• Journal of Korean society of Dental Hygiene
• /
• v.21 no.2
• /
• pp.119-128
• /
• 2021

Objectives: The aim of this study was to investigate the effect of breastfeeding on the occurrence of early childhood caries in Korean infants and toddlers. Methods: Data on oral examinations of infants and toddlers of the National Health Insurance Service were analyzed. The study subjects were children who participated in both the first, second, and third oral examinations and the first general health examination in 2008-2017 (n=142,185). Based on the responses to the questionnaire, the subjects were classified into breastfeeding, formula feeding, and mixed feeding groups. The participants were monitored for the development of early childhood caries in three sequential oral examinations. Results: Based on the oral examination results conducted at 54-65 months old, the decayed-filled teeth index of the breastfeeding group was the highest (2.03±3.08), followed by the mixed (1.96±3.03) and the formula feeding groups (1.82±2.91). The Cox proportional hazard regression model including all the variables showed that the risk of developing dental caries was significantly lower in the formula (hazard ratio [HR], 0.85) and mixed feeding groups (HR, 0.91) than in the breastfeeding group. Conclusions: Breastfeeding children have a higher risk of early childhood caries; therefore, oral hygiene education and regular dental check-ups are necessary.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3889-3903
• /
• 2022

To address the problem of low detection accuracy due to training noise caused by mislabeling when Tri-training for network intrusion detection (NID), we propose a Tri-training algorithm based on cross entropy and K-nearest neighbors (TCK) for network intrusion detection. The proposed algorithm uses cross-entropy to replace the classification error rate to better identify the difference between the practical and predicted distributions of the model and reduce the prediction bias of mislabeled data to unlabeled data; K-nearest neighbors are used to remove the mislabeled data and reduce the number of mislabeled data. In order to verify the effectiveness of the algorithm proposed in this paper, experiments were conducted on 12 UCI datasets and NSL-KDD network intrusion datasets, and four indexes including accuracy, recall, F-measure and precision were used for comparison. The experimental results revealed that the TCK has superior performance than the conventional Tri-training algorithms and the Tri-training algorithms using only cross-entropy or K-nearest neighbor strategy.

• International Journal of Computer Science & Network Security
• /
• v.23 no.9
• /
• pp.65-70
• /
• 2023

The "information roadway" will give us an impact of new PC based assignments and administrations, yet the unusualness of this new condition will ask for another style of human-PC association, where the PC transforms into a sharp, dynamic and customized partner. Interface administrators are PC programs that use Artificial Intelligence frameworks to give dynamic help to a customer with PC based errands. Operators drastically change the present client encounter, through the similitude that a specialist can go about as an individual collaborator. The operator procures its capability by gaining from the client and from specialists helping different clients. A couple of model administrators have been gathered using this methodology, including authorities that give customized help with meeting planning, electronic mail taking care of, Smart Personal Assistant and choice of diversion. Operators help clients in a scope of various ways: they perform assignments for the client's sake; they can prepare or educate the client, they enable diverse clients to work together and they screen occasions and methods.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.43-46
• /
• 2022

The optimal operation of the water purification plant can be carried out only when the required flow rate is supplied in a timely manner using the minimum electrical energy by accurately predicting the pattern and amount of tap water used in the consumer. In order to ensure the stability of tap water production and supply, a system that can be pre-verified before applying AI-based composite sensors to the water purification plant was established to derive complementary matters through the pre-verification model for each composite sensor and improve the quality and operation stability of the composite sensor data.

• Journal of the Korean Society of Visualization
• /
• v.21 no.1
• /
• pp.18-25
• /
• 2023

In these days, high dimensional data prediction technology based on neural network shows compelling results in many different kind of field including engineering. Especially, a lot of variants of convolution neural network are widely utilized to develop pixel level prediction model for high dimensional data such as picture, or physical field value from the sensors. In this study, velocity vector field of ideal flow on ship surface is estimated on pixel level by Unet. First, potential flow analysis was conducted for the set of hull form data which are generated by hull form transformation method. Thereafter, four different neural network with a U-shape structure were conFig.d to train velocity vectors at the node position of pre-processed hull form data. As a result, for the test hull forms, it was confirmed that the network with short skip-connection gives the most accurate prediction results of streamlines and velocity magnitude. And the results also have a good agreement with potential flow analysis results. However, in some cases which don't have nothing in common with training data in terms of speed or shape, the network has relatively high error at the region of large curvature.

• Journal of Information Technology Applications and Management
• /
• v.30 no.6
• /
• pp.1-15
• /
• 2023

With the advent of the Fourth Industrial Revolution, propelled by digital technology, we are transitioning into an era of hyperconnectivity, where everything and objects are becoming interconnected. A smart supply chain refers to a supply chain system where various sensors and RFID tags are attached to objects such as machinery and products used in the manufacturing and transportation of goods. These sensors and tags collect and analyze process data related to the products, providing meaningful information for operational use and decision-making in the supply chain. Before the spread of COVID-19, the fundamental principles of supply chain management were centered around 'cost minimization' and 'high efficiency.' A smart supply chain overcomes the linear delayed action-reaction processes of traditional supply chains by adopting real-time data for better decision-making based on information, providing greater transparency, and enabling enhanced collaboration across the entire supply chain. Therefore, in this study, a hierarchical model for building a smart supply chain was constructed to systematically derive the importance of key factors that should be strategically considered in the construction of a smart supply chain, based on the major factors identified in previous research. We applied AHP (Analytical Hierarchy Process) techniques to identify urgent improvement areas in smart SCM initiatives. The analysis results showed that the external supply chain integration is the most urgent area to be improved in smart SCM initiatives.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.514-517
• /
• 2023

본 연구는 인 컨택스트 러닝 (In-Context Learning)을 오디오-언어 작업에 적용하기 위한 멀티모달 (Multi-Modal) 딥러닝 모델을 다룬다. 해당 모델을 통해 학습 단계에서 오디오와 텍스트의 소통 가능한 형태의 표현 (Representation)을 학습하고 여러가지 오디오-텍스트 작업을 수행할 수 있는 멀티모달 딥러닝 모델을 개발하는 것이 본 연구의 목적이다. 모델은 오디오 인코더와 언어 인코더가 연결된 구조를 가지고 있으며, 언어 모델은 6.7B, 30B 의 파라미터 수를 가진 자동회귀 (Autoregressive) 대형 언어 모델 (Large Language Model)을 사용한다 오디오 인코더는 자기지도학습 (Self-Supervised Learning)을 기반으로 사전학습 된 오디오 특징 추출 모델이다. 언어모델이 상대적으로 대용량이기 언어모델의 파라미터를 고정하고 오디오 인코더의 파라미터만 업데이트하는 프로즌 (Frozen) 방법으로 학습한다. 학습을 위한 과제는 음성인식 (Automatic Speech Recognition)과 요약 (Abstractive Summarization) 이다. 학습을 마친 후 질의응답 (Question Answering) 작업으로 테스트를 진행했다. 그 결과, 정답 문장을 생성하기 위해서는 추가적인 학습이 필요한 것으로 보였으나, 음성인식으로 사전학습 한 모델의 경우 정답과 유사한 키워드를 사용하는 문법적으로 올바른 문장을 생성함을 확인했다.

• Journal of Internet of Things and Convergence
• /
• v.9 no.6
• /
• pp.75-81
• /
• 2023

This study propose the traffic shaping scheme on IoT Network. The proposed scheme can be operated on the gateway which called sink node and control the IoT traffic with considering the traffic type(real-time based or non real-time based). It is proved that the proposed scheme shows a efficient and compatible result by the numerical analysis and the simulation on the proposed model. And the efficient of the proposed scheme by the numerical analysis has a approximate result of the simulation.

• The Journal of Korean Medicine
• /
• v.45 no.1
• /
• pp.203-214
• /
• 2024

Objectives: In the context of competency-based education emphasized in Korean Medicine, this study aimed to develop a pilot version of a CPX (Clinical Performance Examination) Practicing Chatbot utilizing large language models with prompt engineering. Methods: A standardized patient scenario was acquired from the National Institute of Korean Medicine and transformed into text format. Prompt engineering was then conducted using role prompting and few-shot prompting techniques. The GPT-4 API was employed, and a web application was created using the gradio package. An internal evaluation criterion was established for the quantitative assessment of the chatbot's performance. Results: The chatbot was implemented and evaluated based on the internal evaluation criterion. It demonstrated relatively high correctness and compliance. However, there is a need for improvement in confidentiality and naturalness. Conclusions: This study successfully piloted the CPX Practicing Chatbot, revealing the potential for developing educational models using AI technology in the field of Korean Medicine. Additionally, it identified limitations and provided insights for future developmental directions.

• International journal of advanced smart convergence
• /
• v.13 no.1
• /
• pp.37-47
• /
• 2024

This study presents the results of designing a system that determines the location of a person in an indoor environment based on a single IMU sensor attached to the tip of a person's shoe in an area where GPS signals are inaccessible. By adjusting for human footfall, it is possible to accurately determine human location and trajectory by correcting errors originating from the Inertial Measurement Unit (IMU) combined with advanced machine learning algorithms. Although there are various techniques to identify stepping, our study successfully recognized stepping with 98.7% accuracy using an artificial intelligence model known as Long Short-Term Memory (LSTM). Drawing upon the enhancements in our methodology, this article demonstrates a novel technique for generating a 200-meter trajectory, achieving a level of precision marked by a 2.1% error margin. Indoor pedestrian navigation systems, relying on inertial measurement units attached to the feet, have shown encouraging outcomes.