• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.1
• /
• pp.19-25
• /
• 2024

This paper proposes an artificial intelligence-based personal information area object detection optimization method in an embedded system to de-identify personal information in video data. As an object detection optimization method, first, in order to increase the detection rate for personal information areas when detecting objects, a gyro sensor is used to collect the shooting angle of the image data when acquiring the image, and the image data is converted into a horizontal image through the collected shooting angle. Based on this, each learning model was created according to changes in the size of the image resolution of the learning data and changes in the learning method of the learning engine, and the effectiveness of the optimal learning model was selected and evaluated through an experimental method. As a de-identification method, a shuffling-based masking method was used, and double-key-based encryption of the masking information was used to prevent restoration by others. In order to reuse the original image, the original image could be restored through a security key. Through this, we were able to secure security for high personal information areas and improve usability through original image restoration. The research results of this paper are expected to contribute to industrial use of data without personal information leakage and to reducing the cost of personal information protection in industrial fields using video through de-identification of personal information areas included in video data.

• Computers and Concrete
• /
• v.33 no.4
• /
• pp.341-348
• /
• 2024

Ultra-high-performance concrete (UHPC) has received remarkable attentions in civil infrastructure due to its unique mechanical characteristics and durability. UHPC gains increasingly dominant in essential structural elements, while its unique properties pose challenges for traditional inspection methods, as damage may not always manifest visibly on the surface. As such, the need for robust inspection techniques for detecting cracks in UHPC members has become imperative as traditional methods often fall short in providing comprehensive and timely evaluations. In the era of artificial intelligence, computer vision has gained considerable interest as a powerful tool to enhance infrastructure condition assessment with image and video data collected from sensors, cameras, and unmanned aerial vehicles. This paper presents a computer vision-based approach employing deep learning to detect cracks in UHPC beams, with the aim of addressing the inherent limitations of traditional inspection methods. This work leverages computer vision to discern intricate patterns and anomalies. Particularly, a convolutional neural network architecture employing transfer learning is adopted to identify the presence of cracks in the beams. The proposed approach is evaluated with image data collected from full-scale experiments conducted on UHPC beams subjected to flexural and shear loadings. The results of this study indicate the applicability of computer vision and deep learning as intelligent methods to detect major and minor cracks and recognize various damage mechanisms in UHPC members with better efficiency compared to conventional monitoring methods. Findings from this work pave the way for the development of autonomous infrastructure health monitoring and condition assessment, ensuring early detection in response to evolving structural challenges. By leveraging computer vision, this paper contributes to usher in a new era of effectiveness in autonomous crack detection, enhancing the resilience and sustainability of UHPC civil infrastructure.

• Pediatric Gastroenterology, Hepatology & Nutrition
• /
• v.27 no.4
• /
• pp.215-223
• /
• 2024

Purpose: Patients who receive frequent blood transfusions are at an elevated risk of developing hepatic fibrosis due to iron overload in the liver. In this study, we evaluated the effectiveness of transient elastography (TE) (FibroScan^®) for assessing liver fibrosis in patients with pediatric cancer. Methods: We enrolled 106 consecutive cases of acute leukemia in individuals under 21 years of age. The participants were followed for 2 years. Based on their serum ferritin (SF) levels, the patients were divided into two groups: group 1 (SF≥300 ng/mL) and group 2 (SF<300 ng/mL). A liver FibroScan^® was performed, and a p-value of less than 0.05 was considered statistically significant. Results: Among the various parameters in the liver function test (LFT), alkaline phosphatase was significantly higher in a subgroup of patients aged 5-8 years in group 2 compared to those in group 1. The indices of liver fibrosis determined by TE, including the FibroScan score, controlled attenuation parameter score, steatosis percentage, and meta-analysis of histological data in viral hepatitis score, as well as indirect serum markers of liver fibrosis such as the aminotransferase (AST)/alanine aminotransferase (ALT) ratio, Fibrosis 4 score, and AST to platelet ratio index, did not differ significantly between the two groups. The association between the TE results and LFT parameters was only significant for ALT. Conclusion: Transfusion-associated iron overload does not have a significant correlation with severe liver fibrosis. FibroScan^® is not a sensitive tool for detecting early stages of fibrosis in survivors of pediatric leukemia.

• Journal of Gastric Cancer
• /
• v.9 no.3
• /
• pp.110-116
• /
• 2009

Purpose: The aim of this study was to examine the usefulness of positron emission tomography (PET)-computed tomography (CT) in the pre-operative staging of gastric cancer. Materials and Methods: Between February 2006 and August 2008, PET-CT and CT were performed on 70 patients diagnosed with gastric cancer by gastrofiberscopic biopsy. The sensitivities, specificities, Positive predictive value (PPV), and negative predictive value (NPV) of PET-CT and CT imaging for the detection of gastric cancer TNM staging were compared. Results: The detection rates for the primary tumor were as follows: PET-CT, 81.4% (57/70); and CT, 42.9% (30/70). For both early gastric cancer (EGC) and advanced gastric cancer (AGC), PET-CT was more accurate than CT in detecting the lesions. As the size of the tumor exceeded 3 cm, the detection rate increased. The sensitivities, specificities, PPV, and NPV of PET-CT for lymph node staging were 55.6%, 81%, 86.2%, and 45.9%, while the sensitivities, specificities, PPV, and NPV of CT were 40.0%, 85.7%, 85.7% and 40%, respectively. One case of multiple liver metastasis and two cases of dual primary cancer (rectal and pancreatic cancers) were detected by PET-CT. PET-CT also had a higher detection rate for all histologic types of primary tumors. PET-CT was more accurate than CT in detecting primary gastric cancer lesions. The detection of nodal metastasis by PET-CT was similar to CT; small-sized tumors or EGC detection rates were not high. However, PET-CT provided additional information to detect distant metastases and dual primary cancers and reduced unnecessary laparotomies to detect peritoneal seeding or carcinomatosis. Conclusion: It would be useful to make a pre-operative diagnosis of gastric cancer and determine treatment if PET-CT were added to other routine pre-operative studies.

• The Korean Journal of Nuclear Medicine
• /
• v.29 no.4
• /
• pp.511-517
• /
• 1995

Bone scan is a very sensitive diagnostic imaging test for detecting bone and joint disorders. So it might be useful in the diagnosis of temporomandibular disorders of the joint origin. Thus, the effectiveness of bone scan for detecting temporomandibular joint(TMJ) diseases and differentiating the TMJ disc displacement from the TMJ arthritis was evaluated. Bone scan was done in 21 patients with TMJ disc displacement(13 unilaterally affected, 8 bilaterally affected), 25 patients with TMJ arthritis(23 unilateral, 3 bilateral), and 39 volunteers with no signs, symtoms, or history of TMJ disease. TMJ simple uptake rate(SUR) and difference of both TMJ SUR were calculated from the 100,000 count lateral image of head and neck region in 99mTc MDP bone scan. Transcranial and panorama X-ray examination was also done in all patients. TMJ SUR(%) were $1.673{\pm}0.606$ in TMJs affected with arthritis, $1350{\pm}0.351$ in TMJs affected with disc displacement, and $1.084{\pm}0.172$ in TMJs of controls. Significant differences were demonstrated among them(p<0.01) Difference of bith TMJ SUR was highest in patients with unilateral TMJ arthritis($0.608{\pm}$0.533, p<001), and there is no significant difference between that of controls and that of unilateral TMJ dist displacement patients($0.062{\pm}0.063$ vs $0.122{\pm}0.100$). TMJ SUR of Joint with bone change on X-ray finding was not significantly different from that of joint with normal X-ray finding. Those in patients with unilateral TMJ disc displacement(696% and 87% vs 23.1% and 23%). The proportions of patients with increased TMJ SUR and difference of both TMJ SUR(>mean+2SD of controls) in unilateral TMJ arthritis patients were significantly higher than those in patients with unilateral TMJ disc displacement(69.6% and 87% vs 23.1% and 23%). Conclusively, bone scan nay help to detect TMJ disease and differentiate TMJ disc displacement from TMJ arthritis.

• Journal of the Korean earth science society
• /
• v.21 no.4
• /
• pp.408-422
• /
• 2000

Multiple geophysical methods were applied over the Manjang cave area in Cheju Island to compare and contrast the effectiveness of each method for exploration of underground cavities. The used methods are gravity, magnetic, electrical resistivity and GPR(Ground Pentrating Radar) survey, of which instruments are portable and operations are relatively economical. We have chosen seven survey lines and applied appropriate multiple surveys depending on the field conditions. In the case of magnetic method. two-dimensional grid-type surveys were carried out to cover the survey area. The geophysical survey results reveal the characteristic responses of each method relatively well. Among the applied methods, the electric resistivity methods appeared to be the most effective ones in detecting the Manjang Cave and surrounding miscellaneous cavities. Especially, on the inverted resistivity section obtained from the dipole-dipole array data, the two-dimensional distribution of high resistivity cavities are revealed well. The gravity and magnetic data are contaminated easily by various noises and do not show the definitive responses enough to locate and delineate the Manjang cave. But they provide useful information in verifying the dipole-dipole resistivity survey results. The grid-type 2-D magnetic survey data show the trend of cave development well, and it may be used as a reconnaissance regional survey for determining survey lines for further detailed explorations. The GPR data show very sensitive response to the various shallow volcanic structures such as thin spaces between lava flows and small cavities, so we cannot identify the response of the main cave. Although each geophysical method provides its own useful information, the integrated interpretation of multiple survey data is most effective for investigation of the underground caves.

• Journal of Intelligence and Information Systems
• /
• v.14 no.2
• /
• pp.179-192
• /
• 2008

This case study shows constructing the knowledge-based system using a rule-based approach for detecting illegal transactions regarding money laundering in the Korea Financial Intelligence Unit (KoFIU). To better manage the explosive increment of low risk suspicious transactions reporting from financial institutions, the adoption of a knowledge-based system in the KoFIU is essential. Also since different types of information from various organizations are converged into the KoFIU, constructing a knowledge-based system for practical use and data management regarding money laundering is definitely required. The success of the financial information system largely depends on how well we can build the knowledge-base for the context. Therefore we designed and constructed the knowledge-based system for anti-money laundering by committing domain experts of each specific financial industry co-worked with a knowledge engineer. The outcome of the knowledge base implementation, measured by the empirical ratio of Suspicious Transaction Reports (STRs) reported to law enforcements, shows that the knowledge-based system is filtering STRs in the primary analysis step efficiently, and so has made great contribution to improve efficiency and effectiveness of the analysis process. It can be said that establishing the foundation of the knowledge base under the entire framework of the knowledge-based system for consideration of knowledge creation and management is indeed valuable.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.8 no.6
• /
• pp.37-45
• /
• 2008

It is expected that conditions of water resources will be changed in Korea in accordance with world wide climate change. In order to deal with this problem and find a way of minimizing the effect of future climate change, the usefulness of climate model simulation information is examined in this study. The objective of this study is to assess the applicability of GCM (General Circulation Model) information for Korean water resources management through uncertainty analysis. The methods are based on probabilistic measures of the effectiveness of GCM simulations of an indicator variable for discriminating high versus low regional observations of a target variable. The formulation uses the significance probability of the Kolmogorov-Smirnov test for detecting differences between two variables. An estimator that accounts for climate model simulation and spatial association between the GCM data and observed data is used. Atmospheric general circulation model (AGCM) simulations done by ECMWF (European Centre for Medium-Range Weather Forecasts) with a resolution of $2^{\circ}{\times}2^{\circ}$, and METRI (Meteorological Research Institute, Korea) with resolutions of $2^{\circ}{\times}2^{\circ}$ and $4^{\circ}{\times}5^{\circ}$, were used for indicator variables, while observed mean areal precipitation (MAP) data, discharge data and mean areal temperature data on the seven major river basins in Korea were used for target variables. The results show that GCM simulations are useful in discriminating the high from the low of the observed precipitation, discharge, and temperature values. Temperature especially can be useful regardless of model and season.

• Journal of KIISE:Software and Applications
• /
• v.37 no.6
• /
• pp.455-463
• /
• 2010

In this paper, we present an approach to sentence boundary detection for web documents that builds on statistical-based methods and uses rule-based correction. The proposed system uses the classification model learned offline using a training set of human-labeled web documents. The web documents have many word-spacing errors and frequently no punctuation mark that indicates the end of sentence boundary. As sentence boundary candidates, the proposed method considers every Ending Eomis as well as punctuation marks. We optimize engine performance by selecting the best feature, the best training data, and the best classification algorithm. For evaluation, we made two test sets; Set1 consisting of articles and blog documents and Set2 of web community documents. We use F-measure to compare results on a large variety of tasks, Detecting only periods as sentence boundary, our basis engine showed 96.5% in Set1 and 56.7% in Set2. We improved our basis engine by adapting features and the boundary search algorithm. For the final evaluation, we compared our adaptation engine with our basis engine in Set2. As a result, the adaptation engine obtained improvements over the basis engine by 39.6%. We proved the effectiveness of the proposed method in sentence boundary detection.

• Journal of Korean Society for Atmospheric Environment
• /
• v.30 no.4
• /
• pp.327-338
• /
• 2014

The objective of this study is to enhance the effectiveness of Korean Inspection and Maintenance (I/M) program. Three main tasks are: to measure pollutant emissions of in-use light-duty diesel vehicles (LDVs); to evaluate the validity of existing smoke control scheme for low-smoke-emitting vehicles, which have diesel particulate filters, DPF, to meet stringent Euro-5 emission limits; and to assess the necessity and the benefit of $NO_x$ inspection, which is not involved in current I/M program. We measured second-by-second smoke, particulate and gaseous emissions of 27 LDVs using opacity smoke meter, photo-acoustic soot sensor, and portable emissions measurement system, respectively, under the Korean I/M test driving cycle, KD-147. We find that the DPF plays a key role in controlling soot, which can be considered as black carbon contained in particulate matter. Thus, from an I/M perspective, we believe smoke inspection strategies for Euro-5 diesel vehicles should be more focused on the capability of detecting DPF malfunctions or failures, in order to keep DPF properly functional. Fleet averaged distance-specific $NO_x$ emissions are consistently higher than corresponding emission limits, and the values are similar among pre-Euro-3, Euro-3, and Euro-4 vehicle fleets. These findings indicate that the $NO_x$ inspection should be incorporated into current I/M program in order to manage urban $NO_x$ emissions. This research allows the Korean I/M program keep pace with developments in vehicle technologies, as well as the increased emphasis on $NO_x$ with respect to air quality and human health.