• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.12
• /
• pp.3274-3292
• /
• 2013

Unsupervised methods for image segmentation are recently drawing attention because most images do not have labels or tags. A topic model is such an unsupervised probabilistic method that captures latent aspects of data, where each latent aspect, or a topic, is associated with one homogeneous region. The results of topic models, however, usually have noises, which decreases the overall segmentation performance. In this paper, to improve the performance of image segmentation using topic models, we propose two topic masks applicable to topic assignments of homogeneous regions obtained from topic models. The topic masks capture the noises among the assigned topic assignments or topic labels, and remove the noises by replacements, just like image masks for pixels. However, as the nature of topic assignments is different from image pixels, the topic masks have properties that are different from the existing image masks for pixels. There are two contributions of this paper. First, the topic masks can be used to reduce the noises of topic assignments obtained from topic models for image segmentation tasks. Second, we test the effectiveness of the topic masks by applying them to segmented images obtained from the Latent Dirichlet Allocation model and the Spatial Latent Dirichlet Allocation model upon the MSRC image dataset. The empirical results show that one of the masks successfully reduces the topic noises.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.5
• /
• pp.731-740
• /
• 2021

This study applied LDA topic modeling analysis to collect and analyze news media big data related to face masks in the three waves of the COVID-19 pandemic in Korea. The results empirically show that media reports focused on mask production and distribution policies in the first wave and the mandatory mask wearing in the second wave. In contrast, more reports on trivial, gossipy events consist of the media coverage in the second and third waves. The findings imply that Korea's governmental interventions to address the shortage of face masks and to regulate mask wearing were successful relatively in a short time. In contrast, the study also reports that there may be relative less number of science-based news reports like the ones on the effectiveness of face masks or different levels of filter types. This study exemplifies how a big data analysis can be applied to evaluate and enhance public health communication.

• The Journal of the Korea Contents Association
• /
• v.20 no.6
• /
• pp.460-469
• /
• 2020

This study analyzes online news articles and cafe articles on the '5-day Rotation Mask Distribution System', which is emerging as a recent issue due to the COVID-19 incident, to identify the mass media and social media agendas containing media and public reactions. This study figured out the difference between mass media and social media. For analysis, we collected 2,096 full text articles from Naver and 1,840 posts from Naver Cafe, and conducted word frequency analysis, word cloud, and LDA topic modeling analysis through data preprocessing and refinement. As a result of analysis, social media showed real-life topics such as 'family members' purchase', 'the postponement of school opening', ' mask usage', and 'mask purchase', reflecting the characteristics of personal media. Social media was found to play a role of exchanging personal opinions, emotions, and information rather than delivering information. With the application of the research method applied to this study, social issues can be publicized through various media analysis and used as a reference in the process of establishing a policy agenda that evolves into a government agenda.

• Journal of Magnetics
• /
• v.12 no.1
• /
• pp.12-16
• /
• 2007

Magnetic excitation and reversal by a spin polarized current via spin transfer have been a central research topic in spintronics due to its application potential. Special techniques are required to fabricate nano-scale magnetic layers in which the effect can be observed and studied. This work discusses the possibility of using electron-beam resists, the nano-scale patterning media, as ion milling mask in a subtractive fabrication method. The possibility is demonstrated by two resists, one positive tone, the ZEP 520A, and one negative tone, the ma-N2403. The advantage and the key points for success of this process will be also addressed.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.33 no.4
• /
• pp.395-402
• /
• 2023

Objectives: Microbial contamination of face masks used by healthcare professionals can vary depending on the degree of exposure to bioaerosols in various healthcare environments. However, research on this topic is limited. Therefore, we analyzed microbial contamination of N95 respirators used in hospital offices, wards, and outpatient settings. Methods: Samples isolated from N95 respirators worn for 2, 4, and 6 hours were incubated at a temperature of 35-37℃ or 25-28℃ for 24 hours or for 3-7 days, and colony-forming units were counted in chocolate agar, tryptic soy agar, and Sabouraud dextrose agar plates. Total indoor airborne bacteria were also measured in the healthcare environments. Finally, microbial species were identified using Gram staining with a microscopic speculum. Results: The three types of environments did not deviate from the maintenance of standard indoor air quality. There was no difference between the microbial species identified in the healthcare environment and mask contamination. However, the number of bacteria in the masks worn in each environment differed, and the degree of contamination increased with mask-wearing time (p<0.05). Conclusions: Therefore, care must be taken to avoid recontamination of masks due to improper use and exposure to biological hazards in healthcare environments. In conclusion, scientific evidence is necessary for safe mask-wearing times. Based on the results of this study, we hope to conduct further research to establish guidelines for the safe use of face masks during respiratory disease epidemics.

• Journal of the Korean Society of Industry Convergence
• /
• v.23 no.4_2
• /
• pp.693-699
• /
• 2020

355nm UV pulse laser is irradiated on the surface of polyimide (PI) by LDW (Laser Direct Writing) method to produce a high sensitivity flexible humidity sensor using a simple one-step process. The LDW method continuously investigates 2-D CAD data using a galvano scanner and an F-lens. This method is non-contact, so it minimizes physical strain on the PI. Laser-induced graphene (LIG) produced by lasers has a high surface area due to its high flexibility and numerous pores and oxidizers compared to conductors. For this reason, it is highly useful as a flexible humidity sensor. The humidity sensor produced in this study was attached to the inside of a mask filter, which has become a hot topic recently, and its applicability was confirmed.The measurement of humidity measured the sensitivity, reactivity, stability and recovery behavior of the sensor by measuring changes in capacitance and resistance.

• Journal of Broadcast Engineering
• /
• v.27 no.5
• /
• pp.619-628
• /
• 2022

Although face recognition and face generation have been growing in popularity, the privacy issues of using facial images in the wild have been a concurrent topic. In this paper, we propose a face editing network that can reduce privacy issues by generating face images with various properties from a small number of real face images and facial mask information. Unlike the existing methods of learning face attributes using a lot of real face images, the proposed method generates new facial images using a facial segmentation mask and texture images from five parts as styles. The images are then trained with our network to learn the styles and locations of each reference image. Once the proposed framework is trained, we can generate various face images using only a small number of real face images and segmentation information. In our extensive experiments, we show that the proposed method can not only generate new faces, but also localize facial attribute editing, despite using very few real face images.

• Journal of information and communication convergence engineering
• /
• v.19 no.1
• /
• pp.54-60
• /
• 2021

Various digital devices were supplied throughout the Fourth Industrial Revolution. Accordingly, the importance of data processing has increased. Data processing significantly affects equipment reliability. Thus, the importance of data processing has increased, and various studies have been conducted on this topic. This study proposes a modified Gaussian filter algorithm based on a fuzzy membership function. The proposed algorithm calculates the Gaussian filter weight considering the standard deviation of the filtering mask and computes an estimate according to the fuzzy membership function. The final output is calculated by adding or subtracting the Gaussian filter output and estimate. To evaluate the proposed algorithm, simulations were conducted using existing additive white Gaussian noise removal algorithms. The proposed algorithm was then analyzed by comparing the peak signal-to-noise ratio and differential image. The simulation results show that the proposed algorithm has superior noise reduction performance and improved performance compared to the existing method.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.4
• /
• pp.113-119
• /
• 2023

Despite the lifting of the mandatory wearing of masks, which was the main tool of the COVID-19 quarantine policy, we paid attention to the fact that some people are still wearing masks, and we wanted to clarify why people do not take off their masks. Through a survey in this regard, we were able to ascertain why some people continue to wear masks in a broader context. In this article, we directly and indirectly confirm the hidden side of citizens' continued wearing of masks by analyzing how the lifting of the mask-wearing obligation was reported in media articles that have a significant impact on citizens' behavior and attitude. Through this, it was confirmed that citizens continue to wear masks to protect themselves in an uncertain situation where the COVID-19 endemic has not been declared, despite the quarantine authorities' announcement of lifting the mandatory wearing. In a situation where crises such as COVID-19 are expected to repeat frequently in the future, it was concluded that it is important to build trust in the quarantine authorities.

• Korean Journal of Remote Sensing
• /
• v.37 no.1
• /
• pp.111-122
• /
• 2021

Building footprint extraction is an active topic in the domain of remote sensing, since buildings are a fundamental unit of urban areas. Deep convolutional neural networks successfully perform footprint extraction from optical satellite images. However, semantic segmentation produces coarse results in the output, such as blurred and rounded boundaries, which are caused by the use of convolutional layers with large receptive fields and pooling layers. The objective of this study is to generate visually enhanced building objects by directly extracting the vertices of individual buildings by combining instance segmentation and keypoint detection. The target keypoints in building extraction are defined as points of interest based on the local image gradient direction, that is, the vertices of a building polygon. The proposed framework follows a two-stage, top-down approach that is divided into object detection and keypoint estimation. Keypoints between instances are distinguished by merging the rough segmentation masks and the local features of regions of interest. A building polygon is created by grouping the predicted keypoints through a simple geometric method. Our model achieved an F1-score of 0.650 with an mIoU of 62.6 for building footprint extraction using the OpenCitesAI dataset. The results demonstrated that the proposed framework using keypoint estimation exhibited better segmentation performance when compared with Mask R-CNN in terms of both qualitative and quantitative results.