• International Journal of Internet, Broadcasting and Communication
• /
• 제16권3호
• /
• pp.388-393
• /
• 2024

The convergence of machine learning and smart farm is becoming more and more important. The purpose of this research is to quantitatively analyze machine learning and smart farm with bibliographic data from 2013 to 2023. This study analyzed the 251 articles, filtered from the Web of Science, with regard to the article publication trend, the article citation trend, the top 10 research area, and the top 10 keywords representing the articles. The quantitative analysis results reveal the four points: First, the number of article publications in machine learning and smart farm continued growing from 2016. Second, the article citations in machine learning and smart farm drastically increased since 2018. Third, Computer Science, Engineering, Agriculture, Telecommunications, Chemistry, Environmental Sciences Ecology, Material Science, Instruments Instrumentation, Science Technology Other Topics, and Physics are top 10 research areas. Fourth, it is 'machine learning', 'smart farming', 'internet of things', 'precision agriculture', 'deep learning', 'agriculture', 'big data', 'machine', 'smart' and 'smart agriculture' that are the top 10 keywords composing authors' keywords in the articles in machine learning and smart farm from 2013 to 2023.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 춘계학술발표대회
• /
• pp.528-530
• /
• 2022

심층강화학습에 완전 연결 신경망과 합성곱 신경망은 잘 활용되는 것에 반해 순환 신경망은 잘 활용되지 않는다. 이는 강화학습이 마르코프 속성을 전제로 하기 때문이다. 지금까지의 강화학습은 환경이 마르코프 속성을 만족하도록 사전 작업이 필요했다, 본 논문에서는 마르코프 속성을 따르지 않는 환경에서 이러한 사전 작업 없이도 순환 신경망의 은닉 상태를 통해 마르코프 속성을 학습함으로써 학습 성능을 개선할 수 있다는 것을 소개한다.

• International journal of advanced smart convergence
• /
• 제10권4호
• /
• pp.278-288
• /
• 2021

Recently, IoT systems are cloud-based, so that continuous and large amounts of data collected from sensor nodes are processed in the data server through the cloud. However, in the centralized configuration of large-scale cloud computing, computational processing must be performed at a physical location where data collection and processing take place, and the need for edge computers to reduce the network load of the cloud system is gradually expanding. In this paper, a cluster system consisting of 6 inexpensive Raspberry Pi boards was constructed to perform fast data processing. And we propose "Kubernetes cluster system(KCS)" for processing large data collection and analysis by model distribution and data pipeline method. To compare the performance of this study, an ensemble model of deep learning was built, and the accuracy, processing performance, and processing time through the proposed KCS system and model distribution were compared and analyzed. As a result, the ensemble model was excellent in accuracy, but the KCS implemented as a data pipeline proved to be superior in processing speed..

• 한국멀티미디어학회논문지
• /
• 제25권3호
• /
• pp.451-460
• /
• 2022

Recently, several deep learning studies have been reported to automatically identify the location of diagnostic devices using endoscopic data. In previous studies, there was no design to determine whether the configuration of the dataset resulted in differences in the accuracy in which artificial intelligence models perform image classification. Studies that are based on large amounts of data are likely to have different results depending on the composition of the dataset or its proportion. In this study, we intended to determine the existence and extent of accuracy according to the composition of the dataset by compiling it into three main types using larynx, esophagus, gastroscopy, and laryngeal endoscopy images.

• Nuclear Engineering and Technology
• /
• 제54권8호
• /
• pp.3027-3033
• /
• 2022

Background: In this study, various types of deep-learning models for predicting in vitro radiosensitivity from gene-expression profiling were compared. Methods: The clonogenic surviving fractions at 2 Gy from previous publications and microarray gene-expression data from the National Cancer Institute-60 cell lines were used to measure the radiosensitivity. Seven different prediction models including three distinct multi-layered perceptrons (MLP), four different convolutional neural networks (CNN) were compared. Folded cross-validation was applied to train and evaluate model performance. The criteria for correct prediction were absolute error < 0.02 or relative error < 10%. The models were compared in terms of prediction accuracy, training time per epoch, training fluctuations, and required calculation resources. Results: The strength of MLP-based models was their fast initial convergence and short training time per epoch. They represented significantly different prediction accuracy depending on the model configuration. The CNN-based models showed relatively high prediction accuracy, low training fluctuations, and a relatively small increase in the memory requirement as the model deepens. Conclusion: Our findings suggest that a CNN-based model with moderate depth would be appropriate when the prediction accuracy is important, and a shallow MLP-based model can be recommended when either the training resources or time are limited.

• Imaging Science in Dentistry
• /
• 제54권1호
• /
• pp.81-91
• /
• 2024

Purpose: The objective of this study was to propose a deep-learning model for the detection of the mandibular canal on dental panoramic radiographs. Materials and Methods: A total of 2,100 panoramic radiographs (PANs) were collected from 3 different machines: RAYSCAN Alpha (n=700, PAN A), OP-100 (n=700, PAN B), and CS8100 (n=700, PAN C). Initially, an oral and maxillofacial radiologist coarsely annotated the mandibular canals. For deep learning analysis, convolutional neural networks (CNNs) utilizing U-Net architecture were employed for automated canal segmentation. Seven independent networks were trained using training sets representing all possible combinations of the 3 groups. These networks were then assessed using a hold-out test dataset. Results: Among the 7 networks evaluated, the network trained with all 3 available groups achieved an average precision of 90.6%, a recall of 87.4%, and a Dice similarity coefficient (DSC) of 88.9%. The 3 networks trained using each of the 3 possible 2-group combinations also demonstrated reliable performance for mandibular canal segmentation, as follows: 1) PAN A and B exhibited a mean DSC of 87.9%, 2) PAN A and C displayed a mean DSC of 87.8%, and 3) PAN B and C demonstrated a mean DSC of 88.4%. Conclusion: This multi-device study indicated that the examined CNN-based deep learning approach can achieve excellent canal segmentation performance, with a DSC exceeding 88%. Furthermore, the study highlighted the importance of considering the characteristics of panoramic radiographs when developing a robust deep-learning network, rather than depending solely on the size of the dataset.

• 디지털융복합연구
• /
• 제19권6호
• /
• pp.251-258
• /
• 2021

본 논문에서는 U-Net 기반의 semantic segmentation 방법에서 정확도를 향상시키기 위해 residual learning을 활용한 인코더-디코더 구조의 모델을 제안하였다. U-Net은 딥러닝 기반의 semantic segmentation 방법이며 자율주행 자동차, 의료 영상 분석과 같은 응용 분야에서 주로 사용된다. 기존 U-Net은 인코더의 얕은 구조로 인해 특징 압축 과정에서 손실이 발생한다. 특징 손실은 객체의 클래스 분류에 필요한 context 정보 부족을 초래하고 segmentation 정확도를 감소시키는 문제가 있다. 이를 개선하기 위해 제안하는 방법은 기존 U-Net에 특징 손실과 기울기 소실 문제를 방지하는데 효과적인 residual learning을 활용한 인코더를 통해 context 정보를 효율적으로 추출하였다. 또한, 인코더에서 down-sampling 연산을 줄여 특징맵에 포함된 공간 정보의 손실을 개선하였다. 제안하는 방법은 Cityscapes 데이터셋 실험에서 기존 U-Net 방법에 비해 segmentation 결과가 약 12% 향상되었다.

• 한국융합학회논문지
• /
• 제10권11호
• /
• pp.1-7
• /
• 2019

네트워크 공격을 탐지하기 위하여 기계학습을 이용한 다양한 연구가 최근 급격히 증가하고 있다. 이러한 기계학습 방법은 많은 데이터에 의존적이며 연구를 위해 다양한 실험 데이터가 공개되어 사용되고 있다. 하지만 실험 데이터 및 실제 환경에서 수집되는 데이터는 class간의 수량이 불균형하다는 문제점을 가지고 있다. 본 연구에서는 기계 학습을 이용한 침입탐지시스템의 한계점 중 학습데이터의 class간 불균형으로 인한 분류 성능 저하를 해결하기 위한 방법을 제안한다. 이를 위해 네트워크 트래픽 데이터를 처리하고 seqGAN를 이용하여 부족한 데이터를 생성하였다. 제안된 방법은 NSL-KDD, UNSW-NB15 데이터 셋을 대상으로 Text-CNN을 이용하여 분류하는 테스트를 실행한 결과 정밀도가 향상되는 것을 확인할 수 있었다.

• 문화기술의 융합
• /
• 제10권2호
• /
• pp.505-510
• /
• 2024

철도 레일은 차륜과 레일의 접촉면인 레일 표면에서 구름 접촉 피로 균열이 상시 발생할 수 있는 조건이기 때문에 균열의 상태를 철저히 점검하고 절손을 방지하기 위한 정밀한 점검 및 진단이 필요하다. 최근 궤도 시설의 성능 평가에 대한 세부 지침에서는 궤도 성능평가를 위한 방법과 절차에 관한 필요사항을 제시하고 있다. 그러나 레일 표면 손상을 진단하고 등급을 산정하는 것은 주로 외관 조사(육안 조사)에 의존하며, 이는 점검자의 주관적인 판단에 따른 정성적인 평가에 의존할 수밖에 없는 실정이다. 따라서 본 연구에서는 Fast R-CNN을 사용하여 레일 표면 결함 검출에 대한 딥러닝 모델 연구를 수행하였다. 레일 표면 결함 이미지의 데이터 세트를 구축한 후, 모델을 테스트하였다. 딥러닝 모델의 성능평가 결과에서 mAP가 94.9%로 나타났다. Fast R-CNN의 균열 검출 효과가 높기 때문에 이 모델을 사용하면 레일표면 결함을 효율적으로 식별할 수 있을 것으로 판단된다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.540-542
• /
• 2023

Due to the serious issues posed by facial manipulation technologies, many researchers are becoming increasingly interested in the identification of face forgeries. The majority of existing face forgery detection methods leverage powerful data adaptation ability of neural network to derive distinguishing traits. These deep learning-based detection methods frequently treat the detection of fake faces as a binary classification problem and employ softmax loss to track CNN network training. However, acquired traits observed by softmax loss are insufficient for discriminating. To get over these limitations, in this study, we introduce a novel discriminative feature learning based on Vision Transformer architecture. Additionally, a separation-center loss is created to simply compress intra-class variation of original faces while enhancing inter-class differences in the embedding space.