• Journal of information and communication convergence engineering
• /
• v.21 no.2
• /
• pp.152-158
• /
• 2023

In recent years, as computer-generated imagery has been applied to more industries, realistic facial animation is one of the important research topics. The current solution for realistic facial animation is to create realistic rendered 3D characters, but the 3D characters created by traditional methods are always different from the actual characters and require high cost in terms of staff and time. Deepfake technology can achieve the effect of realistic faces and replicate facial animation. The facial details and animations are automatically done by the computer after the AI model is trained, and the AI model can be reused, thus reducing the human and time costs of realistic face animation. In addition, this study summarizes the way human face information is captured and proposes a new workflow for video to image conversion and demonstrates that the new work scheme can obtain higher quality images and exchange effects by evaluating the quality of No Reference Image Quality Assessment.

• Smart Media Journal
• /
• v.13 no.7
• /
• pp.18-26
• /
• 2024

One of the newest trends in AI is emotion recognition utilizing keystroke dynamics, which leverages biometric data to identify users and assess emotional states. This work offers a comparison of four datasets that are frequently used to research keystroke dynamics: BB-MAS, Buffalo, Clarkson II, and CMU. The datasets contain different types of data, both behavioral and physiological biometric data that was gathered in a range of environments, from controlled labs to real work environments. Considering the benefits and drawbacks of each dataset, paying particular attention to how well it can be used for tasks like emotion recognition and behavioral analysis. Our findings demonstrate how user attributes, task circumstances, and ambient elements affect typing behavior. This comparative analysis aims to guide future research and development of applications for emotion detection and biometrics, emphasizing the importance of collecting diverse data and the possibility of integrating keystroke dynamics with other biometric measurements.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.4
• /
• pp.77-89
• /
• 2024

Knee osteoarthritis (OA) is a very common musculoskeletal disorder worldwide. The assessment of knee osteoarthritis, which requires a rapid and accurate initial diagnosis, is determined to be different depending on the currently dispersed classification system, and each classification system has different criteria. Also, because the medical staff directly sees and reads the X-ray pictures, it depends on the subjective opinion of the medical staff, and it takes time to establish an accurate diagnosis and a clear treatment plan. Therefore, in this study, we designed the stenosis length measurement algorithm and Osteophyte detection and length measurement algorithm, which are the criteria for determining the knee osteoarthritis grade, separately using CNN, which is a deep learning technique. In addition, we would like to create a grading system that integrates and complements the existing classification system and show results that match the judgments of actual medical staff. Based on publicly available OAI (Osteoarthritis Initiative) data, a total of 9,786 knee osteoarthritis data were used in this study, eventually achieving an Accuracy of 69.8% and an F1 score of 76.65%.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.23 no.7
• /
• pp.520-527
• /
• 2011

Recently, Influenza(AI, PI) patients have been increasing rapidly. But, there is a lack of isolation hospitals. In particular, according to increase the rate of patients with airborne infection, in order to prevent the spread of pathogens, design of layout plan and air conditioning system of isolation hospitals becomes more important to maintain patient's room as negative pressure. In this study, the spread of pathogens are analyzed as room differential pressure, moving time of medical staff and patients, and moving way in isolation hospitals by multizone simulation; CONTAM 2.4. Through the analysis, the ways to improve isolation hospital considered at the design step are reached to prevent the spread of pathogens effectively. Also, it verifies that HVAC system for isolation hospital is suitably designed as standard.

• The Journal of Korea Robotics Society
• /
• v.16 no.2
• /
• pp.172-178
• /
• 2021

The COVID-19 pandemic has been reshaping the world by accelerating non-contact services and technologies in various domains. Hospitals as a healthcare system lie at the center of the dramatic change because of their fundamental roles: medical diagnosis and treatments. Leading experts in health, science, and technologies have predicted that robotics and artificial intelligence (AI) can drive such a hospital transformation. Accordingly, several government-led projects have been developed and started toward smarter hospitals, where robots and AI replace or support healthcare personnel, particularly in the diagnosis and non-surgical treatment procedures. This article inspects the remaining element of healthcare services, i.e., surgical treatment, focusing on evaluating whether or not currently available laparoscopic surgical robotic systems are sufficiently preparing for the era of post-COVID-19 when contactless is the new normal. Challenges and future directions towards an effective, fully non-contact surgery are identified and summarized, including remote surgery assistance, domain-expansion of robotic surgery, and seamless integration with smart operating rooms, followed by emphasis on robot tranining for surgical staff.

• Journal of Integrative Natural Science
• /
• v.17 no.3
• /
• pp.105-112
• /
• 2024

In the present age of artificial intelligence and metaverse, research on the importance of data and the amount of data is actively being conducted. Among these data, medical data contains the most sensitive information of individuals, so research on data generation, storage, management, and disposal is urgently needed. This study analyzed the status of medical data management in the United States, Europe, and Korea, and identified and analyzed medical data management laws and implementation status through working-level staff working in medical sites. As a result of the analysis, about 70% of medical professionals were able to identify the absence of recognition and management of medical data. The survey subjects were limited to Gwangju and Jeollanam-do, and 237 medical workers were conducted. More than 54% of the awareness of medical record generation, storage, and management came out, but about 70% of the occupations except doctors, oriental doctors, and dentists did not recognize the medical record management method. As necessary for medical record management, cost and the need for professional managers were 91.4%. Through this study, it was confirmed that the expansion of legal education for medical workers, the enactment of related laws, and the need for sincere fostering of medical record managers were required.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.2 no.1
• /
• pp.143-143
• /
• 1996

Recent Class requirements and IMO recommendations concerning Hull Strength Monitoring (HSM) have prompted an increasing number of shipowner to adopt monitoring systems on bulk carriers and tanker. Such systems are designed to give warning when stress levels and the frequency and magnitude of ship motions approach levels which require corrective action. When fitted these systems provide enhanced operational safety and efficiency. This paper describes a development beyond the standard BMT HSM system through the integration of stress, motion and radar-based sea state monitoring with powerful, on-board, artificial intelligence (AI) tools. The latter utilises conceptual clustering techniques as an aid to pattern recognition in stress, fatigue. motion and sea state data clusters. This, in turn, provides additional operational guidance for ship's staff. Feedback from applications of the standard BMT HSM and extended HSM systems on board the British Steel Bulk Shipping fleet is described.

• Journal of information and communication convergence engineering
• /
• v.21 no.3
• /
• pp.216-224
• /
• 2023

Smart lighting systems have become increasingly popular in several public sectors because of trends toward urbanization and intelligent technologies. In this study, we designed and implemented a web application platform to explore and monitor data acquired from lighting devices at Thammasat University (Rangsit Campus, Thailand). The platform provides a convenient interface for administrative and operative staff to monitor, control, and collect data from sensors installed on campus in real time for creating geographically specific big data. Platform development focuses on both back- and front-end applications to allow a seamless process for recording and displaying data from interconnected devices. Responsible persons can interact with devices and acquire data effortlessly, minimizing workforce and human error. The collected data were analyzed using an exploratory data analysis process. Missing data behavior caused by system outages was also investigated.

• Journal of the Korea Society for Simulation
• /
• v.30 no.3
• /
• pp.1-9
• /
• 2021

Commander and staffs on the battlefield are aware of the situation and, based on the results, they perform military activities through their military decisions. Recently, with the development of information technology, the demand for artificial intelligence to support military decisions has increased. It is essential to identify, collect, and pre-process the data set for reinforcement learning to utilize artificial intelligence. However, data on enemies lacking in terms of accuracy, timeliness, and abundance is not suitable for use as AI learning data, so a training model is needed to collect AI learning data. In this paper, a methodology for learning artificial intelligence was presented using the constructive wargame model exercise data. First, the role and scope of artificial intelligence to support the commander and staff in the military decision-making process were specified, and to train artificial intelligence according to the role, learning data was identified in the Chang-Jo 21 model exercise data and the learning results were simulated. The simulation data set was created as imaginary sample data, and the doctrine of ROK Army, which is restricted to disclosure, was utilized with US Army's doctrine that can be collected on the Internet.

• Journal of Internet Computing and Services
• /
• v.22 no.6
• /
• pp.141-150
• /
• 2021

Based on Artificial Intelligence technology, AI-enabled warfare is expected to become the main issue in the future warfare. Natural language processing technology is a core technology of AI technology, and it can significantly contribute to reducing the information burden of underrstanidng reports, information objects and intelligences written in natural language by commanders and staff. In this paper, we propose a Language model-based Multi-source Information Integration (LAMII) framework to reduce the information overload of commanders and support rapid decision-making. The proposed LAMII framework consists of the key steps of representation learning based on language models in self-supervsied way and document integration using autoencoders. In the first step, representation learning that can identify the similar relationship between two heterogeneous sentences is performed using the self-supervised learning technique. In the second step, using the learned model, documents that implies similar contents or topics from multiple sources are found and integrated. At this time, the autoencoder is used to measure the information redundancy of the sentences in order to remove the duplicate sentences. In order to prove the superiority of this paper, we conducted comparison experiments using the language models and the benchmark sets used to evaluate their performance. As a result of the experiment, it was demonstrated that the proposed LAMII framework can effectively predict the similar relationship between heterogeneous sentence compared to other language models.