• 제목/요약/키워드: 1D Convolutional Neural Network

검색결과 77건 처리시간 0.034초

VVC 인코더에서 합성 곱 신경망의 어텐션 맵을 이용한 휘도 매핑 함수 생성 방법 (Luma Mapping Function Generation Method Using Attention Map of Convolutional Neural Network in Versatile Video Coding Encoder)

  • 권나성;이종석;변주형;심동규
    • 방송공학회논문지
    • /
    • 제26권4호
    • /
    • pp.441-452
    • /
    • 2021
  • 본 논문에서는 VVC의 LMCS에서 휘도 신호 매핑 방법의 부호화 효율을 향상시키기 위한 휘도 신호 매핑 함수 생성 방법을 제안한다. 본 논문에서 제안하는 방법은 기존 LMCS에서 지역적 특징을 반영하기 위하여 사용하는 지역적 공간 분산에 합성 곱 신경망의 어텐션 맵을 곱하여 인지 지각적 특징을 추가적으로 반영한다. 제안하는 방법의 성능 평가를 위하여 AI (All Intra) 조건에서 VVC 표준 실험 영상의 A1, A2, B, C, D 클래스를 이용하여 VTM-12.0과 BD-rate 성능을 비교한다. 실험 결과로서 본 논문에서 제안하는 방법이 VTM-12.0 대비 BD-rate 성능 관점에서 휘도 성분이 평균 -0.07%의 성능 향상을 보이고, 부/복호화 시간은 거의 동일하다.

1-D CNN deep learning of impedance signals for damage monitoring in concrete anchorage

  • Quoc-Bao Ta;Quang-Quang Pham;Ngoc-Lan Pham;Jeong-Tae Kim
    • 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.

Semi-supervised based Unknown Attack Detection in EDR Environment

  • Hwang, Chanwoong;Kim, Doyeon;Lee, Taejin
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제14권12호
    • /
    • pp.4909-4926
    • /
    • 2020
  • Cyberattacks penetrate the server and perform various malicious acts such as stealing confidential information, destroying systems, and exposing personal information. To achieve this, attackers perform various malicious actions by infecting endpoints and accessing the internal network. However, the current countermeasures are only anti-viruses that operate in a signature or pattern manner, allowing initial unknown attacks. Endpoint Detection and Response (EDR) technology is focused on providing visibility, and strong countermeasures are lacking. If you fail to respond to the initial attack, it is difficult to respond additionally because malicious behavior like Advanced Persistent Threat (APT) attack does not occur immediately, but occurs over a long period of time. In this paper, we propose a technique that detects an unknown attack using an event log without prior knowledge, although the initial response failed with anti-virus. The proposed technology uses a combination of AutoEncoder and 1D CNN (1-Dimention Convolutional Neural Network) based on semi-supervised learning. The experiment trained a dataset collected over a month in a real-world commercial endpoint environment, and tested the data collected over the next month. As a result of the experiment, 37 unknown attacks were detected in the event log collected for one month in the actual commercial endpoint environment, and 26 of them were verified as malicious through VirusTotal (VT). In the future, it is expected that the proposed model will be applied to EDR technology to form a secure endpoint environment and reduce time and labor costs to effectively detect unknown attacks.

A New Residual Attention Network based on Attention Models for Human Action Recognition in Video

  • Kim, Jee-Hyun;Cho, Young-Im
    • 한국컴퓨터정보학회논문지
    • /
    • 제25권1호
    • /
    • pp.55-61
    • /
    • 2020
  • 딥 러닝 기술의 발전과 컴퓨팅 파워 등의 개선으로 인해 비디오 기반 연구는 최근 많은 관심을 얻고 있다. 비디오 데이터가 이미지 데이터와 비교하여 가장 큰 차이는 비디오 데이터에는 많은 양의 시간적, 공간적 정보가 포함되어 있다는 점이다. 이처럼 비디오에 포함된 많은 양의 데이터로 인해 컴퓨터 비전 연구에 있어서 행동 인식은 중요한 연구 과제 중 하나이지만, 비디오와 같이 움직임이 있는 환경에서 인간의 행동 인식은 매우 복잡하고 도전적인 과제이다. 인간에 대한 여러 연구를 바탕으로 인공지능에서는 인간과 유사한 주의(attention)메커니즘이 효율적인 인식 모델이라는 것을 알게 되었다. 이 효율적인 모델은 이미지 정보와 복잡한 연속 비디오 정보를 처리하는 데 이상적이다. 본 논문에서는 이러한 연구배경을 기반으로, 비디오에서 인간의 행동을 효율적으로 인식하기 위해 먼저 인간의 행동에 주목한 후 비디오 행동 인식에 주의메커니즘을 도입하고자 한다. 논문의 주요내용은 두 가지 주의 메카니즘을 기반으로 컨볼루션 신경망을 이용한 새로운 3D 잔류 주의 네트워크를 제안함으로써 비디오에서 인간의 행동을 식별하고자 한다. 제안 모델의 평가 결과 최대 90.7%정도의 정확도를 보였다.

동작 인식을 위한 교사-학생 구조 기반 CNN (Teacher-Student Architecture Based CNN for Action Recognition)

  • ;이효종
    • 정보처리학회논문지:컴퓨터 및 통신 시스템
    • /
    • 제11권3호
    • /
    • pp.99-104
    • /
    • 2022
  • 대부분 첨단 동작 인식 컨볼루션 네트워크는 RGB 스트림과 광학 흐름 스트림, 양 스트림 아키텍처를 기반으로 하고 있다. RGB 프레임 스트림은 모양 특성을 나타내고 광학 흐름 스트림은 동작 특성을 해석한다. 그러나 광학 흐름은 계산 비용이 매우 높기 때문에 동작 인식 시간에 지연을 초래한다. 이에 양 스트림 네트워크와 교사-학생 아키텍처에서 영감을 받아 행동 인식을 위한 새로운 네트워크 디자인을 개발하였다. 제안 신경망은 두 개의 하위 네트워크로 구성되어있다. 즉, 교사 역할을 하는 광학 흐름 하위 네트워크와 학생 역할을 하는 RGB 프레임 하위 네트워크를 연결하였다. 훈련 단계에서 광학 흐름의 특징을 추출하고 교사 서브 네트워크를 훈련시킨 다음 그 특징을 학생 서브 네트워크를 훈련시키기 위한 기준선으로 지정하여 학생 서브 네트워크에 전송한다. 테스트 단계에서는 광학 흐름을 계산하지 않고 대기 시간이 줄어들도록 학생 네트워크만 사용한다. 제안 네트워크는 실험을 통하여 정확도 면에서 일반 이중 스트림 아키텍처에 비해 높은 정확도를 보여주는 것을 확인하였다.

작물분류에서 기계학습 및 딥러닝 알고리즘의 분류 성능 평가: 하이퍼파라미터와 훈련자료 크기의 영향 분석 (Performance Evaluation of Machine Learning and Deep Learning Algorithms in Crop Classification: Impact of Hyper-parameters and Training Sample Size)

  • 김예슬;곽근호;이경도;나상일;박찬원;박노욱
    • 대한원격탐사학회지
    • /
    • 제34권5호
    • /
    • pp.811-827
    • /
    • 2018
  • 본 연구의 목적은 다중시기 원격탐사 자료를 이용한 작물분류에서 기계학습 알고리즘과 딥러닝 알고리즘의 비교에 있다. 이를 위해 전라남도 해남군과 미국 Illinois 주의 작물 재배지를 대상으로 기계학습 알고리즘과 딥러닝 알고리즘에 대해 (1) 하이퍼파라미터와 (2) 훈련자료의 크기에 따른 영향을 비교 분석하였다. 비교 실험에는 기계학습 알고리즘으로 support vector machine(SVM)을 적용하고 딥러닝 알고리즘으로 convolutional neural network(CNN)를 적용하였다. 특히 CNN에서 2차원의 공간정보를 고려하는 2D-CNN과 시간차원을 확장한 구조의 3D-CNN을 적용하였다. 비교 실험 결과, 다양한 하이퍼파라미터를 고려해야 하는 CNN의 경우 SVM과 다르게 두 지역에서 정의된 하이퍼파라미터 값이 유사한 것으로 나타났다. 이러한 결과를 바탕으로 모델 최적화에 많은 시간이 소요되지만 최적화된 CNN 모델을 다른 지역으로 확장할 수 있는 전이학습의 적용 가능성이 높을 것으로 판단된다. 다음 훈련자료 크기에 따른 비교 실험 결과, SVM 보다 CNN에서 훈련자료 크기의 영향이 큰 것으로 나타났는데 특히 다양한 공간특성을 갖는 Illinois 주에서 이러한 경향이 두드러지게 나타났다. 또한 Illinois 주에서 3D-CNN의 분류 성능이 저하되는 것으로 나타났는데, 이는 모델 복잡도가 증가하면서 과적합의 영향이 발생한 것으로 판단된다. 즉 모델의 훈련 정확도는 높지만 다양한 공간특성이나 입력 자료의 잡음 효과 등으로 오히려 분류 성능이 저하된 것으로 나타났다. 이러한 결과는 대상 지역의 공간특성을 고려해 적절한 분류 알고리즘을 선택해야 하는 것을 의미한다. 또한 CNN에서 특히, 3D-CNN에서 일정 수준의 분류 성능을 담보하기 위해 다량의 훈련자료 수집이 필요하다는 것을 의미한다.

CNN based data anomaly detection using multi-channel imagery for structural health monitoring

  • Shajihan, Shaik Althaf V.;Wang, Shuo;Zhai, Guanghao;Spencer, Billie F. Jr.
    • Smart Structures and Systems
    • /
    • 제29권1호
    • /
    • pp.181-193
    • /
    • 2022
  • Data-driven structural health monitoring (SHM) of civil infrastructure can be used to continuously assess the state of a structure, allowing preemptive safety measures to be carried out. Long-term monitoring of large-scale civil infrastructure often involves data-collection using a network of numerous sensors of various types. Malfunctioning sensors in the network are common, which can disrupt the condition assessment and even lead to false-negative indications of damage. The overwhelming size of the data collected renders manual approaches to ensure data quality intractable. The task of detecting and classifying an anomaly in the raw data is non-trivial. We propose an approach to automate this task, improving upon the previously developed technique of image-based pre-processing on one-dimensional (1D) data by enriching the features of the neural network input data with multiple channels. In particular, feature engineering is employed to convert the measured time histories into a 3-channel image comprised of (i) the time history, (ii) the spectrogram, and (iii) the probability density function representation of the signal. To demonstrate this approach, a CNN model is designed and trained on a dataset consisting of acceleration records of sensors installed on a long-span bridge, with the goal of fault detection and classification. The effect of imbalance in anomaly patterns observed is studied to better account for unseen test cases. The proposed framework achieves high overall accuracy and recall even when tested on an unseen dataset that is much larger than the samples used for training, offering a viable solution for implementation on full-scale structures where limited labeled-training data is available.

Accuracy of artificial intelligence-assisted landmark identification in serial lateral cephalograms of Class III patients who underwent orthodontic treatment and two-jaw orthognathic surgery

  • Hong, Mihee;Kim, Inhwan;Cho, Jin-Hyoung;Kang, Kyung-Hwa;Kim, Minji;Kim, Su-Jung;Kim, Yoon-Ji;Sung, Sang-Jin;Kim, Young Ho;Lim, Sung-Hoon;Kim, Namkug;Baek, Seung-Hak
    • 대한치과교정학회지
    • /
    • 제52권4호
    • /
    • pp.287-297
    • /
    • 2022
  • Objective: To investigate the pattern of accuracy change in artificial intelligence-assisted landmark identification (LI) using a convolutional neural network (CNN) algorithm in serial lateral cephalograms (Lat-cephs) of Class III (C-III) patients who underwent two-jaw orthognathic surgery. Methods: A total of 3,188 Lat-cephs of C-III patients were allocated into the training and validation sets (3,004 Lat-cephs of 751 patients) and test set (184 Lat-cephs of 46 patients; subdivided into the genioplasty and non-genioplasty groups, n = 23 per group) for LI. Each C-III patient in the test set had four Lat-cephs: initial (T0), pre-surgery (T1, presence of orthodontic brackets [OBs]), post-surgery (T2, presence of OBs and surgical plates and screws [S-PS]), and debonding (T3, presence of S-PS and fixed retainers [FR]). After mean errors of 20 landmarks between human gold standard and the CNN model were calculated, statistical analysis was performed. Results: The total mean error was 1.17 mm without significant difference among the four time-points (T0, 1.20 mm; T1, 1.14 mm; T2, 1.18 mm; T3, 1.15 mm). In comparison of two time-points ([T0, T1] vs. [T2, T3]), ANS, A point, and B point showed an increase in error (p < 0.01, 0.05, 0.01, respectively), while Mx6D and Md6D showeda decrease in error (all p < 0.01). No difference in errors existed at B point, Pogonion, Menton, Md1C, and Md1R between the genioplasty and non-genioplasty groups. Conclusions: The CNN model can be used for LI in serial Lat-cephs despite the presence of OB, S-PS, FR, genioplasty, and bone remodeling.

A Three-Dimensional Deep Convolutional Neural Network for Automatic Segmentation and Diameter Measurement of Type B Aortic Dissection

  • Yitong Yu;Yang Gao;Jianyong Wei;Fangzhou Liao;Qianjiang Xiao;Jie Zhang;Weihua Yin;Bin Lu
    • Korean Journal of Radiology
    • /
    • 제22권2호
    • /
    • pp.168-178
    • /
    • 2021
  • Objective: To provide an automatic method for segmentation and diameter measurement of type B aortic dissection (TBAD). Materials and Methods: Aortic computed tomography angiographic images from 139 patients with TBAD were consecutively collected. We implemented a deep learning method based on a three-dimensional (3D) deep convolutional neural (CNN) network, which realizes automatic segmentation and measurement of the entire aorta (EA), true lumen (TL), and false lumen (FL). The accuracy, stability, and measurement time were compared between deep learning and manual methods. The intra- and inter-observer reproducibility of the manual method was also evaluated. Results: The mean dice coefficient scores were 0.958, 0.961, and 0.932 for EA, TL, and FL, respectively. There was a linear relationship between the reference standard and measurement by the manual and deep learning method (r = 0.964 and 0.991, respectively). The average measurement error of the deep learning method was less than that of the manual method (EA, 1.64% vs. 4.13%; TL, 2.46% vs. 11.67%; FL, 2.50% vs. 8.02%). Bland-Altman plots revealed that the deviations of the diameters between the deep learning method and the reference standard were -0.042 mm (-3.412 to 3.330 mm), -0.376 mm (-3.328 to 2.577 mm), and 0.026 mm (-3.040 to 3.092 mm) for EA, TL, and FL, respectively. For the manual method, the corresponding deviations were -0.166 mm (-1.419 to 1.086 mm), -0.050 mm (-0.970 to 1.070 mm), and -0.085 mm (-1.010 to 0.084 mm). Intra- and inter-observer differences were found in measurements with the manual method, but not with the deep learning method. The measurement time with the deep learning method was markedly shorter than with the manual method (21.7 ± 1.1 vs. 82.5 ± 16.1 minutes, p < 0.001). Conclusion: The performance of efficient segmentation and diameter measurement of TBADs based on the 3D deep CNN was both accurate and stable. This method is promising for evaluating aortic morphology automatically and alleviating the workload of radiologists in the near future.

1D-CNN-LSTM Hybrid-Model-Based Pet Behavior Recognition through Wearable Sensor Data Augmentation

  • Hyungju Kim;Nammee Moon
    • Journal of Information Processing Systems
    • /
    • 제20권2호
    • /
    • pp.159-172
    • /
    • 2024
  • The number of healthcare products available for pets has increased in recent times, which has prompted active research into wearable devices for pets. However, the data collected through such devices are limited by outliers and missing values owing to the anomalous and irregular characteristics of pets. Hence, we propose pet behavior recognition based on a hybrid one-dimensional convolutional neural network (CNN) and long short- term memory (LSTM) model using pet wearable devices. An Arduino-based pet wearable device was first fabricated to collect data for behavior recognition, where gyroscope and accelerometer values were collected using the device. Then, data augmentation was performed after replacing any missing values and outliers via preprocessing. At this time, the behaviors were classified into five types. To prevent bias from specific actions in the data augmentation, the number of datasets was compared and balanced, and CNN-LSTM-based deep learning was performed. The five subdivided behaviors and overall performance were then evaluated, and the overall accuracy of behavior recognition was found to be about 88.76%.