• Title/Summary/Keyword: FusionNet

Search Result 167, Processing Time 0.029 seconds

Emergency Sound Classification with Early Fusion (Early Fusion을 적용한 위급상황 음향 분류)

  • Jin-Hwan Yang;Sung-Sik Kim;Hyuk-Soon Choi;Nammee Moon
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2023.11a
    • /
    • pp.1213-1214
    • /
    • 2023
  • 현재 국내외 CCTV 구축량 증가로 사생활 침해와 높은 설치 비용등이 문제점으로 제기되고 있다. 따라서 본 연구는 Early Fusion을 적용한 위급상황 음향 분류 모델을 제안한다. 음향 데이터에 STFT(Short Time Fourier Transform), Spectrogram, Mel-Spectrogram을 적용해 특징 벡터를 추출하고 3차원으로 Early Fusion하여 ResNet, DenseNet, EfficientNetV2으로 학습한다. 실험 결과 Early Fusion 방법이 가장 좋은 결과를 보였고 DenseNet, EfficientNetV2가 Accuracy, F1-Score 모두 0.972의 성능을 보였다.

A Study on Biometric Model for Information Security (정보보안을 위한 생체 인식 모델에 관한 연구)

  • Jun-Yeong Kim;Se-Hoon Jung;Chun-Bo Sim
    • The Journal of the Korea institute of electronic communication sciences
    • /
    • v.19 no.1
    • /
    • pp.317-326
    • /
    • 2024
  • Biometric recognition is a technology that determines whether a person is identified by extracting information on a person's biometric and behavioral characteristics with a specific device. Cyber threats such as forgery, duplication, and hacking of biometric characteristics are increasing in the field of biometrics. In response, the security system is strengthened and complex, and it is becoming difficult for individuals to use. To this end, multiple biometric models are being studied. Existing studies have suggested feature fusion methods, but comparisons between feature fusion methods are insufficient. Therefore, in this paper, we compared and evaluated the fusion method of multiple biometric models using fingerprint, face, and iris images. VGG-16, ResNet-50, EfficientNet-B1, EfficientNet-B4, EfficientNet-B7, and Inception-v3 were used for feature extraction, and the fusion methods of 'Sensor-Level', 'Feature-Level', 'Score-Level', and 'Rank-Level' were compared and evaluated for feature fusion. As a result of the comparative evaluation, the EfficientNet-B7 model showed 98.51% accuracy and high stability in the 'Feature-Level' fusion method. However, because the EfficietnNet-B7 model is large in size, model lightweight studies are needed for biocharacteristic fusion.

Estimation of fuel operating ranges of fusion power plants

  • Slavomir Entler ;Jan Horacek ;Ondrej Ficker ;Karel Kovarik ;Michal Kolovratnik ;Vaclav Dostal
    • Nuclear Engineering and Technology
    • /
    • v.55 no.7
    • /
    • pp.2687-2696
    • /
    • 2023
  • The fuel operating ranges of fusion tokamak-based power plants are estimated using the improved engineering breakeven equation. The Lawson criterion equations are derived in the form of a triple product with a focus on engineering breakeven and the subbreakeven operating range. The relationship of fuel parameters to the power plant net efficiency is outlined. Analysis shows that the operating ranges of the suitable fuel parameters form a closed area, the size of which affects the net efficiency of the power plant. The obtained fuel operating ranges confirm the well-known fact that DT fuel is currently the only fusion fuel useable in tokamak-based fusion power plants. It is also shown that the energy utilization of pB fuel is possible in the subbreakeven operating range but is conditioned by the very high efficiency of the power plant equipment. For the utilization of DD, DHe3, and pB fuels, the required magnetic fields are indicatively estimated.

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
    • /
    • v.29 no.1
    • /
    • 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.

GRAYSCALE IMAGE COLORIZATION USING A CONVOLUTIONAL NEURAL NETWORK

  • JWA, MINJE;KANG, MYUNGJOO
    • Journal of the Korean Society for Industrial and Applied Mathematics
    • /
    • v.25 no.2
    • /
    • pp.26-38
    • /
    • 2021
  • Image coloration refers to adding plausible colors to a grayscale image or video. Image coloration has been used in many modern fields, including restoring old photographs, as well as reducing the time spent painting cartoons. In this paper, a method is proposed for colorizing grayscale images using a convolutional neural network. We propose an encoder-decoder model, adapting FusionNet to our purpose. A proper loss function is defined instead of the MSE loss function to suit the purpose of coloring. The proposed model was verified using the ImageNet dataset. We quantitatively compared several colorization models with ours, using the peak signal-to-noise ratio (PSNR) metric. In addition, to qualitatively evaluate the results, our model was applied to images in the test dataset and compared to images applied to various other models. Finally, we applied our model to a selection of old black and white photographs.

Maneuvering Target Tracking by Perception Net in Clutter Environment (클러터 환경하에서 Perception Net을 이용한 기동 표적 추적)

  • 황태현;최재원;홍금식
    • Proceedings of the Korean Society of Precision Engineering Conference
    • /
    • 1995.10a
    • /
    • pp.602-605
    • /
    • 1995
  • In this paper, we provide the new alogorithm for maneuvering target tracking in clutter environment using perception net. The perception net, as a structural representation of the sensing capabilities of a system, may supply the constraints that target must be satisfied with. The results form perception net applying to IMMPDA are compared with those obtained from IMMPDA.

  • PDF

High-performance of Deep learning Colorization With Wavelet fusion (웨이블릿 퓨전에 의한 딥러닝 색상화의 성능 향상)

  • Kim, Young-Back;Choi, Hyun;Cho, Joong-Hwee
    • IEMEK Journal of Embedded Systems and Applications
    • /
    • v.13 no.6
    • /
    • pp.313-319
    • /
    • 2018
  • We propose a post-processing algorithm to improve the quality of the RGB image generated by deep learning based colorization from the gray-scale image of an infrared camera. Wavelet fusion is used to generate a new luminance component of the RGB image luminance component from the deep learning model and the luminance component of the infrared camera. PSNR is increased for all experimental images by applying the proposed algorithm to RGB images generated by two deep learning models of SegNet and DCGAN. For the SegNet model, the average PSNR is improved by 1.3906dB at level 1 of the Haar wavelet method. For the DCGAN model, PSNR is improved 0.0759dB on the average at level 5 of the Daubechies wavelet method. It is also confirmed that the edge components are emphasized by the post-processing and the visibility is improved.

An Efficient Text Detection Model using Bidirectional Feature Fusion (양방향 특징 결합을 이용한 효율적 문자 탐지 모델)

  • Lim, Seong-Taek;Choi, Hoeryeon;Lee, Hong-Chul
    • Proceedings of the Korean Society of Computer Information Conference
    • /
    • 2021.07a
    • /
    • pp.67-68
    • /
    • 2021
  • 기존 객체탐지는 경계 상자 회귀방식을 적용하였지만, 문자는 왜곡과 변형이 심한 특성을 가진 객체로 U-net 구조의 이미지 분할 방식을 사용하는 경우가 많다. 따라서 최근 문자 탐지는 통계적 모델에 비해 높은 정확도를 보이는 심층 신경망 기반의 모델 연구가 많이 진행되고 있다. 본 연구에서는 이미지 분할을 통한 양방향 특징 결합 기법을 사용한 문자 탐지 모델을 제안한다. 이미지 분할 방식은 메모리의 효율이 떨어지기 때문에 이를 극복하고자 특징 추출 단계에서 경량화된 네트워크를 적용하였다. 또한, 객체 탐지에서 큰 성과를 보인 양방향 특징 결합 모듈을 U-net 구조에 추가하여 추출된 특징이 효과적으로 결합 되는 결과를 얻었다. 제안하는 모델의 문자 탐지 성능은 합성 문자 데이터셋을 이용한 실험을 통해 기존의 U-net 구조의 이미지 분할 방식보다 향상되었음을 확인하였다.

  • PDF

CONSTRUCTION, ASSEMBLY AND COMMISSIONING OF KSTAR MAIN STRUCTURES

  • Yang, Hyung-Lyeol;Bak, Joo-Shik;Kim, Byung-Chul;Choi, Chang-Ho;Kim, Woong-Chae;Her, Nam-Il;Hong, Kwon-Hee;Kim, Geung-Hong;Kim, Hak-Kun;Sa, Jeong-Woo;Kim, Hong-Tack;Kim, Kyung-Min;Kim, Sang-Tae
    • Nuclear Engineering and Technology
    • /
    • v.40 no.6
    • /
    • pp.439-450
    • /
    • 2008
  • The KSTAR device succeeded in first plasma generation on $13^{th}$ June of 2008 through comprehensive system test and commissioning. Among various kinds of the key factors that decisively affected the project, success in the construction and assembly of the major tokamak structure was most important one. Every engineering aspects of each structure were finally confirmed in the integrated commissioning period, and there were no severe troubles and failures prevented the KSTAR device from operating during the commissioning and the first plasma experiments. As a result, all of the experiences and technologies achieved through the KSTAR construction process are expected to be important fundamentals for future construction projects of superconducting fusion devices. This paper summarizes key engineering features of the major structures and of the machine assembly.

An Intelligent Agent System using Multi-View Information Fusion (다각도 정보융합 방법을 이용한 지능형 에이전트 시스템)

  • Rhee, Hyun-Sook
    • Journal of the Korea Society of Computer and Information
    • /
    • v.19 no.12
    • /
    • pp.11-19
    • /
    • 2014
  • In this paper, we design an intelligent agent system with the data mining module and information fusion module as the core components of the system and investigate the possibility for the medical expert system. In the data mining module, fuzzy neural network, OFUN-NET analyzes multi-view data and produces fuzzy cluster knowledge base. In the information fusion module and application module, they serve the diagnosis result with possibility degree and useful information for diagnosis, such as uncertainty decision status or detection of asymmetry. We also present the experiment results on the BI-RADS-based feature data set selected form DDSM benchmark database. They show higher classification accuracy than conventional methods and the feasibility of the system as a computer aided diagnosis system.