• The Journal of Society for e-Business Studies
• /
• v.26 no.1
• /
• pp.93-106
• /
• 2021

Many recent studies on deep learning-based road crack detection have shown significantly more improved performances than previous works using algorithm-based conventional approaches. However, many deep learning-based studies are still focused on classifying the types of cracks. The classification of crack types is highly anticipated in that it can improve the crack detection process, which is currently relying on manual intervention. However, it is essential to calculate the severity of the cracks as well as identifying the type of cracks in actual pavement maintenance planning, but studies related to road crack detection have not progressed enough to automated calculation of the severity of cracks. In order to calculate the severity of the crack, the type of crack and the area of the crack in the image must be identified together. This study deals with a method of using Mobilenet-SSD that is deep learning-based object detection techniques to effectively automate the simultaneous detection of crack types and crack areas. To improve the accuracy of object-detection for road cracks, several experiments were conducted to combine the U-Net for automatic segmentation of input image and object-detection model, and the results were summarized. As a result, image masking with U-Net is able to maximize object-detection performance with 0.9315 mAP value. While referring the results of this study, it is expected that the automation of the crack detection functionality on pave management system can be further enhanced.

• Biomedical Science Letters
• /
• v.5 no.1
• /
• pp.101-107
• /
• 1999

Bovine immunodeficiency virus (BIV) which was grouped into the Lentivirinae of family Retroviridae, was known to be causing many immunodeficiency syndromes among cows. The BIV was studied worldwide during last several years for its importance in cattle industries but nothing was reported in Korea until now Thus we initially tried to study the existence of BIV in cattle around the Daegu·Kyungpook area by PCR related molecular techniques. As a prerequisite investigation for detecting Korean-type BIV, we had focused our aim into BLV infected cows because the BLV infected cows tend to show BIV infection with 5％ ranges. Hence we randomly sampled fresh bloods from 248 cows and bulls near the Daegu·Kyungpook area and collected peripheral blood monocytes (PBMC) from the sample bloods. After extracting genomic DNA from the PBMC, we subjected it to PCR and Soluthern blot analysis for BIV/BLV detection. Overall, 66.9% (81/121) of the cow PBMC samples turned out to be BLV positive by PCR and the result was reconfirmed by Southern blot analysis. The value was two times higher than the previously reported results of BLV infection in Korea. The significant difference was mainly due to 1) applying highly specific methods for BLV detection such as PCR 2) that BLV was continuously spreaded in the Daegu Kyungpook area without any notice during last ten years. We also tested the BLV positive samples with the same techniques for BIV detection. And we found some BIV positives among the lot 3C samples by PCR, which had showed 100% BLV positive.

• Journal of Communications and Networks
• /
• v.11 no.1
• /
• pp.57-71
• /
• 2009

Networking together hundreds or thousands of cheap sensor nodes allows users to accurately monitor a remote environment by intelligently combining the data from the individual nodes. As sensor nodes are typically battery operated, it is important to efficiently use the limited energy of the nodes to extend the lifetime of the wireless sensor network (WSN). One of the fundamental issues in WSNs is the coverage problem. In this paper, the border coverage problem in WSNs is rigorously analyzed. Most existing results related to the coverage problem in wireless sensor networks focused on planar networks; however, three dimensional (3D) modeling of the sensor network would reflect more accurately real-life situations. Unlike previous works in this area, we provide distributed algorithms that allow the selection and activation of an optimal border cover for both 2D and 3D regions of interest. We also provide self-healing algorithms as an optimization to our border coverage algorithms which allow the sensor network to adaptively reconfigure and repair itself in order to improve its own performance. Border coverage is crucial for optimizing sensor placement for intrusion detection and a number of other practical applications.

• Applied Microscopy
• /
• v.41 no.2
• /
• pp.81-88
• /
• 2011

Even though importance of nano-scale structure and compositional analysis have been getting increased, existing analysis tools have been reached to their limitations. Recent development of Atom Probe Tomography (APT), providing 3-dimensional elemental distribution and compositional information with sub-nm scale special resolution and tens of ppm detection limit, is one of key technique which can overcome these limitations. However, due to the fact that APT is not well known yet in the domestic research area, it has been rarely utilized so far. Therefore, in this article, the theoretical background of APT was briefly introduced with sample preparation to help understanding APT analysis.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.28 no.2
• /
• pp.239-246
• /
• 2010

Satellite image has capability of getting a broad data rapidly. It is possible that acquisition of change information about topography, land, ecosystem and urbanization etc. from multi-temporal satellite Images. In this study, the time-series change of vegetation has detected using four period Landsat Imageries. Also, NDVI was used to recognize the vitality of vegetation. Time series change of vegetation about study area was able to detect effectively by the results of classification and NDVI. It is expected that this study should be utilized as the decision making related to the effective management and plan establishment.

• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.294-302
• /
• 2022

Detection of fake news is a complex and a challenging task. Generation of fake news is very hard to stop, only steps to control its circulation may help in minimizing its impacts. Humans tend to believe in misleading false information. Researcher started with social media sites to categorize in terms of real or fake news. False information misleads any individual or an organization that may cause of big failure and any financial loss. Automatic system for detection of false information circulating on social media is an emerging area of research. It is gaining attention of both industry and academia since US presidential elections 2016. Fake news has negative and severe effects on individuals and organizations elongating its hostile effects on the society. Prediction of fake news in timely manner is important. This research focuses on detection of fake news spreaders. In this context, overall, 6 models are developed during this research, trained and tested with dataset of PAN 2020. Four approaches N-gram based; user statistics-based models are trained with different values of hyper parameters. Extensive grid search with cross validation is applied in each machine learning model. In N-gram based models, out of numerous machine learning models this research focused on better results yielding algorithms, assessed by deep reading of state-of-the-art related work in the field. For better accuracy, author aimed at developing models using Random Forest, Logistic Regression, SVM, and XGBoost. All four machine learning algorithms were trained with cross validated grid search hyper parameters. Advantages of this research over previous work is user statistics-based model and then ensemble learning model. Which were designed in a way to help classifying Twitter users as fake news spreader or not with highest reliability. User statistical model used 17 features, on the basis of which it categorized a Twitter user as malicious. New dataset based on predictions of machine learning models was constructed. And then Three techniques of simple mean, logistic regression and random forest in combination with ensemble model is applied. Logistic regression combined in ensemble model gave best training and testing results, achieving an accuracy of 72%.

• Journal of Food Hygiene and Safety
• /
• v.38 no.5
• /
• pp.279-286
• /
• 2023

Rapid and accurate detection of pathogenic bacteria is crucial for various applications, including public health and food safety. However, existing bacteria detection techniques have several drawbacks as they are inconvenient and require time-consuming procedures and complex machinery. Recently, the precision and versatility of CRISPR/Cas system has been leveraged to design biosensors that offer a more efficient and accurate approach to bacterial detection compared to the existing techniques. Significant research has been focused on developing biosensors based on the CRISPR/Cas system which has shown promise in efficiently detecting pathogenic bacteria or virus. In this review, we present a biosensor based on the CRISPR/Cas system that has been specifically developed to overcome these limitations and detect different pathogenic bacteria effectively including Vibrio parahaemolyticus, Salmonella, E. coli O157:H7, and Listeria monocytogenes. This biosensor takes advantage of the CRISPR/Cas system's precision and versatility for more efficiently accurately detecting bacteria compared to the previous techniques. The biosensor has potential to enhance public health and ensure food safety as the biosensor's design can revolutionize method of detecting pathogenic bacteria. It provides a rapid and reliable method for identifying harmful bacteria and it can aid in early intervention and preventive measures, mitigating the risk of bacterial outbreaks and their associated consequences. Further research and development in this area will lead to development of even more advanced biosensors capable of detecting an even broader range of bacterial pathogens, thereby significantly benefiting various industries and helping in safeguard human health

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.11
• /
• pp.305-313
• /
• 2019

Recently, spatial information is being constructed actively based on the images obtained by drones. Because occlusion areas occur due to buildings as well as many obstacles, such as trees, pedestrians, and banners in the urban areas, an efficient way to resolve the problem is necessary. Instead of the traditional way, which replaces the occlusion area with other images obtained at different positions, various models based on deep learning were examined and compared. A comparison of a type of feature descriptor, HOG, to the machine learning-based SVM, deep learning-based DNN, CNN, and RNN showed that the CNN is used broadly to detect and classify objects. Until now, many studies have focused on the development and application of models so that it is impossible to select an optimal model. On the other hand, the upgrade of a deep learning-based detection and classification technique is expected because many researchers have attempted to upgrade the accuracy of the model as well as reduce the computation time. In that case, the procedures for generating spatial information will be changed to detect the occlusion area and replace it with simulated images automatically, and the efficiency of time, cost, and workforce will also be improved.

• Journal of Korea Multimedia Society
• /
• v.16 no.1
• /
• pp.11-18
• /
• 2013

This paper presents a SFF(shape from focus) algorithm using a new focus measure based on higher order statistics for the exact depth estimation. Since conventional SFF-based 3D depth reconstruction algorithms used SML(sum of modified Laplacian) as the focus measure, their performance is strongly depended on the image characteristics. These are efficient only for the rich texture and well focused images. Therefore, this paper adopts a new focus measure using HOS(higher order statistics), in order to extract the focus value for relatively poor texture and focused images. The initial best focus area map is generated by the measure. Thereafter, the area refinement, thinning, and corner detection methods are successively applied for the extraction of the locally best focus points. Finally, a 3D model from the carefully selected points is reconstructed by Delaunay triangulation.

• Health Policy and Management
• /
• v.6 no.1
• /
• pp.85-109
• /
• 1996

Telemedicine can increase accessibility to advance medical technology at the university hospital for community residents living in a remote area. This paper focused on the economic evaluation of telemedicine to identify important factors influencing costs and benefits and to understand how these factors can be changed to improve economic performance of the telemedicine. When the telemedicine project currently operating in Korea was evaluated based on the traditional cost-benefit analysis, the results showed a heavy net loss wiht a B/C ration of 0.56. As several values were added to the analysis based on the Information Economics approach, B/C ratios steadly increased. When the saving of medical expenses from the early detection of diseases was taken into a consideration, the ration exceeded the break-even point. >From the sensitivity analysis, a number of patients and the cost for equipment and communication were found to be the key factors for influencing economic performance of telemedicine.