• East Asian mathematical journal
• /
• v.37 no.1
• /
• pp.41-77
• /
• 2021

Let M be a semi-invariant submanifold of codimension 3 with almost contact metric structure (��, ξ, η, g) in a complex space form Mn+1(c), c ≠ 0. We denote by Rξ = R(·, ξ)ξ and A(i) be Jacobi operator with respect to the structure vector field ξ and be the second fundamental form in the direction of the unit normal C(i), respectively. Suppose that the third fundamental form t satisfies dt(X, Y ) = 2��g(��X, Y ) for certain scalar ��(≠ 2c)and any vector fields X and Y and at the same time Rξ is ��∇ξξ-parallel, then M is a Hopf hypersurface in Mn(c) provided that it satisfies RξA(1) = A(1)Rξ, RξA(2) = A(2)Rξ and ${\bar{r}}-2(n-1)c{\leq}0$, where ${\bar{r}}$ denotes the scalar curvature of M.

• East Asian mathematical journal
• /
• v.38 no.1
• /
• pp.43-63
• /
• 2022

Let M be a semi-invariant submanifold of codimension 3 with almost contact metric structure (φ, ξ, η, g) in a complex space form M_n+1(c). We denote by R_ξ the structure Jacobi operator with respect to the structure vector field ξ and by ${\bar{r}}$ the scalar curvature of M. Suppose that R_ξ is φ∇_ξξ-parallel and at the same time the third fundamental form t satisfies dt(X, Y) = 2θg(φX, Y) for a scalar θ(≠ 2c) and any vector fields X and Y on M. In this paper, we prove that if it satisfies R_ξφ = φR_ξ, then M is a Hopf hypersurface of type (A) in M_n+1(c) provided that ${\bar{r}-2(n-1)c}$ ≤ 0.

• East Asian mathematical journal
• /
• v.38 no.5
• /
• pp.549-581
• /
• 2022

Let M be a semi-invariant submanifold with almost contact metric structure (𝜙, 𝜉, 𝜂, g) of codimension 3 in a complex space form M_n+1(c), c≠ 0. We denote by S and R_𝜉 be the Ricci tensor of M and the structure Jacobi operator in the direction of the structure vector 𝜉, respectively. Suppose that the third fundamental form t satisfies dt(X, Y) = 2𝜃g(𝜙X, Y) for a certain scalar 𝜃(≠ 2c) and any vector fields X and Y on M. In this paper, we prove that M satisfies R_𝜉S = SR_𝜉 and at the same time R_𝜉𝜙 = 𝜙R_𝜉, then M is a Hopf hypersurface of type (A) provided that the scalar curvature s of M holds s - 2(n - 1)c ≤ 0.

• Kyungpook Mathematical Journal
• /
• v.62 no.1
• /
• pp.133-166
• /
• 2022

Let M be a semi-invariant submanifold with almost contact metric structure (𝜙, 𝜉, 𝜂, g) of codimension 3 in a complex space form M_n+1(c) for c ≠ 0. We denote by S and R_𝜉 be the Ricci tensor of M and the structure Jacobi operator in the direction of the structure vector 𝜉, respectively. Suppose that the third fundamental form t satisfies dt(X, Y) = 2𝜃g(𝜙X, Y) for a certain scalar 𝜃 ≠ 2c and any vector fields X and Y on M. In this paper, we prove that if it satisfies R_𝜉𝜙 = 𝜙R_𝜉 and at the same time S𝜉 = g(S𝜉, 𝜉)𝜉, then M is a real hypersurface in M_n(c) (⊂ M_n+1(c)) provided that $\bar{r}-2(n-1)c{\leq}0$, where $\bar{r}$ denotes the scalar curvature of M.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.6
• /
• pp.789-792
• /
• 2004

In various fields as web mining, bioinformatics, statistical data analysis, and so forth, very diversely missing values are found. These values make training data to be sparse. Largely, the missing values are replaced by predicted values using mean and mode. We can used the advanced missing value imputation methods as conditional mean, tree method, and Markov Chain Monte Carlo algorithm. But general imputation models have the property that their predictive accuracy is decreased according to increase the ratio of missing in training data. Moreover the number of available imputations is limited by increasing missing ratio. To settle this problem, we proposed statistical learning theory to preprocess for missing values. Our statistical learning theory is the support vector regression by Vapnik. The proposed method can be applied to sparsely training data. We verified the performance of our model using the data sets from UCI machine learning repository.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.127-146
• /
• 2022

Recently, as word embedding has shown excellent performance in various tasks of deep learning-based natural language processing, researches on the advancement and application of word, sentence, and document embedding are being actively conducted. Among them, cross-language transfer, which enables semantic exchange between different languages, is growing simultaneously with the development of embedding models. Academia's interests in vector alignment are growing with the expectation that it can be applied to various embedding-based analysis. In particular, vector alignment is expected to be applied to mapping between specialized domains and generalized domains. In other words, it is expected that it will be possible to map the vocabulary of specialized fields such as R&D, medicine, and law into the space of the pre-trained language model learned with huge volume of general-purpose documents, or provide a clue for mapping vocabulary between mutually different specialized fields. However, since linear-based vector alignment which has been mainly studied in academia basically assumes statistical linearity, it tends to simplify the vector space. This essentially assumes that different types of vector spaces are geometrically similar, which yields a limitation that it causes inevitable distortion in the alignment process. To overcome this limitation, we propose a deep learning-based vector alignment methodology that effectively learns the nonlinearity of data. The proposed methodology consists of sequential learning of a skip-connected autoencoder and a regression model to align the specialized word embedding expressed in each space to the general embedding space. Finally, through the inference of the two trained models, the specialized vocabulary can be aligned in the general space. To verify the performance of the proposed methodology, an experiment was performed on a total of 77,578 documents in the field of 'health care' among national R&D tasks performed from 2011 to 2020. As a result, it was confirmed that the proposed methodology showed superior performance in terms of cosine similarity compared to the existing linear vector alignment.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.11
• /
• pp.555-562
• /
• 2016

Semantic Role Labeling (SRL) is to determine the semantic relation of a predicate and its argu-ments in a sentence. But Korean semantic role labeling has faced on difficulty due to its different language structure compared to English, which makes it very hard to use appropriate approaches developed so far. That means that methods proposed so far could not show a satisfied perfor-mance, compared to English and Chinese. To complement these problems, we focus on suffix information analysis, such as josa (case suffix) and eomi (verbal ending) analysis. Korean lan-guage is one of the agglutinative languages, such as Japanese, which have well defined suffix structure in their words. The agglutinative languages could have free word order due to its de-veloped suffix structure. Also arguments with a single morpheme are then labeled with statistics. In addition, machine learning algorithms such as Support Vector Machine (SVM) and Condi-tional Random Fields (CRF) are used to model SRL problem on arguments that are not labeled at the suffix analysis phase. The proposed method is intended to reduce the range of argument instances to which machine learning approaches should be applied, resulting in uncertain and inaccurate role labeling. In experiments, we use 15,224 arguments and we are able to obtain approximately 83.24% f1-score, increased about 4.85% points compared to the state-of-the-art Korean SRL research.

• Journal of the Korean Society of Visualization
• /
• v.15 no.2
• /
• pp.21-25
• /
• 2017

If a liquid droplet evaporates on a solid substrate, when it completely dries, it leaves a peculiar pattern, which depends on the composition of the liquid. Not only a single component liquid but also complex liquids are studied for a different purpose. In particular, a binary mixture droplet has been widely studied and used for an ink-jet printing technology. In this study, we focus on investigating to visualize the internal flow field of an ethanol-water mixture by varying a concentration ratio between two liquids. We measure the in-plane velocity vector fields and vorticities. We believe that this fundamental study about the internal flow field provides a basic idea to understand the dried pattern of the binary mixture droplet.

• Proceedings of the KSME Conference
• /
• 2001.06e
• /
• pp.444-449
• /
• 2001

The flow between two concentric cylinders, with the inner one rotating and with an imposed pressure-driven axial flow, is studied using numerical simulation. This study considers the identical flow geometry as in the experiments of Wereley and Lueptow[Phys. Fluid, 11 (12), 1999]. They carried out experiments using PIV to measure the velocity fields in a meridional plane of the annulus in detail. When an axial flow is imposed, the critical Taylor number is increased. The axial flow stabilizes the flow field and decreases the torque required to rotate the inner cylinder. The velocity vector fields obtained also show the same flow features found in the experiments of Wereley and Lueptow.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.22 no.6
• /
• pp.874-887
• /
• 1998

A 2-frame PTV (particle tracking velocimetry) system using the concept of match probability between two consequent image frames has been developed to obtain instantaneous velocity fields. The overall 2-frame PTV system including image pre-processing, tracking algorithm and post-processing routine was implemented to apply to real flows. The developed 2-frame PTV system has several advantages such as high recovery ratio of velocity vectors, low error ratio and small computational time compared with the conventional 4-frame PTV and the FFT-based cross-correlation PIV technique. The 2-frame PTV system was applied to a turbulent channel flow over a rectangular block to check its reliability and usefulness. Total 96 sequential image frames have been captured and processed to get both mean and fluctuating velocity vector fields over the recirculating region. The mean velocity and turbulent intensity profiles were well agreed with hte LDV measurements in the separated region behind the block. Time-averaged reattachment length is about 6.3 times of the block height.