• Journal of the Korean Society of Radiology
• /
• v.17 no.3
• /
• pp.375-384
• /
• 2023

Most Hepatic hemangiomas are asymptomatic and small in size, making them difficult to find by pathological examination. Therefore, radiological diagnosis is essential for the early finding and diagnosis of Hepatic hemangioma. Three-phase method using contrast medium in computed tomography, T1, T2-weighted imaging in magnetic resonance imaging, dynamic magnetic resonance imaging using contrast medium, echo planar imaging method, diffusion-weighted imaging method, blood pool scan using ^99mTc-labeled red blood cells in nuclear medicine, we looked at the color doppler method In ultrasound, and it is important to accurately understand the imaging findings of hepatic hemangioma and perform the examination in order to make an accurate diagnosis. most hepatic hemangioma are benign tumors, care should be taken not to confuse them with malignant tumors such as hepatocellular carcinoma to prevent unnecessary procedures. Therefore, in order to make an accurate diagnosis, it is important to accurately understand the imaging findings of hemangioma and perform the examination.

• Science of Emotion and Sensibility
• /
• v.25 no.4
• /
• pp.3-20
• /
• 2022

The origins of the world-recognized Korean gat can be traced back to Gojoseon, and the jades for the sangtu and gwanja come from Hongshan culture. This study examines the etymology of the hat, the symbolism of the gat and the jade comb, and the history of the development of the accessories for the hat. The research methods of literature review, investigation of relics and murals, and analysis of cases of pronunciation changes were used. Most of the relics excavated from the Hongshan are identical to those excavated from Korea. The Byun-Khan people wore a triangle-shaped conical hat (the byun), which was shaped to fit the protruding sangtu hairstyle, with a foldable brim that, if pulled downward, changed the hat to a gat. The Chu sangtu, a pointed top-knot hairstyle, is uniquely found among Northeast Asian peoples, and it is an ethnic symbol for Koreans. Until the modern period, many Koreans wore their hair in the sangtu style, indicating their descent from the sky. Jade combs shaped like birds and clouds from the Hongshan period emphasized the religious nature and ceremony of hair styling at that period. The word hat is widely used to refer to gat all over the world. The pronunciation of ㄱg, ㅎh. and ㅋq/kh are closely related to each other, and the ancient pronunciation ㄱg gradually evolved to ㅎh or ㅋq/kh. The English 'Hat' and Korean 'Gat' were transformed from the middle-ancient sound 'gasa > gosa > got' of the crown 'gwan, gokkal'. This creative hair style culture that started from the Hongshan culture continued to be fashionable during the Gojoseon Dangun period, and the decoration techniques for hats and accessories were inherited over time and continuously developed. Along with the method of making gat, creative hair-related parts, such as manggeons, donggot pins, gwanja buttons, and fine combs were developed over the course of a thousand years.

• Journal of Korea Water Resources Association
• /
• v.56 no.7
• /
• pp.439-449
• /
• 2023

Recent advancements in data measuring technology have facilitated the installation of various sensors, such as pressure meters and flow meters, to effectively assess the real-time conditions of water distribution systems (WDSs). However, as cities expand extensively, the factors that impact the reliability of measurements have become increasingly diverse. In particular, demand data, one of the most significant hydraulic variable in WDS, is challenging to be measured directly and is prone to missing values, making the development of accurate data generation models more important. Therefore, this paper proposes an adversarially trained autoencoder (ATAE) model based on generative deep learning techniques to accurately estimate demand data in WDSs. The proposed model utilizes two neural networks: a generative network and a discriminative network. The generative network generates demand data using the information provided from the measured pressure data, while the discriminative network evaluates the generated demand outputs and provides feedback to the generator to learn the distinctive features of the data. To validate its performance, the ATAE model is applied to a real distribution system in Austin, Texas, USA. The study analyzes the impact of data uncertainty by calculating the accuracy of ATAE's prediction results for varying levels of uncertainty in the demand and the pressure time series data. Additionally, the model's performance is evaluated by comparing the results for different data collection periods (low, average, and high demand hours) to assess its ability to generate demand data based on water consumption levels.

• Convergence Security Journal
• /
• v.23 no.2
• /
• pp.47-54
• /
• 2023

The global popularity of K-content(Korean Wave) has led to a continuous increase in copyright infringement cases involving domestic works, not only within the country but also overseas. In response to this trend, there is active research on technologies for detecting illegal distribution sites of domestic copyrighted materials, with recent studies utilizing the characteristics of domestic illegal distribution sites that often include a significant number of advertising banners. However, the application of detection techniques similar to those used domestically is limited for overseas illegal distribution sites. These sites may not include advertising banners or may have significantly fewer ads compared to domestic sites, making the application of detection technologies used domestically challenging. In this study, we propose a detection technique based on the similarity comparison of links and text trees, leveraging the characteristic of including illegal sharing posts and images of copyrighted materials in a similar hierarchical structure. Additionally, to accurately compare the similarity of large-scale trees composed of a massive number of links, we utilize Graph Neural Network (GNN). The experiments conducted in this study demonstrated a high accuracy rate of over 95% in classifying regular sites and sites involved in the illegal distribution of copyrighted materials. Applying this algorithm to automate the detection of illegal distribution sites is expected to enable swift responses to copyright infringements.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.06a
• /
• pp.383-384
• /
• 2022

Following the development of technologies such as digital twin, IoT, and AI after the 4th industrial revolution, decision-making problems are being solved based on high-dimensional data analysis. This has recently been applied to the port logistics sector, and a number of studies on big data analysis, deep learning predictions, and simulations have been conducted on container terminals to improve port productivity. These high-dimensional data analysis techniques generally require a large number of data. However, the global port environment has changed due to the COVID-19 pandemic in 2020. It is not appropriate to apply data before the COVID-19 outbreak to the current port environment, and the data after the outbreak was not sufficiently collected to apply it to data analysis such as deep learning. Therefore, this study intends to present a port data augmentation method for data analysis as one of these problem-solving methods. To this end, we generate the container stowage situation of the yard through a generative adversarial neural network model in terms of container terminal operation, and verify similarity through statistical distribution verification between real and augmented data.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.65 no.5
• /
• pp.51-68
• /
• 2023

Due to the recent integrated water management policy, it is important to identify a reliable supply amount for establishing an agricultural water supply plan. In order to identify the amount of agricultural water supply, it is essential to calculate the discharge by measuring the water level and flow velocity of reservoirs and canal agricultural water, and quality control to ensure reliability must be preceded. Unlike agricultural reservoirs, canal agricultural water are more sensitive to the surrounding environment and reservoir irrigation methods (continuous, intermittent irrigation, etc.), making it difficult to estimate general water level patterns and at the same time a lot of erroneous data. The Korea Rural Community Corporation is applying a filter technique as a quality control method capable of processing large quantities and real-time processing of canal agricultural water level data, and applicability evaluation is needed. In this study, the types of errors generated by the automatic water level measurement system were first determined. In addition, by using the manual quality control data, a technique with high applicability is derived by comparing and analyzing data calibrated with Gaussian, Savitzky-Golay, Hampel, and Median filter techniques, RMSE, and NSE, and the optimal parameters of the technique range was derived. As a result, the applicability of the Median filter was evaluated the highest, and the optimal parameters were derived in the range of 120min to 240min. Through the results of this study, it is judged that it can be used for quantitative evaluation to establish an agricultural water supply plan.

• Journal of Internet of Things and Convergence
• /
• v.9 no.6
• /
• pp.23-28
• /
• 2023

Windows operating system generates various logs with timestamps. Timestamp tampering is an act of anti-forensics in which a suspect manipulates the timestamps of data related to a crime to conceal traces, making it difficult for analysts to reconstruct the situation of the incident. This can delay investigations or lead to the failure of obtaining crucial digital evidence. Therefore, various techniques have been developed to detect timestamp tampering. However, there is a limitation in detection if a suspect is aware of timestamp patterns and manipulates timestamps skillfully or alters system artifacts used in timestamp tampering detection. In this paper, a method is designed to detect changes in timestamps, even if a suspect alters the timestamp of a file on a storage device, it is challenging to do so with precision beyond millisecond order. In the proposed detection method, the first step involves verifying the timestamp of a file suspected of tampering to determine its write time. Subsequently, the confirmed time is compared with the file size recorded within that time, taking into consideration the performance of the storage device. Finally, the total capacity of files written at a specific time is calculated, and this is compared with the maximum input and output performance of the storage device to detect any potential file tampering.

• Journal of Korea Water Resources Association
• /
• v.56 no.spc1
• /
• pp.1049-1058
• /
• 2023

The flow passing through river-crossing structures such as weirs and low-fall dams is dominated by rapidly varied flow including hydraulic jump. The intense unsteadiness of flow velocity and free surface profile affects the stability of such hydraulic structures. In particular, the steady hydraulic jump generated at high Froude number conditions includes remarkably air entrainment, making the flow characteristics more complicated. In this study, a large-eddy simulation was performed for turbulence effect and the hybrid VoF technique to simulate the steady hydraulic jump at the Froude number of 7.3 and the Reynolds number of 15,700. The results of the numerical simulation showed that the instantaneous maximum pressure and time-average pressure distribution calculated on the bottom surface downstream of the structure could be reasonably well reproduced being in good agreement with the experimental values. However, the instantaneous minimum pressure distribution in the direct downstream of the structure shows the opposite pattern to the target experimental measurement value. However, the numerical simulation performed in this study is considered to reasonably predict the minimum pressure distributions observed in various experiments conducted at similar conditions. The vertical distributions of flow velocity and air concentration computed in the center of the hydraulic jump were found to be in good agreement with the experimental results measured under similar conditions, showing self-similarity. These results show that the large eddy simulation and hybrid VoF techniques applied in this study can reproduce the hydraulic jump with strong air entrainment and the resulting intense free surface and pressure fluctuations at high Froude number conditions.

• Journal of Industrial Convergence
• /
• v.21 no.12
• /
• pp.55-62
• /
• 2023

Recent ransomware attacks employ various techniques and pathways, posing significant challenges in early detection and defense. Consequently, the scale of damage is continually growing. This paper introduces a machine learning-based approach for effective ransomware detection by focusing on file encryption and encryption patterns, which are pivotal functionalities utilized by ransomware. Ransomware is identified by analyzing password behavior and encryption patterns, making it possible to detect specific ransomware variants and new types of ransomware, thereby mitigating ransomware attacks effectively. The proposed machine learning-based encryption behavior detection technique extracts encryption and encryption pattern characteristics and trains them using a machine learning classifier. The final outcome is an ensemble of results from two classifiers. The classifier plays a key role in determining the presence or absence of ransomware, leading to enhanced accuracy. The proposed technique is implemented using the numpy, pandas, and Python's Scikit-Learn library. Evaluation indicators reveal an average accuracy of 94%, precision of 95%, recall rate of 93%, and an F1 score of 95%. These performance results validate the feasibility of ransomware detection through encryption behavior analysis, and further research is encouraged to enhance the technique for proactive ransomware detection.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.25 no.6
• /
• pp.555-567
• /
• 2023

The cracks in the tunnel are currently determined through visual inspections conducted by inspectors based on images acquired using tunnel imaging acquisition systems. This labor-intensive approach, relying on inspectors, has inherent limitations as it is subject to their subjective judgments. Recently research efforts have actively explored the use of deep learning to automatically detect tunnel cracks. However, most studies utilize public datasets or lack sufficient objectivity in the analysis process, making it challenging to apply them effectively in practical operations. In this study, we selected test datasets consisting of images in the same format as those obtained from the actual inspection system to perform an objective evaluation of deep learning models. Additionally, we introduced ensemble techniques to complement the strengths and weaknesses of the deep learning models, thereby improving the accuracy of crack detection. As a result, we achieved high recall rates of 80%, 88%, and 89% for cracks with sizes of 0.2 mm, 0.3 mm, and 0.5 mm, respectively, in the test images. In addition, the crack detection result of deep learning included numerous cracks that the inspector could not find. if cracks are detected with sufficient accuracy in a more objective evaluation by selecting images from other tunnels that were not used in this study, it is judged that deep learning will be able to be introduced to facility safety inspection.