• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.7
• /
• pp.3756-3777
• /
• 2019

Recent internet development is helping malware researchers to generate malicious code variants through automated tools. Due to this reason, the number of malicious variants is increasing day by day. Consequently, the performance improvement in malware analysis is the critical requirement to stop the rapid expansion of malware. The existing research proved that the similarities among malware variants could be used for detection and family classification. In this paper, a Cross-Platform Malware Variant Classification System (CP-MVCS) proposed that converted malware binary into a grayscale image. Further, malicious features extracted from the grayscale image through Combined SIFT-GIST Malware (CSGM) description. Later, these features used to identify the relevant family of malware variant. CP-MVCS reduced computational time and improved classification accuracy by using CSGM feature description along machine learning classification. The experiment performed on four publically available datasets of Windows OS and Android OS. The experimental results showed that the computation time and malware classification accuracy of CP-MVCS was higher than traditional methods. The evaluation also showed that CP-MVCS was not only differentiated families of malware variants but also identified both malware and benign samples in mix fashion efficiently.

• Journal of information and communication convergence engineering
• /
• v.19 no.2
• /
• pp.79-83
• /
• 2021

This paper proposes a novel image classification method based on few-shot learning, which is mainly used to solve model overfitting and non-convergence in image classification tasks of small datasets and improve the accuracy of classification. This method uses model structure optimization to extend the basic convolutional neural network (CNN) model and extracts more image features by adding convolutional layers, thereby improving the classification accuracy. We incorporated certain measures to improve the performance of the model. First, we used general methods such as setting a lower learning rate and shuffling to promote the rapid convergence of the model. Second, we used the data expansion technology to preprocess small datasets to increase the number of training data sets and suppress over-fitting. We applied the model to 10 monkey species and achieved outstanding performances. Experiments indicated that our proposed method achieved an accuracy of 87.92%, which is 26.1% higher than that of the traditional CNN method and 1.1% higher than that of the deep convolutional neural network ResNet50.

• Imaging Science in Dentistry
• /
• v.52 no.2
• /
• pp.123-131
• /
• 2022

Purpose: The aim of this study was to characterize the cone-beam computed tomographic (CBCT) imaging features of central giant cell granuloma (CGCG) of the jawbone. Materials and Methods: This study retrospectively reviewed 26 CBCT studies of histologically proven cases of CGCG during a period of 20 years, from 1999 to 2019. Patients' demographic data were recorded, and radiographic features were assessed (location, border, cortication, appearance of the internal structure, locularity, septation, expansion, cortical perforation, effects on surrounding tissue, whether the lesion crossed the midline, and lesion volume). Results: In this study, CGCGs were seen almost twice as often in the mandible than in the maxilla, and 64.7% of mandibular lesions involved the anterior region. Only 26.9% of lesions crossed the midline, a feature that was considered characteristic of CGCG. Furthermore, 65.4% of lesions were unilocular and 34.6% were multilocular. The correlation between a lesion's size and its locularity was statistically significant, and larger lesions showed a multilocular appearance. The mean volume of multilocular lesions was greater than that of unilocular lesions. Conclusion: CGCGs showed variable radiographic features on CBCT, and this imaging modality is highly effective at demonstrating the radiographic spectrum and lesional extent of CGCGs in the jawbone.

• The Journal of Economics, Marketing and Management
• /
• v.10 no.2
• /
• pp.1-13
• /
• 2022

Purpose: The findings are expected to be used as basic data for policy establishment for systematic support and upbringing of small and medium-sized suppliers through the current status and characteristics of the industrial structure of the MRO consumable materials industry as a whole and the market trend. Research design, data, and methodology: This survey is conducted in 2019 mainly for companies that operate consumable materials delivery business, and the survey size is about 25,000 in advance (selected) and about 2,000 in the main survey. Using cluster analysis and multidimensional scaling, we derive the visualization of the homogeneous grouping of cases and the relationship structure between them. Results: Based on the attributes of reason for not having an online trading system, it is classified into three and four clusters for industry and company size, respectively, and the feature and pattern of each individual can be are relatively evaluated and visualized. Conclusions: Small and medium-sized consumable material suppliers specialize in products rather than fierce pricing strategies or external expansion strategies and it is more effective to establish a plan to promote the growth of both large and small enterprises through cooperation with large corporations.

• Food Science and Preservation
• /
• v.31 no.2
• /
• pp.245-255
• /
• 2024

The proximate composition, quality characteristics, antioxidant activity, and sensory evaluation scores of yakgwa added with mealworm powder (MP) were examined. MP contained 5.83 wt% moisture, 55.70 wt% crude protein, 35.96 wt% crude fat, 3.70 wt% crude ash, and 2.43 wt% carbohydrate and feature total polyphenol and flavonoid contents of 406.52 mg GAE/100 g and 21.18 mg NE/100 g, respectively. The DPPH and ABTS^•+ radical scavenging activities and the reducing power of MP were determined as 90.25%, 44.06%, and 1.74, respectively. Except for moisture and carbohydrate content, the proximate composition of mealworm yakgwa (MY) increased with the amount of MP increased. The pH of the dough increased with the addition of MP, whereas the expansion degree tended to decrease. Sugar content was highest at MP contents of 0 wt% and 12 wt% (FM4 group), and hardness was lowest in the FM4 group. With the increasing MP content, the L, b values and antioxidant activity increased, whereas a value decreased. The sensory evaluation scores for the overall preference, appearance, color, and taste were lowest in the FM4 group. These results suggested that MP contents of 6-9 wt% were optimal for mealworm-based yakgwa.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.4
• /
• pp.19-29
• /
• 2024

In this paper, we examine the effectiveness of StyleGAN-generated images for data augmentation in training deep neural networks for medical image classification. We apply StyleGAN data augmentation to train VGG-16 networks for pneumonia diagnosis from chest X-ray images and focal liver lesion classification from abdominal CT images. Through quantitative and qualitative analyses, our experiments reveal that StyleGAN data augmentation expands the outer class boundaries in the feature space. Thanks to this expansion characteristics, the StyleGAN data augmentation can enhance classification performance when properly combined with real training images.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.1888-1906
• /
• 2024

Aiming at the problems that the edge of melanoma image is fuzzy, the contrast with the background is low, and the hair occlusion makes it difficult to segment accurately, this paper proposes a model MSCNet for melanoma segmentation based on U-net frame. Firstly, a multi-scale pyramid fusion module is designed to reconstruct the skip connection and transmit global information to the decoder. Secondly, the contextural information conduction module is innovatively added to the top of the encoder. The module provides different receptive fields for the segmented target by using the hole convolution with different expansion rates, so as to better fuse multi-scale contextural information. In addition, in order to suppress redundant information in the input image and pay more attention to melanoma feature information, global channel attention mechanism is introduced into the decoder. Finally, In order to solve the problem of lesion class imbalance, this paper uses a combined loss function. The algorithm of this paper is verified on ISIC 2017 and ISIC 2018 public datasets. The experimental results indicate that the proposed algorithm has better accuracy for melanoma segmentation compared with other CNN-based image segmentation algorithms.

• Spatial Information Research
• /
• v.23 no.6
• /
• pp.109-116
• /
• 2015

In this study, define the concept of spatial big data and special feature of spatial big data, examine information visualization methodology for increase the insight into the data. Also presented problems and solutions in the visualization process. Spatial big data is defined as a result of quantitative expansion from spatial information and qualitative expansion from big data. Characteristics of spatial big data id defined as 6V (Volume, Variety, Velocity, Value, Veracity, Visualization), As the utilization and service aspects of spatial big data at issue, visualization of spatial big data has received attention for provide insight into the spatial big data to improve the data value. Methods of information visualization is organized in a variety of ways through Matthias, Ben, information design textbook, etc, but visualization of the spatial big data will go through the process of organizing data in the target because of the vast amounts of raw data, need to extract information from data for want delivered to user. The extracted information is used efficient visual representation of the characteristic, The large amounts of data representing visually can not provide accurate information to user, need to data reduction methods such as filtering, sampling, data binning, clustering.

• Korean Journal of Social Welfare
• /
• v.57 no.2
• /
• pp.165-184
• /
• 2005

Japan has remained a welfare laggard among advanced industrial democracies. Therefore, the introduction of the public long-term care insurance(koteki kaigo hoken in Japanese) in April of 2000 looks very unique in terms of the Japanese social security tradition, because it can be interpreted as the expansion of social security system and the weakening of the market power over the livelihood of the ordinary people. In the era of globalization, in which even the highly developed welfare states are forced to shrink their social security systems, Japan, a welfare laggard, looks like being headed to the opposite direction. This article aims to define the character of the public long-term care insurance, and thereby, to evaluate the recent social policy of the Japanese government. This study follows the social democratic model in the study of the welfare state development, which assumes that, under the condition of a weak social democratic party and a fragmented labor movement, the introduction of the long-term care insurance is not equal to the improvement of the Japanese social security system. The main argument of this article is that the long-term care insurance, notwithstanding its appearance as an expansion of public sphere, is part of market-oriented neo-liberal social reforms, which have remained the main feature of the Japanese social policies since the mid-1970's. For this, this study will do a longitudinal analysis on the social consequences of the long-term care insurance incurred to the Japanese social security system for the long-term care, focusing on the income redistribution, the marketization of long-term care sector and the changes in the financial burden of the government, social insurers and general citizens.

• Journal of Korea Water Resources Association
• /
• v.54 no.5
• /
• pp.289-299
• /
• 2021

This study analyzes bifurcation characteristics of the Seolmacheon experimental catchment by extracting the shape variation of channel network due to variable scale of source basin or threshold area. As the area of source basin decreases, a bifurcation process of channel network occurs within the basin of interest, resulting in the elongation of channel network (increase of total channel length) as well as the expansion of channel network (increase of the source number). In the former case, the elongation of channel reaches overwhelms the generation of sources, whereas, in the latter case, the drainage path network tends to fulfill the inner space of the basin of interest reflecting the opposite trend. Therefore, scale invariance of natural channel network could be expressed to be a balanced geomorphologic feature between the elongation of channel network and the expansion of channel network due to decrease of source basin scale. The bifurcation structure of the Seolmacheon experimental catchment can be characterized by the coexistence of the elongation and scale invariance of channel network, and thus a further study is required to find out which factor is more crucial to rainfall transformation into runoff.