• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.47-49
• /
• 2022

Robot navigation has seen a major improvement since the the rediscovery of the potential of Artificial Intelligence (AI) and the attention it has garnered in research circles. A notable achievement in the area was Deep Learning (DL) application in computer vision with outstanding daily life applications such as face-recognition, object detection, and more. However, robotics in general still depend on human inputs in certain areas such as localization, navigation, etc. In this paper, we propose a study case of robot navigation based on deep reinforcement technology. We look into the benefits of switching from traditional ROS-based navigation algorithms towards machine learning approaches and methods. We describe the state-of-the-art technology by introducing the concepts of Reinforcement Learning (RL), Deep Learning (DL) and DRL before before focusing on visual navigation based on DRL. The case study preludes further real life deployment in which mobile navigational agent learns to navigate unbeknownst areas.

• Annual Conference of KIPS
• /
• 2021.11a
• /
• pp.209-212
• /
• 2021

현재 IT 보안 관제 시스템을 구축하여 사용하고 있는 기업들은 여러 보안 솔루션을 도입하고 있어 각 솔루션에 따라 서로 다른 IT 이상징후 탐지 모델을 필요로 하고 있다. 이에 따라 솔루션별로 상이한 모델이 필요하며, 유지보수에 어려움이 대두되었다. 이러한 보안 관제 시장의 문제를 해결하기 위해 요구된 것이 이기종 보안 솔루션의 공통 정보 모델로의 표준화 및 탐지 모델 체계화이다. 현재 JCIM은 보안 관제 시장에서 데이터를 공통 정보 모델로 표준화하고, 선택한 솔루션의 시나리오를 보여주며 즉시 탐지까지 가능한 제품을 구현하였다. 이를 통해 AI 기반의 이상 탐지 시나리오를 구현할 수 있는 인력을 양성하고, 이를 기반으로 다양한 고객(산업군)사에 적응하는 것을 기대한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.45-46
• /
• 2023

In order to improve and promote immersive learning experiences for English as a Second Language (ESL) students, the deployment of a YOLOv5 model for object identification in videos is proposed. The procedure includes collecting annotated datasets, preparing the data, and then fine-tuning a model using the YOLOv5 framework. The study's major objective is to integrate a well-trained model into ESL instruction in order to analyze the effectiveness of AI application in the field.

• Annual Conference of KIPS
• /
• 2023.05a
• /
• pp.2-4
• /
• 2023

Sequence data plays an important role in the field of intelligence, especially for industrial control, traffic control and other aspects. Finding abnormal parts in sequence data has long been an application field of AI technology. In this paper, we propose an anomaly detection method for sequence data using a diffusion model. The diffusion model has two major advantages: interpretability derived from rigorous mathematical derivation and unrestricted selection of backbone models. This method uses the diffusion model to predict and reconstruct the sequence data, and then detects the abnormal part by comparing with the real data. This paper successfully verifies the feasibility of the diffusion model in the field of anomaly detection. We use the combination of MLP and diffusion model to generate data and compare the generated data with real data to detect anomalous points.

• Electronics and Telecommunications Trends
• /
• v.38 no.6
• /
• pp.95-106
• /
• 2023

As artificial intelligence has become commonplace in various fields, the transparency of AI in its development and implementation has become an important issue. In safety-critical areas, the eXplainable and/or understandable of artificial intelligence is being actively studied. On the other hand, machine learning have been applied to the intelligence of self-organizing network (SON), but transparency in this application has been neglected, despite the critical decision-makings in the operation of mobile communication systems. We describes concepts of eXplainable machine learning (ML), along with research trends, major issues, and research directions. After summarizing the ML research on SON, research directions are analyzed for explainable ML required in intelligent SON of beyond 5G and 6G communication.

• International journal of advanced smart convergence
• /
• v.13 no.2
• /
• pp.229-234
• /
• 2024

A smart factory is defined as a cutting-edge, intelligent factory that integrates all production processes from product planning to sales with information and communication technology. Through these factories, each company produces customized products with minimal cost and time. The smart factory promotion project in Korea has produced positive results even in difficult environments such as the COVID-19 situation. Through the transition to a smart manufacturing production system, the competitiveness of small and medium-sized businesses has been greatly strengthened, including increased productivity and reduced costs. This study was based on surveyed data conducted by organizations related to smart factory promotion in 2020. Significant contents and major characteristics that emerged from the surveyed data were inferred and described. Since the meaningful contents reflect the reality of the company, more efficient promotion of smart factories will be possible in the future.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.20 no.1
• /
• pp.31-45
• /
• 2024

The purpose of this study is to explain employment factors in the software field. For it, the Graduates Occupational Mobility Survey by the Korea employment information service is used. This paper proposes employment models in the software field using machine learning. Then, it explains employment factors of the models using explainable artificial intelligence. The models focus on both university graduates and vocational college graduates. Our works explain and interpret both black box model and glass box model. The SHAP and EBM explanation are used to interpret black box model and glass box model, respectively. The results describes that positive employment impact factors are major, vocational education and training, employment preparation setting semester, and intern experience in the employment models. This study provides a job preparation guide to universitiy and vocational college students that want to work in software field.

• Journal of Information Technology Services
• /
• v.23 no.4
• /
• pp.35-44
• /
• 2024

This study aims to provide suggestions for a paradigm shift in the Korean government platform in the era of virtual society. We have examined examples of digital governance construction implemented in major advanced countries and derived 13 tasks in four areas for the construction of digital platform governance in Korea. In other words, the Korean government must 1) be a government that runs national affairs based on AI and data, 2) a government that does a good job through digital transformation, 3) a government that provides preemptive customized services, and 4) a government that aims for a convenient and safe digital inclusive society. We have proposed 13 specific detailed tasks and key promotion plans for paradigm shift, which we hope will help the Korean government to quickly establish a digital platform governance for public-private cooperation.

• The Journal of the Korea Contents Association
• /
• v.20 no.4
• /
• pp.86-98
• /
• 2020

The artificial intelligence (AI) is a technology that will lead the future connective and intelligent era by combining with almost all industries in manufacturing and service industry. Although Korea is one of the world's leading artificial intelligence group with the United States, Japan, and Germany, but its competitiveness in terms of artificial intelligence patent is relatively low compared to others. Therefore, it is necessary to carry out quantitative analysis of artificial intelligence patents in various aspects in order to examine national competitiveness, major industries and future development directions in artificial intelligence technology. In this study, we use the IPC technology classification code to estimate the overall life cycle and the speed of development of the artificial intelligence technology. We collected patents related to artificial intelligence from 2008 to 2018, and analyze patent trends through one-dimensional statistical analysis, two-dimensional statistical analysis and network analysis. We expect that the technological trends of the artificial intelligence industry discovered from this study will be exploited to the strategies of the artificial intelligence technology and the policy making of the government.

• Journal of Embryo Transfer
• /
• v.26 no.2
• /
• pp.105-109
• /
• 2011

Ovulation synchronization (ovsynch) has proved to increase the number of insemination in cattle by overcoming the problems of heat detection. The aim of this study was to do ovsynch in water buffaloes where heat detection is a major reproductive problem and to determine the conception rates after timed artificial insemination (TAI). Twenty cyclic buffaloes at ${\geq}$ 60 days postpartum were selected by examining 24 unobserved estrus buffaloes based on milk progesterone assay (progesterone concentration ${\geq}$ 1.0 ng/ml) from the Mymensingh district of Bangladesh. Ovsynch treatment regimen was started irrespective of the stage of estrous cycle. Gonadorelin (500 ${\mu}g$) was injected intramuscularly at Day 0 followed by Alfaprostol (8 mg) at Day 7. A second injection of Gonadorelin was given at Day 9 and TAI was done with frozen semen from Mediterranean buffalo bulls at 16~20 hours of the second Gonadorelin injection. Milk progesterone ELISA at Day 10~12 post AI confirmed ovulation in 16 out of 20 (80%) buffaloes (progesterone concentration ${\geq}$ 1.0 ng/ml). High progesterone concentration (${\geq}$ 1.0 ng/ml) at Day 10~12 and Day 22~24 of AI showed pregnancy in six out of 20 (30%) buffaloes. Pregnancy was further confirmed by ultrasonography at Day 40 in these six buffaloes. In conclusion, ovsynch followed by TAI could be applied in cyclic buffaloes for overcoming the estrus detection problems; however, more studies are needed to increase the conception rate.