• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.9
• /
• pp.2361-2376
• /
• 2023

The electrocardiogram (ECG) signal is commonly used to screen and diagnose cardiovascular diseases. In recent years, deep neural networks have been regarded as an effective way for automatic ECG disease diagnosis. The convolutional neural network is widely used for ECG signal extraction because it can obtain different levels of information. However, most previous studies adopt single scale convolution filters to extract ECG signal features, ignoring the complementarity between ECG signal features of different scales. In the paper, we propose a dual-scale network with convolution filters of different sizes for 12-lead ECG classification. Our model can extract and fuse ECG signal features of different scales. In addition, different spatial and time periods of the feature map obtained from the 12-lead ECG may have different contributions to ECG classification. Therefore, we add a spatial-temporal attention to each scale sub-network to emphasize the representative local spatial and temporal features. Our approach is evaluated on PTB-XL dataset and achieves 0.9307, 0.8152, and 89.11 on macro-averaged ROC-AUC score, a maximum F1 score, and mean accuracy, respectively. The experiment results have proven that our approach outperforms the baselines.

• ETRI Journal
• /
• v.42 no.2
• /
• pp.230-238
• /
• 2020

Human-object interaction (HOI) detection is a popular computer vision task that detects interactions between humans and objects. This task can be useful in many applications that require a deeper understanding of semantic scenes. Current HOI detection networks typically consist of a feature extractor followed by detection layers comprising small filters (eg, 1 × 1 or 3 × 3). Although small filters can capture local spatial features with a few parameters, they fail to capture larger context information relevant for recognizing interactions between humans and distant objects owing to their small receptive regions. Hence, we herein propose a three-stream HOI detection network that employs a context convolution module (CCM) in each stream branch. The CCM can capture larger contexts from input feature maps by adopting combinations of large separable convolution layers and residual-based convolution layers without increasing the number of parameters by using fewer large separable filters. We evaluate our HOI detection method using two benchmark datasets, V-COCO and HICO-DET, and demonstrate its state-of-the-art performance.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.2E
• /
• pp.51-59
• /
• 2009

Mutual radiation impedance becomes more important in the design and analysis of acoustic transducers for higher power, better beam pattern, and wider bandwidth at low frequency sonar systems. This review paper focused on literature survey about the researches of mutual radiation impedance in the acoustic transducer arrays over 60 years. The papers of mutual radiation impedance were summarized in terms of transducer array structures on various baffle geometries such as planar, cylindrical, spherical, conformal, spheroidal, and elliptic cylindrical arrays. Then the computation schemes of solving conventional quadruple integral in the definition of mutual radiation impedance were surveyed including spatial convolution method, which reduces the quadruple integral to a double integral for efficient computation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.8
• /
• pp.2053-2067
• /
• 2023

This paper proposes two video quality assessment methods based on deep neural network. (i)The first method uses the IQF-CNN (convolution neural network based on image quality features) to build image quality assessment method. The LIVE image database is used to test this method, the experiment show that it is effective. Therefore, this method is extended to the video quality assessment. At first every image frame of video is predicted, next the relationship between different image frames are analyzed by the hysteresis function and different window function to improve the accuracy of video quality assessment. (ii)The second method proposes a video quality assessment method based on convolution neural network (CNN) and gated circular unit network (GRU). First, the spatial features of video frames are extracted using CNN network, next the temporal features of the video frame using GRU network. Finally the extracted temporal and spatial features are analyzed by full connection layer of CNN network to obtain the video quality assessment score. All the above proposed methods are verified on the video databases, and compared with other methods.

• Journal of Environmental Science International
• /
• v.8 no.3
• /
• pp.299-307
• /
• 1999

In order to fast predict the wind-driven current in a small bay, a convolution method in which the wind-driven current can be generated only with the local wind is developed and applied in the idealized bay and the idealized Sachon Bay. The accuracy of the convlution method is assessed through a series of the numerical experiements carried out in the jidealized bay and the idealized Sachon Bay. The optimum response function for the convolution method is obtained by minimizing the root man square (rms) difference between the current given by the numerical model and the current given by the convolution method. The north-south component of the response function shows simultaneous fluctuations in the wind and wind-driven current at marginal region while it shows "sea-saw" fluctuations (in which the wind and wind-driven current have opposite direction) at the central region in the idealized Sachon Bay. The present wind is strong enough to influence on the wind-driven current especially in the idealized Sachon Bay. The spatial average of the rms ratio defined as the ratio of the rms error to the rms speed is 0.05 in the idealized bay and 0.26 in the idealized Sachon Bay. The recover rate of kinetic energy(rrke) is 99% in the idealized bay and 94% in the idealized Sachon Bay. Thus, the predicted wind-driven current by the convolution model is in a good agreement with the computed one by the numerical model in the idealized bay and the idealized Sachon Bay.achon Bay.

• Journal of Environmental Science International
• /
• v.8 no.3
• /
• pp.309-318
• /
• 1999

In order to fast predict the wind-driven current in a small bay, a convolution method in which the wind-driven current can be generated only wih the local wind is developed and applied in the Sachon Bay. The root mean square(rms) ratio defined as the ratio of the rms error to the rms speed is 0.37. The rms ratio is generally less than 0.2, except for all the mouths of Junju Bay and Namhae-do and in the region between Saryang Island and Sachon. The spatial average of the recover rate of kinetic energy(rrke) is 87%. Thus, the predicted wind-driven current by the convolution model is in a good agreement with the computed one by the numerical model. The raio of the difference between observed residual current (Vr) and predicted wind-driven current (Vc) to a residual current, that is, (Vr-Vc)/Vr shows 56%, 62% at 2 moorings in the Sachon Bay.

• Smart Structures and Systems
• /
• v.30 no.6
• /
• pp.601-612
• /
• 2022

The prediction of structural mechanical behaviors is vital important to early perceive the abnormal conditions and avoid the occurrence of disasters. Especially for underground engineering, complex geological conditions make the structure more prone to disasters. Aiming at solving the problems existing in previous studies, such as incomplete consideration factors and can only predict the continuous performance, the deep attention fused temporal convolution network (DATCN) is proposed in this paper to predict the spatial mechanical behaviors of structure, which integrates both the temporal effect and spatial effect and realize the cross-time prediction. The temporal convolution network (TCN) and self-attention mechanism are employed to learn the temporal correlation of each monitoring point and the spatial correlation among different points, respectively. Then, the predicted result obtained from DATCN is compared with that obtained from some classical baselines, including SVR, LR, MLP, and RNNs. Also, the parameters involved in DATCN are discussed to optimize the prediction ability. The prediction result demonstrates that the proposed DATCN model outperforms the state-of-the-art baselines. The prediction accuracy of DATCN model after 24 hours reaches 90 percent. Also, the performance in last 14 hours plays a domain role to predict the short-term behaviors of the structure. As a study case, the proposed model is applied in an underwater shield tunnel to predict the stress variation of concrete segments in space.

• Journal of the Korea Convergence Society
• /
• v.12 no.12
• /
• pp.31-37
• /
• 2021

In this paper proposed a feature fusion and spatial attention-based modified YOLOv4S for small and occluded detection. Conventional YOLOv4S is a lightweight network and lacks feature extraction capability compared to the method of the deep network. The proposed method first combines feature maps of different scales with feature fusion to enhance semantic and low-level information. In addition expanding the receptive field with dilated convolution, the detection accuracy for small and occluded objects was improved. Second by improving the conventional spatial information with spatial attention, the detection accuracy of objects classified and occluded between objects was improved. PASCAL VOC and COCO datasets were used for quantitative evaluation of the proposed method. The proposed method improved mAP by 2.7% in the PASCAL VOC dataset and 1.8% in the COCO dataset compared to the Conventional YOLOv4S.

• Journal of the Korea Convergence Society
• /
• v.11 no.12
• /
• pp.15-22
• /
• 2020

In this paper, we proposed a deep learning based super-resolution method that combines Channel Attention and Spatial Attention feature enhancement methods. It is important to restore high-frequency components, such as texture and features, that have large changes in surrounding pixels during super-resolution processing. We proposed a super-resolution method using feature enhancement that combines Channel Attention and Spatial Attention. The existing CNN (Convolutional Neural Network) based super-resolution method has difficulty in deep network learning and lacks emphasis on high frequency components, resulting in blurry contours and distortion. In order to solve the problem, we used an emphasis block that combines Channel Attention and Spatial Attention to which Skip Connection was applied, and a Residual Block. The emphasized feature map extracted by the method was extended through Sub-pixel Convolution to obtain the super resolution. As a result, about PSNR improved by 5%, SSIM improved by 3% compared with the conventional SRCNN, and by comparison with VDSR, about PSNR improved by 2% and SSIM improved by 1%.

• Journal of Internet of Things and Convergence
• /
• v.8 no.2
• /
• pp.79-84
• /
• 2022

This paper presents an enhancement method of document restoration capability which is robust for security, loss, and contamination, It is based on two methods, that is, encryption and DnCNN(DeNoise Convolution Neural Network). In order to implement this encryption method, a mathematical model is applied as a spatial frequency transfer function used in optics of 2D image information. Then a method is proposed with optical interference patterns as encryption using spatial frequency transfer functions and using mathematical variables of spatial frequency transfer functions as ciphers. In addition, by applying the DnCNN method which is bsed on deep learning technique, the restoration capability is enhanced by removing noise. With an experimental evaluation, with 65% information loss, by applying Pre-Training DnCNN Deep Learning, the peak signal-to-noise ratio (PSNR) shows 11% or more superior in compared to that of the spatial frequency transfer function only. In addition, it is confirmed that the characteristic of CC(Correlation Coefficient) is enhanced by 16% or more.