• 한국인터넷방송통신학회논문지
• /
• 제20권1호
• /
• pp.225-229
• /
• 2020

이미지 인식 및 영상처리, 컴퓨터 비전 등의 분야에서 합성곱 인공신경망 (Convolutional Neural Network, CNN)은 다양하게 응용되고 탁월한 성능을 내고 있다. 본 논문에서는 CNN을 활용한 이미지 인식 시스템에서 인식률을 저하시키는 요인 중 하나인 이미지의 회전에 대한 해결책으로써 CNN 기반 이미지 회전 보정 알고리즘을 제안한다. 본 논문에서는 Leeds Sports Pose 데이터셋을 활용하여 이미지를 임의의 각도만큼 회전시킨 학습데이터로 인공지능 모델을 학습시켜 출력으로 회전된 각도를 추정하도록 실험을 진행하였다. 학습된 인공지능 모델을 100장의 테스트 데이터 이미지로 실험하여 mean absolute error (MAE) 성능지표를 기준으로 4.5951의 값을 얻었다.

• 한국인터넷방송통신학회논문지
• /
• 제23권6호
• /
• pp.1-7
• /
• 2023

본 논문은 인공지능 기술을 활용하여 일반 도로와 침수 도로를 분류하는 학습모델을 개발하였다. 다양한 데이터 증강기법을 사용하여 학습 데이터의 다양성을 확장하며, 여러 환경에서도 좋은 성능을 보이는 모델을 구현하였다. CNN 기반의 Resnet152v2 모델을 사전 학습모델로 활용하여, 전이 학습을 진행하였다. 모델의 학습 과정에서 다양한 파라미터 튜닝 및 최적화 과정을 거쳐 최종 모델의 성능을 향상하였다. 학습은 파이선으로 Google Colab NVIDIA Tesla T4 GPU를 사용하여 구현하였고, 테스트 결과 시험 데이터 세트에서 매우 높은 정확도로 침수상황을 탐지함을 알 수 있었다.

• 한국멀티미디어학회논문지
• /
• 제23권6호
• /
• pp.729-737
• /
• 2020

Screening with low-dose spiral computed tomography (LDCT) has been shown to reduce lung cancer mortality by about 20% when compared to standard chest radiography. One of the problems arising from screening programs is that large amounts of CT image data must be interpreted by radiologists. To solve this problem, automated detection of pulmonary nodules is necessary; however, this is a challenging task because of the high number of false positive results. Here we demonstrate detection of pulmonary nodules using six off-the-shelf convolutional neural network (CNN) models after modification of the input/output layers and end-to-end training based on publicly databases for comparative evaluation. We used the well-known CNN models, LeNet-5, VGG-16, GoogLeNet Inception V3, ResNet-152, DensNet-201, and NASNet. Most of the CNN models provided superior results to those of obtained using customized CNN models. It is more desirable to modify the proven off-the-shelf network model than to customize the network model to detect the pulmonary nodules.

• International journal of advanced smart convergence
• /
• 제9권2호
• /
• pp.20-27
• /
• 2020

Sound event detection in real-world environments suffers from the interference of non-stationary and time-varying noise. This paper presents an adaptive noise reduction method for sound event detection based on non-negative matrix factorization (NMF). In this paper, we proposed a deep learning model that integrates Convolution Neural Network (CNN) with Non-Negative Matrix Factorization (NMF). To improve the separation quality of the NMF, it includes noise update technique that learns and adapts the characteristics of the current noise in real time. The noise update technique analyzes the sparsity and activity of the noise bias at the present time and decides the update training based on the noise candidate group obtained every frame in the previous noise reduction stage. Noise bias ranks selected as candidates for update training are updated in real time with discrimination NMF training. This NMF was applied to CNN and Hidden Markov Model(HMM) to achieve improvement for performance of sound event detection. Since CNN has a more obvious performance improvement effect, it can be widely used in sound source based CNN algorithm.

• 산업경영시스템학회지
• /
• 제44권3호
• /
• pp.33-38
• /
• 2021

Recently, transfer learning techniques with a base convolutional neural network (CNN) model have widely gained acceptance in early detection and classification of crop diseases to increase agricultural productivity with reducing disease spread. The transfer learning techniques based classifiers generally achieve over 90% of classification accuracy for crop diseases using dataset of crop leaf images (e.g., PlantVillage dataset), but they have ability to classify only the pre-trained diseases. This paper provides with an evaluation scheme on selecting an effective base CNN model for crop disease transfer learning with regard to the accuracy of trained target crops as well as of untrained target crops. First, we present transfer learning models called CDC (crop disease classification) architecture including widely used base (pre-trained) CNN models. We evaluate each performance of seven base CNN models for four untrained crops. The results of performance evaluation show that the DenseNet201 is one of the best base CNN models.

• Smart Structures and Systems
• /
• 제23권5호
• /
• pp.507-520
• /
• 2019

In the structural health monitoring field, damage detection has been commonly carried out based on the structural model and the engineering features related to the model. However, the extracted features are often subjected to various errors, which makes the pattern recognition for damage detection still challenging. In this study, an automated damage identification method is presented for hanger cables in a tied-arch bridge using a convolutional neural network (CNN). Raw measurement data for Fourier amplitude spectra (FAS) of acceleration responses are used without a complex data pre-processing for modal identification. A CNN is a kind of deep neural network that typically consists of convolution, pooling, and fully-connected layers. A numerical simulation study was performed for multiple damage detection in the hangers using ambient wind vibration data on the bridge deck. The results show that the current CNN using FAS data performs better under various damage states than the CNN using time-history data and the traditional neural network using FAS. Robustness of the present CNN has been proven under various observational noise levels and wind speeds.

• Structural Monitoring and Maintenance
• /
• 제10권1호
• /
• pp.43-62
• /
• 2023

Damage monitoring is a prerequisite step to ensure the safety and performance of concrete structures. Smart aggregate (SA) technique has been proven for its advantage to detect early-stage internal cracks in concrete. In this study, a 1-D CNN-based method is developed for autonomously classifying the damage feature in a concrete anchorage zone using the raw impedance signatures of the embedded SA sensor. Firstly, an overview of the developed method is presented. The fundamental theory of the SA technique is outlined. Also, a 1-D CNN classification model using the impedance signals is constructed. Secondly, the experiment on the SA-embedded concrete anchorage zone is carried out, and the impedance signals of the SA sensor are recorded under different applied force levels. Finally, the feasibility of the developed 1-D CNN model is examined to classify concrete damage features via noise-contaminated signals. The results show that the developed method can accurately classify the damaged features in the concrete anchorage zone.

• Journal of information and communication convergence engineering
• /
• 제21권4호
• /
• pp.346-350
• /
• 2023

Trajectory prediction is an essential element for driving autonomous vehicles, and various trajectory prediction models have emerged with the development of deep learning technology. Convolutional neural network (CNN) is the most commonly used neural network architecture for extracting the features of visual images, and the latest models exhibit high performances. This study was conducted to identify an efficient CNN backbone model among the components of deep learning models for trajectory prediction. We changed the existing CNN backbone network of multiple-trajectory prediction models used as feature extractors to various state-of-the-art CNN models. The experiment was conducted using nuScenes, which is a dataset used for the development of autonomous vehicles. The results of each model were compared using frequently used evaluation metrics for trajectory prediction. Analyzing the impact of the backbone can improve the performance of the trajectory prediction task. Investigating the influence of the backbone on multiple deep learning models can be a future challenge.

• 한국정보통신학회논문지
• /
• 제25권11호
• /
• pp.1471-1476
• /
• 2021

수해는 홍수나 해일을 유발하여 막대한 인명과 재산의 피해를 초래할 수 있다. 이에 대해 홍수 예측을 통한 빠른 대피 결정으로 피해를 줄일 수 있으며, 해당 분야에서는 시계열 데이터를 활용하여 홍수를 예측하려는 연구들도 많이 진행되고 있다. 본 논문에서는 CNN 기반의 시계열 예측 모델을 제안한다. 하천의 수위와 강수량을 사용하여 CNN 기반의 수위 예측 모델을 구현하였고, 시계열 예측에 많이 사용되는 LSTM, GRU 모델과 비교하여 성능을 확인하였다. 또한 입력 데이터의 크기에 따른 성능 차이를 확인하여 보완해야 할 점을 찾을 수 있었고, LSTM과 GRU보다 더 좋은 성능을 낼 수 있다는 것을 확인하였다. 이를 통해 홍수 예측을 위한 초기 연구로서 활용할 수 있을 것으로 사료된다.

• 한국정보통신학회논문지
• /
• 제26권10호
• /
• pp.1490-1499
• /
• 2022

부정맥이란 심장이 불규칙한 리듬이나 비정상적인 심박동수를 갖는 것을 말하며, 뇌졸중, 심정지 등을 유발하거나 사망에도 이를 수 있는 만큼, 조기 진단과 관리가 무엇보다 중요하다. 본 연구에서는 심전도 신호의 QRS 특징 추출에 적합한 CNN과 기존 LSTM의 직전 패턴의 수렴 한계를 해결할 수 있는 BLSTM을 연결한 CNN-BLSTM 결합 모델을 이용한 부정맥 분류 방법을 제안한다. 이를 위해 먼저 전처리 과정을 통해 잡음을 제거한 심전도 신호에서 QRS 특징점을 검출하고 단일 비트 세그먼트를 추출하였다. 이때 데이터의 불균형 문제를 해결하기 위해 GAN 오버샘플링 기법을 적용하였다. 이 후 합성곱 계층을 통해 부정맥 신호의 패턴을 정밀하게 추출하도록 구성하고 이를 BLSTM의 입력으로 사용한 후 매개변수를 학습시키고 검증 데이터로 학습 모델을 평가한 후 부정맥 분류의 정확도를 확인하였다. 제안한 방법의 우수성을 입증하기 위해 MIT-BIH 부정맥 데이터베이스를 이용하여 분류의 정확도, 정밀도, 재현율, F1-score를 비교하였다. 성능평가 결과 각각 99.30%, 98.70%, 97.50%, 98.06%로 우수한 분류율을 나타내는 것을 확인할 수 있었다.