• 대한한방소아과학회지
• /
• 제37권2호
• /
• pp.1-11
• /
• 2023

Objectives We aimed to compare the bone age (BA) estimation by a deep learning-based program and by a specialist in pediatrics of Korean medicine using the Tanner-Whitehouse 3 (TW3) technique for the cases of children who visited a Korean medicine hospital for growth, and to report the effect of Korean medicine treatment. Methods For three children who visited the Korean medicine hospital for growth, BA estimation by the deep learning program and by the specialist in pediatrics of Korean medicine using the TW3 technique was compared, and the time required for estimation was investigated. The change of height, BA, and predicted adult height (PAH) using deep learning program after Korean medicine treatment was observed. Results BA estimation of the left hand bone X-ray by the specialist using the TW3 technique showed a difference of -0.03 to +0.15 years from the estimation by the deep learning program. The mean estimation time was 5 minutes and 49 seconds per one for the specialist and 48 seconds for the deep learning program. During the treatment period, the height percentile and PAH estimated by deep learning program were increased after Korean medicine treatment compared to baseline while acceleration of BA was suppressed compared to chronological age. Conclusions BA estimation using the deep learning program and the TW3 technique showed a difference of less than 0.15 years, and in three cases of patients with growth as the chief complaint, Korean medicine treatment increased height percentile and PAH without accelerating BA maturation.

• 정보교육학회논문지
• /
• 제23권6호
• /
• pp.583-590
• /
• 2019

본 연구는 초등학생의 딥러닝 개념 학습을 위한 교육 프로그램을 개발하는 것이다. 교육 프로그램의 모델은 CT요소 중심 모델을 토대로 딥러닝 교수학습모델을 개발하였다. 개발한 프로그램의 주제는 인공지능의 이미지 인식 CNN알고리즘으로 정하고, 9개 차시 교육프로그램을 개발하였다. 프로그램은 6학년을 대상으로 2주간에 걸쳐 적용을 하였다. 프로그램에 대한 학습 적합도 검사는 전문가 타당도 분석 결과로 CVR이 타당하게 나왔다. 학습자 수준 적합도와 교사 지도 수준의 적합도 문항의 경우 .80이하로 나타났으며 .96이 넘은 학습 환경과 매체의 적합도 문항에서는 높게 나타났다. 학생들의 만족도 분석 결과 학습의 이해도와 유익성, 흥미도, 학습자료 등에 대해서 평균 4.0이상을 보여 긍정적인 평가를 하여 본 연구의 가치를 확인할 수 있었다.

• Structural Engineering and Mechanics
• /
• 제81권5호
• /
• pp.647-664
• /
• 2022

The powerful data mapping capability of computational deep learning methods has been recently explored in academic works to develop strategies for structural health monitoring through appropriate characterization of dynamic responses. In many cases, these studies concern laboratory prototypes and finite element models to validate the proposed methodologies. Therefore, the present work aims to investigate the capability of a deep learning algorithm called Sparse Autoencoder (SAE) specifically focused on detecting structural alterations in real-case studies. The idea is to characterize the dynamic responses via SAE models and, subsequently, to detect the onset of abnormal behavior through the Shewhart T control chart, calculated with SAE extracted features. The anomaly detection approach is exemplified using data from the Z24 bridge, a classical benchmark, and data from the continuous monitoring of the San Vittore bell-tower, Italy. In both cases, the influence of temperature is also evaluated. The proposed approach achieved good performance, detecting structural changes even under temperature variations.

• 에너지공학
• /
• 제26권3호
• /
• pp.11-29
• /
• 2017

인공지능 특히 심층신경망기계학습기법(딥러닝)의 제조업분야에서의 이용이 효율적이며 실용적일 수 있다는 인식이 넓게 수용되고 있다 이 보고서는 최근의 신경망기계학습 개발환경을 개관하고 제조업분야에서 활용되고 있는 딥 러닝기술을 개관한다.

• 통합자연과학논문집
• /
• 제11권4호
• /
• pp.204-208
• /
• 2018

Comparison of different optimizer performance in photovoltaic power modeling using artificial neural deep learning techniques is described in this paper. Six different deep learning optimizers are tested for Long-Short-Term Memory networks in this study. The optimizers are namely Adam, Stochastic Gradient Descent, Root Mean Square Propagation, Adaptive Gradient, and some variants such as Adamax and Nadam. For comparing the optimization techniques, high and low fluctuated photovoltaic power output are examined and the power output is real data obtained from the site at Mokpo university. Using Python Keras version, we have developed the prediction program for the performance evaluation of the optimizations. The prediction error results of each optimizer in both high and low power cases shows that the Adam has better performance compared to the other optimizers.

• 대한의용생체공학회:의공학회지
• /
• 제43권2호
• /
• pp.102-108
• /
• 2022

Purpose: To propose a deep learning-based clinical decision support technique for laryngeal disease on epiglottis, tongue and vocal cords. Materials and Methods: A total of 873 laryngeal endoscopic images were acquired from the PACS database of Pusan N ational University Yangsan Hospital. and VGG16 model was applied with transfer learning and fine-tuning. Results: The values of precision, recall, accuracy and F1-score for test dataset were 0.94, 0.97, 0.95 and 0.95 for epiglottis images, 0.91, 1.00, 0.95 and 0.95 for tongue images, and 0.90, 0.64, 0.73 and 0.75 for vocal cord images, respectively. Conclusion: Experimental results demonstrated that the proposed model have a potential as a tool for decision-supporting of otolaryngologist during manual inspection of laryngeal endoscopic images.

• International journal of advanced smart convergence
• /
• 제12권4호
• /
• pp.182-189
• /
• 2023

A recently research, object detection and segmentation have emerged as crucial technologies widely utilized in various fields such as autonomous driving systems, surveillance and image editing. This paper proposes a program that utilizes the QT framework to perform real-time object detection and precise instance segmentation by integrating YOLO(You Only Look Once) and Mask R CNN. This system provides users with a diverse image editing environment, offering features such as selecting specific modes, drawing masks, inspecting detailed image information and employing various image processing techniques, including those based on deep learning. The program advantage the efficiency of YOLO to enable fast and accurate object detection, providing information about bounding boxes. Additionally, it performs precise segmentation using the functionalities of Mask R CNN, allowing users to accurately distinguish and edit objects within images. The QT interface ensures an intuitive and user-friendly environment for program control and enhancing accessibility. Through experiments and evaluations, our proposed system has been demonstrated to be effective in various scenarios. This program provides convenience and powerful image processing and editing capabilities to both beginners and experts, smoothly integrating computer vision technology. This paper contributes to the growth of the computer vision application field and showing the potential to integrate various image processing algorithms on a user-friendly platform

• 정보보호학회논문지
• /
• 제29권4호
• /
• pp.785-794
• /
• 2019

최근 4차 산업 혁명 기술 중 하나인 딥러닝(Deep Learning) 기술은 보안 분야에서는 탐지하기 어려운 네트워크 데이터의 숨겨진 의미를 식별하고 공격을 예측하는 데 사용되고 있다. 침입탐지에 사용될 딥러닝 알고리즘을 선택하기 전에 데이터의 속성과 품질 분석이 필요하다. 학습에 사용되는 데이터의 오염여부에 따라 탐지 방법에 영향을 주기 때문이다. 따라서 데이터의 특징을 파악하고 특성을 선정해야 한다. 본 논문에서는 네트워크 데이터 셋을 이용하여 악성코드의 단계적 특징을 분석하고 특성을 추출하여 딥러닝 모델을 적용하였을 때 각 특성이 성능에 미치는 영향을 분석하였다. 네트워크 특징에 따른 특성들의 비교에 대한 트래픽 분류 실험을 진행하였으며 선정한 특성을 기반으로 96.52% 정확도를 분류하였다.

• 한국수학교육학회지시리즈A:수학교육
• /
• 제63권2호
• /
• pp.209-231
• /
• 2024

4차 산업혁명과 인공지능의 발전으로 교육 분야에서 많은 변화가 일어나고 있다. 특히, 인공지능을 기반으로 하는 교육의 중요성이 강조되고 있다. 이러한 흐름에 따라 본 연구에서는 고등학교 수학에서 딥러닝 예측을 이용한 통계교육 프로그램을 개발하고 이러한 통계적 문제해결 과정 중심의 통계교육 프로그램이 고등학생들의 통계적 소양 및 컴퓨팅 사고력에 미치는 영향을 고찰하고자 한다. 먼저, 본 연구에서는 고등학교 수학에 적용할 수 있는 딥러닝 예측을 이용한 통계교육 프로그램을 개발하였고, 이를 실제 수업상황에 적용하여 분석하였다. 분석 결과, 학생들은 자료가 어떤 맥락에서 생성되고 수집되었는지 경험함으로써 맥락에 대한 이해도가 향상되었으며, 다양한 데이터셋을 탐색하고 분석하는 과정에서 자료의 변이성에 대한 이해도가 높아졌고, 자료의 신뢰성을 검증하는 과정에서 자료를 비판적으로 분석하는 능력을 보였다. 통계교육 프로그램이 고등학생들의 컴퓨팅 사고력에 미치는 영향을 분석하고자 대응 표본 t-검정 시행하였고, 수업 전과 후의 컴퓨팅 사고력 (t=-11.657, p<0.001)은 통계적으로 유의한 차이가 있음을 확인하였다.

• International Journal of Computer Science & Network Security
• /
• 제22권6호
• /
• pp.172-180
• /
• 2022

Crypto-mining malware (known as crypto-jacking) is a novel cyber-attack that exploits the victim's computing resources such as CPU and GPU to generate illegal cryptocurrency. The attacker get benefit from crypto-jacking by using someone else's mining hardware and their electricity power. This research focused on the possibility of detecting the potential crypto-mining malware in an environment by analyzing both static and dynamic approaches of deep learning. The Program Executable (PE) files were utilized with deep learning methods which are Long Short-Term Memory (LSTM). The finding revealed that LTSM outperformed both SVM and RF in static and dynamic approaches with percentage of 98% and 96%, respectively. Future studies will focus on detecting the malware using larger dataset to have more accurate and realistic results.