Recently, many researches have been conducted to automatically recognize license plates of vehicles and use the analyzed information to manage stolen vehicles and track the vehicle. However, such a system must eventually be investigated by people through direct monitoring. Therefore, in this paper, the system of tracking a vehicle is implemented by sharing the information analyzed by the vehicle image among cameras registered in the IoT environment to minimize the human intervention. The distance between cameras is indicated by the node and the weight value of the weighted-graph, and the eigenvector centrality is used to select the camera to search. It demonstrates efficiency by comparing the time between analyzing data using weighted graph searching algorithm and analyzing all data stored in databse. Finally, the path of the vehicle is indicated on the map using parsed json data.

A practical animal face classification system that classifies animals in image and video data is considered as a pivotal topic in machine learning. In this research, we are proposing a novel method of fully connected dual Deep Convolutional Neural Network (DCNN), which extracts and analyzes image features on a large scale. With the inclusion of the state of the art Batch Normalization layer and Exponential Linear Unit (ELU) layer, our proposed DCNN has gained the capability of analyzing a large amount of dataset as well as extracting more features than before. For this research, we have built our dataset containing ten thousand animal faces of ten animal classes and a dual DCNN. The significance of our network is that it has four sets of convolutional functions that work laterally with each other. We used a relatively small amount of batch size and a large number of iteration to mitigate overfitting during the training session. We have also used image augmentation to vary the shapes of the training images for the better learning process. The results demonstrate that, with an accuracy rate of 92.0%, the proposed DCNN outruns its counterparts while causing less computing costs.

Deep learning technology is currently being used and applied in many different fields. Convolution neural network (CNN) is a method of artificial neural networks in deep learning, which is commonly used for analyzing different types of images through classification. In the conventional classification of histopathology images of prostate carcinomas, the rating of cancer is classified by human subjective observation. However, this approach has produced to some misdiagnosing of cancer grading. To solve this problem, CNN based classification method is proposed in this paper, to train the histological images and classify the prostate cancer grading into two classes of the benign and malignant. The CNN architecture used in this paper is based on the VGG models, which is specialized for image classification. However, color normalization was performed based on the contrast enhancement technique, and the normalized images were used for CNN training, to compare the classification results of both original and normalized images. In all cases, accuracy was over 90%, accuracy of the original was 96%, accuracy of other cases was higher, and loss was the lowest with 9%.

Chinese is the most spoken language in the world. However, because Chinese is a hieroglyphic language, using Chinese in a digital environment is very inconvenient. Chinese users are using Pinyin for Chinese input, but the phonetic representation of the Latin alphabet is not good. Hunminjeongeum has an excellent phonetic representation which can improve Chinese usage in digital environment. Therefore, it is possible to improve the use of Chinese by Chinese users in digital environment and to help Korean users who are learning Chinese. Therefore, this paper proposes a Chinese input method using Hunminjeongeum. In addition, we develop an input software using this input method and verify its effectiveness by evaluating usability.

In this study, presents geographic analysis of Heuksando Island We classified each area of the island according to physical attributes. Then, we derived the meaning of each area as a physical space and virtual space. In order to symbolize the events that happens around the spaces, we set directions and relations for those spaces. In this process, we figured the stages of voluntary experience that originates from the user's actions. This study proposes hierarchical categories of virtual environments from spacial reality, experience and the creation of simulacrum.

Computers are the most common tool when using the Internet and utilizing a mouse to select and execute objects. Eye tracking technology is welcomed as an alternative technology to help control computers for users who cannot use their hands due to their disabilities. However, the pointer execution method of the existing eye tracking technique causes many malfunctions. Therefore, in this paper, we developed a gaze tracking interface that combines voice commands to solve the malfunction problem when the upper limb disabled uses the existing gaze tracking technology to execute computer menus and objects. Usability verification was conducted through comparative experiments regarding the improvements of the malfunction. The upper limb disabled who are hand-impaired use eye tracking technology to move the pointer and utilize the voice commands, such as, "okay" while browsing the computer screen for instant clicks. As a result of the comparative experiments on the reduction of the malfunction of pointer execution with the existing gaze interfaces, we verified that our system, Eye-Voice, reduced the malfunction rate of pointer execution and is effective for the upper limb disabled to use.

Stress induces change to the body functions and causes chronic problems such as worsening a disease. Thus, humans want to evade anxiety and would try any means to reduce stressful situations. Generally, a person would handle their stress by either regulating their emotions or merely coping with the situation, for which the former is most widely used. Our research aims to effectively reduce stress by using the emotional response structure developed by Plutichik and the vitalization method. We extracted the relevant components of the stress-reduction method that would be applicable in any space using digital technologies such as sensors, IoT, and augmented reality. An architect or designer may incorporate these structural components into any structure to effectively reduce people's stress. The research aims to provide a new perspective of architectural space and to show applications of the stress-reducing architectural spaces, which should also fulfill the people's needs. Further research is needed to develop an automatic system to utilize spatial components more effectively.

In this study, we investigated the correlation between logotype elements and brand recognition among corporate logos using quantification methodology 2. In addition, this study wanted to find out if consumers could easily recognize the product according to the design elements of the logotype. Our study showed that feminine tendency in logotype design was associated with clothes and cosmetics and masculine design element that will make people recall the game and health products. There were clothes and cosmetics for men but feminine design factor was strongly associated with clothes and cosmetics. In other words, logotype for cosmetic and clothing needed to be feminine by using neutral and cold colors. The relationship between the logotype and related products affected the brand recognition and this result can be used as a key element of corporate marketing.

This study analyzes the current status of drone journalism in Korean broadcasting industry, with a case study of TV Chosun Company's drone use for news gathering. It analyzes TV Chosun's record of drone logs between 2014 and 2018. The log consists of date, time, news content, users, machine and on-air date. In 2014, the total of 31 cases of using drones for news gathering is identified, while in 2018, the frequency increases to 60, with a gradual, annual increase, making the total frequency of 160, during the period between 2014 and 2018. This means that the broadcasting company used the drone news gathering system every week. The analysis also reveals that the company used this drone news gathering system mostly in the metropolitan area in Korea, amounting to more than 76 per cent of its total use: 31.3 per cent in Seoul, 36.9 per cent in Kyunggi, and 8.1 percent in Incheon. The system was more frequently used in the summer and autumn than the winter and spring. Interestingly, it was first popularly used for disaster related news, but the use of drone for social and other issues is increasing every year, which may imply its diverse use in the future.

We propose a generative probabilistic model with Dirichlet prior distribution for topic modeling and text similarity analysis. It assigns a topic and calculates text correlation between documents within a corpus. It also provides posterior probabilities that are assigned to each topic of a document based on the prior distribution in the corpus. We then present a Gibbs sampling algorithm for inference about the posterior distribution and compute text correlation among 50 abstracts from the papers published by IEEE. We also conduct a supervised learning to set a benchmark that justifies the performance of the LDA (Latent Dirichlet Allocation). The experiments show that the accuracy for topic assignment to a certain document is 76% for LDA. The results for supervised learning show the accuracy of 61%, the precision of 93% and the f1-score of 96%. A discussion for experimental results indicates a thorough justification based on probabilities, distributions, evaluation metrics and correlation coefficients with respect to topic assignment.

Analyzing various works of Nam June Paik who pioneered the world of video art, we can find a number of audiovisual art pieces - in a broad sense - with the characteristics of "intermedia" that are not clearly identified as one genre. Especially, his career as a musician becomes an important clue for us to discuss the unique originality found in Paik's works. Nevertheless, examples of research that specifically explore how Paik's musicality is reflected in his artistry and could be deeply understood is still rare. This article examines Paik's audiovisual art world, and reviews how his musicality is expressed through the characteristics of media and form, as well as contributed to the ultimate technical and aesthetic realizations of his pieces from the perspective of musical synesthesia. The fact that Paik expanded the concept of music through technology, and fused different media to visualize music, is an important achievement in the context of aesthetic, synesthetic music in the field of audiovisual art.

By enabling musicians to freely control the elements involved in sound production and tone generation with a variety of timbre, synthesizers have revolutionized and permanently changed music since the 1960s. Paik-Abe Video Synthesizer, a masterpiece of video art maestro Nam June Paik, is a prominent example of re-interpretation of this new musical instrument in the realm of video and audio. This article examines Paik-Abe Video Synthesizer as an innovative instrument to play videos from the perspective of audiovisual art, and establishes its aesthetic value and significance through both artistic and technical analysis. The instrument, which embodied the concept of image sampling and real-time interactive video as an image-based multi-channel music production tool, contributed to establishing a new relationship between sound and image within the realm of audiovisual art. The fact that his video synthesizer not only adds image to sound, but also presents a complete fusion of image and sound as an image instrument with musical characteristics, becomes highly meaningful in this age of synesthesia.