• Journal of KIISE:Databases
• /
• v.28 no.3
• /
• pp.512-527
• /
• 2001

In a client-server spatial database, it is desirable to maintain the cached data in a client side to minimize the communication overhead across a network. This paper deals with the issues of concurrency and consistency of map updates in this environment. A client transaction to update map data is an interactive work and takes a long time to complete it. The map update in a client site may affect the other sites'updates because of dependencies between spatial data stored at different sites. The concurrent updates should be propagated to the other clients as well as the server to keep the consistency of map replicated in a client cache, and also the communication overhead of the update propagation should be minimized not to lose the benefit of caching. The newly proposed cache region locking with CR lock and CX lock controls the update dependency due to spatial relationships. CS lock and COD lock are suggested to use optimistic detection-based approaches for guaranteeing the consistency of cached client data. The cooperative update protocol uses these extended locking primitives and Spatial Relationship-based 2PC (SR-based 2PC). This paper argues that the concurrent updates of cached client spatial data can be achieved by deciding on collaborative updates or independent updates based on spatial relationships.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.6
• /
• pp.513-524
• /
• 2022

Recently, detecting damages of civil infrastructures from digital images using deep learning technology became a very popular research topic. In order to adapt those methodologies to the field, it is essential to explain robustness of deep learning models. Our research points out that the existing pixel-based deep learning model evaluation metrics are not sufficient for detecting cracks since cracks have linear appearance, and proposes a new evaluation methodology to explain crack segmentation deep learning model more rationally. Specifically, we design, implement and validate a methodology to generate tolerance buffer alongside skeletonized ground truth data and prediction results to consider overall similarity of topology of the ground truth and the prediction rather than pixel-wise accuracy. We could overcome over-estimation or under-estimation problem of crack segmentation model evaluation through using our methodology, and we expect that our methodology can explain crack segmentation deep learning models better.

• Journal of Cadastre & Land InformatiX
• /
• v.52 no.1
• /
• pp.17-36
• /
• 2022

The purpose of this study is to diagnose problems in the regulation and management of Restricted Development Zone and to prepare a construction plan to convert it to a data-based monitoring system. Unlike other land-use zones, the Restricted Development Zone is a exceptional zone that prohibits all development activities other than the minimum maintenance and must be strictly controlled and managed by the local government. However, the current Restricted Development Zone management is distributed according to the conditions of each local government, and it is not possible to monitor changes in the entire Restricted Development Zone as shown in the survey results. In particular, in this study, by introducing an AI-based monitoring system, MOLIT sends the results of detecting changes across the country at regular time points(monthly and quarterly) to the local governments based on the same regulation standards, and the local governments can be trusted while inputting the regulation results into the system. To propose this methodology, first, a survey and interview were conducted with local government officials and experts. Second, we analyzed cases in which AI analysis was applied to local governments and proposed a plan to improve the efficiency of regulation work according to the introduction of the monitoring system. Third, a plan was prepared to establish a monitoring system based on the advancement of the management information system. This monitoring system can be expanded and applied to land that needs periodic regulation and management in the future, and this study tried to propose a methodology and policy for this.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.2
• /
• pp.71-82
• /
• 2022

In order to replace the sampling tensile test of products produced in the tab welding process, which is one of the automotive battery manufacturing processes, vision inspectors are currently being developed and used. However, the vision inspection has the problem of inspection position error and the cost of improving it. In order to solve these problems, there are recent cases of applying deep learning technology. As one such case, this paper tries to examine the usefulness of applying Faster R-CNN, one of the deep learning technologies, to existing product inspection. The images acquired through the existing vision inspection machine are used as training data and trained using the Faster R-CNN ResNet101 V1 1024x1024 model. The results of the conventional vision test and Faster R-CNN test are compared and analyzed based on the test standards of 0% non-detection and 10% over-detection. The non-detection rate is 34.5% in the conventional vision test and 0% in the Faster R-CNN test. The over-detection rate is 100% in the conventional vision test and 6.9% in Faster R-CNN. From these results, it is confirmed that deep learning technology is very useful for detecting welding error of lead tabs in automobile batteries.

• Journal of the Korea Society for Simulation
• /
• v.32 no.3
• /
• pp.43-53
• /
• 2023

In this detailed and comprehensive study, our primary focus has been placed on accurately gauging the number of visitors and their real-time locations in commercial spaces. Particularly, in a real cafe, using security cameras, we have developed a system that can offer live updates on available seating and predict future congestion levels. By employing YOLO, a real-time object detection and tracking algorithm, the number of visitors and their respective locations in real-time are also monitored. This information is then used to update a cafe's indoor map, thereby enabling users to easily identify available seating. Moreover, we developed a model that predicts the congestion of a cafe in real time. The sophisticated model, designed to learn visitor count and movement patterns over diverse time intervals, is based on Long Short Term Memory (LSTM) to address the vanishing gradient problem and Sequence-to-Sequence (Seq2Seq) for processing data with temporal relationships. This innovative system has the potential to significantly improve cafe management efficiency and customer satisfaction by delivering reliable predictions of cafe congestion to all users. Our groundbreaking research not only demonstrates the effectiveness and utility of indoor location tracking technology implemented through security cameras but also proposes potential applications in other commercial spaces.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.3
• /
• pp.199-206
• /
• 2023

This study utilizes deep learning algorithms to automatically classify construction waste into three categories: wood waste, plastic waste, and concrete waste. Two models, VGG-16 and ViT (Vision Transformer), which are convolutional neural network image classification algorithms and NLP-based models that sequence images, respectively, were compared for their performance in classifying construction waste. Image data for construction waste was collected by crawling images from search engines worldwide, and 3,000 images, with 1,000 images for each category, were obtained by excluding images that were difficult to distinguish with the naked eye or that were duplicated and would interfere with the experiment. In addition, to improve the accuracy of the models, data augmentation was performed during training with a total of 30,000 images. Despite the unstructured nature of the collected image data, the experimental results showed that VGG-16 achieved an accuracy of 91.5%, and ViT achieved an accuracy of 92.7%. This seems to suggest the possibility of practical application in actual construction waste data management work. If object detection techniques or semantic segmentation techniques are utilized based on this study, more precise classification will be possible even within a single image, resulting in more accurate waste classification

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.1
• /
• pp.105-122
• /
• 2022

According to the statistics about the fatal crashes that have occurred on the expressways for the last 5 years, those who died on the shoulders of the road has been as 3 times high as the others who died on the expressways. It suggests that the crashes on the shoulders of the road should be fatal, and that it would be important to prevent the traffic crashes by cracking down on the vehicles intruding the shoulders of the road. Therefore, this study proposed a method to detect a vehicle that violates the shoulder lane by using the Faster R-CNN. The vehicle was detected based on the Faster R-CNN, and an additional reading module was configured to determine whether there was a shoulder violation. For experiments and evaluations, GTAV, a simulation game that can reproduce situations similar to the real world, was used. 1,800 images of training data and 800 evaluation data were processed and generated, and the performance according to the change of the threshold value was measured in ZFNet and VGG16. As a result, the detection rate of ZFNet was 99.2% based on Threshold 0.8 and VGG16 93.9% based on Threshold 0.7, and the average detection speed for each model was 0.0468 seconds for ZFNet and 0.16 seconds for VGG16, so the detection rate of ZFNet was about 7% higher. The speed was also confirmed to be about 3.4 times faster. These results show that even in a relatively uncomplicated network, it is possible to detect a vehicle that violates the shoulder lane at a high speed without pre-processing the input image. It suggests that this algorithm can be used to detect violations of designated lanes if sufficient training datasets based on actual video data are obtained.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.27 no.1
• /
• pp.115-127
• /
• 2024

This research aimed to construct models with various structures based on the Transformer module and to perform land cover classification, thereby examining the applicability of the Transformer module. For the classification of land cover, the Unet model, which has a CNN structure, was selected as the base model, and a total of four deep learning models were constructed by combining both the encoder and decoder parts with the Transformer module. During the training process of the deep learning models, the training was repeated 10 times under the same conditions to evaluate the generalization performance. The evaluation of the classification accuracy of the deep learning models showed that the Model D, which utilized the Transformer module in both the encoder and decoder structures, achieved the highest overall accuracy with an average of approximately 89.4% and a Kappa coefficient average of about 73.2%. In terms of training time, models based on CNN were the most efficient. however, the use of Transformer-based models resulted in an average improvement of 0.5% in classification accuracy based on the Kappa coefficient. It is considered necessary to refine the model by considering various variables such as adjusting hyperparameters and image patch sizes during the integration process with CNN models. A common issue identified in all models during the land cover classification process was the difficulty in detecting small-scale objects. To improve this misclassification phenomenon, it is deemed necessary to explore the use of high-resolution input data and integrate multidimensional data that includes terrain and texture information.

• Korean Journal of Environment and Ecology
• /
• v.32 no.6
• /
• pp.686-697
• /
• 2018

Due to the advance in remote sensing technology, it has become easier to more frequently obtain high resolution imagery to detect delicate changes in an extensive area, particularly including forest which is not readily sub-classified. Time-series analysis on high resolution images requires to collect extensive amount of ground truth data. In this study, the potential of land coverage mapas ground truth data was tested in classifying high-resolution imagery. The study site was Wonju-si at Gangwon-do, South Korea, having a mix of urban and natural areas. KOMPSAT-3A imagery taken on March 2015 and land coverage map published in 2017 were used as source data. Two pixel-based classification algorithms, Support Vector Machine (SVM) and Random Forest (RF), were selected for the analysis. Forest only classification was compared with that of the whole study area except wetland. Confusion matrixes from the classification presented that overall accuracies for both the targets were higher in RF algorithm than in SVM. While the overall accuracy in the forest only analysis by RF algorithm was higher by 18.3% than SVM, in the case of the whole region analysis, the difference was relatively smaller by 5.5%. For the SVM algorithm, adding the Majority analysis process indicated a marginal improvement of about 1% than the normal SVM analysis. It was found that the RF algorithm was more effective to identify the broad-leaved forest within the forest, but for the other classes the SVM algorithm was more effective. As the two pixel-based classification algorithms were tested here, it is expected that future classification will improve the overall accuracy and the reliability by introducing a time-series analysis and an object-based algorithm. It is considered that this approach will contribute to improving a large-scale land planning by providing an effective land classification method on higher spatial and temporal scales.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.22 no.2
• /
• pp.36-49
• /
• 2019

The objectives of this study were to extract "Field Survey Based Infection Tree of Pine Wilt Disease(FSB_ITPWD)" and "Object Classification Based Infection Tree of Pine Wilt Disease(OCB_ITPWD)" from the Research Forest at Kangwon National University, and evaluate the spatial distribution characteristics and occurrence intensity of wood infested by pine wood nematode. It was found that the OCB optimum weights (OCB) were 11 for Scale, 0.1 for Shape, 0.9 for Color, 0.9 for Compactness, and 0.1 for Smoothness. The overall classification accuracy was approximately 94%, and the Kappa coefficient was 0.85, which was very high. OCB_ITPWD area is approximately 2.4ha, which is approximately 0.05% of the total area. When the stand structure, distribution characteristics, and topographic and geographic factors of OCB_ITPWD and those of FSB_ITPWD were compared, age class IV was the most abundant age class in FSB_ITPWD (approximately 55%) and OCB_ITPWD (approximately 44%) - the latter was 11% lower than the former. The diameter at breast heigh (DBH at 1.2m from the ground) results showed that (below 14cm) and (below 28cm) DBH trees were the majority (approximately 93%) in OCB_ITPWD, while medium and (more then 30cm) DBH trees were the majority (approximately 87%) in FSB_ITPWD, indicating different DBH distribution. On the other hand, the elevation distribution rate of OCB_ITPWD was mostly between 401 and 500m (approximately 30%), while that of FSB_ITPWD was mostly between 301 and 400m (approximately 45%). Additionally, the accessibility from the forest road was the highest at "100m or less" for both OCB_ITPWD (24%) and FSB_ITPWD (31%), indicating that more trees were infected when a stand was closer to a forest road with higher accessibility. OCB_ITPWD hotspots were 31 and 32 compartments, and it was highly distributed in areas with a higher age class and a higher DBH class.