Kwangwoon University

About: Kwangwoon University is a education organization based out in Seoul, South Korea. It is known for research contribution in the topics: Thin film & Resonator. The organization has 4020 authors who have published 8217 publications receiving 104365 citations.

Machine-Learning Approach to Optimize SMOTE Ratio in Class Imbalance Dataset for Intrusion Detection

Abstract: The KDD CUP 1999 intrusion detection dataset was introduced at the third international knowledge discovery and data mining tools competition, and it has been widely used for many studies. The attack types of KDD CUP 1999 dataset are divided into four categories: user to root (U2R), remote to local (R2L), denial of service (DoS), and Probe. We use five classes by adding the normal class. We define the U2R, R2L, and Probe classes, which are each less than 1% of the total dataset, as rare classes. In this study, we attempt to mitigate the class imbalance of the dataset. Using the synthetic minority oversampling technique (SMOTE), we attempted to optimize the SMOTE ratios for the rare classes (U2R, R2L, and Probe). After randomly generating a number of tuples of SMOTE ratios, these tuples were used to create a numerical model for optimizing the SMOTE ratios of the rare classes. The support vector regression was used to create the model. We assigned each instance in the test dataset to the model and chose the best SMOTE ratios. The experiments using machine-learning techniques were conducted using the best ratios. The results using the proposed method were significantly better than those of previous approach and other related work.

Ontology-based construction knowledge retrieval system

Abstract: Managing knowledge effectively is critical to the competitive power of a company. Knowledge is used as an important resource in many industrial areas, and so it follows that there is a growing interest in knowledge management within the construction industry. Yet because of the unique characteristics of construction knowledge created during projects, there are limitations to its capture and reuse. The knowledge produced during construction projects is project-oriented, experiential, and context specific; due to these characteristics, the reuse of knowledge is difficult. In this research, research team focus on capturing and identifying the characteristics of construction knowledge, then propose a method for applying these characteristics to the development of an ontology-based construction knowledge retrieval system. Moreover, research team developed a system prototype that applies ontology in suggesting related search words during the search process and validated the effectiveness of the prototype in terms of precision and recall rate. By applying the prototype, the precision and recall rate was improved by approximately 10∼30%.

Preparation of graphene–TiO2 nanocomposite and photocatalytic degradation of Rhodamine-B under solar light irradiation

Abstract: GR–TiO2 nanocomposite was prepared by simple chemical method using graphene oxide and titanium isopropoxide (Ti [OCH (CH3)2]4) precursors. The crystalline nature of the composite was characterised by powder X-ray diffraction and the intercalation was explained by Raman spectroscopy. The morphology of the composite was analysed by field emission scanning electron microscopy. The elemental and quantitative measurement of the composite was determined by electron dispersive spectroscopy. The shape and size of the particle was measured by transmission electron spectroscopy and high resolution spectroscopy. The surface area and elemental composition of the composite was studied by using Brunauer–Emmett–Teller (BET) method and X-ray photoelectron spectroscopy. Photo-generated electrons were studied by photoluminescence spectra. The photocatalytic activity of nanocomposite was investigated by the degradation of Rhodamine-B (Rh-B) in an aqueous solution under solar light irradiation. The GR–TiO2 demonstrat...

Highly Conductive Aromatic Functionalized Multi-Walled Carbon Nanotube for Inkjet Printable High Performance Supercapacitor Electrodes

Abstract: We report the functionalization of multiwalled carbon nanotubes (MWCNT) via the 1,3-dipolar [3+2] cycloaddition of aromatic azides, which resulted in a detangled CNT as shown by transmission electron microscopy (TEM). Carboxylic moieties (-COOH) on aromatic azide result in highly stable aqueous dispersion (max. conc. ~ 10 mg/mL H2O), making the suitable for inkjet printing. Printed patterns on polyethylene terephthalate (PET) flexible substrate exhibit low sheet resistivity ~65 Ω. cm, which is attributed to enhanced conductivity. Fabricated Supercapacitors (SC) assembled using these printed substrates exhibit good electrochemical performance in organic as well as aqueous electrolytes. High energy and power density (57.8 Wh/kg and 0.85 kW/kg) in 1M H2SO4 aqueous electrolyte demonstrate the excellent performance of the proposed supercapacitor. Capacitive retention varies from ~85–94% with columbic efficiency ~95% after 1000 charge/discharge cycles in different electrolytes, demonstrating the excellent potential of the device for futuristic power applications.