• Journal of Microbiology and Biotechnology
• /
• v.32 no.5
• /
• pp.575-581
• /
• 2022

A Gram-stain-negative, white-coloured, and rod-shaped bacterium, strain DR4-4^T, was isolated from Daechung Reservoir, Republic of Korea, during Microcystis bloom. Strain DR4-4^T was most closely related to Caenimonas terrae SGM1-15^T and Caenimonas koreensis EMB320^T with 98.1% 16S rRNA gene sequence similarities. The average nucleotide identity (ANI) and digital DNA-DNA hybridization (dDDH) values between strain DR4-4^T and closely related type strains were below 79.46% and 22.30%, respectively. The genomic DNA G+C content was 67.5%. The major cellular fatty acids (≥10% of the total) were identified as C_16:0, cyclo C_17:0, summed feature 3 (C_16:1ω7c and/or C_16:1ω6c), and summed feature 8 (C_18:1ω7c and/or C_18:1ω6c). Strain DR4-4^T possessed phosphatidylethanolamine, diphosphatidylglycerol, and phosphatidylglycerol as the main polar lipids and Q-8 as the respiratory quinone. The polyamine profile was composed of putrescine, cadaverine, and spermidine. The results of polyphasic characterization indicated that the isolated strain DR4-4^T represents a novel species within the genus Caenimonas, for which the name Caenimonas aquaedulcis sp. nov. is proposed. The type strain is DR4-4^T (=KCTC 82470^T =JCM 34453^T).

• Journal of Microbiology and Biotechnology
• /
• v.32 no.7
• /
• pp.855-861
• /
• 2022

A white-pigmented, non-motile, gram-negative, and rod-shaped bacterium, designated CYS-02^T, was isolated from soil sampled at Suwon, Gyeonggi-do, Republic of Korea. Cells were strictly aerobic, grew optimally at 20-28℃ and hydrolyzed Tween 40. Phylogenetic analysis based on 16S rRNA gene sequence indicated that strain CYS-02^T formed a lineage within the family Comamonadaceae and clustered as members of the genus Variovorax. The closest members were Variovorax guangxiensis DSM 27352^T (98.6% sequence similarity), Variovorax paradoxus NBRC 15149^T (98.5%), and Variovorax gossypii JM-310^T (98.3%). The principal respiratory quinone was Q-8 and the major polar lipids contain phosphatidylethanolamine (PE), phosphatidylethanolamine (PG), and diphosphatidylglycerol (DPG). The predominant cellular fatty acids were C_16:0, summed feature 3 (C_16:1ω7c and/or C_16:1ω6c) and summed feature 8 (C_18:1ω7c and/or C_18:1ω6c). The DNA GC content was 67.7 mol%. The ANI and dDDH values between strain CYS-02T and the closest members in the genus Variovorax were ≤ 79.0 and 22.4%, respectively, and the AAI and POCP values between CYS-02^T and the other related species in the family Comamonadaceae were > 70% and > 50%, respectively. The genome of strain CYS-02^T showed a putative terpene biosynthetic cluster responsible for antioxidant activity which was supported by DPPH radical scavenging activity test. Based on genomic, phenotypic and chemotaxonomic analyses, strain CYS-02^T was classified into a novel species in the genus Variovorax, for which the name Variovorax terrae sp. nov., has been proposed. The type strain is CYS-02^T (= KACC 22656^T = NBRC 00115645^T).

• Journal of Software Assessment and Valuation
• /
• v.17 no.2
• /
• pp.143-150
• /
• 2021

There is a need for an artificial intelligent technology that can reduce various types of safety accidents by analyzing the risk factors that cause safety accidents in industrial site. In this paper, user safety profiling methods are proposed that can prevent safety accidents in advance by specifying and modeling user information data related to safety accidents. User information data is classified into normal and abnormal conditions through deep learning based artificial intelligence analysis. As a result of verifying user safety profiling technology using more than 10 types of industrial field data, 93.6% of user safety profiling accuracy was obtained.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.173-198
• /
• 2020

For a long time, many studies have been conducted on predicting the success of campaigns for customers in academia, and prediction models applying various techniques are still being studied. Recently, as campaign channels have been expanded in various ways due to the rapid revitalization of online, various types of campaigns are being carried out by companies at a level that cannot be compared to the past. However, customers tend to perceive it as spam as the fatigue of campaigns due to duplicate exposure increases. Also, from a corporate standpoint, there is a problem that the effectiveness of the campaign itself is decreasing, such as increasing the cost of investing in the campaign, which leads to the low actual campaign success rate. Accordingly, various studies are ongoing to improve the effectiveness of the campaign in practice. This campaign system has the ultimate purpose to increase the success rate of various campaigns by collecting and analyzing various data related to customers and using them for campaigns. In particular, recent attempts to make various predictions related to the response of campaigns using machine learning have been made. It is very important to select appropriate features due to the various features of campaign data. If all of the input data are used in the process of classifying a large amount of data, it takes a lot of learning time as the classification class expands, so the minimum input data set must be extracted and used from the entire data. In addition, when a trained model is generated by using too many features, prediction accuracy may be degraded due to overfitting or correlation between features. Therefore, in order to improve accuracy, a feature selection technique that removes features close to noise should be applied, and feature selection is a necessary process in order to analyze a high-dimensional data set. Among the greedy algorithms, SFS (Sequential Forward Selection), SBS (Sequential Backward Selection), SFFS (Sequential Floating Forward Selection), etc. are widely used as traditional feature selection techniques. It is also true that if there are many risks and many features, there is a limitation in that the performance for classification prediction is poor and it takes a lot of learning time. Therefore, in this study, we propose an improved feature selection algorithm to enhance the effectiveness of the existing campaign. The purpose of this study is to improve the existing SFFS sequential method in the process of searching for feature subsets that are the basis for improving machine learning model performance using statistical characteristics of the data to be processed in the campaign system. Through this, features that have a lot of influence on performance are first derived, features that have a negative effect are removed, and then the sequential method is applied to increase the efficiency for search performance and to apply an improved algorithm to enable generalized prediction. Through this, it was confirmed that the proposed model showed better search and prediction performance than the traditional greed algorithm. Compared with the original data set, greed algorithm, genetic algorithm (GA), and recursive feature elimination (RFE), the campaign success prediction was higher. In addition, when performing campaign success prediction, the improved feature selection algorithm was found to be helpful in analyzing and interpreting the prediction results by providing the importance of the derived features. This is important features such as age, customer rating, and sales, which were previously known statistically. Unlike the previous campaign planners, features such as the combined product name, average 3-month data consumption rate, and the last 3-month wireless data usage were unexpectedly selected as important features for the campaign response, which they rarely used to select campaign targets. It was confirmed that base attributes can also be very important features depending on the type of campaign. Through this, it is possible to analyze and understand the important characteristics of each campaign type.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.7
• /
• pp.49-55
• /
• 2016

In digital forensic images, there is a serious problem that is distributed with various image types. For the problem solution, this paper proposes a classification algorithm of the forensic image types. The proposed algorithm extracts the 21-dim. feature vector with the contrast and energy from GLCM (Gray Level Co-occurrence Matrix), and the entropy of each image type. The classification test of the forensic images is performed with an exhaustive combination of the image types. Through the experiments, TP (True Positive) and FN (False Negative) is detected respectively. While it is confirmed that performed class evaluation of the proposed algorithm is rated as 'Excellent(A)' because of the AUROC (Area Under Receiver Operating Characteristic Curve) is 0.9980 by the sensitivity and the 1-specificity. Also, the minimum average decision error is 0.1349. Also, at the minimum average decision error is 0.0179, the whole forensic image types which are involved then, our classification effectiveness is high.

• Journal of IKEEE
• /
• v.13 no.2
• /
• pp.159-166
• /
• 2009

So far, many researches have been done to retrieve music information using static classification descriptors such as genre and mood. Since static classification descriptors are based on diverse content-based musical features, they are effective in retrieving similar music in terms of such features. However, human emotion or mood transition triggered by music enables more effective and sophisticated query in music retrieval. So far, few works have been done to evaluate the effect of human mood transition by music. Using formal representation of such mood transitions, we can provide personalized service more effectively in the new applications such as music recommendation. In this paper, we first propose our Emotion State Transition Model (ESTM) for describing human mood transition by music and then describe a music classification and recommendation scheme based on the ESTM. In the experiment, diverse content-based features were extracted from music clips, dimensionally reduced by NMF (Non-negative Matrix Factorization, and classified by SVM (Support Vector Machine). In the performance analysis, we achieved average accuracy 67.54% and maximum accuracy 87.78%.

• Polymer(Korea)
• /
• v.27 no.4
• /
• pp.275-284
• /
• 2003

The positive temperature coefficient (PTC) effects of high density polyethylene (HDPE)/carbon black composite materials were investigated by enhancing adhesive characteristics of electrodes and controlling HDPE chemical crosslinking. When the silver paste was used as an electrode for the same 45 wt% HDPE/carbon composites, the resistance was over 1 $\Omega$, which should be compared with the resistance of 0.2 $\Omega$ for the dendritic copper electrode. In general, the silver-paste electrode exhibited higher electrical resistance than cupper electrode due to the interfacial resistance between the electrode and PTC composites. The HDPE/carbon composite exhibited typical PTC characteristics maintaining a constant resistance up to vicat point and showing a maximum at the melting point of HDPE. The crosslinked HDPE significantly decreased the negative temperature coefficient (NTC) phenomena, and desirably showed a constant or slightly increasing feature of electrical resistance in the high temperature region.

• Tuberculosis and Respiratory Diseases
• /
• v.77 no.4
• /
• pp.178-183
• /
• 2014

Here, we report a case of pulmonary paragonimiasis that was improved with initial anti-tuberculosis (TB) therapy but confused with reactivated pulmonary TB. A 53-year-old Chinese female presented with a persistent productive cough with foul smelling phlegm and blood streaked sputum. Radiologic findings showed subpleural cavitary consolidation in the right upper lobe (RUL). Bronchoscopic and cytological examination showed no remarkable medical feature. She was diagnosed with smear-negative TB, and her radiologic findings improved after receiving a 6-month anti-TB therapy. The chest CT scans, however, obtained at 4 months after completion of anti-TB therapy showed a newly developed subpleural consolidation in the RUL. She refused pathologic confirmation and was re-treated with anti-TB medication. Nevertheless, her chest CT scans revealed newly developed cavitary nodules at 5 months after re-treatment. She underwent thoracoscopic wedge resection; the pathological examination reported that granuloma caused by Paragonimus westermani. Paragonimiasis should also be considered in patients assessed with smear-negative pulmonary TB.

• Polymer(Korea)
• /
• v.26 no.3
• /
• pp.367-374
• /
• 2002

Electrical characteristics of crystalline polymer composites filled with nano-sized carbon black particle were studied. The developed composite system exhibited a typical positive temperature coefficient resistance (PTCR) characteristic, where the electrical resistance sharply increased at a specific temperature. The PTCR effect was sometimes followed by a negative temperature coefficient resistance (NTCR) feature with temperature, which seemingly caused by the coagulation of nano-sized carbon black particles in the excessive quantity. The PTCR temperature was controlled by the carbon black content and the external voltage. The change of electric conductivity was shown as a function of carbon black content, and the resistance was constant when the carbon black content was over 20 wt%. The room-temperature resistance was maintained by a repeated heating and cooling. The excellent PTCR characteristic was demonstrated by the low resistance in the initial stage and the instantaneous heating capability.

• Journal of Microbiology and Biotechnology
• /
• v.16 no.11
• /
• pp.1728-1733
• /
• 2006

A Gram-negative, strictly aerobic, nonmotile, and nonspore-forming bacterial strain, designated $T5-12^T$, was isolated from compost and characterized using a polyphasic taxonomical approach. The isolate was positive for catalase and oxidase tests. It could degrade DNA, but was negative for degradation of macromolecules such as casein, collagen, starch, chitin, cellulose, and xylan. The DNA G+C content was 36.0 mol%. The predominant isoprenoid quinone was menaquinone 7 (MK-7). The major fatty acids were $iso-C_{15:0}$ (45.6%), $iso-C_{17:0}$ 3OH (17.2%), and summed feature 4 ($C_{16:0}\;{\omega}7c$ and/or $iso-C_{15:0}$ 2OH, 14.9%). Comparative 16S rRNA gene sequence analysis showed that strain $T5-12^T$ fell within the radiation of the cluster comprising members of the genus Sphingobacterium. Strain $T5-12^T$ exhibited lower than 94% of 16S rRNA gene sequence similarity with respect to the type strains of recognized Sphingobacterium species. On the basis of its phenotypic properties and phylogenetic distinctiveness, strain $T5-12^T$ ($=KCTC\;12578^T=LMG\;23401^T=CCUG\;52467^T$) should be classified in the genus Sphingobacterium as the type strain of a novel species, for which the name Sphingobacterium composti sp. novo is proposed.