• Annual Conference of KIPS
• /
• 2011.11a
• /
• pp.429-430
• /
• 2011

Roughness set theory is a popular topic to use in color-image segmentation. A new popular color image segmentation algorithm is proposed by scientists with the point using traditional histogram and Histon construct roughness set histogram. But, there is still a problem about that is the correlativity of color vector in roughness set histogram, which take an inactive effect in the process of color-image segmentation. Therefore, this paper represents further research based on this and proposed an improved method proved through lot of experiments. The experimental result reduces the correlativity of color vector in roughness set histogram and calculation time remarkably.

• Journal of Digital Convergence
• /
• v.10 no.6
• /
• pp.213-218
• /
• 2012

Modern culture has describing the year's situation along the social environment. A literary work changed as if the year's situation change. Therefore we can understand the age through the literary work and get knowledge the social request of the year's. This literary works have made a chance to know approaching more closely to user as producing media resources. Recently, IT convergence and digital convergence become a new trend to combine each other academic area and get much synergy effect. In this paper, we propose an application and design of the ontology that needs to make digital content from modern literary work's information. For this works, we specify the structure of the year's literary work and the relation of each factor. The specification method used topic map. Each relation model was specified the connection by topic vector.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.6_2
• /
• pp.585-592
• /
• 2013

CBIR is an effective tool to search and extract image contents in a large remote sensing image database queried by an operator or end user. However, as imaging principles are different by sensors, their visual representation thus varies among image modality type. Considering images of various modalities archived in the database, image modality difference has to be tackled for the successful CBIR implementation. However, this topic has been seldom dealt with and thus still poses a practical challenge. This study suggests a cross modality CBIR (termed as the CM-CBIR) method that transforms given query feature vector by a supervised procedure in order to link between modalities. This procedure leverages the skill of analyst in training steps after which the transformed query vector is created for the use of searching in target images with different modalities. Current initial results show the potential of the proposed CM-CBIR method by delivering the image content of interest from different modality images. Despite its retrieval capability is outperformed by that of same modality CBIR (abbreviated as the SM-CBIR), the lack of retrieval performance can be compensated by employing the user's relevancy feedback, a conventional technique for retrieval enhancement.

• 한국경영정보학회:학술대회논문집
• /
• 2007.06a
• /
• pp.608-613
• /
• 2007

Prediction of corporate bankruptcies has long been an important topic and has been studied extensively in the finance and management literature because it is an essential basis for the risk management of financial institutions. Recently, support vector machines (SVMs) are becoming popular as a tool for bankruptcy prediction because they use a risk function consisting of the empirical error and a regularized term which is derived from the structural risk minimization principle. In addition, they don't require huge training samples and have little possibility of overfitting. However. in order to Use SVM, a user should determine several factors such as the parameters ofa kernel function, appropriate feature subset, and proper instance subset by heuristics, which hinders accurate prediction results when using SVM In this study, we propose a novel hybrid SVM classifier with simultaneous optimization of feature subsets, instance subsets, and kernel parameters. This study introduces genetic algorithms (GAs) to optimize the feature selection, instance selection, and kernel parameters simultaneously. Our study applies the proposed model to the real-world case for bankruptcy prediction. Experimental results show that the prediction accuracy of conventional SVM may be improved significantly by using our model.

• The Journal of Industrial Distribution & Business
• /
• v.11 no.5
• /
• pp.7-16
• /
• 2020

Purpose: Prior studies empirically examine how financial flexibility is related to required returns by using realized returns and considering cash holdings as net debts, but they fail to find consistent results. Conjecturing that inappropriate proxy of required returns and aggregation of cash and debts caused the inconsistent results, this study revisits this topic by using a refined proxy of required returns and separating cash holdings from debts. Research design, data and methodology: This study uses a multivariate regression model to investigate the relationship between required returns on cash holdings and financial leverage. The required returns are estimated using the return decomposition method by vector autoregression model. Empirical tests use US stock market data from1968 to 2011. Results: Empirical results reveal that both cash holdings and leverage are positively related to required returns. The positive relation is stronger in economic downturns than in economic upturns. Conclusions: Three major findings are drawn. First, risky firms prefer large cash balance. Second, information shocks in the realized returns caused failure of prior studies to find consistent positive relationship between leverage and realized returns. Third, cash and leverage are related to required returns in the same direction; therefore, cash cannot be considered as negative debts.

• Journal of Electrical Engineering and information Science
• /
• v.1 no.2
• /
• pp.77-86
• /
• 1996

In this paper we deal with the problem of recovering 3-D motion and structure from a time-varying 2-D velocity vector field. A great deal has been done on this topic, most of which has concentrated on finding necessary and sufficient conditions for there to be a unique 3-D solution corresponding to a given 2-D motion. While previous work provides useful theoretical insight, in most situations the known algorithms have turned out to be too sensitive to be of much practical use. It appears that any robust algorithm must improve the 3-D solutions over time. As a step toward such algorithm, we present a method for recovering 3-D motion and structure from a given time-varying 2-D velocity vector field. The surface of the object in the scene is assumed to be locally planar. It is also assumed that 3-D velocity vectors are piecewise constant over three consecutive frames (or two snapshots of flow field). Our formulation relates 3-D motion and object geometry with the optical flow vector as well as its spatial and temporal derivatives. The linearization parameters, or equivalently, the first-order flow approximation (in space and time) is sufficient to recover rigid body motion and local surface structure from the local instantaneous flow field. We also demonstrate, through a sensitivity analysis carried out for synthetic and natural motions in space, that 3-D motion can be recovered reliably.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.3
• /
• pp.61-69
• /
• 2007

This paper proposes new preprocessing algorithm to extract minutiae in the process of fingerprint recognition. Fingerprint images quality enhancement is a topic phase to ensure good performance in a topic phase to ensure good performance in a Automatic Fingerprint Identification System(AFIS) based on minutiae matching. This paper proposes an algorithm to improve fingerprint image preprocessing to extract minutiae accurately based on directional filter. We improved the suitability of low quality fingerprint images to better suit fingerprint recognition by using valid ridge vector and ridge probability of fingerprint images. With the proposed fingerprint improvement algorithm, noise is removed and presumed ridges are more clearly ascertained. The algorithm is based on five step: computation of effective ridge vector, computation of ridge probability, noise reduction, ridge emphasis, and orientation compensation and frequency estimation. The performance of the proposed approach has been evaluated on two set of images: the first one is self collected using a capacitive semiconductor sensor and second one is DB3 database from Fingerprint Verification Competition (FVC).

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.6
• /
• pp.703-708
• /
• 2024

LSTM, a deep learning technique for building language models, can be easily trained on systems with small computing resources, unlike large language models. In this paper, we propose a convergent technique to train LSTM-based language models on small-scale texts and perform objective semantic and relational analysis on the main topic words of the text using the word vectors of the vocabulary comprising the text. Using the word vectors of a small language model trained on the English script of the 2021 movie "Green Knight" directed by David Lowery as a text, we proposed a technique that can analyze the meaning and relationship of the main topic words. Through the similarity operation of the word vector, the meaning and symbolism of each theme word can be objectively analyzed with the similarity scores between the words. The relationship between each theme word can be intuitively recognized by displaying the dimensionality-reduced two-dimensional word vector. By using a small-scale language model of the LSTM method, we proposed a method to analyze complex texts using word vectors while minimizing the cost of learning.

• Archives of Craniofacial Surgery
• /
• v.23 no.3
• /
• pp.111-118
• /
• 2022

Background: Although the zygomatic arch is an important structure determining facial prominence and width, no consensus exists regarding the classification of isolated zygomatic arch fractures, and the literature on this topic is scarce. To date, five papers have subdivided zygomatic arch fractures; however, only one of those proposed classifications includes the injury vector, although the injury vector is one of the most important factors to consider in fracture cases. Furthermore, the only classification that does include the injury vector is too complicated to be suitable for daily practice. In addition, the existing classifications are clinically limited because they do not consider greenstick fractures, nondisplaced fractures, or coronoid impingement. In the present study, we present a rearrangement of the previously published classifications and propose a modified classification of isolated zygomatic arch fractures that maximizes the advantages and overcomes the disadvantages of previous classification systems. Methods: The classification criteria for isolated zygomatic arch fractures described in five previous studies were analyzed, rearranged, and supplemented to generate a modified classification. The medical records, radiographs, and facial bone computed tomography findings of 134 patients with isolated zygomatic arch fractures who visited our hospital between January 2010 and December 2019 were also retrospectively analyzed. Results: We analyzed major classification criteria (displacement, the force vector of the injury, V-shaped fracture, and coronoid impingement) for isolated zygomatic arch fracture from the five previous studies and developed a modified classification by subdividing zygomatic arch fractures. We applied the modified classification to cases of isolated zygomatic arch fracture at our hospital. The surgery rate and injury severity differed significantly from fracture types I to VI. Conclusion: Using our modified classification, we could determine that both the injury force and the injury vector meaningfully influenced the surgery rate and the severity of the injuries.

• Korean Journal of Artificial Intelligence
• /
• v.12 no.4
• /
• pp.9-19
• /
• 2024

Indonesia ranks fifth as the country of origin for spammers. Attention is urgently needed to tackle spam, especially in Bahasa Indonesia (Indonesian language), which can be achieved by building the best spam detection model. This study aims to compare machine learning models for spam detection, study spam email modeling topics, and design the implementation on the REST API. Spam detection is carried out using machine learning algorithms, i.e., Long Short Term Memory (LSTM), K-Nearest Neighbours (KNN), Naive Bayes, Random Forest, Adaboost, and Support Vector Machine (SVM) combined with slang preprocessing convert and translate. Furthermore, Latent Dirichlet Allocation (LDA) is used for topic modeling of spam emails. The results show that slang processes convert and translate can improve accuracy and f1-score, Long Short Term Memory (LSTM) was the best method with accuracy 93.15% and f1-score of 93.01%, compared to the other methods. In addition, there were five main topics on data categorized as spam: promotions, job vacancies, educational offers, bulletins and news, and investment and finance. A REST API model was successfully developed to separate spam categories based on promotional and other topics.