate the model and visualize the result simultaneously as time and urban conditions change.