• 소성∙가공
• /
• 제17권2호
• /
• pp.124-129
• /
• 2008

Net shape forging technologies give many effects into the costs and qualities for the finished products. So, the studies to reduce the additional machining amount are very important in forging industry. Specially, there are two main topics in cold forging industry, such as, tool life and precision forging. In this study, new forging technique was proposed to eliminate the machining process for fixing up the length and improve the lead accuracy of gear. The luck-up hub is manufactured through many processes, such as upsetting, piercing and direct extrusion. The gear is formed in direct extrusion process; however, lead accuracy of the gear is over allowance limit. Therefore, the additional sizing process must be added. In this study, process design for closed-die forging of a lock-up hub used for a component of automobile transmission was made using three-dimensional finite element simulations, and the strain distributions and velocity distributions are investigated through the post processor. The rigid-plastic finite-element method for back pressure forging has been used in order to reduce development time and die cost. Using the FEM simulation, we found the optimum value of back pressure. The prototypes of lock-up hub parts were forged into the net-shape. In the experiment, lead precision of tooth are measured by the CCMM(Contact Coordinate Measuring Machine). The dimensional accuracy of forged part was improved up to the 40% when back press was applied.

• 대한두개안면성형외과학회지
• /
• 제25권3호
• /
• pp.116-122
• /
• 2024

Background: Due to the importance of evidence-based research in plastic surgery, the authors of this study aimed to assess the accuracy of ChatGPT in generating novel systematic review ideas within the field of craniofacial surgery. Methods: ChatGPT was prompted to generate 20 novel systematic review ideas for 10 different subcategories within the field of craniofacial surgery. For each topic, the chatbot was told to give 10 "general" and 10 "specific" ideas that were related to the concept. In order to determine the accuracy of ChatGPT, a literature review was conducted using PubMed, CINAHL, Embase, and Cochrane. Results: In total, 200 total systematic review research ideas were generated by ChatGPT. We found that the algorithm had an overall 57.5% accuracy at identifying novel systematic review ideas. ChatGPT was found to be 39% accurate for general topics and 76% accurate for specific topics. Conclusion: Craniofacial surgeons should use ChatGPT as a tool. We found that ChatGPT provided more precise answers with specific research questions than with general questions and helped narrow down the search scope, leading to a more relevant and accurate response. Beyond research purposes, ChatGPT can augment patient consultations, improve healthcare equity, and assist in clinical decision-making. With rapid advancements in artificial intelligence (AI), it is important for plastic surgeons to consider using AI in their clinical practice to improve patient-centered outcomes.

• 대한치매학회지
• /
• 제23권1호
• /
• pp.1-10
• /
• 2024

Background and Purpose: Voice, reflecting cerebral functions, holds potential for analyzing and understanding brain function, especially in the context of cognitive impairment (CI) and Alzheimer's disease (AD). This study used voice data to distinguish between normal cognition and CI or Alzheimer's disease dementia (ADD). Methods: This study enrolled 3 groups of subjects: 1) 52 subjects with subjective cognitive decline; 2) 110 subjects with mild CI; and 3) 59 subjects with ADD. Voice features were extracted using Mel-frequency cepstral coefficients and Chroma. Results: A deep neural network (DNN) model showed promising performance, with an accuracy of roughly 81% in 10 trials in predicting ADD, which increased to an average value of about 82.0%±1.6% when evaluated against unseen test dataset. Conclusions: Although results did not demonstrate the level of accuracy necessary for a definitive clinical tool, they provided a compelling proof-of-concept for the potential use of voice data in cognitive status assessment. DNN algorithms using voice offer a promising approach to early detection of AD. They could improve the accuracy and accessibility of diagnosis, ultimately leading to better outcomes for patients.

• 한국컴퓨터정보학회논문지
• /
• 제29권8호
• /
• pp.165-170
• /
• 2024

본 연구는 인공지능 평가 모델을 활용하여 양주시의 대기질 관리 시스템의 정확성을 검증하는 데 목적이 있다. 환경부 미세먼지 공공 데이터와 양주시 대기질 관리 시스템 데이터를 비교하여 미세먼지 데이터의 정합성과 신뢰성을 평가하였다, 이를 위해 데이터의 완전성, 유일성, 유효성, 일관성, 정확성, 무결성을 분석하였다. 데이터의 정합성을 비교하기 위해 탐색적 통계 분석을 활용하였다. 분석 결과, AI 기반 데이터 품질 지수 평가 결과, 두 데이터 세트 간에 통계적으로 유의미한 차이가 없음을 확인하였다. AI 기반 알고리즘 중 랜덤 포레스트 모델이 가장 높은 예측 정확도를 보였으며, ROC 커브와 AUC를 통해 예측 성능을 평가하였다. 특히, 랜덤 포레스트 모델은 대기질 관리 시스템의 최적화에 유용한 모델로 확인되었으며, 미세먼지 데이터의 신뢰성과 적합성을 AI 기반 모델 성능 평가로 활용할 수 있음을 확인하였다.

• 대한소아치과학회지
• /
• 제51권3호
• /
• pp.299-309
• /
• 2024

This study aimed to assess the competency of artificial intelligence (AI) in pediatric dentistry and compare it with that of dentists. We used open-source data obtained from the Korea Health Personnel Licensing Examination Institute. A total of 32 item multiple-choice pediatric dentistry exam questions were included. Two AI-based chatbots (ChatGPT 3.5 and Gemini) were evaluated. Each chatbot received the same questions seven times in separate chat sessions initiated on April 25, 2024. The accuracy was assessed by measuring the percentage of correct answers, and consistency was evaluated using Cronbach's alpha coefficient. Both ChatGPT 3.5 and Gemini demonstrated similar accuracy, with no significant differences observed between them. However, neither chatbot achieved the minimum passing score set by the Pediatric Dentistry National Examination. However, both chatbots exhibited acceptable consistency in their responses. Within the limits of this study, both AI-based chatbots did not sufficiently answer the pediatric dentistry exam questions. This finding suggests that pediatric dentists should be aware of the advantages and limitations of this new tool and effectively utilize it to promote patient health.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.2430-2434
• /
• 2005

Automatic FPC punching instrument for the improvement of working condition and cost saving is introduced in this paper. FPC(flexible printed circuit) is used to detect the contact position of K/B and button like a cellular phone. Depending on the quality of the printed ink and position of reference punching point to the FPC, the resistance and current are varied to the malfunctioning values. The size of reference punching point is 2mm and the above. Because the punching operation is done manually, the accuracy of the punching degree is varied with operator's condition. Recently, The punching accuracy has deteriorated severely to the 2mm punching reference hall so that assembly of the K/B has hardly done. To improve this manual punching operation to the FPC, automatic FPC punching system is introduced. Precise mechanical parts like a 5-step stepping motor and ball screw mechanism are designed and tested and low cost PC camera is used for the sake of cost down instead of using high quality vision systems for the FA. 3D Mechanical design tool(Pro/E) is used to manage the exact tolerance circumstances and avoid design failures. Simulation is performed to make the complete vision based punching machine before assembly, and this procedure led to the manufacturing cost saving. As the image processing algorithms, dilation, erosion, and threshold calculation is applied to obtain an exact center position from the FPC print marks. These image processing algorithms made the original images having various noises have clean binary pixels which is easy to calculate the center position of print marks. Moment and Least square method are used to calculate the center position of objects. In this development circumstance, Moment method was superior to the Least square one at the calculation of speed and against noise. Main control panel is programmed by Visual C++ and graphical Active X for the whole management of vision based automatic punching machine. Operating modes like manual, calibration, and automatic mode are added to the main control panel for the compensation of bad FPC print conditions and mechanical tolerance occurring in the case of punch and die reassembly. Test algorithms and programs showed good results to the designed automatic punching system and led to the increase of productivity and huge cost down to law material like FPC by avoiding bad quality.

• International Journal of Internet, Broadcasting and Communication
• /
• 제12권4호
• /
• pp.232-237
• /
• 2020

Given the recent pace of development and expansion of Artificial Intelligence (AI) technology, the influence and ripple effects of AI technology on the whole of our lives will be very large and spread rapidly. The National Artificial Intelligence R&D Strategy, published in 2019, emphasizes the importance of artificial intelligence education for K-12 students. It also mentions STEM education, AI convergence curriculum, and budget for supporting the development of teaching materials and tools. However, it is necessary to create a new type of curriculum at a time when artificial intelligence curriculum has never existed before. With many attempts and discussions going very fast in all countries on almost the same starting line. Also, there is no suitable professor for K-12 students, and it is difficult to make K-12 students understand the concept of AI. In particular, it is difficult to teach elementary school students through professional programming in AI education. It is also difficult to learn tools that can teach AI concepts. In this paper, we propose an educational model for elementary school students to improve their understanding of AI through play or experience. This an experiential education model that combineds exploratory learning and discovery learning using multi-intelligence and the PLAY teaching-learning model to undertand the importance of data training or data required for AI education. This educational model is designed to learn how a computer that knows only binary numbers through UA recognizes images. Through code.org, students were trained to learn AI robots and configured to understand data bias like play. In addition, by learning images directly on a computer through TeachableMachine, a tool capable of supervised learning, to understand the concept of dataset, learning process, and accuracy, and proposed the process of AI inference.

• 한국인터넷방송통신학회논문지
• /
• 제19권4호
• /
• pp.169-174
• /
• 2019

본 연구에서는 설문지를 이용한 데이터 수집과 데이터 마이닝에서 클러스터링 기법으로 군집하여 지도학습을 이용하여 유사성을 판단하고, 성격들의 상관 관계의 적합성을 분석하기 위해 특징 추출 알고리즘들과 지도학습을 이용하는 것을 목표로 진행한다. 연구 수행은 설문조사를 진행 후 그 설문조사를 토대로 모인 데이터들을 정제하고, 오픈 소스 기반의 데이터 마이닝 도구인 WEKA의 클러스터링 기법들을 통해 데이터 세트를 분류하고 지도학습을 이용하여 유사성을 판단한다. 그리고 특징 추출 알고리즘들과 지도학습을 이용하여 성격에 대해 적합한 결과가 나오는지에 대한 적합성을 판단한다. 그 결과 유사성 판단에 가장 정확도 높게 도움을 주는 것은 EM 클러스터링으로 3개의 분류하고 Naïve Bayes 지도학습을 시킨 것이 가장 높은 유사성 분류 결과를 도출하였고, 적합성을 판단하는데 도움이 되도록 특징추출과 지도학습을 수행하였을 때, Big-5 각 성격마다 문항에 추가되고 삭제되는 것에 따라 정확도가 변하는 모습을 찾게 되었고, 각 성격 마다 차이에 대한 분석을 완료하였다.

• Steel and Composite Structures
• /
• 제45권2호
• /
• pp.159-173
• /
• 2022

This paper proposes a hybrid machine-learning model, which is called DANN-IP, that combines a deep artificial neural network (DANN) and an interior-point (IP) algorithm in order to improve the prediction capacity on the patch loading resistance of steel plate girders. For this purpose, 394 steel plate girders that were subjected to patch loading were tested in order to construct the DANN-IP model. Firstly, several DANN models were developed in order to establish the relationship between the patch loading resistance and the web panel length, the web height, the web thickness, the flange width, the flange thickness, the applied load length, the web yield strength, and the flange yield strength of steel plate girders. Accordingly, the best DANN model was chosen based on three performance indices, which included the R^2, RMSE, and a20-index. The IP algorithm was then adopted to optimize the weights and biases of the DANN model in order to establish the hybrid DANN-IP model. The results obtained from the proposed DANN-IP model were compared with of the results from the DANN model and the existing empirical formulas. The comparison showed that the proposed DANN-IP model achieved the best accuracy with an R^2 of 0.996, an RMSE of 23.260 kN, and an a20-index of 0.891. Finally, a Graphical User Interface (GUI) tool was developed in order to effectively use the proposed DANN-IP model for practical applications.

• 한국컴퓨터정보학회논문지
• /
• 제29권5호
• /
• pp.11-20
• /
• 2024

최근 IT 기술의 발전과 더불어 금융 시장에서의 불확실성이 증대되는 상황에서 기업 신용등급 평가의 중요성을 인식하고, 이를 개선하기 위한 새로운 접근 방식으로 딥러닝 모델인 TabNet을 제안한다. 이에 본 연구에서는 TabNet을 활용하여 기업 신용등급을 예측하고, 이의 예측 성능을 기존 머신러닝 방법론과 상세하게 비교한다. 한국의 주요 증권시장에 상장된 기업들의 재무 데이터를 기반으로 TabNet 알고리즘을 적용하여 신용등급 예측 모델을 구축하고, 다양한 머신러닝 모델과의 성능을 비교 분석하였다. 실험 결과, TabNet 모델은 Precision 0.884, F1이 0.895로 기존의 머신러닝 모델들보다 우수한 성능을 보였으며, 고위험 기업을 저위험 기업으로 잘못 분류하는 경우가 다른 머신러닝 모델보다 적어 TabNet의 우수성을 확인하였다. 이는 TabNet이 기업 신용등급 예측에 있어 효과적인 도구로 활용될 수 있으며, 금융기관의 신용 위험 관리 및 의사 결정 과정을 지원할 수 있을 것으로 기대한다.