• Genomics & Informatics
• /
• 제4권2호
• /
• pp.71-76
• /
• 2006

We have investigated biological responses to radiofrequency (RF) radiation in in vitro and in vivo models. By measuring the levels of heat shock proteins as well as the activation of mitogen activated protein kinases (MAPKs), we could not detect any differences upon RF exposure. In this study, we used more sensitive method to find the molecular responses to RF radiation. Jurkat, human T-Iymphocyte cells were exposed to 1763 MHz RF radiation at an average specific absorption rate (SAR) of 10 W/kg for one hour and harvested immediately (R0) or after five hours (R5). From the profiles of 30,000 genes, we selected 68 differentially expressed genes among sham (S), R0 and R5 groups using a random-variance F-test. Especially 45 annotated genes were related to metabolism, apoptosis or transcription regulation. Based on support vector machine (SVM) algorithm, we designed prediction model using 68 genes to discriminate three groups. Our prediction model could predict the target class of 19 among 20 examples exactly (95% accuracy). From these data, we could select the 68 biomarkers to predict the RF radiation exposure with high accuracy, which might need to be validated in in vivo models.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2005년도 공동추계학술대회
• /
• pp.241-250
• /
• 2005

New product development (NPD) is defined as the transformation of a market opportunity and a set of assumptions about product technology into a product available for sale. Managers charged with project selection decisions in the NPD process, such as go/no-go choices and specific resource allocation decisions, are faced with a complicated problem. Therefore, the ability to develop new successful products has identifies as a major determinant in sustaining a firm's competitive advantage. The purpose of this study is to develop a new evaluation model for NPD project selection in the high -tech industry using support vector machines (SYM). The evaluation model is developed through two phases. In the first phase, binary (go/no-go) classification prediction model, i.e. SVM for high-tech NPD project selection is developed. In the second phase. using the predicted output value of SVM, feasibility grade is calculated for the final NPD project decision making. In this study, the feasibility grades are also divided as three level grades. We assume that the frequency of NPD project cases is symmetrically determined according to the feasibility grades and misclassification errors are partially minimized by the multiple grades. However, the horizon of grade level can be changed by firms' NPD strategy. Our proposed feasibility grade method is more reasonable in NPD decision problems by considering particularly risk factor of NPD in viewpoints of future NPD success probability. In our empirical study using Korean NPD cases, the SVM significantly outperformed ANN and logistic regression as benchmark models in hit ratio. And the feasibility grades generated from the predicted output value of SVM showed that they can offer a useful guideline for NPD project selection.

• 한국IT서비스학회지
• /
• 제11권4호
• /
• pp.233-250
• /
• 2012

In this paper, credit card delinquency means the possibility of occurring bad debt within the certain near future from the normal accounts that have no debt and the problem is to predict, on the monthly basis, the occurrence of delinquency 3 months in advance. This prediction is typical binary classification problem but suffers from the issue of data imbalance that means the instances of target class is very few. For the effective prediction of bad debt occurrence, Support Vector Machine (SVM) with kernel trick is adopted using credit card usage and payment patterns as its inputs. SVM is widely accepted in the data mining society because of its prediction accuracy and no fear of overfitting. However, it is known that SVM has the limitation in its ability to processing the large-scale data. To resolve the difficulties in applying SVM to bad debt occurrence prediction, two stage clustering is suggested as an effective data reduction method and ensembles of SVM models are also adopted to mitigate the difficulty due to data imbalance intrinsic to the target problem of this paper. In the experiments with the real world data from one of the major domestic credit card companies, the suggested approach reveals the superior prediction accuracy to the traditional data mining approaches that use neural networks, decision trees or logistics regressions. SVM ensemble model learned from T2 training set shows the best prediction results among the alternatives considered and it is noteworthy that the performance of neural networks with T2 is better than that of SVM with T1. These results prove that the suggested approach is very effective for both SVM training and the classification problem of data imbalance.

• 한국멀티미디어학회논문지
• /
• 제17권2호
• /
• pp.232-239
• /
• 2014

온라인에서의 글쓰기가 늘어나면서, 기계학습을 통해 이를 분류하는 연구가 늘고 있다. 그럼에도 불구하고 한국어로 작성된 마이크로블로그를 대상으로 한 연구는 많지 않다. 또한 통계적으로 기계학습을 평가한 연구를 찾아보기 힘들다. 본 논문에서는 트위터를 대상으로, 표본을 추출하고, 형태소와 음절을 자질로 사용하여 기계학습에 따라 감정을 분류하였다. 그 결과 약 76%정도 트위터에 포함된 감정이 분류되었다. Support Vector Machine이 Na$\ddot{i}$ve Bayes보다 정확했고, 선형모델도 비구조적인 텍스트 처리에 비선형모델에 상응하는 정확성을 보였다. 또한 형태소가 음절 자질에 비해 높은 정확성을 보이지 않았다.

• Structural Monitoring and Maintenance
• /
• 제5권2호
• /
• pp.243-260
• /
• 2018

Detection of damages in fibre reinforced plastic (FRP) composite structures is important from the safety and serviceability point of view. Usually, damage is realized as a local reduction of stiffness and if dynamic responses of the structure are sensitive enough to such changes in stiffness, then a well posed inverse problem can provide an efficient solution to the damage detection problem. Usually, such inverse problems are solved within the framework of pattern recognition. Support Vector Machine (SVM) Algorithm is one such methodology, which minimizes the weighted differences between the experimentally observed dynamic responses and those computed using the finite element model- by optimizing appropriately chosen parameters, such as stiffness. A damage detection strategy is hereby proposed using SVM which perform stepwise by first locating and then determining the severity of the damage. The SVM algorithm uses simulations of only a limited number of damage scenarios and trains the algorithm in such a way so as to detect damages at unknown locations by recognizing the pattern of changes in dynamic responses. A rectangular fiber reinforced plastic composite plate has been investigated both numerically and experimentally to observe the efficiency of the SVM algorithm for damage detection. Experimentally determined modal responses, such as natural frequencies and mode shapes are used as observable parameters. The results are encouraging since a high percentage of damage cases have been successfully determined using the proposed algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권10호
• /
• pp.5143-5158
• /
• 2018

Improving the intrusion detection system (IDS) is a pressing need for cyber security world. With the growth of computer networks, there are constantly daily new attacks. Machine Learning (ML) is one of the most important fields which have great contribution to address the intrusion detection issues. One of these issues relates to the imbalance of the diverse classes of network traffic. Accuracy paradox is a result of training ML algorithm with imbalanced classes. Most of the previous efforts concern improving the overall accuracy of these models which is truly important. However, even they improved the total accuracy of the system; it fell in the accuracy paradox. The seriousness of the threat caused by the minor classes and the pitfalls of the previous efforts to address this issue is the motive for this work. In this paper, we consolidated stratified sampling, cost function and weighted Support Vector Machine (WSVM) method to address the accuracy paradox of ID problem. This model achieved good results of total accuracy and superior results in the small classes like the User-To-Remote and Remote-To-Local attacks using the improved version of the benchmark dataset KDDCup99 which is called NSL-KDD.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2006년도 춘계학술대회
• /
• pp.167-175
• /
• 2006

Building accurate corporate bankruptcy prediction models has been one of the most important research issues in finance. Recently, support vector machines (SVMs) are popularly applied to bankruptcy prediction because of its many strong points. However, in order to use SVM, a modeler should determine several factors by heuristics, which hinders from obtaining accurate prediction results by using SVM. As a result, some researchers have tried to optimize these factors, especially the feature subset and kernel parameters of SVM But, there have been no studies that have attempted to determine appropriate instance subset of SVM, although it may improve the performance by eliminating distorted cases. Thus in the study, we propose the simultaneous optimization of the instance selection as well as the parameters of a kernel function of SVM by using genetic algorithms (GAs). Experimental results show that our model outperforms not only conventional SVM, but also prior approaches for optimizing SVM.

• Journal of Power Electronics
• /
• 제17권5호
• /
• pp.1288-1297
• /
• 2017

The estimation of the remaining useful life (RUL) of lithium-ion (Li-ion) batteries is important for intelligent battery management system (BMS). Data mining technology is becoming increasingly mature, and the RUL estimation of Li-ion batteries based on data-driven prognostics is more accurate with the arrival of the era of big data. However, the support vector machine (SVM), which is applied to predict the RUL of Li-ion batteries, uses the traditional single-radial basis kernel function. This type of classifier has weak generalization ability, and it easily shows the problem of data migration, which results in inaccurate prediction of the RUL of Li-ion batteries. In this study, a novel multi-kernel SVM (MSVM) based on polynomial kernel and radial basis kernel function is proposed. Moreover, the particle swarm optimization algorithm is used to search the kernel parameters, penalty factor, and weight coefficient of the MSVM model. Finally, this paper utilizes the NASA battery dataset to form the observed data sequence for regression prediction. Results show that the improved algorithm not only has better prediction accuracy and stronger generalization ability but also decreases training time and computational complexity.

• 응용통계연구
• /
• 제25권4호
• /
• pp.669-680
• /
• 2012

Noise removal of document images is a necessary step during preprocessing to recognize characters effectively because it has influences greatly on processing speed and performance for character recognition. We have considered using the spatial filters such as traditional mean filters and Gaussian filters, and wavelet transformed based methods for noise deduction in natural images. However, these methods are not effective for the noise removal of document images. In this paper, we present noise removal of document images using support vector regression. The proposed approach consists of two steps which are SVR training step and SVR test step. We construct an optimal prediction model using grid search with cross-validation in SVR training step, and then apply it to noisy images to remove noises in test step. We evaluate our SVR based method both quantitatively and qualitatively for noise removal in Korean, English and Chinese character documents, and compare it to some existing methods. Experimental results indicate that the proposed method is more effective and can get satisfactory removal results.

• 응용통계연구
• /
• 제25권5호
• /
• pp.829-835
• /
• 2012

When the input features are generated by factors in a classification problem, it is more meaningful to identify important factors, rather than individual features. The $F_{\infty}$-norm support vector machine(SVM) has been developed to perform automatic factor selection in classification. However, the $F_{\infty}$-norm SVM may suffer from estimation inefficiency and model selection inconsistency because it applies the same amount of shrinkage to each factor without assessing its relative importance. To overcome such a limitation, we propose the adaptive $F_{\infty}$-norm ($AF_{\infty}$-norm) SVM, which penalizes the empirical hinge loss by the sum of the adaptively weighted factor-wise $L_{\infty}$-norm penalty. The $AF_{\infty}$-norm SVM computes the weights by the 2-norm SVM estimator and can be formulated as a linear programming(LP) problem which is similar to the one of the $F_{\infty}$-norm SVM. The simulation studies show that the proposed $AF_{\infty}$-norm SVM improves upon the $F_{\infty}$-norm SVM in terms of classification accuracy and factor selection performance.