• 제목/요약/키워드: Deep Learning based System

검색결과 1,194건 처리시간 0.028초

Data-Driven-Based Beam Selection for Hybrid Beamforming in Ultra-Dense Networks

  • Ju, Sang-Lim;Kim, Kyung-Seok
    • International journal of advanced smart convergence
    • /
    • 제9권2호
    • /
    • pp.58-67
    • /
    • 2020
  • In this paper, we propose a data-driven-based beam selection scheme for massive multiple-input and multiple-output (MIMO) systems in ultra-dense networks (UDN), which is capable of addressing the problem of high computational cost of conventional coordinated beamforming approaches. We consider highly dense small-cell scenarios with more small cells than mobile stations, in the millimetre-wave band. The analog beam selection for hybrid beamforming is a key issue in realizing millimetre-wave UDN MIMO systems. To reduce the computation complexity for the analog beam selection, in this paper, two deep neural network models are used. The channel samples, channel gains, and radio frequency beamforming vectors between the access points and mobile stations are collected at the central/cloud unit that is connected to all the small-cell access points, and are used to train the networks. The proposed machine-learning-based scheme provides an approach for the effective implementation of massive MIMO system in UDN environment.

Learning Algorithms in AI System and Services

  • Jeong, Young-Sik;Park, Jong Hyuk
    • Journal of Information Processing Systems
    • /
    • 제15권5호
    • /
    • pp.1029-1035
    • /
    • 2019
  • In recent years, artificial intelligence (AI) services have become one of the most essential parts to extend human capabilities in various fields such as face recognition for security, weather prediction, and so on. Various learning algorithms for existing AI services are utilized, such as classification, regression, and deep learning, to increase accuracy and efficiency for humans. Nonetheless, these services face many challenges such as fake news spread on social media, stock selection, and volatility delay in stock prediction systems and inaccurate movie-based recommendation systems. In this paper, various algorithms are presented to mitigate these issues in different systems and services. Convolutional neural network algorithms are used for detecting fake news in Korean language with a Word-Embedded model. It is based on k-clique and data mining and increased accuracy in personalized recommendation-based services stock selection and volatility delay in stock prediction. Other algorithms like multi-level fusion processing address problems of lack of real-time database.

딥러닝 기반 음향 신호 대역 확장 시스템 (Deep Learning based Raw Audio Signal Bandwidth Extension System)

  • 김윤수;석종원
    • 전기전자학회논문지
    • /
    • 제24권4호
    • /
    • pp.1122-1128
    • /
    • 2020
  • 대역 확장(Bandwidth Extension)이란 채널 용량 부족 혹은 이동통신 기기에 탑재된 코덱의 특성으로 인해 부호화 및 복호화 과정에서 대역 제한(band limited)되거나 손상된 협대역 신호(NB, Narrow Band)를 복원, 확장하여 광대역 신호(WB, Wide Band)로 전환 시켜주는 것을 의미한다. 대역 확장 연구는 주로 음성 신호 위주로 대역 복제(SBR, Spectral Band Replication), IGF(Intelligent Gap Filling)과 같이 고대역을 주파수 영역으로 변환하여 복잡한 특징 추출 과정을 거쳐 이를 바탕으로 사라지거나 손상된 고대역을 복원한다. 본 논문에서는 딥러닝 모델 중 오토인코더(Autoencoder)를 바탕으로 1차원 합성곱 신경망(CNN, Convolutional Neural Network)들의 잔차 연결을 활용하여 복잡한 사전 전처리 과정 없이 일정한 길이의 시간 영역 신호를 입력시켜 대역 확장 시킨 음향 신호를 출력하는 모델을 제안한다. 또한 음성 영역에 제한되지 않는 음악을 포함한 여러 종류의 음원을 포함하는 데이터셋에 훈련시켜도 손상된 고대역을 복원할 수 있음을 확인하였다.

Deep learning based Person Re-identification with RGB-D sensors

  • Kim, Min;Park, Dong-Hyun
    • 한국컴퓨터정보학회논문지
    • /
    • 제26권3호
    • /
    • pp.35-42
    • /
    • 2021
  • 본 연구에서는 3차원 RGB-D Xtion2 카메라를 이용하여 보행자의 골격좌표를 추출한 결과를 바탕으로 동적인 특성(속도, 가속도)을 함께 고려하여 딥러닝 모델을 통해 사람을 인식하는 방법을 제안한다. 본 논문의 핵심목표는 RGB-D 카메라로 손쉽게 좌표를 추출하고 새롭게 생성한 동적인 특성을 기반으로 자체 고안한 1차원 합성곱 신경망 분류기 모델(1D-ConvNet)을 통해 자동으로 보행 패턴을 파악하는 것이다. 1D-ConvNet의 인식 정확도와 동적인 특성이 정확도에 미치는 영향을 알아보기 위한 실험을 수행하였다. 정확도는 F1 Score를 기준으로 측정하였고, 동적인 특성을 고려한 분류기 모델(JCSpeed)과 고려하지 않은 분류기 모델(JC)의 정확도 비교를 통해 영향력을 측정하였다. 그 결과 동적인 특성을 고려한 경우의 분류기 모델이 그렇지 않은 경우보다 F1 Score가 약 8% 높게 나타났다.

Efficient Semi-automatic Annotation System based on Deep Learning

  • Hyunseok Lee;Hwa Hui Shin;Soohoon Maeng;Dae Gwan Kim;Hyojeong Moon
    • 대한임베디드공학회논문지
    • /
    • 제18권6호
    • /
    • pp.267-275
    • /
    • 2023
  • This paper presents the development of specialized software for annotating volume-of-interest on 18F-FDG PET/CT images with the goal of facilitating the studies and diagnosis of head and neck cancer (HNC). To achieve an efficient annotation process, we employed the SE-Norm-Residual Layer-based U-Net model. This model exhibited outstanding proficiency to segment cancerous regions within 18F-FDG PET/CT scans of HNC cases. Manual annotation function was also integrated, allowing researchers and clinicians to validate and refine annotations based on dataset characteristics. Workspace has a display with fusion of both PET and CT images, providing enhance user convenience through simultaneous visualization. The performance of deeplearning model was validated using a Hecktor 2021 dataset, and subsequently developed semi-automatic annotation functionalities. We began by performing image preprocessing including resampling, normalization, and co-registration, followed by an evaluation of the deep learning model performance. This model was integrated into the software, serving as an initial automatic segmentation step. Users can manually refine pre-segmented regions to correct false positives and false negatives. Annotation images are subsequently saved along with their corresponding 18F-FDG PET/CT fusion images, enabling their application across various domains. In this study, we developed a semi-automatic annotation software designed for efficiently generating annotated lesion images, with applications in HNC research and diagnosis. The findings indicated that this software surpasses conventional tools, particularly in the context of HNC-specific annotation with 18F-FDG PET/CT data. Consequently, developed software offers a robust solution for producing annotated datasets, driving advances in the studies and diagnosis of HNC.

Vehicle Manufacturer Recognition using Deep Learning and Perspective Transformation

  • Ansari, Israfil;Shim, Jaechang
    • Journal of Multimedia Information System
    • /
    • 제6권4호
    • /
    • pp.235-238
    • /
    • 2019
  • In real world object detection is an active research topic for understanding different objects from images. There are different models presented in past and had significant results. In this paper we are presenting vehicle logo detection using previous object detection models such as You only look once (YOLO) and Faster Region-based CNN (F-RCNN). Both the front and rear view of the vehicles were used for training and testing the proposed method. Along with deep learning an image pre-processing algorithm called perspective transformation is proposed for all the test images. Using perspective transformation, the top view images were transformed into front view images. This algorithm has higher detection rate as compared to raw images. Furthermore, YOLO model has better result as compare to F-RCNN model.

Multiple Plankton Detection and Recognition in Microscopic Images with Homogeneous Clumping and Heterogeneous Interspersion

  • Soh, Youngsung;Song, Jaehyun;Hae, Yongsuk
    • 융합신호처리학회논문지
    • /
    • 제19권2호
    • /
    • pp.35-41
    • /
    • 2018
  • The analysis of plankton species distribution in sea or fresh water is very important in preserving marine ecosystem health. Since manual analysis is infeasible, many automatic approaches were proposed. They usually use images from in situ towed underwater imaging sensor or specially designed, lab mounted microscopic imaging system. Normally they assume that only single plankton is present in an image so that, if there is a clumping among multiple plankton of same species (homogeneous clumping) or if there are multiple plankton of different species scattered in an image (heterogeneous interspersion), they have a difficulty in recognition. In this work, we propose a deep learning based method that can detect and recognize individual plankton in images with homogeneous clumping, heterogeneous interspersion, or combination of both.

딥러닝 기반 산업현장 고소작업자 행동분석 시스템 (Deep Learning based Behavior Analysis System for High Rise Worker at Industrial Field.)

  • 이세훈;문효재;유진환;김현우;염대훈
    • 한국컴퓨터정보학회:학술대회논문집
    • /
    • 한국컴퓨터정보학회 2018년도 제57차 동계학술대회논문집 26권1호
    • /
    • pp.51-52
    • /
    • 2018
  • 산업 현장에서 작업자의 잘못된 작업행동으로 인한 안전사고가 꾸준히 발생하고 있다. 현재는 관리자가 육안으로 작업자의 위험행동 여부를 관리하고 있지만, 모든 작업자를 관리자 한명이 관리하기에는 현실적으로 어려움이 있다. 본 논문에서는 이 문제를 해결하기 위해 고소 작업자의 안전벨트에 IoT 장치를 부착하여 행동 데이터를 클라우드에 업로드하고, 딥러닝을 통해 작업자 위험행동 여부를 분석한다. 분석한 결과를 관리자가 쉽게 모니터링 할 수 있도록 하여, 안전사고를 예방하도록 하는 시스템을 설계하였다.

  • PDF

딥러닝을 통한 움직이는 객체 검출 알고리즘 구현 (Implementation of Moving Object Recognition based on Deep Learning)

  • 이유경;이용환
    • 반도체디스플레이기술학회지
    • /
    • 제17권2호
    • /
    • pp.67-70
    • /
    • 2018
  • Object detection and tracking is an exciting and interesting research area in the field of computer vision, and its technologies have been widely used in various application systems such as surveillance, military, and augmented reality. This paper proposes and implements a novel and more robust object recognition and tracking system to localize and track multiple objects from input images, which estimates target state using the likelihoods obtained from multiple CNNs. As the experimental result, the proposed algorithm is effective to handle multi-modal target appearances and other exceptions.

딥러닝 기반 어선조업종류 판별 방법 (Deep-learning based Fishing Gear Type Classification)

  • 김광일;김지희
    • 한국컴퓨터정보학회:학술대회논문집
    • /
    • 한국컴퓨터정보학회 2019년도 제60차 하계학술대회논문집 27권2호
    • /
    • pp.33-34
    • /
    • 2019
  • 대부분의 나라에서는 어선의 위치발신장치를 이용하여 어선 조업상황을 모니터링 한다. 우리나라도 어선의 위치발신장치를 이용하여 어선 조업량, 불법조업 유무를 판별한다. 현재까지는 어선의 불법조업 유무 판별은 어선의 위치정보 기반으로 이루어 졌으나, 허가받지 않는 어구를 사용하는 불법조업에 대한 판별은 불가능 하였다. 이에 본 논문에서는 어선 항적과 조업면허 데이터를 이용하여 데이터 기반의 어선 조업 판별모델을 개발하고자 한다. 이를 위해 어선 항적데이터를 시계열 단위로 전처리하여 학습 이미지들을 생성하고, 해당 어선의 조업면허 정보를 레이블로 하여 학습 데이터를 제안하는 딥러닝 모델에 적용한다. 제안하는 방법의 검증을 위해 1년 동안 제주 주변해역에서 조업하는 어선의 선박자동식별장치의 항적데이터를 수집하여 실험을 하였다. 실험 결과 제안한 방법의 분류정확도는 71.5%를 얻었다.

  • PDF