• Industrial Engineering and Management Systems
• /
• v.16 no.1
• /
• pp.64-79
• /
• 2017

Identifying disease genes from human genome is a critical task in biomedical research. Important biological features to distinguish the disease genes from the non-disease genes have been mainly selected based on traditional feature selection approaches. However, the traditional feature selection approaches unnecessarily consider many unimportant biological features. As a result, although some of the existing classification techniques have been applied to disease gene identification, the prediction performance was not satisfactory. A small set of the most important biological features can enhance the accuracy of disease gene identification, as well as provide potentially useful knowledge for biologists or clinicians, who can further investigate the selected biological features as well as the potential disease genes. In this paper, we propose a new stepwise random forests (SRF) approach for biological feature selection and disease gene identification. The SRF approach consists of two stages. In the first stage, only important biological features are iteratively selected in a forward selection manner based on one-dimensional random forest regression, where the updated residual vector is considered as the current response vector. We can then determine a small set of important biological features. In the second stage, random forests classification with regard to the selected biological features is applied to identify disease genes. Our extensive experiments show that the proposed SRF approach outperforms the existing feature selection and classification techniques in terms of biological feature selection and disease gene identification.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.10
• /
• pp.3538-3556
• /
• 2014

This paper proposes a novel video stitching method that improves real-time performance and visual quality of a multi-camera video surveillance system. A two-stage seam searching algorithm based on enhanced dynamic programming is proposed. It can obtain satisfactory result and achieve better real-time performance than traditional seam-searching methods. The experiments show that the computing time is reduced by 66.4% using the proposed algorithm compared with enhanced dynamic programming, while the seam-searching accuracy is maintained. A real-time local update scheme reduces the deformation effect caused by moving objects passing through the seam, and a seam-based local color transfer model is constructed and applied to achieve smooth transition in the overlapped area, and overcome the traditional pixel blending methods. The effectiveness of the proposed method is proved in the experiements.

• Journal of KIISE:Databases
• /
• v.27 no.2
• /
• pp.247-255
• /
• 2000

Traditional object decomposition techniques do not decompose spatial objects dynamically during spatial joins, because the object decomposition is very expensive. In this paper, we propose a modified object decomposition technique that can be applied in PBSM(Partition Based Spatial Merge-Join). In real-life data, there are much differences among the sizes of objects. We decompose only large objects with great effects on spatial joins. This technique decreases the decomposition cost of objects during spatial joins and enables efficient filter-refinement steps. Experiments show that the PBSM used with our proposed method performs significantly better than the traditional PBSM.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.1
• /
• pp.1-6
• /
• 2012

In this paper, we present an obstacle avoidance control algorithm for mobile robots based on SFLC (single-input fuzzy logic controller) with an efficient fuzzy logic look-up table to replace the traditional complicated operation. This method achieves better performance than traditional methods in terms of efficiency. The output of a SFLC leads the robot to the target automatically although many obstacles on the path. Our experiments show that the robot has good performance in the view of path tracking and other efficiency.

• The Journal of Korean Medicine
• /
• v.30 no.5
• /
• pp.42-49
• /
• 2009

Objectives: To summarize and make a reference number of herbal plant-derived antioxidant researches worldwide. Methods: We surveyed all papers of antioxidant-focused studies using plants in PubMed database as "herbal plant AND antioxidant" of Default Tag "Title". The type of materials used in the studies, formation of experiments, frequency of herbal plants studied and their actions, and main study subjects were analyzed. Results: The number of studies on herbal plant-related antioxidant effects have increased worldwide since 2000. Studies have been performed using mainly single plant and single compounds for medical disorders such as immunity, heart/blood, liver, and central nerve functions. The list of plants frequently includes SalviamiltiorrhizaBge.,GinkgobilobaL., ScutellabaicalensisGeorgi.,and so on. Most of these plants have strong effects against oxidative stress and also against free radicals and increase the activities of antioxidant enzymes. Conclusion: This study produced an overview of previous research on antioxidant-focused herbal plants. This result will provide useful information for the field of Korean traditional medicine for the development of drugs related to antioxidants.

• The Research Journal of the Costume Culture
• /
• v.9 no.1
• /
• pp.111-126
• /
• 2001

This study concentrates on the relationship between the early 20th century italian artists and their works in the field of clothing design. They advocated the creation of art for life and introduced a new type of work of art which I will call 'experimental clothing for art'. The experimental clothing for art showed its dynamic characteristics in the field s of line and form, color, pattern, and material. The Italian artists made simple and functionalistic dresses, using asymmetric, geometric cuts. in pattern making. They employed dynamic patterns in textile design and favored brilliant colors which they debunked as storage and traditional. With regard to material, they used unusual materials such as metal, net, wire, and paper and inexpensive materials. To investigations of the visual expression of experimental clothing for art in Italy have led us to the internal expressions which are avant-garde, dynamic & speed, functionality & popularity, ephemeral & transformable, and warlike. As a result of the reflection of the times and the artists's will and roles the experimental clothing for art in Italy implicated contemporary clothing in the early twentieth century and it was only laboratory art that underwent various experiments in canvas but a model of efforts for the at of living, which was anti-traditional. It offered a new future and created a new environment. It is left for future research how the experimental clothing for art developed in countries other than Italian.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.12
• /
• pp.6028-6042
• /
• 2019

Since Sparse Nonnegative Matrix Factorization (SNMF) method can control the sparsity of the decomposed matrix, and then it can be adopted to control the sparsity of facial feature extraction and recognition. In order to improve the accuracy of SNMF method for facial feature recognition, new additive iterative rules based on the improved iterative step sizes are proposed to improve the SNMF method, and then the traditional multiplicative iterative rules of SNMF are transformed to additive iterative rules. Meanwhile, to further increase the sparsity of the basis matrix decomposed by the improved SNMF method, a threshold-sparse constraint is adopted to make the basis matrix to a zero-one matrix, which can further improve the accuracy of facial feature recognition. The improved SNMF method based on the additive iterative rules and threshold-sparse constraint is abbreviated as ASNMF, which is adopted to recognize the ORL and CK+ facial datasets, and achieved recognition rate of 96% and 100%, respectively. Meanwhile, from the results of the contrast experiments, it can be found that the recognition rate achieved by the ASNMF method is obviously higher than the basic NMF, traditional SNMF, convex nonnegative matrix factorization (CNMF) and Deep NMF.

• Journal of the Optical Society of Korea
• /
• v.20 no.3
• /
• pp.381-388
• /
• 2016

The performance of a staring infrared imaging system can be characterized based on estimating the modulation transfer function (MTF). The slant edge method is a widely used MTF estimation method, which can effectively solve the aliasing problem caused by the discrete undersampling of the infrared focal plane array. However, the traditional slant edge method has some limitations such as the low precision of the edge angle extraction and using the approximate function to fit the edge spread function (ESF), which affects the accuracy of the MTF estimation. In this paper, we propose a modified slant edge method, including an edge angle extraction method that can improve the precision of the edge angle extraction and an ESF fitting algorithm which is based on the transfer function model of the imaging system, to enhance the accuracy of the MTF estimation. This modified slant edge method presents higher estimation accuracy and better immunity to noise and edge angle than other traditional methods, which is demonstrated by the simulation and application experiments operated in our study.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2007.04a
• /
• pp.241-246
• /
• 2007

The capacity of a lateral load resistance of a joint with Jangbu-connection of Dori-directional frame in traditional wood structure system was studied, through experiments of 1/2 scaled and T-shaped 7 subassemblies of joint of Dori-directional frame for Deawoongjeon of Bongjungsa. From the experiment, it was shown that the capacity of a lateral load resistance was influenced by the vertical load confining joint and not influenced by the number of Chok and the depth of Changbang, And lateral load resistance mechanism is developed by the restraint between the vertical load and the contacting edge of column; if structure is pushed to the left, the top-right end of Pyeongju contacts with Changbang and left Changbang loses the contacts with Pyeongju and therefore only right Changbang can resist to lateral load.

• Korean Journal of Materials Research
• /
• v.25 no.6
• /
• pp.305-316
• /
• 2015

The study of grinding behavior characteristics on the metal powders has recently gained scientific interest due to their useful applications to enhance advanced nano materials and components. This could significantly improve the property of new mechatronics integrated materials and components. So, a new evaluation method for standardizing grinding equipment and a comparative study for the grinding experiment during the grinding process with various grinding mills were investigated. The series of grinding experiments were carried out by a traditional ball mill, stirred ball mill, and planetary ball mill with various experimental conditions. The relationship between the standardization of equipment and experimental results showed very significant conclusions. Furthermore, the comparative study on the grinding experiment, which investigated changes in particle size, particle morphology, and crystal structure of materials with changes in experimental conditions for grinding equipment, found that the value of particle size distribution is related to the various experimental conditions as a revolution speed of grinding mill and media size.