• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.276-278
• /
• 2022

All drugs have a specific action in the body, and in many cases, drugs are combinated due to complications or new symptoms during existing drug treatment. In this case, unexpected interactions may occur within the body. Therefore, predicting drug-drug interactions is a very important task for safe drug use. In this study, we propose a deep learning-based predictive model that learns using drug information documents to predict drug interactions that may occur when using multiple drugs. The drug information document was created by combining several properties such as the drug's mechanism of action, toxicity, and target using DrugBank data. And drug information document is pair with another drug documents and used as an input to a deep learning-based predictive model, and the model outputs the interaction between the two drugs. This study can be used to predict future interactions between new drug pairs by analyzing the differences in experimental results according to changes in various conditions.

• Journal of Korea Multimedia Society
• /
• v.24 no.10
• /
• pp.1380-1390
• /
• 2021

The video face recognition (FR) is one of the most popular researches in the field of computer vision due to a variety of applications. In particular, research using the attention mechanism is being actively conducted. In video face recognition, attention represents where to focus on by using the input value of the whole or a specific region, or which frame to focus on when there are many frames. In this paper, we propose a novel attention based deep learning method. Main novelties of our method are (1) the use of combining two loss functions, namely weighted Softmax loss function and a Triplet loss function and (2) the feasibility of end-to-end learning which includes the feature embedding network and attention weight computation. The feature embedding network has a positive effect on the attention weight computation by using combined loss function and end-to-end learning. To demonstrate the effectiveness of our proposed method, extensive and comparative experiments have been carried out to evaluate our method on IJB-A dataset with their standard evaluation protocols. Our proposed method represented better or comparable recognition rate compared to other state-of-the-art video FR methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.6
• /
• pp.1833-1848
• /
• 2022

Named entity recognition (NER) is an important basic task in the field of Natural Language Processing (NLP). Recently deep learning approaches by extracting word segmentation or character features have been proved to be effective for Chinese Named Entity Recognition (CNER). However, since this method of extracting features only focuses on extracting some of the features, it lacks textual information mining from multiple perspectives and dimensions, resulting in the model not being able to fully capture semantic features. To tackle this problem, we propose a novel Multi-view Semantic Feature Fusion Model (MSFM). The proposed model mainly consists of two core components, that is, Multi-view Semantic Feature Fusion Embedding Module (MFEM) and Multi-head Self-Attention Mechanism Module (MSAM). Specifically, the MFEM extracts character features, word boundary features, radical features, and pinyin features of Chinese characters. The acquired font shape, font sound, and font meaning features are fused to enhance the semantic information of Chinese characters with different granularities. Moreover, the MSAM is used to capture the dependencies between characters in a multi-dimensional subspace to better understand the semantic features of the context. Extensive experimental results on four benchmark datasets show that our method improves the overall performance of the CNER model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.9
• /
• pp.4023-4043
• /
• 2016

Network virtualization has been regarded as a core attribute of the Future Internet. In a network virtualization environment (NVE), multiple heterogeneous virtual networks can coexist on a shared substrate network. Thus, a substrate network failure may affect multiple virtual networks. In this case, it is increasingly critical to provide survivability for the virtual networks against the substrate network failures. Previous research focused on mechanisms that ensure the resilience of the virtual network. However, the resource efficiency is still important to make the mapping scheme practical. In this paper, we study the survivable virtual network embedding mechanisms against substrate link and node failure from the perspective of improving the resource efficiency. For substrate link survivability, we propose a load-balancing and re-configuration strategy to improve the acceptance ratio and bandwidth utilization ratio. For substrate node survivability, we develop a minimum cost heuristic based on a divided network model and a backup resource cost model, which can both satisfy the location constraints of virtual node and increase the sharing degree of the backup resources. Simulations are conducted to evaluate the performance of the solutions. The proposed load balancing and re-configuration strategy for substrate link survivability outperforms other approaches in terms of acceptance ratio and bandwidth utilization ratio. And the proposed minimum cost heuristic for substrate node survivability gets a good performance in term of acceptance ratio.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.3
• /
• pp.183-194
• /
• 2004

We propose a now watermarking scheme that can be used to embed multiple bits and also resilient to geometrical transforms such as scaling, rotation, and cropping, based on off - axis holographic watermark that allows multiple watermark recovery without original content(cover image). The holographic watermark is that Fourier transformed digital hologram is embedded into cover image in the spatial domain. The proposed method has not only increased robustness with a stronger embedding but also imprescriptibility of the watermark in the evaluation process. To compare with the convention기 scheme, the spread spectrum, we embedded and recovered maximum 1,024 bits that consist of binary number over PSNR(peak signal-to-noise ratio) 39dB. And also, we computed robustness with BER(bit error rate) corresponding the above attack

• Journal of The Korean Association For Science Education
• /
• v.31 no.6
• /
• pp.931-941
• /
• 2011

This study aimed to examine the effects of argument-based chemistry laboratory investigations using the Science Writing Heuristic (SWH) approach on students' use and embedding of multimodal representations in summary writing. Participants of this study were thirty-nine freshman students majoring in science education at a National University in Korea. Argument-based chemistry laboratory investigations using the SWH approach were implemented for twenty-three students enrolled in one cohort, and the traditional chemistry laboratory teaching was implemented for 16 students enrolled in the other cohort. Summary writing samples were collected from students before and after the implementation. Summary writing samples produced by students were examined using an analysis framework for examining the use and embeddedness of multimodal representations. Summary writing was categorized into one of verbal mode, symbolic mode, and visual mode. With regard to the embedding of multi-modal representations, summary writing samples were analyzed in terms of 'constructing understanding,' 'integrating multiple modes,' 'providing valid claims and evidence,' and 'representing multiple modes.' Data analysis shows that the students of the SWH group were better at utilizing and embedding multimodal representations in summary writing as they provided evidence supporting their claims. This study provides important implications on pre-service science teacher education.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.23 no.6 s.165
• /
• pp.968-978
• /
• 1999

The effective elastic properties of materials containing spherical inclusions were calculated by the elastic wave scattering theory. In the formulation additional scattering fields by the presence of random multiple scatterers that affects the effective properties were found by the single scattering approximation. In calculating the scattering fields the ensemble average on the displacements and strains inside the scatterer was found from the static approximation at long wavelength limit. The displacements were assumed to be equal to the incident field, while the strains were calculated by Eshelby's equivalent inclusion principle on the single inclusion problem. Four different models were considered and they reflected different degrees of multiple scattering effects based on the approximation introduced in the process of embedding the inclusion in the matrix. The expressions for the effective elastic constants were given in each model, and their relations to the results obtained from other scattering theory and elasticity theory were discussed. The theoretical predictions were compared with experimental results on the epoxy matrix composites containing tungsten particles of different sizes and volume fractions

• Journal of Korea Multimedia Society
• /
• v.20 no.2
• /
• pp.244-253
• /
• 2017

Reversible DNA watermarking is capable of continuous DNA storage and forgery prevention, and has the advantage of being able to analyze biological mutation processes by external watermarking by iterative process of concealment and restoration. In this paper, we propose a reversible DNA watermarking method based on histogram multiple shifting of noncoding DNA sequence that can prevent false start codon, maintain original sequence length, maintain high watermark capacity without biologic mutation. The proposed method transforms the non-coding region DNA sequence to the n-th code coefficients and embeds the multiple bits of the n-th code coefficients by the non-recursive histogram multiple shifting method. The multi-bit embedding process prevents the false start codon generation through comparison search between adjacent concealed nucleotide sequences. From the experimental results, it was confirmed that the proposed method has higher watermark capacity of 0.004-0.382 bpn than the conventional method and has higher watermark capacity than the additional data. Also, it was confirmed that false start codon was not generated unlike the conventional method.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.4
• /
• pp.1614-1622
• /
• 2018

The research related to fault diagnosis in permanent magnet synchronous motors (PMSMs) has attracted considerable attention in recent years because various faults such as permanent magnet demagnetization and short-circuited turns can occur and result in unexpected failure of motor related system. Several conventional current and back electromotive force (BEMF) analysis techniques were proposed to detect certain faults in PMSMs; however, they generally deal with a single fault only. On the contrary, cases of multiple faults are common in PMSMs. We propose a fault diagnosis method for PMSMs with single and multiple combined faults. Our method uses three phase BEMF voltages based on the fast Fourier transform (FFT), support vector machine(SVM), and visualization tools for identifying fault types and severities in PMSMs. Principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE) are used to visualize the high-dimensional data into two-dimensional space. Experimental results show good visualization performance and high classification accuracy to identify fault types and severities for single and multiple faults in PMSMs.

• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.21-31
• /
• 2023

In this paper, we focused on the problem of evaluating multi-class classification accuracy and simulation of multiple classifier performance metrics. Multi-class classifiers for sentiment analysis involved many challenges, whereas previous research narrowed to the binary classification model since it provides higher accuracy when dealing with text data. Thus, we take inspiration from the non-linear Support Vector Machine to modify the algorithm by embedding dynamic hyperplanes representing multiple class labels. Then we analyzed the performance of multi-class classifiers using macro-accuracy, micro-accuracy and several other metrics to justify the significance of our algorithm enhancement. Furthermore, we hybridized Enhanced Convolution Neural Network (ECNN) with Dynamic Support Vector Machine (DSVM) to demonstrate the effectiveness and efficiency of the classifier towards multi-class text data. We performed experiments on three hybrid classifiers, which are ECNN with Binary SVM (ECNN-BSVM), and ECNN with linear Multi-Class SVM (ECNN-MCSVM) and our proposed algorithm (ECNNDSVM). Comparative experiments of hybrid algorithms yielded 85.12 % for single metric accuracy; 86.95 % for multiple metrics on average. As for our modified algorithm of the ECNN-DSVM classifier, we reached 98.29 % micro-accuracy results with an f-score value of 98 % at most. For the future direction of this research, we are aiming for hyperplane optimization analysis.