• Smart Media Journal
• /
• v.10 no.2
• /
• pp.48-54
• /
• 2021

Sepsis is one of the leading causes of mortality globally, and it costs billions of dollars annually. However, treating septic patients is currently highly challenging, and more research is needed into a general treatment method for sepsis. Therefore, in this work, we propose a reinforcement learning method for learning the optimal treatment strategies for septic patients. We model the patient physiological time series data as the input for a deep recurrent Q-network that learns reliable treatment policies. We evaluate our model using an off-policy evaluation method, and the experimental results indicate that it outperforms the physicians' policy, reducing patient mortality up to 3.04%. Thus, our model can be used as a tool to reduce patient mortality by supporting clinicians in making dynamic decisions.

• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1049-1058
• /
• 2022

HAR(Human Action Recognition) such as anomaly and object detection has become a trend in research field(s) that focus on utilizing Artificial Intelligence (AI) methods to analyze patterns of human action in crime-ridden area(s), media services, and industrial facilities. Especially, in real-time system(s) using video streaming data, HAR has become a more important AI-based research field in application development and many different research fields using HAR have currently been developed and improved. In this paper, we propose and analyze a deep-learning-based HAR that provides more efficient scheme(s) using an intelligent AI models, such system can be applied to media services using RGB video streaming data usage without feature extraction pre-processing. For the method, we adopt Slowfast based on the Deep Neural Network(DNN) model under an open dataset(HMDB-51 or UCF101) for improvement in prediction accuracy.

• Smart Media Journal
• /
• v.12 no.4
• /
• pp.41-46
• /
• 2023

UWB is a type of technology used for indoor positioning and is characterized by higher accuracy than RSSI-based schemes. Mobile equipment operating based on ROS can monitor the environment around the equipment using lidar and cameras. When applying the loop closing technique to determine the starting position in this monitoring process, the existing method has a problem of low accuracy because the closing operation occurs only when there are feature points on the image. In this paper, to solve this problem, we designed a system that increases the accuracy of loop closing work by providing location information by mounting a UWB tag on a mobile device. In addition, the accuracy of the UWB-based indoor positioning system was evaluated through experiments, and it was verified that it could be used for loop closing techniques.

• Smart Media Journal
• /
• v.12 no.9
• /
• pp.159-170
• /
• 2023

It takes a lot of time and manpower to search for the missing. As part of the solution, a missing person search AI system was implemented using a YOLO-based model. In order to train object detection models, the model was learned by collecting recognition images (road fixation) of drone mobile objects from AI-Hub. Additional mountainous terrain datasets were also collected to evaluate performance in training datasets and other environments. In order to optimize the missing person search AI system, performance evaluation based on model size and hyperparameters and additional performance evaluation for concerns about overfitting were conducted. As a result of performance evaluation, it was confirmed that the YOLOv5-L model showed excellent performance, and the performance of the model was further improved by applying data augmentation techniques. Since then, the web service has been applied with the YOLOv5-L model that applies data augmentation techniques to increase the efficiency of searching for missing people.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.676-691
• /
• 2022

An increasing number of companies in the fashion industry are using AI curation services. The purpose of this study is to investigate perceptions of and intentions to use AI fashion curation services among customers by using text mining. To accomplish this goal, we collected a total of 34,190 online posts from two Korean portals, Naver and Daum. We conducted frequency analysis to identify the most frequently mentioned keywords using Textom. The analysis extracted "various," "good," "many," "right," and "new" at the highest frequency, indicating that consumers had positive perceptions of AI fashion curation services. In addition, we conducted a semantic network analysis with the top-50 most frequently used keywords, classifying customers' perceptions of AI fashion curation services into three groups: shopping, platform, and business profit. We also identified the factors that boost continuous use intentions: usability, usefulness, reliability, enjoyment, and personalization. We conclude this paper by discussing the theoretical and practical implications of these findings.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.32-33
• /
• 2020

쿠버네티스는 컨테이너를 사용하는 분산 클라우드에서 컨테이너화를 쉽고 빠르게 배포/확장할 수 있어 유용한 플랫폼이다. 쿠버네티스에서 다양한 애플리케이션들이 동작하며 서비스를 제공하고 있다. 서비스의 원활한 제공을 위하여 고객과 서비스수준에 대한 약속인 SLA와 SLA의 기준이 되는 SLO에 필요한 지표를 확인하는 것은 중요하다. 본 논문은 쿠버네티스 클러스터로 구성된 분산 클라우드 DECENTER를 소개하고 DECENTER에서 분산 AI 애플리케이션의 효율적인 SLO를 지원하는 모니터링 시스템을 제안한다.

• Korean Journal of Childcare and Education
• /
• v.19 no.2
• /
• pp.43-59
• /
• 2023

Objective: This study investigated the differences in preschool children's perceptions of artificial intelligence (AI) and their distribution by latent profiles according to their experience with AI robots in daycare centers. Methods: The participants included 119 five-year-old children, 52 of whom had experience with AI robots in daycare centers and 67 of whom did not. Children's perceptions of AI were measured using the Godspeed scale from Bartneck et al.(2009). Data were analyzed using a t-test, latent profile analysis, and chi-square test. Results: The results showed that compared to the inexperienced group, the experienced group reported lower levels of animacy and perceived intelligence of AI robots, indicating higher levels of AI knowledge and understanding. In addition, the experienced group had a higher probability of belonging to the 'machine recognition' type than 'organism recognition' type, although the difference was not statistically significant. Conclusion/Implications: The findings suggest that experience with AI robots in daycare centers can improve children's AI knowledge and understanding. To further enhance this effect, it is necessary to increase the number of robots put into classrooms, and to consider various teaching media that reflect children's preferences.

• Smart Media Journal
• /
• v.10 no.2
• /
• pp.22-29
• /
• 2021

In the past decade, deep learning has been applied to various medical image analysis tasks. Skeletal bone age estimation is clinically important as it can help prevent age-related illness and pave the way for new anti-aging therapies. Recent research has applied deep learning techniques to the task of bone age assessment and achieved positive results. In this paper, we propose a bone age prediction method using a deep convolutional neural network. Specifically, we first train a classification model that automatically localizes the most discriminative region of an image and crops it from the original image. The regions of interest are then used as input for a regression model to estimate the age of the patient. The experiments are conducted on a whole-body scintigraphy dataset that was collected by Chonnam National University Hwasun Hospital. The experimental results illustrate the potential of our proposed method, which has a mean absolute error of 3.35 years. Our proposed framework can be used as a robust supporting tool for clinicians to prevent age-related diseases.

• Smart Media Journal
• /
• v.11 no.11
• /
• pp.32-39
• /
• 2022

As IoT applications that provide AI services increase, various hardware and software that support autonomous learning and inference are being developed. However, as the characteristics and constraints of each hardware increase difficulties in developing IoT applications, the development of an integrated platform is required. In this paper, we propose a tool for automatically generating components based on artificial neural networks and spiking neural networks as well as IoT technologies to be compatible with open platforms. The proposed component automatic generation tool supports the creation of components considering the characteristics of various hardware devices through the virtual component layer of IoT and AI and enables automatic application to open platforms.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.1242-1244
• /
• 2021

한국교통안전공단이 발표한 자료에 따르면 교통사고로 사망한 원인의 70%가 졸음운전이다. 최근에는 졸음운전을 예방하기 위해 눈 깜박임 인식 등의 운전자의 생체 데이터를 활용한 방법들이 대두되고 있다. 특히 운전자의 졸음운전 판단 기술로 뇌파를 이용하는 연구가 활발히 진행되고 있다. 본 논문에서는 뇌파를 사용하여 효과적으로 졸음 상태를 판단할 수 있는 딥러닝 알고리즘을 제안한다. 졸음 상태인 경우, 아닌 경우인 2가지의 운전자 상태를 85%의 정확도로 판단한다. 또한 제안한 알고리즘을 활용해 졸음운전 감지 시스템과 더불어 졸음운전 예방 시스템을 제안하고자 한다.