• 제목/요약/키워드: Binary CNN

검색결과 61건 처리시간 0.021초

The Study on The Identification Model of Friend or Foe on Helicopter by using Binary Classification with CNN

  • Kim, Tae Wan;Kim, Jong Hwan;Moon, Ho Seok
    • 한국컴퓨터정보학회논문지
    • /
    • 제25권3호
    • /
    • pp.33-42
    • /
    • 2020
  • 각종 감시체계에서 육안에 의존하여 물체를 식별해내는 것은 어렵고 실수하기 쉬우므로 군 감시체계에서 자동식별능력의 필요성은 더욱 높아지고 있다. 사회에 발표되는 모형들은 군 무기체계에 대한 데이터가 반영되지 않아 군에 바로 적용하는 것은 제한된다. 본 연구는 군용 헬기의 이미지에 합성곱 신경망을 적용하여 피아식별 모형을 구축한 연구이다. 제안하는 모형은 우리나라에서 주로 사용하고 있는 헬기인 AH-64 기종과 공산권 국가에서 주로 사용하고 있는 헬기인 Mi-17 기종의 이미지를 통해 학습시켜 구축되었다. 제안하는 모형의 성능을 살펴보면, 평가척도를 이용하여 평가한 결과 97.8%의 정확도, 97.3%의 정밀도, 98.5% 재현율과 97.9%의 F-measure의 성능을 보임을 확인하였다. 이런 분류 결과에 대해서 Feature-map을 통해 아군 헬기의 바퀴와 무장, 그리고 흡기구 주변이, 적군 헬기의 바퀴, 흡기구, 그리고 창문 부위가 피아식별 모형의 분류 기준임을 확인할 수 있었다. 본 연구는 CNN을 이용하여 군 무기체계 중 헬기의 영상정보에 대한 피아식별에 대한 분류를 처음으로 시도한 연구이며, 본 연구에서 제안하는 모형은 기존의 다른 무기체계에 대한 분류 모형보다 높은 정확도를 보인다.

Crack segmentation in high-resolution images using cascaded deep convolutional neural networks and Bayesian data fusion

  • Tang, Wen;Wu, Rih-Teng;Jahanshahi, Mohammad R.
    • Smart Structures and Systems
    • /
    • 제29권1호
    • /
    • pp.221-235
    • /
    • 2022
  • Manual inspection of steel box girders on long span bridges is time-consuming and labor-intensive. The quality of inspection relies on the subjective judgements of the inspectors. This study proposes an automated approach to detect and segment cracks in high-resolution images. An end-to-end cascaded framework is proposed to first detect the existence of cracks using a deep convolutional neural network (CNN) and then segment the crack using a modified U-Net encoder-decoder architecture. A Naïve Bayes data fusion scheme is proposed to reduce the false positives and false negatives effectively. To generate the binary crack mask, first, the original images are divided into 448 × 448 overlapping image patches where these image patches are classified as cracks versus non-cracks using a deep CNN. Next, a modified U-Net is trained from scratch using only the crack patches for segmentation. A customized loss function that consists of binary cross entropy loss and the Dice loss is introduced to enhance the segmentation performance. Additionally, a Naïve Bayes fusion strategy is employed to integrate the crack score maps from different overlapping crack patches and to decide whether a pixel is crack or not. Comprehensive experiments have demonstrated that the proposed approach achieves an 81.71% mean intersection over union (mIoU) score across 5 different training/test splits, which is 7.29% higher than the baseline reference implemented with the original U-Net.

Proposal of a new method for learning of diesel generator sounds and detecting abnormal sounds using an unsupervised deep learning algorithm

  • Hweon-Ki Jo;Song-Hyun Kim;Chang-Lak Kim
    • Nuclear Engineering and Technology
    • /
    • 제55권2호
    • /
    • pp.506-515
    • /
    • 2023
  • This study is to find a method to learn engine sound after the start-up of a diesel generator installed in nuclear power plant with an unsupervised deep learning algorithm (CNN autoencoder) and a new method to predict the failure of a diesel generator using it. In order to learn the sound of a diesel generator with a deep learning algorithm, sound data recorded before and after the start-up of two diesel generators was used. The sound data of 20 min and 2 h were cut into 7 s, and the split sound was converted into a spectrogram image. 1200 and 7200 spectrogram images were created from sound data of 20 min and 2 h, respectively. Using two different deep learning algorithms (CNN autoencoder and binary classification), it was investigated whether the diesel generator post-start sounds were learned as normal. It was possible to accurately determine the post-start sounds as normal and the pre-start sounds as abnormal. It was also confirmed that the deep learning algorithm could detect the virtual abnormal sounds created by mixing the unusual sounds with the post-start sounds. This study showed that the unsupervised anomaly detection algorithm has a good accuracy increased about 3% with comparing to the binary classification algorithm.

인지 무선 통신을 위한 합성곱 신경망 기반 스펙트럼 센싱 기법 (CNN Based Spectrum Sensing Technique for Cognitive Radio Communications)

  • 정태윤;이의수;김도경;오지명;노우영;정의림
    • 한국정보통신학회논문지
    • /
    • 제24권2호
    • /
    • pp.276-284
    • /
    • 2020
  • 본 논문에서는 인지 무선 통신을 위한 새로운 합성곱 신경망 기반 스펙트럼 센싱 기법을 제안한다. 제안하는 기법은 주 사용자 신호에 대한 어떠한 사전 정보도 알지 못하는 상황에서 에너지 검출을 통해 주 사용자 신호 유무를 판단한다. 제안하는 기법은 센싱하고자 하는 전체 대역을 고려하여 수신신호를 고속으로 샘플링한다. 이후 신호의 FFT(fast Fourier transform)을 통해 주파수 스펙트럼으로 변환하고 연속적으로 이와 같은 스펙트럼을 쌓아서 2차원 신호를 만든다. 이렇게 만든 2차원 신호를 탐지하고자 하는 채널 대역폭 단위로 자르고 합성곱 신경망에 입력하여 채널이 사용 중인지 비어있는지 판단한다. 판단하고자 하는 분류의 종류가 두 가지이므로 이진 분류 합성곱 신경망을 사용한다. 제안하는 기법의 성능은 컴퓨터 모의실험과 실제 실내환경에서의 실험을 통해 검증하는데 이 결과에 따르면 제안하는 기법은 기존 문턱값 기반 기법보다 2 dB 이상 우수한 성능을 보인다.

딥러닝 기술을 활용한 차별 및 혐오 표현 탐지 : 어텐션 기반 다중 채널 CNN 모델링 (Bias & Hate Speech Detection Using Deep Learning: Multi-channel CNN Modeling with Attention)

  • 이원석;이현상
    • 한국정보통신학회논문지
    • /
    • 제24권12호
    • /
    • pp.1595-1603
    • /
    • 2020
  • 포털 사이트의 인터넷 뉴스 댓글, SNS, 커뮤니티 사이트 등의 온라인상에서 명예 훼손 사건이 최근 점점 증가하고 있다. 온라인상의 차별 및 혐오 표현은 명예 훼손 문제뿐만 아니라 사생활 침해, 인신 공격 등 다양한 형태로 온라인 서비스 이용자들을 위협하고 있다. 지난 몇 년간 산업계와 학계는 이러한 문제를 해결하고자 다양한 방법으로 연구해왔다. 하지만 한국어 대상으로 수행된 딥러닝 기반 혐오 표현 탐지 연구는 아직까지 부족한 상황이다. 본 연구의 목적은 혐오 표현뿐만 아니라 다양한 차별적 표현에 대한 탐지를 위해 데이터셋을 구축하고 이를 분류하기 위한 딥러닝 모델링을 실험하는 것이다. 데이터셋 구축은 10명의 인원이 교차적으로 검토를 하면서 7개 항목에 대한 라벨링 기준을 확립했다. 본 연구는 약 137,111개에 해당하는 한국어 인터넷 뉴스 댓글 데이터셋에 대해 7개의 항목을 각각 이진 분류하고, 이를 딥러닝 기법을 통해 분석한다. 본 연구에서 제안하는 기법은 어텐션 기반 다중 채널 CNN 모델링 기법이다. 실험 결과 7개 항목에 대해 가중 평균 f1 점수를 평가했을 때, 70.32%의 성능을 달성했다.

Visual Object Tracking Fusing CNN and Color Histogram based Tracker and Depth Estimation for Automatic Immersive Audio Mixing

  • Park, Sung-Jun;Islam, Md. Mahbubul;Baek, Joong-Hwan
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제14권3호
    • /
    • pp.1121-1141
    • /
    • 2020
  • We propose a robust visual object tracking algorithm fusing a convolutional neural network tracker trained offline from a large number of video repositories and a color histogram based tracker to track objects for mixing immersive audio. Our algorithm addresses the problem of occlusion and large movements of the CNN based GOTURN generic object tracker. The key idea is the offline training of a binary classifier with the color histogram similarity values estimated via both trackers used in this method to opt appropriate tracker for target tracking and update both trackers with the predicted bounding box position of the target to continue tracking. Furthermore, a histogram similarity constraint is applied before updating the trackers to maximize the tracking accuracy. Finally, we compute the depth(z) of the target object by one of the prominent unsupervised monocular depth estimation algorithms to ensure the necessary 3D position of the tracked object to mix the immersive audio into that object. Our proposed algorithm demonstrates about 2% improved accuracy over the outperforming GOTURN algorithm in the existing VOT2014 tracking benchmark. Additionally, our tracker also works well to track multiple objects utilizing the concept of single object tracker but no demonstrations on any MOT benchmark.

머신러닝 기법을 활용한 대용량 시계열 데이터 이상 시점탐지 방법론 : 발전기 부품신호 사례 중심 (Anomaly Detection of Big Time Series Data Using Machine Learning)

  • 권세혁
    • 산업경영시스템학회지
    • /
    • 제43권2호
    • /
    • pp.33-38
    • /
    • 2020
  • Anomaly detection of Machine Learning such as PCA anomaly detection and CNN image classification has been focused on cross-sectional data. In this paper, two approaches has been suggested to apply ML techniques for identifying the failure time of big time series data. PCA anomaly detection to identify time rows as normal or abnormal was suggested by converting subjects identification problem to time domain. CNN image classification was suggested to identify the failure time by re-structuring of time series data, which computed the correlation matrix of one minute data and converted to tiff image format. Also, LASSO, one of feature selection methods, was applied to select the most affecting variables which could identify the failure status. For the empirical study, time series data was collected in seconds from a power generator of 214 components for 25 minutes including 20 minutes before the failure time. The failure time was predicted and detected 9 minutes 17 seconds before the failure time by PCA anomaly detection, but was not detected by the combination of LASSO and PCA because the target variable was binary variable which was assigned on the base of the failure time. CNN image classification with the train data of 10 normal status image and 5 failure status images detected just one minute before.

One-step deep learning-based method for pixel-level detection of fine cracks in steel girder images

  • Li, Zhihang;Huang, Mengqi;Ji, Pengxuan;Zhu, Huamei;Zhang, Qianbing
    • Smart Structures and Systems
    • /
    • 제29권1호
    • /
    • pp.153-166
    • /
    • 2022
  • Identifying fine cracks in steel bridge facilities is a challenging task of structural health monitoring (SHM). This study proposed an end-to-end crack image segmentation framework based on a one-step Convolutional Neural Network (CNN) for pixel-level object recognition with high accuracy. To particularly address the challenges arising from small object detection in complex background, efforts were made in loss function selection aiming at sample imbalance and module modification in order to improve the generalization ability on complicated images. Specifically, loss functions were compared among alternatives including the Binary Cross Entropy (BCE), Focal, Tversky and Dice loss, with the last three specialized for biased sample distribution. Structural modifications with dilated convolution, Spatial Pyramid Pooling (SPP) and Feature Pyramid Network (FPN) were also performed to form a new backbone termed CrackDet. Models of various loss functions and feature extraction modules were trained on crack images and tested on full-scale images collected on steel box girders. The CNN model incorporated the classic U-Net as its backbone, and Dice loss as its loss function achieved the highest mean Intersection-over-Union (mIoU) of 0.7571 on full-scale pictures. In contrast, the best performance on cropped crack images was achieved by integrating CrackDet with Dice loss at a mIoU of 0.7670.

Fault diagnosis of linear transfer robot using XAI

  • Taekyung Kim;Arum Park
    • International Journal of Internet, Broadcasting and Communication
    • /
    • 제16권3호
    • /
    • pp.121-138
    • /
    • 2024
  • Artificial intelligence is crucial to manufacturing productivity. Understanding the difficulties in producing disruptions, especially in linear feed robot systems, is essential for efficient operations. These mechanical tools, essential for linear movements within systems, are prone to damage and degradation, especially in the LM guide, due to repetitive motions. We examine how explainable artificial intelligence (XAI) may diagnose wafer linear robot linear rail clearance and ball screw clearance anomalies. XAI helps diagnose problems and explain anomalies, enriching management and operational strategies. By interpreting the reasons for anomaly detection through visualizations such as Class Activation Maps (CAMs) using technologies like Grad-CAM, FG-CAM, and FFT-CAM, and comparing 1D-CNN with 2D-CNN, we illustrates the potential of XAI in enhancing diagnostic accuracy. The use of datasets from accelerometer and torque sensors in our experiments validates the high accuracy of the proposed method in binary and ternary classifications. This study exemplifies how XAI can elucidate deep learning models trained on industrial signals, offering a practical approach to understanding and applying AI in maintaining the integrity of critical components such as LM guides in linear feed robots.

블록정보를 이용한 CNN기반 인 루프 필터 (CNN-based In-loop Filtering Using Block Information)

  • 김양우;이영렬
    • 한국방송∙미디어공학회:학술대회논문집
    • /
    • 한국방송∙미디어공학회 2019년도 추계학술대회
    • /
    • pp.27-29
    • /
    • 2019
  • VVC(Versatile Video Coding)는 입력 YUV영상을 CTU(Coding Tree Unit)으로 분할하고, 다시 이를 QTBTTT(Quad Tree, Binary Tree, Ternery Tree)로 최적의 블록으로 분할하고 각각의 블록을 공간적, 시간적 정보를 이용하여 예측하고 예측블록과 원본블록의 차분신호를 변환, 양자화를 통해 전송한다. 이를 위해 여러가지 인코딩정보가 디코더에 전송되며 이를 이용하여 디코더는 인코더와 똑같은 순서로 영상을 복원 할 수 있다. 본 논문에서는 이러한 VVC 인코더에서 반드시 전송하는 정보를 추가적으로 이용하여 딥러닝 기반의 Convolutional Neural Netwrok로 영상의 압축률 및 화질개선 하는 방법을 제안한다.

  • PDF