• 제목/요약/키워드: Deep Convolutional Neural Networks

검색결과 396건 처리시간 0.032초

자동문서분류를 위한 텐서공간모델 기반 심층 신경망 (A Tensor Space Model based Deep Neural Network for Automated Text Classification)

  • 임푸름;김한준
    • 데이타베이스연구회지:데이타베이스연구
    • /
    • 제34권3호
    • /
    • pp.3-13
    • /
    • 2018
  • 자동문서분류(Text Classification)는 주어진 텍스트 문서를 이에 적합한 카테고리로 분류하는 텍스트 마이닝 기술 중의 하나로서 스팸메일 탐지, 뉴스분류, 자동응답, 감성분석, 쳇봇 등 다양한 분야에 활용되고 있다. 일반적으로 자동문서분류 시스템은 기계학습 알고리즘을 활용하며, 이 중에서 텍스트 데이터에 적합한 알고리즘인 나이브베이즈(Naive Bayes), 지지벡터머신(Support Vector Machine) 등이 합리적 수준의 성능을 보이는 것으로 알려져 있다. 최근 딥러닝 기술의 발전에 따라 자동문서분류 시스템의 성능을 개선하기 위해 순환신경망(Recurrent Neural Network)과 콘볼루션 신경망(Convolutional Neural Network)을 적용하는 연구가 소개되고 있다. 그러나 이러한 최신 기법들이 아직 완벽한 수준의 문서분류에는 미치지 못하고 있다. 본 논문은 그 이유가 텍스트 데이터가 단어 차원 중심의 벡터로 표현되어 텍스트에 내재한 의미 정보를 훼손하는데 주목하고, 선행 연구에서 그 효능이 검증된 시멘틱 텐서공간모델에 기반하여 심층 신경망 아키텍처를 제안하고 이를 활용한 문서분류기의 성능이 대폭 상승함을 보인다.

Estimation of tomato maturity as a continuous index using deep neural networks

  • Taehyeong Kim;Dae-Hyun Lee;Seung-Woo Kang;Soo-Hyun Cho;Kyoung-Chul Kim
    • 농업과학연구
    • /
    • 제49권4호
    • /
    • pp.785-793
    • /
    • 2022
  • In this study, tomato maturity was estimated based on deep learning for a harvesting robot. Tomato images were obtained using a RGB camera installed on a monitoring robot, which was developed previously, and the samples were cropped to 128 × 128 size images to generate a dataset for training the classification model. The classification model was constructed based on convolutional neural networks, and the mean-variance loss was used to learn implicitly the distribution of the data features by class. In the test stage, the tomato maturity was estimated as a continuous index, which has a range of 0 to 1, by calculating the expected class value. The results show that the F1-score of the classification was approximately 0.94, and the performance was similar to that of a deep learning-based classification task in the agriculture field. In addition, it was possible to estimate the distribution in each maturity stage. From the results, it was found that our approach can not only classify the discrete maturation stages of the tomatoes but also can estimate the continuous maturity.

Deep Adversarial Residual Convolutional Neural Network for Image Generation and Classification

  • Haque, Md Foysal;Kang, Dae-Seong
    • 한국정보기술학회 영문논문지
    • /
    • 제10권1호
    • /
    • pp.111-120
    • /
    • 2020
  • Generative adversarial networks (GANs) achieved impressive performance on image generation and visual classification applications. However, adversarial networks meet difficulties in combining the generative model and unstable training process. To overcome the problem, we combined the deep residual network with upsampling convolutional layers to construct the generative network. Moreover, the study shows that image generation and classification performance become more prominent when the residual layers include on the generator. The proposed network empirically shows that the ability to generate images with higher visual accuracy provided certain amounts of additional complexity using proper regularization techniques. Experimental evaluation shows that the proposed method is superior to image generation and classification tasks.

Wavelet-like convolutional neural network structure for time-series data classification

  • Park, Seungtae;Jeong, Haedong;Min, Hyungcheol;Lee, Hojin;Lee, Seungchul
    • Smart Structures and Systems
    • /
    • 제22권2호
    • /
    • pp.175-183
    • /
    • 2018
  • Time-series data often contain one of the most valuable pieces of information in many fields including manufacturing. Because time-series data are relatively cheap to acquire, they (e.g., vibration signals) have become a crucial part of big data even in manufacturing shop floors. Recently, deep-learning models have shown state-of-art performance for analyzing big data because of their sophisticated structures and considerable computational power. Traditional models for a machinery-monitoring system have highly relied on features selected by human experts. In addition, the representational power of such models fails as the data distribution becomes complicated. On the other hand, deep-learning models automatically select highly abstracted features during the optimization process, and their representational power is better than that of traditional neural network models. However, the applicability of deep-learning models to the field of prognostics and health management (PHM) has not been well investigated yet. This study integrates the "residual fitting" mechanism inherently embedded in the wavelet transform into the convolutional neural network deep-learning structure. As a result, the architecture combines a signal smoother and classification procedures into a single model. Validation results from rotor vibration data demonstrate that our model outperforms all other off-the-shelf feature-based models.

Human Gait Recognition Based on Spatio-Temporal Deep Convolutional Neural Network for Identification

  • Zhang, Ning;Park, Jin-ho;Lee, Eung-Joo
    • 한국멀티미디어학회논문지
    • /
    • 제23권8호
    • /
    • pp.927-939
    • /
    • 2020
  • Gait recognition can identify people's identity from a long distance, which is very important for improving the intelligence of the monitoring system. Among many human features, gait features have the advantages of being remotely available, robust, and secure. Traditional gait feature extraction, affected by the development of behavior recognition, can only rely on manual feature extraction, which cannot meet the needs of fine gait recognition. The emergence of deep convolutional neural networks has made researchers get rid of complex feature design engineering, and can automatically learn available features through data, which has been widely used. In this paper,conduct feature metric learning in the three-dimensional space by combining the three-dimensional convolution features of the gait sequence and the Siamese structure. This method can capture the information of spatial dimension and time dimension from the continuous periodic gait sequence, and further improve the accuracy and practicability of gait recognition.

딥 뉴럴네트워크 기반의 소리 이벤트 검출 (Sound Event Detection based on Deep Neural Networks)

  • 정석환;정용주
    • 한국전자통신학회논문지
    • /
    • 제14권2호
    • /
    • pp.389-396
    • /
    • 2019
  • 본 논문에서는 다양한 구조의 딥 뉴럴 네트워크를 소리 이벤트 검출을 위하여 적용하였으며 공통의 오디오 데이터베이스를 이용하여 그들 간의 성능을 비교하였다. FNN, CNN, RNN 그리고 CRNN이 주어진 오디오데이터베이스 및 딥 뉴럴 네트워크의 구조에 최적화된 하이퍼파라미터 값을 이용하여 구현되었다. 구현된 방식 중에서 CRNN이 모든 테스트 환경에서 가장 좋은 성능을 보였으며 그 다음으로 CNN의 성능이 우수함을 알 수 있었다. RNN은 오디오 신호에서의 시간 상관관계를 잘 추적하는 장점에도 불구하고 CNN 과 CRNN에 비해서 저조한 성능을 보임을 확인할 수 있었다.

심층 학습 모델을 이용한 EPS 동작 신호의 인식 (EPS Gesture Signal Recognition using Deep Learning Model)

  • 이유라;김수형;김영철;나인섭
    • 스마트미디어저널
    • /
    • 제5권3호
    • /
    • pp.35-41
    • /
    • 2016
  • 본 논문에서는 심층 학습 모델 방법을 이용하여 EPS(Electronic Potential Sensor) 기반의 손동작 신호를 인식하는 시스템을 제안한다. 전기장 기반 센서인 EPS로부터 추출된 신호는 다량의 잡음이 포함되어 있어 이를 제거하는 전처리과정을 거쳐야 한다. 주파수 대역 특징 필터를 이용한 잡음 제거한 후, 신호는 시간에 따른 전압(Voltage) 값만 가지는 1차원적 특징을 지닌다. 2차원 데이터를 입력으로 하여 컨볼루션 연산을 하는 알고리즘에 적합한 형태를 갖추기 위해 신호는 차원 변형을 통해 재구성된다. 재구성된 신호데이터는 여러 계층의 학습 층(layer)을 가지는 심층 학습 기반의 모델을 통해 분류되어 최종 인식된다. 기존 확률 기반 통계적 모델링 알고리즘은 훈련 후 모델을 생성하는 과정에서 초기 파라미터에 결과가 좌우되는 어려움이 있었다. 심층 학습 기반 모델은 학습 층을 쌓아 훈련을 반복하므로 이를 극복할 수 있다. 실험에서, 제안된 심층 학습 기반의 서로 다른 구조를 가지는 컨볼루션 신경망(Convolutional Neural Networks), DBN(Deep Belief Network) 알고리즘과 통계적 모델링 기반의 방법을 이용한 인식 결과의 성능을 비교하였고, 컨볼루션 신경망 알고리즘이 다른 알고리즘에 비해 EPS 동작신호 인식에서 보다 우수한 성능을 나타냄을 보였다.

DeepLabCut과 Mask R-CNN 기반 반려동물 행동 분류 설계 (Design of Pet Behavior Classification Method Based On DeepLabCut and Mask R-CNN)

  • 권주영;신민찬;문남미
    • 한국정보처리학회:학술대회논문집
    • /
    • 한국정보처리학회 2021년도 추계학술발표대회
    • /
    • pp.927-929
    • /
    • 2021
  • 최근 펫팸족(Pet-Family)과 같이 반려동물을 가족처럼 생각하는 가구가 증가하면서 반려동물 시장이 크게 성장하고 있다. 이러한 이유로 본 논문에서는 반려동물의 객체 식별을 통한 객체 분할과 신체 좌표추정에 기반을 둔 반려동물의 행동 분류 방법을 제안한다. 이 방법은 CCTV를 통해 반려동물 영상 데이터를 수집한다. 수집된 영상 데이터는 반려동물의 인스턴스 분할을 위해 Mask R-CNN(Region Convolutional Neural Networks) 모델을 적용하고, DeepLabCut 모델을 통해 추정된 신체 좌푯값을 도출한다. 이 결과로 도출된 영상 데이터와 추정된 신체 좌표 값은 CNN(Convolutional Neural Networks)-LSTM(Long Short-Term Memory) 모델을 적용하여 행동을 분류한다. 본 모델을 바탕으로 행동을 분석 및 분류하여, 반려동물의 위험 상황과 돌발 행동에 대한 올바른 대처를 제공할 수 있는 기반을 제공할 것이라 기대한다.

얼굴인식 성능 향상을 위한 얼굴 전역 및 지역 특징 기반 앙상블 압축 심층합성곱신경망 모델 제안 (Compressed Ensemble of Deep Convolutional Neural Networks with Global and Local Facial Features for Improved Face Recognition)

  • 윤경신;최재영
    • 한국멀티미디어학회논문지
    • /
    • 제23권8호
    • /
    • pp.1019-1029
    • /
    • 2020
  • In this paper, we propose a novel knowledge distillation algorithm to create an compressed deep ensemble network coupled with the combined use of local and global features of face images. In order to transfer the capability of high-level recognition performances of the ensemble deep networks to a single deep network, the probability for class prediction, which is the softmax output of the ensemble network, is used as soft target for training a single deep network. By applying the knowledge distillation algorithm, the local feature informations obtained by training the deep ensemble network using facial subregions of the face image as input are transmitted to a single deep network to create a so-called compressed ensemble DCNN. The experimental results demonstrate that our proposed compressed ensemble deep network can maintain the recognition performance of the complex ensemble deep networks and is superior to the recognition performance of a single deep network. In addition, our proposed method can significantly reduce the storage(memory) space and execution time, compared to the conventional ensemble deep networks developed for face recognition.

Text Classification Using Parallel Word-level and Character-level Embeddings in Convolutional Neural Networks

  • Geonu Kim;Jungyeon Jang;Juwon Lee;Kitae Kim;Woonyoung Yeo;Jong Woo Kim
    • Asia pacific journal of information systems
    • /
    • 제29권4호
    • /
    • pp.771-788
    • /
    • 2019
  • Deep learning techniques such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) show superior performance in text classification than traditional approaches such as Support Vector Machines (SVMs) and Naïve Bayesian approaches. When using CNNs for text classification tasks, word embedding or character embedding is a step to transform words or characters to fixed size vectors before feeding them into convolutional layers. In this paper, we propose a parallel word-level and character-level embedding approach in CNNs for text classification. The proposed approach can capture word-level and character-level patterns concurrently in CNNs. To show the usefulness of proposed approach, we perform experiments with two English and three Korean text datasets. The experimental results show that character-level embedding works better in Korean and word-level embedding performs well in English. Also the experimental results reveal that the proposed approach provides better performance than traditional CNNs with word-level embedding or character-level embedding in both Korean and English documents. From more detail investigation, we find that the proposed approach tends to perform better when there is relatively small amount of data comparing to the traditional embedding approaches.