• Information Systems Review
• /
• v.5 no.2
• /
• pp.241-256
• /
• 2003

This empirical study is to explain critical success factors for building effective regional IT cluster from the literature reviews which have some limitations, and is to suggest new key factors from the views of Regional Innovation System and Sectoral Systems of Innovation. For building successful cluster, the new key factors not only stress on regional networks, the spill-over of tacit knowledge through learning by interacting, institutions which contain regional custom, norms, established practices, culture, and characteristics from the Regional Innovation System, but also emphasize on heterogeneous agents who are interacting by each others from Sectoral Systems of Innovation. From these factors we suggest some strategies for building effective "Daegu IT Cluster" as following; making characterized IT brands which are selected and concentrated based on regional and IT sectoral characteristics, strengthening learning competence of tacit knowledge built in multiple heterogeneous agents network, establishing strong agent networks which are composed of universities, companies, institutes and government, and sharing the institution of mind-opening culture in order to correspond with environmental changes and link to other industrial clusters. By putting above strategies in force, the compatabilities of Daegu region are reinforced. Tacit knowledges spill over and the regional innovation competence are accumulated. Also IT cluster plays core role of employment in Daegu for long term. Especially, "Daegu IT Cluster" changes city's image from medium and small manufacturing city to new industrial city based on high technologies.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_3
• /
• pp.1389-1403
• /
• 2021

Disaster management using VHR (very high resolution) satellite images supports rapid damage assessment and also offers detailed information of the damages. However, the acquisition of pre-event VHR satellite images is usually limited due to the long revisit time of VHR satellites. The absence of the pre-event data can reduce the accuracy of damage assessment since it is difficult to distinguish the changed region from the unchanged region with only post-event data. To address this limitation, in this study, we conducted the wildfire-induced change detection on national wildfire cases using post-fire VHR satellite images and GIS (Geographic Information System) data. For GIS data, a national land cover map was selected to simulate the pre-fire NIR (near-infrared) images using the spatial information of the pre-fire land cover. Then, the simulated pre-fire NIR images were used to analyze bi-temporal NDVI (Normalized Difference Vegetation Index) correlation for unsupervised change detection. The whole process of change detection was performed on a superpixel basis considering the advantages of superpixels being able to reduce the complexity of the image processing while preserving the details of the VHR images. The proposed method was validated on the 2019 Gangwon wildfire cases and showed a high overall accuracy over 98% and a high F1-score over 0.97 for both study sites.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.6
• /
• pp.121-127
• /
• 2022

Smart mirror is an IoT device that attaches a display and an embedded computer to the mirror and provides various information to the useer along with the mirror function. This paper went beyond the form of dealing with smart mirrors only stand alone device the provide information to users, and constructed a network in which smart mirrors are connected, and proposed and implemented a CoMirror system that allows users to talk and share information with other smart mirror users. The CoMirror system has a structure in which several CoMirror clients are connected on one CoMirror server. The CoMirror client consists of Raspberry Pi, a mirror film, a touch pad, a display device, an web camera, etc. The server has functions such as face learning and recognition, user management, a relay role for exchanging messages between clients, and setting up for video call. Users can communicate with other CoMirror users via the server, such as text, image, and audio messages, as well as 1:1 video call.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.1
• /
• pp.182-192
• /
• 2022

Motorcycle accidents are increasing at an average annual rate of 10.01%, and fatalities are also increasing by 2.64%. Enforcement cameras are installed to enforce safe driving of more-than or equal-to four-wheeled vehicles on the road. Even though the main purpose of this enforcement camera is to disencourage the speed violation of all types of vehicle, one cannot expect complete enforcement by these cameras. In particular, enforcement of the motorcycle should rely on on-site activities through the input of on-site personnel. Recently, to discourage the illegal acts of motorcycling, the National Police Agency introduced the 'National Police Agency SMART National Report'. However, it is necessary to prepare an appropriate practical plan to maximize the effect of enforcement requiring continuous manpower management. This study proposed four types of rider certification IDs for delivery motorcycles. These IDs are institutional devices to manage delivery motorcycle riders. In addition, a experiment on enforcement was conducted using those license ID systems for delivery motorcycles. This experiment confirmed through the image-processing program (D-MESO) if one of the systems was possible to implement for enforcement on the delivery motorcycle rider's license.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.2
• /
• pp.113-128
• /
• 2024

Items of road tunnel PISD (Precise Inspection for Safety and Diagnosis) were reviewed and analyzed using newly enhanced MMS (Mobile Mapping System) technology. Possible items with MMS can be visual inspection, survey and non-destructive test, structural analysis, and maintenance plan. The resolution of 3D point cloud decreased when the vehicle speed of MMS is too fast while the calibration error increased when it is too slow. The speed measurement of 50 km/h is determined to be effective in this study. Although image resolution by MMS has a limit to evaluating the width of crack with high precision, it can be used as data to identify the status of facilities in the tunnel and determine whether they meet disaster prevention management code of tunnel. 3D point cloud with MMS can be applicable for matching of cross-section and also possible for the variation of longitudinal survey, which can intuitively check vehicle clearance throughout the road tunnel. Compared with the measurement of current PISD, number of test and location of survey is randomly sampled, the continuous measurement with MMS for environment condition can be effective and meaningful for precise estimation in various analysis.

• Journal of the Society of Disaster Information
• /
• v.16 no.2
• /
• pp.267-275
• /
• 2020

Purpose: In this study, GPR exploration equipment, spray vehicles and flow meters, core drill, borehole image processing system(BIPS), 3D cavity imagery equipment, and cavity formatting equipment were used to identify this cavity growth process. Method: A certain amount of water was injected in proportion to the mass of the cavity, and the cavity was observed to expand as the injected water was drained out. The cavity rating change was evaluated by quantitatively evaluating the expansion factors and the speed of growth. Results: According to the results of examining the volume change through injection time - injection flow rate - volume increase for the four experimenters, the volume increase decreased as the injection time increased, and there was no further increase in volume if injected for one hour or so. Conclusion: In addition, the injection test analyzed the volumetric variation to determine whether the cause of the cavity occurrence was the effect of the underground burial in the vicinity of the cavity. Therefore, it was found that the cavity expansion is caused by the repetition of the relaxation soil collapse due to the groundwater flow and the loss of the collapsed soil below the cavity.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.16 no.3
• /
• pp.136-146
• /
• 2013

This study has specified terminology for mountain ridgeline, and organized the present condition of Korean mountain ridgeline and empirical management measures of Beakdudeagan and Jeongmeak. Moreover, based on previously published paper maps, mountain map, and numerical maps, this study has used GIS to reorganize Jeongmaek of Korea, including Hanbukjeongmaek, Hannamjeongmaek, and Gumbukjoengmaek. To ensure accuracy, DEM, Shaded Relief Image, gradient, curvature, and aspect have been analyzed from recent numerical maps. On extraction process, this study analyzes more specifically the results, previous Beakdudaegan is modified and new Jeongmaeks have been extracted. Moreover, for analyzing natural environment of surrounding of major mountain ridgeline, ecological zoning grade of mountain ridgeline is analyzed. With the analyzed result, domestic and foreign mountain ridgeline management policy is suggested, and environmental impact assessment method for major mountain ridgeline development is also suggested. In this study, Baekdudaegan and its Jeongmaek are organized and analyzed. With the results, this study suggested political linkage of mountain ridgelines and guidelines for environmental impact assessment of ridgeline development.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.15-30
• /
• 2023

Recently, various services using artificial intelligence(AI) are emerging in the media field as well However, most of the video editing, which involves finding an editing point and attaching the video, is carried out in a passive manner, requiring a lot of time and human resources. Therefore, this study proposes a methodology that can detect the edit points of video according to whether person in video are spoken by using Video Swin Transformer. First, facial keypoints are detected through face alignment. To this end, the proposed structure first detects facial keypoints through face alignment. Through this process, the temporal and spatial changes of the face are reflected from the input video data. And, through the Video Swin Transformer-based model proposed in this study, the behavior of the person in the video is classified. Specifically, after combining the feature map generated through Video Swin Transformer from video data and the facial keypoints detected through Face Alignment, utterance is classified through convolution layers. In conclusion, the performance of the image editing point detection model using facial keypoints proposed in this paper improved from 87.46% to 89.17% compared to the model without facial keypoints.

• Journal of the Society of Disaster Information
• /
• v.20 no.1
• /
• pp.199-205
• /
• 2024

Purpose: This study aims to improve the recognition rate of Auto People Counting (APC) in accurately identifying and providing information on remaining evacuees in disaster-vulnerable facilities such as nursing homes to firefighting and other response agencies in the event of a disaster. Methods: In this study, a baseline model was established using CNN (Convolutional Neural Network) models to improve the algorithm for recognizing images of incoming and outgoing individuals through cameras installed in actual disaster-vulnerable facilities operating APC systems. Various algorithms were analyzed, and the top seven candidates were selected. The research was conducted by utilizing transfer learning models to select the optimal algorithm with the best performance. Results: Experiment results confirmed the precision and recall of Densenet201 and Resnet152v2 models, which exhibited the best performance in terms of time and accuracy. It was observed that both models demonstrated 100% accuracy for all labels, with Densenet201 model showing superior performance. Conclusion: The optimal algorithm applicable to APC among various artificial intelligence algorithms was selected. Further research on algorithm analysis and learning is required to accurately identify the incoming and outgoing individuals in disaster-vulnerable facilities in various disaster situations such as emergencies in the future.

• Journal of the Korean Society for information Management
• /
• v.41 no.1
• /
• pp.261-282
• /
• 2024

This study proposed and evaluated electroencephalography (EEG)-based and eye-tracking-based methods to determine relevance by utilizing users' implicit relevance feedback while navigating content in a digital library. For this, EEG/eye-tracking experiments were conducted on 32 participants using video, image, and text data. To assess the usefulness of the proposed methods, deep learning-based artificial intelligence (AI) techniques were used as a competitive benchmark. The evaluation results showed that EEG component-based methods (av_P600 and f_P3b components) demonstrated high classification accuracy in selecting relevant videos and images (faces/emotions). In contrast, AI-based methods, specifically object recognition and natural language processing, showed high classification accuracy for selecting images (objects) and texts (newspaper articles). Finally, guidelines for implementing a digital library interface based on EEG, eye-tracking, and artificial intelligence technologies have been proposed. Specifically, a system model based on implicit relevance feedback has been presented. Moreover, to enhance classification accuracy, methods suitable for each media type have been suggested, including EEG-based, eye-tracking-based, and AI-based approaches.