• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.04a
• /
• pp.89-93
• /
• 2000

구조 적응형 자기구성 지도는 일반적으로 자기구성 지도의 구조가 초기에 결정되어 학습이 끝날 때까지 변하지 않기 때문에 발생하는 문제를 해결하기 위해 지도의 구조를 학습 중에 적절하게 변경시킨다. 이때, 변화된 구조의 가중치를 어떻게 초기화시킬 것인가 하는 것이 중요한 문제이다. 이 논문에서는 기존의 비교사 학습방법에 LVQ 알고리즘을 이용한 교사 학습방법을 결합한 구조 적응형 자기구성 지도 모델에서 유전자 알고리즘을 이용하여 분화된 노드의 가중치를 결정하는 방법을 제안한다. 이 방법은 기존의 구조 적응형 자기구성 지도 알고리즘보다 빠르게 학습되었고, 인식률 면에서도 기존의 방법보다 높은 값을 나타내었으며, 자기구성 지도의 특성인 위상 보존도 잘 이루어졌다. 오프라인 필기 숫자 데이터로 실험한 결과, 제안한 방법이 유용함을 알 수 있었다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.387-390
• /
• 2012

In this paper, we propose a fast booting solution with embedded linux-based smart devices. We have divided the fast boot process into six steps, such as boot loader, kernel, file system, the init-scripts, shared libraries, and applications for an embedded linux-based boot process to improve the fast booting. Improvements for the fast boot are made in the boot loader phase, which is the first phase at power-up, and the init-script that runs the boot loader phase. To improve the fast booting, standby time from the boot loader and unnecessary initialization routine have been removed, and uncompressed kernel image loading as well as optimized copy routine have been applied. Further, a technology that replaces binary scripts in init-script phase and light-weight init process have been utilized to improve the boot.

• Journal of Korea Multimedia Society
• /
• v.21 no.6
• /
• pp.698-704
• /
• 2018

When the new ammunition is designed, it is necessary to confirm in advance how long the target distance is depends on the shape and weight of the designed ammunition. Therefore we can use commercial software such as PRODAS to predict the target distance in the design stage. This commercial software has aerodynamic data for various ammunition shape and calculates the target range by calculating the kinetic equations of the ammunition using the aerodynamic data most similar to the designed ammunition. The ammunition for predicting the target distance through software such as PRODAS is a non-guided ammunition that has no control after launch but the glide type ammunition is guided and control ammunition. So it is predicts the state of ammunition after the launch. A new type of simulator is needed to analyze the maximum range and to verify the onboard guided and control algorithm. The simulator constructed in this paper is an optimized simulator for glide type ammunition. Unlike unmanned aircraft and guided missiles. The rotation characteristics of the ammunition are considered and the navigation initialization algorithm is applied. The constructed simulator confirmed the performance by performing maximum range analysis of glide type ammunition.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.49 no.7
• /
• pp.389-398
• /
• 2000

The popular methods to check the identity of individuals include passwords and ID cards. These conventional method for user identification and authentication are not altogether reliable because they can be stolen and forgotten. As an alternative of the existing methods, biometric technology has been paid much attention for the last few decades. In this paper, we propose an efficient system for recognizing the identity of a living person by analyzing iris patterns which have a high level of stability and distinctiveness than other biometric measurements. The proposed system is based on wavelet transform and a competitive neural network with the improved mechanisms. After preprocessing the iris data acquired through a CCD camera, feature vectors are extracted by using Haar wavelet transform. LVQ(Learning Vector Quantization) is exploited to classify these feature vectors. We improve the overall performance of the proposed system by optimizing the size of feature vectors and by introducing an efficient initialization of the weight vectors and a new method for determining the winner in order to increase the recognition accuracy of LVQ. From the experiments, we confirmed that the proposed system has a great potential of being applied to real applications in an efficient and effective way.

• Journal of IKEEE
• /
• v.24 no.2
• /
• pp.570-578
• /
• 2020

In this paper, we propose an efficient method for implementing the adaptive second-order Volterra filter. To reduce computational load, the UCFD-SVF has been proposed. The UCFD-SVF, however, shows deteriorated convergence performance. We propose a new method that initializes the adaptive filter weights periodically on the fact that the energy of the filter weights is slowly increased. Furthermore, we propose another method that the interval for the weight initialization is variable to guarantee the performance and we shows the method gives the better performance under the non-stationary environment through the computer simulation for the adaptive system identification.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.976-990
• /
• 2020

The k-means algorithm is widely used in academia and industry due to easy and simple implementation, enabling fast learning for complex datasets. However, k-means struggles to classify datasets without prior knowledge of specific domains. We proposed the repulsive k-means (RK-means) algorithm in a previous study to improve the k-means algorithm, using the repulsive force concept, which allows deleting unnecessary cluster centroids. Accordingly, the RK-means enables to classifying of a dataset without domain knowledge. However, three main problems remain. The RK-means algorithm includes a cluster repulsive force offset, for clusters confined in other clusters, which can cause cluster locking; we were unable to prove RK-means provided optimal convergence in the previous study; and RK-means shown better performance only normalize term and weight. Therefore, this paper proposes the advanced RK-means (ARK-means) algorithm to resolve the RK-means problems. We establish an initialization strategy for deploying cluster centroids and define a metric for the ARK-means algorithm. Finally, we redefine the mass and normalize terms to close to the general dataset. We show ARK-means feasibility experimentally using blob and iris datasets. Experiment results verify the proposed ARK-means algorithm provides better performance than k-means, k'-means, and RK-means.

• Applied Chemistry for Engineering
• /
• v.21 no.4
• /
• pp.463-468
• /
• 2010

The polycarboxylic (PC) type concrete superplasticizer was synthesized. The effects of ethylene oxide group number and its molecular weight on the properties of the polycarboxylic type concrete superplasticizer and the concrete motar properties were studied. To investigated of the interfacial properties of the premixed-concrete with the superplasticizer, the type and the amount of polyethylene glycol, meta acrylate added, and type of the initialization agent were studied. Also the interfacial properties of the superplasticizer aqueous phase, the wettability on the cement particle, the fluidity of the cement mortar, and the strength properties of the concrete were measured. For a high fluidity of the cement mortar and a high strength of concrete, a low value of the surface tension and contact angle were required for PC. To have a good performance for PC, the reaction condition of 1.3 mol ratio of MA against to MPEG was suitable with KSP initiator.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.3
• /
• pp.223-230
• /
• 2001

Since self-organizing map (SOM) preserves the topology of ordering in input spaces and trains itself by unsupervised algorithm, it is Llsed in many areas. However, SOM has a shortcoming: structure cannot be easily detcrmined without many trials-and-errors. Structure-adaptive self-orgnizing map (SASOM) which can adapt its structure as well as its weights overcome the shortcoming of self-organizing map: SASOM makes use of structure adaptation capability to place the nodes of prototype vectors into the pattern space accurately so as to make the decision boundmies as close to the class boundaries as possible. In this scheme, the initialization of weights of newly adapted nodes is important. This paper proposes a method which optimizes SASOM with genetic algorithm (GA) to determines the weight vector of newly split node. The leanling algorithm is a hybrid of unsupervised learning method and supervised learning method using LVQ algorithm. This proposed method not only shows higher performance than SASOM in terms of recognition rate and variation, but also preserves the topological order of input patterns well. Experiments with 2D pattern space data and handwritten digit database show that the proposed method is promising.

• Journal of Biomedical Engineering Research
• /
• v.42 no.6
• /
• pp.268-276
• /
• 2021

Functional near-infrared spectroscopy-based brain-computer interface (fNIRS-based BCI) has been receiving much attention. However, we are practically constrained to obtain a lot of fNIRS data by inherent hemodynamic delay. For this reason, when employing machine learning techniques, a problem due to the high-dimensional feature vector may be encountered, such as deteriorated classification accuracy. In this study, we employ an elastic net-based feature selection which is one of the embedded methods and demonstrate the utility of which by analyzing the results. Using the fNIRS dataset obtained from 18 participants for classifying brain activation induced by mental arithmetic and idle state, we calculated classification accuracies after performing feature selection while changing the parameter α (weight of lasso vs. ridge regularization). Grand averages of classification accuracy are 80.0 ± 9.4%, 79.3 ± 9.6%, 79.0 ± 9.2%, 79.7 ± 10.1%, 77.6 ± 10.3%, 79.2 ± 8.9%, and 80.0 ± 7.8% for the various values of α = 0.001, 0.005, 0.01, 0.05, 0.1, 0.2, and 0.5, respectively, and are not statistically different from the grand average of classification accuracy estimated with all features (80.1 ± 9.5%). As a result, no difference in classification accuracy is revealed for all considered parameter α values. Especially for α = 0.5, we are able to achieve the statistically same level of classification accuracy with even 16.4% features of the total features. Since elastic net-based feature selection can be easily applied to other cases without complicated initialization and parameter fine-tuning, we can be looking forward to seeing that the elastic-based feature selection can be actively applied to fNIRS data.

• Tribology and Lubricants
• /
• v.39 no.5
• /
• pp.167-172
• /
• 2023

Titanium alloys are widely recognized among engineering materials owing to their impressive mechanical properties, including high strength-to-weight ratios, fracture toughness, resistance to fatigue, and corrosion resistance. Consequently, applications involving titanium alloys are more susceptible to damage from unforeseen events, such as scratches. Nevertheless, the impact of microscopic damage remains an area that requires further investigation. This study delves into the microscopic wear behavior of α-titanium crystal structures when subjected to linear scratch-induced damage conditions, utilizing molecular dynamics simulations as the primary methodology. The configuration of crystal lattice structures plays a crucial role in influencing material properties such as slip, which pertains to the movement of dislocations within the crystal structure. The molecular dynamics technique surpasses the constraints of observing microscopic phenomena over brief intervals, such as sub-nano- or pico-second intervals. First, we demonstrate the localized transformation of lattice structures at the end of initialization, indentation, and wear processes. In addition, we obtain the exerted force on a rigid sphere during scratching under linear movement. Furthermore, we investigate the effect of the relaxation period between indentation and scratch deformation. Finally, we conduct a comparison study of nanoindentation between crystal and amorphous Ti substrates. Thus, this study reveals the underlying physics of the microscopic transformation of the α-titanium crystal structure under wear-like accidental events.