• Korean Journal of Materials Research
• /
• v.23 no.3
• /
• pp.177-182
• /
• 2013

Nanosphere lithography is an inexpensive, simple, high-throughput nanofabrication process. NSL can be done in different ways, such as drop coating, spin coating or by means of tilted evaporation. Nitride-based light-emitting diodes (LEDs) are applied in different places, such as liquid crystal displays and traffic signals. The characteristics of gallium nitride (GaN)-based LEDs can be enhanced by fabricating nanopatterns on the top surface of the LEDs. In this work, we created differently sized (420, 320 and 140 nm) nanopatterns on the upper surfaces of GaN-based LEDs using a modified nanosphere lithography technique. This technique is quite different from conventional NSL. The characterization of the patterned GaN-based LEDs revealed a dependence on the size of the holes in the pattern created on the LED surface. The depths of the patterns were 80 nm as confirmed by AFM. Both the photoluminescence and electroluminescence intensities of the patterned LEDs were found to increase with an increase in the size of holes in the pattern. The light output power of the 420-nm hole-patterned LED was 1.16 times higher than that of a conventional LED. Moreover, the current-voltage characteristics were improved with the fabrication of differently sized patterns over the LED surface using the proposed nanosphere lithography method.

• The Transactions of the Korean Institute of Electrical Engineers C
• /
• v.55 no.1
• /
• pp.45-49
• /
• 2006

A nano-stereolithography (NSL) process has been developed for the fabrication of three-dimensional (3D) micro-devices with high spatital resolution of approximately 100 nm. In the NSL process, a complicated 3D structure can be created by stacking layer-by-layer, so it does not require any sacrificial layer or any supporting structure. A laminated layer was fabricated by means of solidifying liquid-state monomers using two-photon absorption (TPA) which was induced by a femtosecond laser. When the fabrication of a 3D stacked structure was finished, unsolidified liquid resins were rinsed by ethanol to develop the fabricated structures; then, the polymerized structure was only left on the glass substrate. Through this work, several 3D microstructures such as a micro-channel, shell structures, and photonic crystals were fabricated to evaluate the possibility of the developed system.

• Polymer(Korea)
• /
• v.29 no.2
• /
• pp.146-150
• /
• 2005

A nano-stereolithouaphy (NSL) apparatus has been developed for fabrication of microstructures with the resolution of 150 nanometers. In the NSL process, a complicated 3D structure can be fabricated by building layer by layer, so it does not require any sacrificial layer or any supporting structure. A laminated layer was fabricated by means of solidifying liquid-state monomers using two-photon absorption (TPA) which was induced by a femtosecond laser. When the fabrication of a 3D laminated structure was finished, unsolidified liquid-stage resins were removed to develop the fabricated structure by dropping several droplets of solvent, then the polymerized structure was only left on the glass substrate. A microstructure is fabricated by vector scanning method to save the fabrication time. The shell thickness of a structure is very thin within 200 nm, when it is fabricated by a single contour scanning (SCS) path. So, a fabricated structure can be deformed easily in the developing process. In this work, a double contour scanning (DCS) method was proposed to reinforce the strength of a shell typed structure, and a microcup was fabricated to show the usefulness of the developed NSL system and the DCS method.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.4
• /
• pp.617-629
• /
• 2020

In order to overcome the limitations of the rule-based intrusion detection system due to changes in Internet computing environments, the emergence of new services, and creativity of attackers, network anomaly detection (NAD) using machine learning and deep learning technologies has received much attention. Most of these existing machine learning and deep learning technologies for NAD use supervised learning methods to learn a set of training data set labeled 'normal' and 'attack'. This paper presents the feasibility of the unsupervised learning AutoEncoder(AE) to NAD from data sets collecting of secured network traffic without labeled responses. To verify the performance of the proposed AE mode, we present the experimental results in terms of accuracy, precision, recall, f1-score, and ROC AUC value on the NSL-KDD training and test data sets. In particular, we model a reference AE through the deep analysis of diverse AEs varying hyper-parameters such as the number of layers as well as considering the regularization and denoising effects. The reference model shows the f1-scores 90.4% and 89% of binary classification on the KDDTest+ and KDDTest-21 test data sets based on the threshold of the 82-th percentile of the AE reconstruction error of the training data set.

• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.29-39
• /
• 2021

As damages to individuals, private sectors, and businesses increase due to newly occurring cyber attacks, the underlying network security problem has emerged as a major problem in computer systems. Therefore, NIDS using machine learning and deep learning is being studied to improve the limitations that occur in the existing Network Intrusion Detection System. In this study, a deep learning-based NIDS model study is conducted using the Convolution Neural Network (CNN) algorithm. For the image classification-based CNN algorithm learning, a discrete algorithm for continuity variables was added in the preprocessing stage used previously, and the predicted variables were expressed in a linear relationship and converted into easy-to-interpret data. Finally, the network packet processed through the above process is mapped to a square matrix structure and converted into a pixel image. For the performance evaluation of the proposed model, NSL-KDD, a representative network packet data, was used, and accuracy, precision, recall, and f1-score were used as performance indicators. As a result of the experiment, the proposed model showed the highest performance with an accuracy of 85%, and the harmonic mean (F1-Score) of the R2L class with a small number of training samples was 71%, showing very good performance compared to other models.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 1998.04a
• /
• pp.392-398
• /
• 1998

In order to check the validity of nonlinear normal modes of continuous, systems by means of the energy-based formulation, we consider a beam with a nonlinear boundary condition. The initial and boundary e c6nsl of a linear partial differential equation and a nonlinear boundary condition is reduced to a linear boundary value problem consisting of an 8th order ordinary differential equations and linear boundary conditions. After obtaining the asymptotic solution corresponding to each normal mode, we compare this with numerical results by the finite element method.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.10a
• /
• pp.264-267
• /
• 2005

A subregional slicing method (SSM) is proposed to increase the nanofabrication efficiency of a nano-stereolithography (NSL) process based on two-photon polymerization (TPP). The NSL process can be used to fabricate 3D microstructures via the accumulation of layers of uniform thickness; hence, the precision of the final 3D microstructure depends on the layer thickness. The use of a uniform layer thickness means that, to fabricate a precise microstructure, a large number of thin slices is inevitably required. leading to long processing times. In the SSM proposed here, however, the 3D microstructure is divided into several subregions on the basis of the geometric slope, and then each of these subregions is uniformly sliced with a layer thickness determined by the geometric slope characteristics of each subregion. Subregions with gentle slopes are sliced with thin layer thicknesses, whereas subregions with steep slopes are sliced with thick layer thicknesses. Here, we describe the procedure of the SSM based on TPP, and discuss the fabrication efficiency of the method through the fabrication of a 3D microstructure.

• Journal of the Korea Convergence Society
• /
• v.10 no.11
• /
• pp.1-7
• /
• 2019

Recently, various approaches to detect network attacks using machine learning have been studied and are being applied to detect new attacks and to increase precision. However, the machine learning method is dependent on feature extraction and takes a long time and complexity. It also has limitation of performace due to learning data imbalance. In this study, we propose a method to solve the degradation of classification performance due to imbalance of learning data among the limit points of detection system. To do this, we generate data using Generative Adversarial Networks (GANs) and propose a classification method using Convolutional Neural Networks (CNNs). Through this approach, we can confirm that the accuracy is improved when applied to the NSL-KDD and UNSW-NB15 datasets.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.342-345
• /
• 2014

Network intrusion detection system based on machine learning methods is quite dependent on the selected features in terms of accuracy and efficiency. Nevertheless, choosing the optimal combination of features from generally used features to detect network intrusion requires extensive computing resources. For instance, the number of possible feature combinations from given n features is $2^n-1$. In this paper, to tackle this problem we propose a optimal feature selection algorithm. Proposed algorithm is based on the local search algorithm, one of representative meta-heuristic algorithm for solving optimization problem. In addition, the accuracy of clusters which obtained using selected feature components and k-means clustering algorithm is adopted to evaluate a feature assembly. In order to estimate the performance of our proposed algorithm, comparing with a method where all features are used on NSL-KDD data set and multi-layer perceptron.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.2
• /
• pp.65-72
• /
• 2021

Recently, attacks on the network environment have been rapidly escalating and intelligent. Thus, the signature-based network intrusion detection system is becoming clear about its limitations. To solve these problems, research on machine learning-based intrusion detection systems is being conducted in many ways, but two problems are encountered to use machine learning for intrusion detection. The first is to find important features associated with learning for real-time detection, and the second is the imbalance of data used in learning. This problem is fatal because the performance of machine learning algorithms is data-dependent. In this paper, we propose the HSF-DNN, a network intrusion detection model based on a deep neural network to solve the problems presented above. The proposed HFS-DNN was learned through the NSL-KDD data set and performs performance comparisons with existing classification models. Experiments have confirmed that the proposed Hybrid Feature Selection algorithm does not degrade performance, and in an experiment between learning models that solved the imbalance problem, the model proposed in this paper showed the best performance.