• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권8호
• /
• pp.4026-4040
• /
• 2019

In this paper, we present an approach for detecting slide transitions in lecture videos by introducing the spatio-temporal residual networks. Given a lecture video which records the digital slides, the speaker, and the audience by multiple cameras, our goal is to find keyframes where slide content changes. Since temporal dependency among video frames is important for detecting slide changes, 3D Convolutional Networks has been regarded as an efficient approach to learn the spatio-temporal features in videos. However, 3D ConvNet will cost much training time and need lots of memory. Hence, we utilize ResNet to ease the training of network, which is easy to optimize. Consequently, we present a novel ConvNet architecture based on 3D ConvNet and ResNet for slide transition detection in lecture videos. Experimental results show that the proposed novel ConvNet architecture achieves the better accuracy than other slide progression detection approaches.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권5호
• /
• pp.1431-1445
• /
• 2022

We construct a deep neural network model named ECGResNet. This model can diagnosis diseases based on 12-lead ECG data of eight common cardiovascular diseases with a high accuracy. We chose the 16 Blocks of ResNet50 as the main body of the model and added the Squeeze-and-Excitation module to learn the data information between channels adaptively. We modified the first convolutional layer of ResNet50 which has a convolutional kernel of 7 to a superposition of convolutional kernels of 8 and 16 as our feature extraction method. This way allows the model to focus on the overall trend of the ECG signal while also noticing subtle changes. The model further improves the accuracy of cardiovascular and cerebrovascular disease classification by using a fully connected layer that integrates factors such as gender and age. The ECGResNet model adds Dropout layers to both the residual block and SE module of ResNet50, further avoiding the phenomenon of model overfitting. The model was eventually trained using a five-fold cross-validation and Flooding training method, with an accuracy of 95% on the test set and an F1-score of 0.841.We design a new deep neural network, innovate a multi-scale feature extraction method, and apply the SE module to extract features of ECG data.

• Current Optics and Photonics
• /
• 제7권5호
• /
• pp.511-517
• /
• 2023

Pipelines play an important role in urban water supply and drainage, oil and gas transmission, etc. This paper presents a technique for pattern recognition of fiber optic vibration signals collected by a distributed vibration sensing (DVS) system using a deep learning residual network (ResNet). The optical fiber is laid on the pipeline, and the signal is collected by the DVS system and converted into a 64 × 64 single-channel grayscale image. The grayscale image is input into the ResNet to extract features, and finally the K-nearest-neighbors (KNN) algorithm is used to achieve the classification and recognition of pipeline damage.

• 한국컴퓨터정보학회논문지
• /
• 제25권5호
• /
• pp.11-18
• /
• 2020

본 연구는 컨베이어 시스템에서 딥러닝을 이용한 배출구 막힘 판단 기술에 대하여 제안한다. 제안 방법은 산업 현장의 CCTV에서 수집한 영상을 이용하여 배출구 막힘 판단을 위한 다양한 CNN 모델들을 학습시키고, 성능이 가장 좋은 모델을 사용하여 실제 공정에 적용하는 것을 목적으로 한다. CNN 모델로는 잘 알려진 VGGNet, ResNet, DenseNet, 그리고 NASNet을 사용하였으며, 모델 학습과 성능 테스트를 위하여 CCTV에서 수집한 18,000장의 영상을 이용하였다. 다양한 모델에 대한 실험 결과, VGGNet은 99.89%의 정확도와 29.05ms의 처리 시간으로 가장 좋은 성능을 보였으며, 이로부터 배출구 막힘 판단 문제에 VGGNet이 가장 적합함을 확인하였다.

• 한국컴퓨터정보학회논문지
• /
• 제23권4호
• /
• pp.147-153
• /
• 2018

In this paper, we propose an efficient WBC 14-Diff classification which performs using the WBC-ResNet-152, a type of CNN model. The main point of view is to use Super-pixel for the segmentation of the image of WBC, and to use ResNet for the classification of WBC. A total of 136,164 blood image samples (224x224) were grouped for image segmentation, training, training verification, and final test performance analysis. Image segmentation using super-pixels have different number of images for each classes, so weighted average was applied and therefore image segmentation error was low at 7.23%. Using the training data-set for training 50 times, and using soft-max classifier, TPR average of 80.3% for the training set of 8,827 images was achieved. Based on this, using verification data-set of 21,437 images, 14-Diff classification TPR average of normal WBCs were at 93.4% and TPR average of abnormal WBCs were at 83.3%. The result and methodology of this research demonstrates the usefulness of artificial intelligence technology in the blood cell image classification field. WBC-ResNet-152 based morphology approach is shown to be meaningful and worthwhile method. And based on stored medical data, in-depth diagnosis and early detection of curable diseases is expected to improve the quality of treatment.

• 스마트미디어저널
• /
• 제9권1호
• /
• pp.23-29
• /
• 2020

This paper presents an approach for dynamic hand gesture recognition by using algorithm based on 3D Convolutional Neural Network (3D_CNN), which is later extended to 3D Residual Networks (3D_ResNet), and the neural network based key frame selection. Typically, 3D deep neural network is used to classify gestures from the input of image frames, randomly sampled from a video data. In this work, to improve the classification performance, we employ key frames which represent the overall video, as the input of the classification network. The key frames are extracted by SegNet instead of conventional clustering algorithms for video summarization (VSUMM) which require heavy computation. By using a deep neural network, key frame selection can be performed in a real-time system. Experiments are conducted using 3D convolutional kernels such as 3D_CNN, Inflated 3D_CNN (I3D) and 3D_ResNet for gesture classification. Our algorithm achieved up to 97.8% of classification accuracy on the Cambridge gesture dataset. The experimental results show that the proposed approach is efficient and outperforms existing methods.

• Journal of Information Processing Systems
• /
• 제16권5호
• /
• pp.1145-1157
• /
• 2020

A convolution neural networks (CNNs) has demonstrated outstanding performance compared to other algorithms in the field of face recognition. Regarding the over-fitting problem of CNN, researchers have proposed a residual network to ease the training for recognition accuracy improvement. In this study, a novel face recognition model based on game theory for call-over in the classroom was proposed. In the proposed scheme, an image with multiple faces was used as input, and the residual network identified each face with a confidence score to form a list of student identities. Face tracking of the same identity or low confidence were determined to be the optimisation objective, with the game participants set formed from the student identity list. Game theory optimises the authentication strategy according to the confidence value and identity set to improve recognition accuracy. We observed that there exists an optimal mapping relation between face and identity to avoid multiple faces associated with one identity in the proposed scheme and that the proposed game-based scheme can reduce the error rate, as compared to the existing schemes with deeper neural network.

• 정보과학회 논문지
• /
• 제45권1호
• /
• pp.94-98
• /
• 2018

본 논문은 자율주행을 위한 실시간 의미론적 분할 방법으로 최적화된 심층 신경망 구조인 Wide Inception ResNet (WIR Net)을 제안한다. 신경망 구조는 Residual connection과 Inception module을 적용하여 특징을 추출하는 인코더와 Transposed convolution과 낮은 층의 특징 맵을 사용하여 해상도를 높이는 디코더로 구성하였고 ELU 활성화 함수를 적용함으로써 성능을 올렸다. 또한 신경망의 전체 층수를 줄이고 필터 수를 늘리는 방법을 통해 성능을 최적화하였다. 성능평가는 NVIDIA Geforce gtx 1080과 TX1 보드를 사용하여 주행환경의 Cityscapes 데이터에 대해 클래스와 카테고리별 IoU를 평가하였다. 실험 결과를 통해 클래스 IoU 53.4, 카테고리 IoU 81.8의 정확도와 TX1 보드에서 $640{\times}360$, $720{\times}480$ 해상도 영상처리에 17.8fps, 13.0fps의 실행속도를 보여주는 것을 확인하였다.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2023년도 제68차 하계학술대회논문집 31권2호
• /
• pp.519-520
• /
• 2023

본 논문에서는 최근 반려동물 등록제가 확대되고 있는 바, 기존의 마이크로 칩 삽입 방법을 회피하고 반려견 이미지를 통하여 개체를 인식하는 방법을 연구하였다. 반려견의 전체 이미지를 학습시켜 해당 개체를 식별하는 지능형 시스템을 ResNet 알고리즘을 이용하여 구현하고, 수집된 반려견의 개체 사진을 학습시켜 필요한 개체를 식별할 수 있도록 하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.3991-4007
• /
• 2022

In the public healthcare, a computational system that can automatically and efficiently detect and classify falls from a video sequence has significant potential. With the advancement of deep learning, which can extract temporal and spatial information, has become more widespread. However, traditional 3D CNNs that usually adopt shallow networks cannot obtain higher recognition accuracy than deeper networks. Additionally, some experiences of neural network show that the problem of gradient explosions occurs with increasing the network layers. As a result, an enhanced three-dimensional ResNet-based method for fall detection (3D-ERes-FD) is proposed to directly extract spatio-temporal features to address these issues. In our method, a 50-layer 3D residual network is used to deepen the network for improving fall recognition accuracy. Furthermore, enhanced residual units with four convolutional layers are developed to efficiently reduce the number of parameters and increase the depth of the network. According to the experimental results, the proposed method outperformed several state-of-the-art methods.