• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.556-570
• /
• 2021

The existing video expression recognition methods mainly focus on the spatial feature extraction of video expression images, but tend to ignore the dynamic features of video sequences. To solve this problem, a multi-mode convolution neural network method is proposed to effectively improve the performance of facial expression recognition in video. Firstly, OpenFace 2.0 is used to detect face images in video, and two deep convolution neural networks are used to extract spatiotemporal expression features. Furthermore, spatial convolution neural network is used to extract the spatial information features of each static expression image, and the dynamic information feature is extracted from the optical flow information of multiple expression images based on temporal convolution neural network. Then, the spatiotemporal features learned by the two deep convolution neural networks are fused by multiplication. Finally, the fused features are input into support vector machine to realize the facial expression classification. Experimental results show that the recognition accuracy of the proposed method can reach 64.57% and 60.89%, respectively on RML and Baum-ls datasets. It is better than that of other contrast methods.

• Journal of the Economic Geographical Society of Korea
• /
• v.16 no.1
• /
• pp.50-70
• /
• 2013

The creation of new economic paradigm shift in creative economy age have influence on the characteristics of social networks and space, it leads to the formation of new relationship in space depending on social network service development. In this paper, it gives a name to 'social network resource' the power affecting these features and to find the meaning of spatial changes in the economic geography perspectives. 'Social network resource' shows the characteristics of openness, sharing, participation and cooperation, with features of encompassing all the features of local and global characteristics in space. This features are related the meaning of 'trans-locality' and can be found in the case of 'WikiSeoul.com (http:/www.wikiseoul.com)', Seoul's social knowledge sharing web platform. In particular, physical resources, human resources, information resources, and the characteristics of the relationship as a resource features was found and these features appear in space is projected to the space of social relations, it reflects the characteristics of qualitative space regarding social network resource.

• Journal of Computing Science and Engineering
• /
• v.9 no.4
• /
• pp.204-213
• /
• 2015

Under the conditional independence assumption among local features, the Naive Bayes Nearest Neighbor (NBNN) classifier has been recently proposed and performs classification without any training or quantization phases. While the original NBNN shows high classification accuracy without adopting an explicit training phase, the conditional independence among local features is against the compositionality of objects indicating that different, but related parts of an object appear together. As a result, the assumption of the conditional independence weakens the accuracy of classification techniques based on NBNN. In this work, we look into this issue, and propose a novel Bayesian network for an NBNN based classification to consider the conditional dependence among features. To achieve our goal, we extract a high-level feature and its corresponding, multiple low-level features for each image patch. We then represent them based on a simple, two-level layered Bayesian network, and design its classification function considering our Bayesian network. To achieve low memory requirement and fast query-time performance, we further optimize our representation and classification function, named relation-based Bayesian network, by considering and representing the relationship between a high-level feature and its low-level features into a compact relation vector, whose dimensionality is the same as the number of low-level features, e.g., four elements in our tests. We have demonstrated the benefits of our method over the original NBNN and its recent improvement, and local NBNN in two different benchmarks. Our method shows improved accuracy, up to 27% against the tested methods. This high accuracy is mainly due to consideration of the conditional dependences between high-level and its corresponding low-level features.

• Journal of the Speleological Society of Korea
• /
• no.88
• /
• pp.38-44
• /
• 2008

This study aims to identify the efficiency by applying diverse index to the positions of vertex in the network among the network analysis methods in order to identify the relational location features of caves. The first consideration was about the relational location features according to the linking degree and centrality of cave. The second consideration was about the structural equivalence between caves or between caves and the surrounding tourists attractions. A variety of index examined in this study is very efficient for identifying the positions of caves in the network. Furthermore, the relational location features in consideration of surrounding tourists attractions identified the availability of more objective and quantitative expression. In particular, when there are other caves around a cave, it is also very useful to identify the structural equivalence or comparison with other caves.

• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.11
• /
• pp.5580-5593
• /
• 2019

A malicious Uniform Resource Locator (URL) recognition and detection method based on the combination of Attention mechanism with Convolutional Neural Network and Long Short-Term Memory Network (Attention-Based CNN-LSTM), is proposed. Firstly, the WHOIS check method is used to extract and filter features, including the URL texture information, the URL string statistical information of attributes and the WHOIS information, and the features are subsequently encoded and pre-processed followed by inputting them to the constructed Convolutional Neural Network (CNN) convolution layer to extract local features. Secondly, in accordance with the weights from the Attention mechanism, the generated local features are input into the Long-Short Term Memory (LSTM) model, and subsequently pooled to calculate the global features of the URLs. Finally, the URLs are detected and classified by the SoftMax function using global features. The results demonstrate that compared with the existing methods, the Attention-based CNN-LSTM mechanism has higher accuracy for malicious URL detection.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.6
• /
• pp.198-207
• /
• 1996

A PSRI (position, scale, and rotation invariant ) feature extraction and automatic target recognition system using a cooperative network and an MLP is proposed. We can extract position invarient features by obtaining the target center using the projection and the moment in preprocessing stage. The scale and rotation invariant features are extracted from the contour projection of the number of edge pixels on each of the concentric circles, which is input to the cooperative network. By extracting the representative PSRI features form the features and their differentiations using max-net and min-net, we can rdduce the number of input neurons of the MLP, and make the resulted automatic target recognition system less sensitive to input variances. Experiments are conduted on various complex images which are shifted, rotated, or scaled, and the results show that the proposed system is very efficient for PSRI feature extractions and automatic target recognitions.

• Journal of Korea Multimedia Society
• /
• v.16 no.11
• /
• pp.1338-1347
• /
• 2013

Face recognition is a science of automatically identifying individuals based their unique facial features. In order to avoid overfitting and reduce the computational reduce the computational burden, a new face recognition algorithm using PCA-fisher linear discriminant (PCA-FLD) and fuzzy radial basis function neural network (RBFNN) is proposed in this paper. First, face features are extracted by the principal component analysis (PCA) method. Then, the extracted features are further processed by the Fisher's linear discriminant technique to acquire lower-dimensional discriminant patterns, the processed features will be considered as the input of the fuzzy RBFNN. As a widely applied algorithm in fuzzy RBF neural network, BP learning algorithm has the low rate of convergence, therefore, an improved learning algorithm based on Levenberg-Marquart (L-M) for fuzzy RBF neural network is introduced in this paper, which combined the Gradient Descent algorithm with the Gauss-Newton algorithm. Experimental results on the ORL face database demonstrate that the proposed algorithm has satisfactory performance and high recognition rate.

• Proceedings of the IEEK Conference
• /
• 2003.11b
• /
• pp.53-56
• /
• 2003

Ethernet is one of the most successful LAN technologies. Now gigabit ethernet is available in real network and some network interface cards(NIC) supports TCP segment offloading (TSO), IP checksum offloading(ICO), Jumbo frame and interrupt moderation. If we use this features appropriately, we obtain high throughput with low CPU utilization. This paper represents the network performance by varying above features.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.269-276
• /
• 2022

The robustness of a supply chain (i.e., the ability to cope with external and internal disruptions and disturbances) becomes more critical in ensuring the success of a construction project because the supply chain of today's construction project includes more and diverse suppliers. Previous studies indicate that topological features of the supply chain critically affect its robustness, but there is still a great challenge in characterizing and quantifying the impact of network topological features on its robustness. In this context, this study aims to identify network measures that characterize topological features of the supply chain and evaluate their impact on the robustness of the supply chain. Network centrality measures that are commonly used in assessing topological features in social network analysis are identified. Their validity in capturing the impact on the robustness of the supply chain was evaluated through an experiment using randomly generated networks and their simulations. Among those network centrality measures, the PageRank centrality and its standard deviation are found to have the strongest association with the robustness of the network, with a positive correlation coefficient of 0.6 at the node level and 0.74 at the network level. The findings in this study allows for the evaluation of the supply chain network's robustness based only on its topological design, thereby enabling practitioners to better design a robust supply chain and easily identify vulnerable links in their supply chains.