Clustering methods essentially take a two-step approach; extracting feature vectors for dimensionality reduction and then employing clustering algorithm on the extracted feature vectors. However, for clustering images, the traditional clustering methods such as stacked auto-encoder based k-means are not effective since they tend to ignore the local information. In this paper, we propose a method first to effectively reduce data dimensionality using convolutional auto-encoder to capture and reflect the local information and then to accurately cluster similar data samples by using a hierarchical clustering approach. The experimental results confirm that the clustering results are improved by using the proposed model in terms of clustering accuracy and normalized mutual information.

For a reliable fingerprinting system, improving fingerprint matching accuracy is crucial. In this paper, we try to improve a binary image fingerprint matching performance by utilizing auxiliary information, power mask, which is obtained while constructing fingerprint DB. The power mask is an expected robustness of each fingerprint bit. A caveat of the power mask is the increased storage cost of the fingerprint DB. This paper mitigates the problem by reducing the size of the power mask utilizing spatial correlation of an image. Experiments on a publicly-available image dataset confirmed that the power mask is effective in improving fingerprint matching accuracy.

Recently, the increase in the elderly population due to an aging society has led to a relative increase in senile diseases such as vascular dementia or Alzheimer's disease, and the social burden for rehabilitation has increased. In addition, studies have been conducted for the risk assessment and prevention of musculoskeletal disorders. The purpose of this study is to suggest a system that can be used to help with dementia prevention training by tracking the movement of motion and virtual reality contents for the risk factors of musculoskeletal disorders of the elderly. We propose a training method for preventing dementia through musculoskeletal motion analysis algorithm and virtual reality content. Through motion recognition algorithm based on motion region design, we will track and analyze the moving radius of the target joint. The purpose of this study is to calculate and evaluate scores based on the time to accomplish the goals on virtual reality contents for the prevention of musculoskeletal disorders and the support of dementia prevention training, and the degree of difficulty, and to analyze the correlation between the results of performing K-MMSE and VR contents.

As the number of internet-connected appliances and the variety of IoT services are rapidly increasing, it is hard to protect IT assets with traditional network security techniques. Most traditional network log analysis systems use rule based mechanisms to reduce the raw logs. But using predefined rules can't detect new attack patterns. So, there is a need for a mechanism to reduce congested raw logs and detect new attack patterns. This paper suggests enterprise security management for IoT services using graph and network measures. We model an event network based on a graph of interconnected logs between network devices and IoT gateways. And we suggest a network clustering algorithm that estimates the attack probability of log clusters and detects new attack patterns.

During the 4th Industrial Revolution, service platforms utilizing diverse contents are emerging, and research on recommended systems that can be customized to users to provide quality service is being conducted. hybrid recommendation systems that provide high accuracy recommendations are being researched in various domains, and various filtering techniques, machine learning, and deep learning are being applied to recommended systems. However, in a recommended service environment where data must be analyzed and processed real time, the accuracy of the recommendation is important, but the computational speed is also very important. Due to high level of model complexity, a hybrid recommendation system or a Deep Learning-based recommendation system takes a long time to calculate. In this paper, a Cascade-hybrid recommended algorithm is proposed that can reduce the computational time while maintaining the accuracy of the recommendation. The proposed algorithm was designed to reduce the complexity of the model and minimize the computational speed while processing sequentially, rather than using existing weights or using a hybrid recommendation technique handled in parallel. Therefore, through the algorithms in this paper, contents can be analyzed and recommended effectively and real time through services such as SNS environments or shared economy platforms.

Along side with the rapid growth of local governments' advertising bills, there are few studies focused on the effectiveness of these ads. Especially one of the media being used by the local governments is the Korea Express Train (KTX), where they advertise in the train coaches' KTX video monitor. Unfortunately the ads in KTX are exposed without audio mostly. The current study, therefore, probed on the effectiveness of these ads. This study utilized transportation theory and content analysis methodology to give insight to its discourse. We established two analysis units (camera and subtitles), and then analyzed 107 local government ads. From the camera analysis, it is observed that local governments' festival and tour promotion ads more often employ dynamic angles such as drone shot and long shot. Also, from subtitles usage analysis, it is observed that many of the ads make use of large size titles and subtitles which could prevent viewers seeing visual shots. In the special case audio-less KTX ads, this study recommends emphasis on subtitles which will enhance the ad effectiveness of the ad messages.

The work that detection and elimination to disease and pest have important in agricultural field because it is directly related to the production of the crops, early detection and treatment of the disease insects. Image classification technology based on traditional computer vision have not been applied in part such as disease and pest because that is falling a accuracy to extraction and classification of feature. In this paper, we proposed model that determine to disease and pest of shiitake based on deep-CNN which have high image recognition performance than exist study. For performance evaluation, we compare evaluation with Alexnet to a proposed deep learning evaluation model. We were compared a proposed model with test data and extend test data. The result, we were confirmed that the proposed model had high performance than Alexnet which approximately 48% and 72% such as test data, approximately 62% and 81% such as extend test data.

5G-based HMD technology grew rapidly in the context of the environment change of convergence technology media and mobile networks in the fourth industrial era. It has also grown into a core technology that transforms our digital visual system. However, there is no research or system that can understand and verify radical visual system changes. Therefore, it is necessary to have an engineering understanding and verification of the diffusion of HMD media imaging devices. Beyond the distinction between virtual and real, research is urgently needed on the new three-dimensional interface of the 21st century through viewer participation. For this reason, research on the algorithm structure of interactive video media using L-System is an essential process and will be a guide to understanding the virtual reality interactive environment.

This paper analyzed the characteristics of Motion Poster (Moster) and discussed the visual expression methods. To this end, the existing literature on motion posters was organized. The visual representation of motion posters was analyzed by dividing into 'Main Visual', 'Mode of Movement', 'Playtime' and 'Sound'. The analysis results were as follows. As motion posters are kind of movie posters, they are made from the original movie poster images, characters, or scenes of the movie. Graphical representations used either photo-realism or computer realism. The movement methods are 'simple movement of visual elements(movement, gesture and rotation, appear or disappear)+fixed camera movement' or' camera movement (zoom in/out, rotate, move) + fixed visual element movement'. Playback time ranged from about 10 seconds to over 1 minute of video, and the longer the video, the higher the probability of including sound.

In November 2018, virtual pop band K/DA, with the use of holograms and actual K-pop girl group members, performed its debut album titled "POP/STARS" at the opening ceremony of the League of Legends S8 final, hosted by Riot Games. The fan culture that exists for real singers adapts itself to virtual bands, and K/DA, consisting of virtual characters, encouraging the production of user created content (UCC). However, this form of UCC is different from the most common one, meaning that this type of band generates another way of consuming content. Therefore, this study examines how K/DA's digital characters are transformed and reproduced by UCC and how the original producers' content differs from them. Firstly, the development of this study considers the open characteristics of UCC, such as user type, created motivation, created process, content type and sharing method. In the second part, the virtual idol Hatsune Miku and virtual band Pentakill will be analysed to understand UCC. Thirdly, K/DA will be analyzed as a case study based on three factors: created motivation, content type and sharing method. In this manner, this study aims to explain how UCC for virtual bands reproduce and consume original content and expand their commercial value.

This paper analyzes the design and usability of maternal notebook mobile application and suggests the improvement direction of the application. The researcher compared and analyzed the functions of maternal notebook applications, conducted user interviews and expert evaluations. The conclusions of this study are the use of appropriate information volume, proportional screen division focusing on main functions, the use of GNB format of main menus, the prohibition of double menu configuration, the use of color consistent with the image of the service, the use of few font sizes, the use of appropriate colors in typography, the use of rich icons with uniform design, card format, list format, but also timeline and infographic forms that make rich user interface design. Maternal notebook application research is expected to be an important reference for research on similar mobile applications with complex functions such as information provision, user history, and community, along with improved research in healthcare design.

Korea, as a leader of Internet and game sector in IT industry, has been playing an important role in increasing its industrial development. This country has won the first place in wireless broadband usage and contributed to Internet game industry development. This means that Korean use smartphones most. It is juveniles that use Internet and smartphones most among Korean who use teenage., the number of the teenagers who overuse smartphones or Internet has surpassed 200,000. The number of the adolescents who spend more time using smartphone and Internet is about 180,000 and the number of the teens who are over-dependent to smartphone having trouble living their lives is over 22,000. The SNS usage rate of the contents that teens are most likely to use has accounted for over 80 percent. Among teens, SNS is being considered as a major means that builds relationship due to smartphone technology and the prevalence of smartphones. However, the use of SNS among youths has two sides; one is positive, the other negative. Not only does SNS have a positive function that it keeps relationship but it also has a negative function that it can lead to smartphone addiction.

This study covers exploration of seabed around Heuksando Island using hover drones. To do so, we inspected the terrain of the island and set autonomous flight waypoints on each area of the island's shores. Next, we designated seabed scan radius for drones. Then the drones fitted with laser sensor hover autonomously on their assigned area and acquire seabed data. Finally, we match the seabed data on all areas according to GPS. Our final goal is to make immersive VR maritime cultural map based on 『Jasan Urbo』.

In modern society, dementia patients are increasing due to busy daily life. Due to the nature of dementia, family members are having a hard time with their caring activities. Dementia diseases reduce the quality of life not only of the patient, but also of the family, and nursing activities lead to social problems such as unemployment or frequent turnover. This study aims to reduce the difficulty and stress of the nursing process by supporting daily life of dementia patients and nursing activities through smart care platform. Ultimately, we will reduce the cost of treatment for people with dementia and delay the worsening of symptoms through a systematic care program for people with dementia. The smart dementia care platform features smart technology to help the dementia patients' daily lives and support their caregivers.