Earticle

본 연구는 여러 단어로 구성된 기억 단서에 의해 유발된 뇌파를 이용하여 목격 여부를 우연 수준 이상으로 구별할 수 있는지 알아보기 위해 수행되었다. Ham, Kim과 Jeong(2018)의 연구에서 수집한 사건관련전위 자료(n=69)를 재분석하여 선형 서포트 벡터 머신(support vector machine, SVM) 분류 모델의 정확성을 평가했다. 참가자들마다 절도 범죄를 재연한 동영상에서 목격할 수 있었던 물건과 목격하지 않은 물건을 정확하게 분류한 적중 시행과 정확 기각 시행의 뇌파가 분석에 이용되었다. 선형 SVM 커널을 이용하여 뇌파를 분류한 결과, 기억 단서 제시 후 800∼850ms 구간에서 분류 정확률 평균이 57.43%로 가장 높았다. 이런 결과는 기억 단서가 제시되었을 때 이 단서와 관련된 세부적인 정보 인출이 이뤄지는 것으로 여겨지는 구간의 뇌파를 분석하여 목격 여부를 구별할 수 있음을 시사한다. 마지막으로 수사 현장에서 뇌파를 활용할 때 고려해야 할 점에 대해 논의하였다.

The focus of this study was discriminating the eyewitness memory using single-trial electroencephalogram (EEG) evoked by memory cues composed of multiple words. We reanalyzed the event-related potentials (ERP) data (n=69) from Ham, Kim, & Jeong (2018) studies, and two-class classification was conducted to distinguish correctly witnessed objects vs unwitnessed objects trials using linear support vector machine (SVM) algorithm. The single-trial classification analysis showed the post-stimulus EEG activity between 800 to 850 ms was the most accurate interval for the memory classification (57.43%). This result suggests that the EEG during memory retrieval can be used to determine whether or not it is witnessed. Finally, we discussed some points to consider when using EEG for eyewitness memory classification.

In this paper, a novel rotor flux estimation method of an induction motor using support vector regression(SVR) is presented. Two well-known different flux models with respect to voltage and current are necessary to estimate the rotor flux of an induction motor. Training of SVR which the theory of the SVR algorithm leads to a quadratic programming(QP) problem. The proposed SVR rotor flux estimator guarantees the improvement of performance in the transient and steady state in spite of parameter variation circumstance. The validity and the usefulness of proposed algorithm are throughly verified through numerical simulation.

고품위 석회암은 다양한 산업에서 활용되고 있는 고부가가치 자원으로 광체의 안정적인 확보, 채광기술의 효율적인 개선이 요구되고 있다. 본 연구에서는 석회암 광산 현장에서의 신속한 품위 측정 기술 개발을위하여 가시광/근적외선 영역의 스펙트럼을 이용한 CaO 품위 평가 기법을 개발하였다. 개발한 기법은 측정대상 암석을 support vector machine을 이용하여 스펙트럼이 가장 유사한 석회암으로 구분하고, 대상의 CaO 품위를 분류된 석회암의 평균 품위로 평가한다. 제안한 기법을 갑산층 고품위 석회암 광산의 암석에 적용한결과 암석의 재분류 정확도는 59%, 품위의 평균 제곱근 오차는 1.96%로 나타났다. 개발된 기법은 광산에 대한경험이 풍부한 작업자가 없는 경우 석회암의 CaO 품위 추정에 유용하게 활용될 수 있을 것으로 판단된다.

High-calcium limestone is a highly valuable geological material since it has been used as an industrial source material for various applications. Therefore, maintenance of a sustainable ore reserves and development of cost-effective mining techniques are necessary. This study presents a CaO estimation technique using visible/near-infrared reflectance spectrum and support vector machine for rapid in-situ CaO analysis in limestone mining. The proposed method classifies rock samples based on the spectral properties of training datasets using support vector machine and estimates the CaO content as average of CaO of classified results. The developed method was applied to limestone rocks collected from high-calcium limestone mines of Gabsan Formation in Korea. The data analysis results show that the success rate of reclassification is 59% and the root mean square error of estimation is 1.96%, hence it is concluded that the developed method is able to analyze the CaO content in a limestone mine even if experienced mining geologists are unavailable.

폭발적으로 증가하는 인터넷 환경에서 정보보호는 가장 중요한 고려사항 중의 하나이다. 현재 이에 대한 대응방안으로 IDS, 방화벽, VPN 등 여러 보안 솔루션들이 사용되고 있지만 TCP/IP를 근간으로 하는 인터넷 환경은 기본적으로 프로토콜 자체의 취약성을 가지고 있다. 그 중에서도, TCP/IP 헤더 중 ICMP Payload. Identification(ID), Sequence Number(SEQ), Acknowledge(ACK). Timestamp의 필드 내용을 조작함으로써 특정 정보를 전송할 수 있는 은닉채널이 가능하다고 이미 알려져 있다. 특히 본 논문에서는 TCP/IP 헤더의 여러 필드들 중에서도 IP 헤더의 ID 필드, TCP 헤더의 SEQ 필드를 이용한 은닉채널 탐지에 초점을 맞추었으며, 이러한 은닉채널의 탐지를 위하여, 패턴분류 문제 있어서 우수한 성능을 보이는 것으로 알려져 있는 Support Vector Machine(SVM)을 사용하였다. 본 논문의 실험결과에서는 제안된 탐지방안이 정상 TCP/IP 트래픽으로부터 은닉채널이 포함된 TCP/IP 패킷을 구분할 수 있음을 보여주었다.

In explosively increasing internet environments, information security is one of the most important consideration. Nowadays, various security solutions are used as such problems countermeasure; IDS, Firewall and VPN. However, basically internet has much vulnerability of protocol itself. Specially, it is possible to establish a covert channel using TCP/IP header fields such as identification, sequence number, acknowledge number, timestamp and so on. In this Paper, we focus cm the covert channels using identification field of IP header and the sequence number field of TCP header. To detect such covert channels, we used Support Vector Machine which has excellent performance in pattern classification problems. Our experiments showed that proposed method could discern the abnormal cases(including covert channels) from normal TCP/IP traffic using Support Vector Machine.

인터넷 환경의 급속한 발전으로 인하여 이메일을 통한 메시지 교환은 급속히 증가하고 있다. 그러나 이메일의 편리성에도 불구하고 개인이나 기업에서는 스팸메일로 인한 시간과 비용의 낭비가 크게 증가하고 있다. 이러한 스팸메일에 대한 문제들을 해결하기 위하여 많은 방법들이 연구되고 있으며, 대표적인 방법으로 키워드를 이용한 패턴매칭이나 나이의 베이지안 방식과 같은 확률을 이용한 방법들이 있다. 본 논문에서는 기존의 연구에 대한 문제점을 보완하기 위하여 패턴 분류문제에 있어서 우수한 성능을 보이는 Support Vector Machine을 사용하여 정상적인 메일과 스팸메일을 분류하는 방안을 제시하였으며, 특히 n-Gram을 사용하여 생성된 색인어와 단어사전을 학습데이터 생성에 사용함으로서 효율적인 학습을 수행하도록 하였다. 결론에서는 제안된 방법에 대한 성능을 검증하기 위하여 기존의 연구 결과와 비교함으로서 제안된 방법의 성능을 검증하였다.

Because of a rapid growth of internet environment, it is also fast increasing to exchange message using e-mail. But, despite the convenience of e-mail, it is rising a currently bi9 issue to waste their time and cost due to the spam mail in an individual or enterprise. Many kinds of solutions have been studied to solve harmful effects of spam mail. Such typical methods are as follows; pattern matching using the keyword with representative method and method using the probability like Naive Bayesian. In this paper, we propose a classification method of spam mails from normal mails using Support Vector Machine, which has excellent performance in pattern classification problems, to compensate for the problems of existing research. Especially, the proposed method practices efficiently a teaming procedure with a word dictionary including a generated index by the n-Gram. In the conclusion, we verified the proposed method through the accuracy comparison of spm mail separation between an existing research and proposed scheme.

The prediction of short-term traffic flow is the theoretical basis of intelligent transportation as well as the key technology in traffic flow induction systems. The research on short-term traffic flow prediction has showed the considerable social value. At present, the support vector regression (SVR) intelligent prediction model that is suitable for small samples has been applied in this domain. Aiming at parameter selection difficulty and prediction accuracy improvement, the artificial bee colony (ABC) is adopted in optimizing SVR parameters, which is referred to as the ABC-SVR algorithm in the paper. The simulation experiments are carried out by comparing the ABC-SVR algorithm with SVR algorithm, and the feasibility of the proposed ABC-SVR algorithm is verified by result analysis. Continuously, the simulation experiments are carried out by comparing the ABC-SVR algorithm with particle swarm optimization SVR (PSO-SVR) algorithm and genetic optimization SVR (GA-SVR) algorithm, and a better optimization effect has been attained by simulation experiments and verified by statistical test. Simultaneously, the simulation experiments are carried out by comparing the ABC-SVR algorithm and wavelet neural network time series (WNN-TS) algorithm, and the prediction accuracy of the proposed ABC-SVR algorithm is improved and satisfactory prediction effects have been obtained.

Condition classification is an important step in machinery fault detection, which is a problem of pattern recognition. Currently, there are a lot of techniques in this area and the purpose of this paper is to investigate two popular recognition techniques, namely hidden Markov model and support vector machine. At the beginning, we briefly introduced the procedure of feature extraction and the theoretical background of this paper. The comparison experiment was conducted for gearbox fault detection and the analysis results from this work showed that support vector machine has better classification performance in this area.

Currently, microarray gene expression data take advantage of the sufficient classification of cancers, which addresses the problems relating to cancer causes and treatment regimens. However, the sample size of gene expression data is often restricted, because the price of microarray technology on studies in humans is high. We propose enhancing the gene expression classification of support vector machines with generative adversarial networks (GAN-SVMs). A GAN that generates new data from original training datasets was implemented. The GAN was used in conjunction with nonlinear SVMs that efficiently classify gene expression data. Numerical test results on 20 low-sample-size and very high-dimensional microarray gene expression datasets from the Kent Ridge Biomedical and Array Expression repositories indicate that the model is more accurate than state-of-the-art classifying models.

Automobile credit business has developed rapidly in recent years, and corresponding default phenomena occur frequently. Credit default will bring great losses to automobile financial institutions. Therefore, the successful prediction of automobile credit default is of great significance. Firstly, the missing values are deleted, then the random forest is used for feature selection, and then the sample data are randomly grouped. Finally, six prediction models of support vector machine (SVM), random forest and k-nearest neighbor (KNN), logistic, decision tree, and artificial neural network (ANN) are constructed. The results show that these six machine learning models can be used to predict the default of automobile credit. Among these six models, the accuracy of decision tree is 0.79, which is the highest, but the comprehensive performance of SVM is the best. And random grouping can improve the efficiency of model operation to a certain extent, especially SVM.

In order to classify a web page as being benign or malicious, we designed 14 basic and 16 extended features. The basic features that we implemented were selected to represent the essential characteristics of a web page. The system heuristically combines two basic features into one extended feature in order to effectively distinguish benign and malicious pages. The support vector machine can be trained to successfully classify pages by using these features. Because more and more malicious web pages are appearing, and they change so rapidly, classifiers that are trained by old data may misclassify some new pages. To overcome this problem, we selected an adaptive support vector machine (aSVM) as a classifier. The aSVM can learn training data and can quickly learn additional training data based on the support vectors it obtained during its previous learning session. Experimental results verified that the aSVM can classify malicious web pages adaptively.

Among the "five major injuries" in the construction industry-namely, falls from height, electric shock, object strike, mechanical injury, and collapse-fall accidents from height exhibit the highest incidence rate and pose significant dangers. To mitigate the frequency of fall accidents, a fall detection algorithm was developed based on three-axis acceleration sensors. This intelligent algorithm analyzes the acceleration data of the human body during different motion states. It extracts eigenvalues from the acceleration data, processes and analyzes them using the support vector machine method, and performs data classification to determine if a person has undergone a fall. Through experimental testing and validation, this method has demonstrated a high level of reliability in the detection of falling behavior. The accuracy of this algorithm surpasses that of traditional threshold detection methods and decision tree-based algorithms. This enhancement improves its potential for application in the detection of falls from heights in construction settings.

There are many factors that affect the wind speed. In addition, the randomness of wind speed also leads to low prediction accuracy for wind speed. According to this situation, this paper constructs the short-time forecasting model based on the least squares support vector machines (LSSVM) to forecast the wind speed. The basis of the model used in this paper is support vector regression (SVR), which is used to calculate the regression relationships between the historical data and forecasting data of wind speed. In order to improve the forecast precision, historical data is clustered by cluster analysis so that the historical data whose changing trend is similar with the forecasting data can be filtered out. The filtered historical data is used as the training samples for SVR and the parameters would be optimized by particle swarm optimization (PSO). The forecasting model is tested by actual data and the forecast precision is more accurate than the industry standards. The results prove the feasibility and reliability of the model.

Support vector machines (SVMs) have become one of the most popular approaches to learning from examples and have many potential applications in science and engineering. However, their applications in fault diagnosis of rotating machinery are rather limited. Most of the published papers focus on some special fault diagnoses. This study covers the overall diagnosis procedures on most of the faults experienced in rotating machinery and examines the performance of different SVMs strategies. The excellent characteristics of SVMs are demonstrated by comparing the results obtained by artificial neural networks (ANNs) using vibration signals of a fault simulator.

Music brings pleasure and relaxation to people. Therefore, it is necessary to classify musical genres based on scenes. Identifying favorite musical genres from massive music data is a time-consuming and laborious task. Recent studies have suggested that machine learning algorithms are effective in distinguishing between various musical genres. However, meeting the actual requirements in terms of accuracy or timeliness is challenging. In this study, a hybrid machine learning model that combines a deep residual auto-encoder (DRAE) and support vector machine (SVM) for musical genre recognition was proposed. Eight manually extracted features from the Mel-frequency cepstral coefficients (MFCC) were employed in the preprocessing stage as the hybrid music data source. During the training stage, DRAE was employed to extract feature maps, which were then used as input for the SVM classifier. The experimental results indicated that this method achieved a 91.54% F1-score and 91.58% top-1 accuracy, outperforming existing approaches. This novel approach leverages deep architecture and conventional machine learning algorithms and provides a new horizon for musical genre classification tasks.

A model based on genetic algorithm optimization, GA-SVM, is proposed to warn university students of their status. This model improves the predictive effect of support vector machines. The genetic optimization algorithm is used to train the hyperparameters and adjust the kernel parameters, kernel penalty factor C, and gamma to optimize the support vector machine model, which can rapidly achieve convergence to obtain the optimal solution. The experimental model was trained on open-source datasets and validated through comparisons with random forest, backpropagation neural network, and GA-SVM models. The test results show that the genetic algorithm-optimized radial basis kernel support vector machine model GA-SVM can obtain higher accuracy rates when used for early warning in university learning.

Regression analysis is one of the most widely utilized methods because of its adaptability and simplicity. Recently, the machine learning (ML) approach, which is one aspect of regression methods, has been gaining attention from researchers, including social science, but there are only a few studies that compared the traditional approaches with the ML approach. This study was conducted to explore the usefulness of the ML approach by comparing the ordinary least square estimate (OLS), the stochastic gradient descent algorithm (SGD), and the support vector regression (SVR) with a model predicting and explaining the tuberculosis screening intention. The optimized models were evaluated by four aspects: computational speed, effect and importance of individual predictor, and model performance. The result demonstrated that each model yielded a similar direction of effect and importance in each predictor, and the SVR with the radial kernel had the finest model performance compared to its computational speed. Finally, this study discussed the usefulness and attentive points of the ML approach when a researcher utilizes it in the field of communication.

SNS의 확산으로 온라인 상점에서는 상품에 대한 주관적인 의견이 내포되어 있는 고객리뷰 정보가 빠르게 생성되고 확산되어 다른 고객들에게 큰 영향을 미치고 있다. 이와 더불어, 고객들의 긍정적 또는 부정적 의견을 분석하여 개선방안을 모색하려는 오피니언마이닝(opinion mining)이 주목 받고 있다. 고객리뷰에 내포된 감성정보를 가진 용어들은 감성분류를 하는데 가장 중요한 역할을 하기 때문에 영향력이 높은 용어를 선별하는 것이 가장 중요하다. 본 연구에서는 품사태깅을 이용하여 최적의 용어들을 선별하고 용어정보에 기반한 문서수준에서의 감성분류모형을 제안하고자 한다. 고객 리뷰의 감성분류모형에 대표적인 기계학습기법인 SVM을 적용하고, SVM의 입력변수 선정과정에 품 사태깅 방식과 용어추출기법을 다르게 조합하고 사용하여 긍정적/부정적 문서를 분류하였다. 본 연구 에서 제안한 감성분류모형의 성과를 검증하기 위해 아마존(Amazon.com)의 영화와 도서에 대한 고객리 뷰 80,000개를 수집하여 불필요한 용어들을 제거한 후 품사태깅을 통해 용어를 추출하였다. 추출된 용어는 문서빈도, TF-IDF, 정보획득량, 카이제곱 통계량의 값을 산출하여 값을 통해 용어들을 순위화하 고, 각 상위 20개에 해당하는 최적의 용어를 선정한 후 SVM을 이용하였다. 제안된 감성분류모형을 통해 기존 연구에서 언급한 형용사만을 사용한 예측변수와 4품사를 사용한 예측변수에서의 실험결과 를 통해 비교 분석하였다. 카이제곱 통계량 기반의 감성분류모형이 다른 모형보다 예측성과가 가장 우수하게 나타나는 것을 확인할 수 있었다. 본 연구에서 제안된 문서수준에서의 용어기반 감성분류모 형을 이용함으로써 온라인 상점에서의 서비스 개선과 경쟁력 확보에 많은 도움이 될 것으로 기대된다.

Customer reviews which include subjective opinions for the product or service in online store have been generated rapidly and their influence on customers has become immense due to the widespread usage of SNS. In addition, a number of studies have focused on opinion mining to analyze the positive and negative opinions and get a better solution for customer support and sales. It is very important to select the key terms which reflected the customers’ sentiment on the reviews for opinion mining. We proposed a document-level terms-based sentiment classification model by select in the optimal terms with part of speech tag. SVMs (Support vector machines) are utilized to build a predictor for opinion mining and we used the combination of POS tag and four terms extraction methods for the feature selection of SVM. To validate the proposed opinion mining model, we applied it to the customer reviews on Amazon. We eliminated the unmeaning terms known as the stopwords and extracted the useful terms by using part of speech tagging approach after crawling 80,000 reviews. The extracted terms gained from document frequency, TF-IDF, information gain, chi-squared statistic were ranked and 20 ranked terms were used to the feature of SVM model. Our experimental results show that the performance of SVM model with four POS tags is superior to the benchmarked model, which are built by extracting only adjective terms. In addition, the SVM model based on Chi-squared statistic for opinion mining shows the most superior performance among SVM models with 4 different kinds of terms extraction method. Our proposed opinion mining model is expected to improve customer service and gain competitive advantage in online store.

기업 경쟁력 강화의 중요한 이슈인 대량 개별화(mass-customization)의 실행을 위하여 통합 고객관계 관리 프로세스로서의 CRM(customer relationship management)에 대한 관심과 활용에 대한 필요성은 점점 더 높아지고 있다. 특히, 기존 고객들의 구매 정보를 기반으로 고객의 구매 패턴을 파악하고 의도를 예측하는 것은 오늘날 실질적인 판매 전략을 수립하는 마케팅 분야에서 상당히 큰 비중을 차지하고 있다. 고객의 구매의도 예측에는 대량의 데이터로부터 과거에 인지하지 못했던 의미 있고, 근거 있는 정보를 추출하는 데이터마이닝(datamining)이 주로 사용되고 있다. 기존의 구매의도 예측에 사용된 데이터마이닝 기법들은 주로 신경망(neural networks)과 로지스틱 회귀분석(logistic regression analysis)이었 는데, 예측 정확성 및 모형 구축의 어려움으로 인한 다양한 문제점들이 제기되고 있는 실정이다. 따라 서, 본 논문에서는 기존의 기법들이 가지고 있는 단점들을 개선하기 위하여 신경망과 로지스틱 회귀분 석 외에 연관규칙(association rule), 연관성 매트릭스(association matrix), 의사결정 나무(decision tree), 베이지안 망(bayesian network), SVM(support vector machine) 기법들을 추가로 제안하였다. 본 연구의 목적은 고객의 특정 상품에 대한 구매의도 예측을 위하여 새로운 알고리즘을 제시하기보다는 기존의 다양한 데이터마이닝 기법들을 적용시켜 봄으로써, 가장 우수한 예측 성과를 나타내는 기법을 발견하는 것이다. 연구에 사용된 자료는 기존의 연구에서는 적용되지 않았던 편의점의 영수증 데이터이다. 예측 목표상품은 카테고리화 된 ‘우유'와 ‘냉동식품'이며, 제안된 기법들의 신뢰성을 위하여 전체 데이터를 10개의 training과 test 셋으로 중복되지 않게 구분함과 동시에 10번의 교차 검증(cross validation)을 실시하였다. 실험 결과 SVM이 영수증 데이터를 이용한 고객의 특정 상품에 대한 구매의도 예측에서 가장 우수한 성과를 나타내는 것을 확인하였다