• Journal of Electrical Engineering and Technology
• /
• 제13권5호
• /
• pp.2099-2106
• /
• 2018

This study presents a novel approach of discriminative feature vectors based on manifold learning using nonlinear dimension reduction (DR) technique to improve loss function, and combine with the Adversarial examples to regularize the object function for image classification. The traditional convolutional neural networks (CNN) with many new regularization approach has been successfully used for image classification tasks, and it achieved good results, hence it costs a lot of Calculated spacing and timing. Significantly, distrinct from traditional CNN, we discriminate the feature vectors for objects without empirically-tuned parameter, these Discriminative features intend to remain the lower-dimensional relationship corresponding high-dimension manifold after projecting the image feature vectors from high-dimension to lower-dimension, and we optimize the constrains of the preserving local features based on manifold, which narrow the mapped feature information from the same class and push different class away. Using Adversarial examples, improved loss function with additional regularization term intends to boost the Robustness and generalization of neural network. experimental results indicate that the approach based on discriminative feature of manifold learning is not only valid, but also more efficient in image classification tasks. Furthermore, the proposed approach achieves competitive classification performances for three benchmark datasets : MNIST, CIFAR-10, SVHN.

• 한국인터넷방송통신학회논문지
• /
• 제19권1호
• /
• pp.145-152
• /
• 2019

본 논문에서는 딥러닝을 활용한 흔들림 영상 안정화 알고리즘을 제안하였다. 제안하는 알고리즘은 기존 몇 가지 2D, 2.5D 및 3D 기반 안정화 기술과 다르게 딥러닝을 활용한다. 제안하는 알고리즘은 흔들리는 영상을 CNN 네트워크 구조와 LSTM 네트워크 구조를 통한 특징 추출 및 비교하여 이전 프레임과 현재 프레임 간의 특징점 위치 차이를 통해 특징점의 이동 크기와 방향의 반대로 영상을 변환하는 알고리즘이다. 흔들림 안정화를 위한 알고리즘은 각 프레임의 특징 추출 및 비교를 위해 Tensorflow를 활용하여 CNN 네트워크과 LSTM 구조를 구현하였으며, 영상 흔들림 안정화는 OpenCV open source를 활용해 구현하였다. 실험결과 영상의 흔들림이 상하좌우로 흔들리는 영상과, 급격한 카메라 이동이 없는 영상을 실험에 사용하여, 제안한 알고리즘을 적용한 결과 사용한 상하좌우 흔들림 영상에서는 안정적인 흔들림 안정화 성능을 기대할 수 있었다.

• 한국정보전자통신기술학회논문지
• /
• 제13권6호
• /
• pp.605-610
• /
• 2020

소프트웨어 정의 네트워크가 확장성, 유연성, 네트워크상 프로그래밍이 가능한 특징으로 네트워크 관리에서 표준으로 자리잡아 가고 있지만 많은 장점에도 불구하고 하나의 컨트롤러에 대한 사이버 공격이 전체 네트워크를 영향을 주는 문제점을 가지고 있다. 특히, 컨트롤러에 대한 DDoS 공격이 대표적인 사례로서 다양한 공격 탐지 기술에 대한 연구가 진행되고 있다. 본 논문에서는 최초로 84개 DDoS 공격 Feature 데이터셋을 Kaggle에서 획득한 후 Permutation Feature Importance 알고리즘을 이용하여 상위 20의 중요도를 갖는 Feature를 선택하여 딥 러닝 기반의 CNN 모델에서 학습과 검증을 수행하였다. 이를 통해, 최적의 공격 탐지율을 갖는 상위 13개의 DDoS Feature 선택이 DDoS 공격 탐지율 96%을 유지하면서 적정한 공격 탐지 시간, 정확성 등에서 매우 우수한 결과를 제시하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권9호
• /
• pp.4412-4428
• /
• 2018

The purpose of this work is to solve the problem of representing an entire video using Convolutional Neural Network (CNN) features for human action recognition. Recently, due to insufficient GPU memory, it has been difficult to take the whole video as the input of the CNN for end-to-end learning. A typical method is to use sampled video frames as inputs and corresponding labels as supervision. One major issue of this popular approach is that the local samples may not contain the information indicated by the global labels and sufficient motion information. To address this issue, we propose a binary hashing method to enhance the local feature extractors. First, we extract the local features and aggregate them into global features using maximum/minimum pooling. Second, we use the binary hashing method to capture the motion features. Finally, we concatenate the hashing features with global features using different normalization methods to train the classifier. Experimental results on the JHMDB and MPII-Cooking datasets show that, for these new local features, binary hashing mapping on the sparsely sampled features led to significant performance improvements.

• 한국멀티미디어학회논문지
• /
• 제20권2호
• /
• pp.126-133
• /
• 2017

The conventional hand-crafted features used to track objects have limitations in object representation. Convolutional neural networks, which show good performance results in various areas of computer vision, are emerging as new ways to break through the limitations of feature extraction. CNN extracts the features of the image through layers of multiple layers, and learns the kernel used for feature extraction by itself. In this paper, we use the feature map extracted from the convolution layer of the convolution neural network to create an outline model of the object and use it for tracking. We propose a method to adaptively update the outline model to cope with various environment change factors affecting the tracking performance. The proposed algorithm evaluated the validity test based on the 11 environmental change attributes of the CVPR2013 tracking benchmark and showed excellent results in six attributes.

• 문화기술의 융합
• /
• 제3권4호
• /
• pp.171-175
• /
• 2017

최근 CNN(Convolutional Neural Network)의 구조가 복잡해지고 신견망의 깊이가 깊어지고 있다. 이에 따라 신경망의 학습에 요구되는 연산량 및 학습 시간이 증가하게 되었다. 최근 GPGPU 및 FPGA를 이용하여 신경망의 학습 속도를 가속화 하는 방법에 대한 연구가 활발히 진행되고 있다. 본 논문에서는 NVIDIA GPGPU를 제어하는 CUDA를 이용하여 CNN의 특징추출부와 분류부에 대한 연산을 가속화하는 방법을 제시한다. 특징추출부와 분류부에 대한 연산을 GPGPU의 블록 및 스레드로 할당하여 병렬로 처리하였다. 본 논문에서 제안하는 방법과 기존 CPU를 이용하여 CNN을 학습하여 학습 속도를 비교하였다. MNIST 데이터세트에 대하여 총 5 epoch을 학습한 결과 제안하는 방법이 CPU를 이용하여 학습한 방법에 비하여 약 314% 정도 학습 속도가 향상된 것을 확인하였다.

• 대한원격탐사학회지
• /
• 제37권4호
• /
• pp.719-731
• /
• 2021

This study proposes a two-stage hybrid classification model for crop classification using multi-temporal remote sensing images; the model combines feature embedding by using an autoencoder (AE) with a convolutional neural network (CNN) classifier to fully utilize features including informative temporal and spatial signatures. Long short-term memory (LSTM)-based AE (LAE) is fine-tuned using class label information to extract latent features that contain less noise and useful temporal signatures. The CNN classifier is then applied to effectively account for the spatial characteristics of the extracted latent features. A crop classification experiment with multi-temporal unmanned aerial vehicle images is conducted to illustrate the potential application of the proposed hybrid model. The classification performance of the proposed model is compared with various combinations of conventional deep learning models (CNN, LSTM, and convolutional LSTM) and different inputs (original multi-temporal images and features from stacked AE). From the crop classification experiment, the best classification accuracy was achieved by the proposed model that utilized the latent features by fine-tuned LAE as input for the CNN classifier. The latent features that contain useful temporal signatures and are less noisy could increase the class separability between crops with similar spectral signatures, thereby leading to superior classification accuracy. The experimental results demonstrate the importance of effective feature extraction and the potential of the proposed classification model for crop classification using multi-temporal remote sensing images.

• Journal of Information Processing Systems
• /
• 제19권6호
• /
• pp.842-857
• /
• 2023

Currently, most sentiment classification models on microblogging platforms analyze sentence parts of speech and emoticons without comprehending users' emotional inclinations and grasping moral nuances. This study proposes a hybrid sentiment analysis model. Given the distinct nature of microblog comments, the model employs a combined stop-word list and word2vec for word vectorization. To mitigate local information loss, the TextCNN model, devoid of pooling layers, is employed for local feature extraction, while BiLSTM is utilized for contextual feature extraction in deep learning. Subsequently, microblog comment sentiments are categorized using a classification layer. Given the binary classification task at the output layer and the numerous hidden layers within BiLSTM, the Tanh activation function is adopted in this model. Experimental findings demonstrate that the enhanced TextCNN-BiLSTM model attains a precision of 94.75%. This represents a 1.21%, 1.25%, and 1.25% enhancement in precision, recall, and F1 values, respectively, in comparison to the individual deep learning models TextCNN. Furthermore, it outperforms BiLSTM by 0.78%, 0.9%, and 0.9% in precision, recall, and F1 values.

• 한국ITS학회 논문지
• /
• 제19권5호
• /
• pp.178-188
• /
• 2020

본 논문에서는 split-attention 네트워크를 백본으로 특징을 추출하는 차선인식 CNN 네트워크를 제안한다. split-attention은 CNN의 특징 추출 과정에서 feature map의 각 channel에 가중치를 부여하는 방법으로, 빠르게 변화하는 자동차의 주행 환경에서 안정적으로 이미지의 특징을 추출할 수 있다. Tusimple 데이터 셋을 활용하여 본 논문에서 제안하는 네트워크를 학습·평가하였으며, 백본 네트워크의 레이어 수에 따른 성능 변화를 비교·분석 하였다. 평가 결과 최대 96.26%의 정확도로 최신 연구에 준하는 결과를 얻었으며, FP의 경우 0.0234(2.34%)로 비교 연구 중 가장 좋은 결과를 보여준다. 따라서, 실제 차량의 주행 환경 등에서도 본 연구에서 제안하는 모델을 사용하여 오인식 없이 안정적인 차선 인식이 가능하다.

• Journal of the Korean Wood Science and Technology
• /
• 제45권6호
• /
• pp.797-808
• /
• 2017

Automatic wood species identification systems have enabled fast and accurate identification of wood species outside of specialized laboratories with well-trained experts on wood species identification. Conventional automatic wood species identification systems consist of two major parts: a feature extractor and a classifier. Feature extractors require hand-engineering to obtain optimal features to quantify the content of an image. A Convolutional Neural Network (CNN), which is one of the Deep Learning methods, trained for wood species can extract intrinsic feature representations and classify them correctly. It usually outperforms classifiers built on top of extracted features with a hand-tuning process. We developed an automatic wood species identification system utilizing CNN models such as LeNet, MiniVGGNet, and their variants. A smartphone camera was used for obtaining macroscopic images of rough sawn surfaces from cross sections of woods. Five Korean softwood species (cedar, cypress, Korean pine, Korean red pine, and larch) were under classification by the CNN models. The highest and most stable CNN model was LeNet3 that is two additional layers added to the original LeNet architecture. The accuracy of species identification by LeNet3 architecture for the five Korean softwood species was 99.3%. The result showed the automatic wood species identification system is sufficiently fast and accurate as well as small to be deployed to a mobile device such as a smartphone.