In the diagnosis of lung cancer, the tumor size is measured by the longest diameter of the tumor in the entire slice of the CT. In order to accurately estimate the size of the tumor, it is better to measure the volume, but there are some limitations in calculating the volume in the clinic. In this study, we propose an algorithm to segment lung cancer by applying a custom loss function that combines focal loss and dice loss to a U-Net model that shows high performance in segmentation problems in chest CT images. The combination of values of the various parameters in custom loss function was compared to the results of the model learned. The purposed loss function showed F1 score of 88.77%, precision of 87.31%, recall of 90.30% and average precision of 0.827 at α=0.25, γ=4, β=0.7. The performance of the proposed custom loss function showed good performance in lung cancer segmentation.

Defect region segmentation of TFT-LCD images is performed by combining defect pixels detected by a defect detection method into defect region, or by using morphological operations to segment defect region. Therefore, the result of segmentation of the defect region is highly dependent on the defect detection result. In this paper, we propose a method which segments defect regions sequentially according to the possibility of being included in defect regions in TFT-LCD images. The proposed method repeats the process of detecting a seed using the median value and the median absolute deviation of the image, and segments the defect region using the seeded region growing method. We confirmed the superiority of the proposed method to segment defect regions using pseudo-images and real TFT-LCD images.

As the usage of mobile devices extremely increases, malicious mobile apps(applications) that target mobile users are also increasing. It is challenging to detect these malicious apps using traditional malware detection techniques due to intelligence of today's attack mechanisms. Deep learning (DL) is an alternative technique of traditional signature and rule-based anomaly detection techniques and thus have actively been used in numerous recent studies on malware detection. In order to develop DL-based defense mechanisms against intelligent malicious apps, feeding recent datasets into DL models is important. In this paper, we develop a DL-based model for detecting intelligent malicious apps using KU-CISC 2018-Android, the most up-to-date dataset consisting of benign and malicious Android apps. This dataset has hardly been addressed in other studies so far. We extract OPcode sequences from the Android apps and preprocess the OPcode sequences using an N-gram model. We then feed the preprocessed data into LSTM and apply the concept of Information Gain to improve performance of detecting malicious apps. Furthermore, we evaluate our model with numerous scenarios in order to verify the model's design and performance.

The rapid growth of internet users and faster network speed are driving the new ICT services. ICT Technology has improved our way of thinking and style of life, but it has created security problems such as malware, ransomware, and so on. Therefore, we should research against the increase of malware and the emergence of malicious code. For this, it is necessary to accurately and quickly detect and classify malware family. In this paper, we analyzed and classified visualization technology, which is a preprocessing technology used for deep learning-based malware classification. The first method is to convert each byte into one pixel of the image to produce a grayscale image. The second method is to convert 2bytes of the binary to create a pair of coordinates. The third method is the method using LSH. We proposed improving the technique of using the entire existing malicious code file for visualization, extracting only the areas where important information is expected to exist and then visualizing it. As a result of experimenting in the method we proposed, it shows that selecting and visualizing important information and then classifying it, rather than containing all the information in malicious code, can produce better learning results.

PGP is an encryption software designed to provide information protection, security and authentication services for online communication systems. The characteristic of behavior done on the Internet is that you don't know the other person. It is very important to protect information from someone you cannot trust. So identification of the other person is an important task. PGP uses an digital signature algorithm to verify the identity of the other party. However, it is not accurate to check the other party's credibility. PGP increases trust as other users sign more on public keys of user. In other words, credibility is not perfect. In this paper, PGP certification system that key management in Ethereum blockchain, one of the blockchain platforms, is proposed. Key management in blockchain ensures data integrity, transparency and reliability.

Defense M&S (Modeling&Simulation) is a tool that creates a virtual battle situation similar to the real world, measuring and evaluating the effects of war or combat elements. However, it is very challenging to consider all the possible outcomes on the battlefield. To solve this problem, we propose a battlefield ontology, which conceptualizes the data of battlefield situation with tactical considerations. The proposed battlefield ontology is evaluated based on various communication posts in war game scenarios. The battlefield ontology is expected to assist the process of quick and accurate command decisions in convoluted battlefield situations.

Buildings are becoming more and more high-rise and large-scale in recent years, so in the event of a disaster such as a fire, enormous human and economic damage is expected. Therefore, management, security, and fire control are essential for large buildings in the city. Because these large buildings are very complex outside and inside, they need a three-dimensional control based on 3D modeling rather than a simple flat-oriented control. To do this, this paper designed and implemented a building control system based on 3D modeling. Specifically, we designed a 3D building / facility editing module for 3D modeling of buildings, a 3D based control module for building control, and a linkage module that connects information such as firefighting equipment, electrical equipment and IoT equipment. Based on this design, a building control system based on 3D modeling was implemented.

Recently, the earth's highest temperature is rising due to severe climate change and heat wave. In addition, due to the increase of elderly population over 65, the number of heat patients is also increasing. In particular, the elderly who live alone in poor living environments, the lower income group, and the socially disadvantaged, such as children and pregnant women, are exposed to the dangers of heat waves, so the government's practical measures are urgently needed. In this study, we will build a visualization platform for each level of heat wave and provide the necessary countermeasure solution according to the heat wave risk. "The Hazard Visualization Platform for Heatwave" provide not only simple information, but also a customized safety service for citizens to prevent heatwaves, respond to heatwaves, and utilize heat wave information.

With the development of virtual reality (VR)-related technology and the advent of the 5G era, VR-based streaming games or content have been developed and transmitted at high speed. Although VR technology is also being applied in education, health care, manufacturing, and production fields, its main application is for entertainment. VR technology has been developed based on hardware and various contents have been developed accordingly; however, the number of VR content with high entertainment value is insufficient, and there are primarily hands-on contents. In this paper, we propose a method for developing an writing tool that can enhance the productivity in the development and editing of VR content and create VR contents based on a timeline by reflecting the storytelling rather than by a simple empirical type to solve the bias in content style. The proposed VR content writing tool is expected to increase the productivity in VR content development and contribute to the creation of various styles of content. Its implementation can enable developers to create specific stories in a timeline and support several animation effects.

Tsunami occurred by a rapid change in the ocean floor is a natural disaster that causes serious damage worldwide. South Korea seems to be out of the range of this damage, but it is quite possible that South Korea will fall within the range due to the long-distance propagation features of tsunami and many earthquakes occurred in Japan. However, the analysis and preparation for tsunami have been still insufficient. In this paper, we propose a tsunami simulation model based on cellular automata for analyzing coastal inundation. The proposed model calculates the range of inundation in coastal areas by propagating the energy of tsunami using the interaction between neighboring cells. We define interaction rules and algorithms for the energy transfer and propose a software tool to effectively utilize the model. In addition, to verify and tune the simulation model, we used the actual tsunami data in 2010 at Dichato, Chile. As a case study, the proposed model was applied to analyze the coastal inundation according to tsunami height in Gwangali Beach, a famous site in Busan. It is expected that the simulation model can be a help to prepare an effective countermeasure against tsunami and be used for a virtual evacuating training.

The change in 21st century imaging media technology is changing our modern visual system. Virtual reality HMD devices, one of the core technologies of 5G, reproduce the new visual system. However, there is a lack of analysis and understanding of the visual operating system to understand the visual system of the fast-changing variety of imaging media. This study analyzed the three visual systems appearing in the recent imaging media art area and presented an engineering perspective algorithm for its procedures and methods. Through these results, we want to build algorithms that understand the visual system of virtual reality HMD devices.