• 한국지능시스템학회논문지
• /
• 제17권5호
• /
• pp.679-683
• /
• 2007

Vapnik의 통계적 학습이론은 분류, 회귀, 그리고 군집화를 위하여 SVM(support vector machine), SVR(support vector regression), 그리고 SVC(support vector clustering)의 3가지 학습 알고리즘을 포함한다. 이들 중에서 SVC는 가우시안 커널함수에 기반한 지지벡터를 이용하여 비교적 우수한 군집화 결과를 제공하고 있다. 하지만 SVM, SVR과 마찬가지로 SVC도 커널모수와 정규화상수에 대한 최적결정이 요구된다 하지만 대부분의 분석작업에서 사용자의 주관적 경험에 의존하거나 격자탐색과 같이 많은 컴퓨팅 시간을 요구하는 전략에 의존하고 있다. 본 논문에서는 SVC에서 사용되는 커널모수와 정규화상수의 효율적인 결정을 위하여 차분진화를 이용한 DESVC(differential evolution based SVC)를 제안한다 UCI Machine Learning repository의 학습데이터와 시뮬레이션 데이터 집합들을 이용한 실험을 통하여 기존의 기계학습 알고리즘과의 성능평가를 수행한다.

• Communications for Statistical Applications and Methods
• /
• 제14권1호
• /
• pp.133-140
• /
• 2007

The support vector machine has been well developed as a powerful tool for solving classification problems. In many real world applications, each training point has a different effect on constructing classification rule. Lin and Wang (2002) proposed fuzzy support vector machines for this kind of classification problems, which assign fuzzy memberships to the input data and reformulate the support vector classification. In this paper another intuitive approach is proposed by using the fuzzy ${\alpha}-cut$ set. It will show us the trend of classification functions as ${\alpha}$ changes.

• 한국데이터정보과학회:학술대회논문집
• /
• 한국데이터정보과학회 2003년도 추계학술대회
• /
• pp.123-123
• /
• 2003

More elaborated methods allowing the usage of binary classifiers for the resolution of multi-class classification problems are briefly presented. This way of using FSVC to learn a K-class classification problem consists in choosing the maximum applied to the outputs of K FSVC solving a one-per-class decomposition of the general problem.

• 대한원격탐사학회지
• /
• 제40권1호
• /
• pp.93-101
• /
• 2024

Accurate field crop classification is essential for various agricultural applications, yet existing methods face challenges due to diverse crop types and complex field conditions. This study aimed to address these issues by combining support vector machine (SVM) models with multi-seasonal unmanned aerial vehicle (UAV) images, texture information extracted from Gray Level Co-occurrence Matrix (GLCM), and RGB spectral data. Twelve high-resolution UAV image captures spanned March-October 2021, while field surveys on three dates provided ground truth data. We focused on data from August (-A), September (-S), and October (-O) images and trained four support vector classifier (SVC) models (SVC-A, SVC-S, SVC-O, SVC-AS) using visual bands and eight GLCM features. Farm maps provided by the Ministry of Agriculture, Food and Rural Affairs proved efficient for open-field crop identification and served as a reference for accuracy comparison. Our analysis showcased the significant impact of hyperparameter tuning (C and gamma) on SVM model performance, requiring careful optimization for each scenario. Importantly, we identified models exhibiting distinct high-accuracy zones, with SVC-O trained on October data achieving the highest overall and individual crop classification accuracy. This success likely stems from its ability to capture distinct texture information from mature crops.Incorporating GLCM features proved highly effective for all models,significantly boosting classification accuracy.Among these features, homogeneity, entropy, and correlation consistently demonstrated the most impactful contribution. However, balancing accuracy with computational efficiency and feature selection remains crucial for practical application. Performance analysis revealed that SVC-O achieved exceptional results in overall and individual crop classification, while soybeans and rice were consistently classified well by all models. Challenges were encountered with cabbage due to its early growth stage and low field cover density. The study demonstrates the potential of utilizing farm maps and GLCM features in conjunction with SVM models for accurate field crop classification. Careful parameter tuning and model selection based on specific scenarios are key for optimizing performance in real-world applications.

• International Journal of Computer Science & Network Security
• /
• 제24권7호
• /
• pp.108-117
• /
• 2024

The selection and recommendation of a suitable job applicant from the pool of thousands of applications are often daunting jobs for an employer. The recommendation and selection process significantly increases the workload of the concerned department of an employer. Thus, Resume Classification System using the Natural Language Processing (NLP) and Machine Learning (ML) techniques could automate this tedious process and ease the job of an employer. Moreover, the automation of this process can significantly expedite and transparent the applicants' selection process with mere human involvement. Nevertheless, various Machine Learning approaches have been proposed to develop Resume Classification Systems. However, this study presents an automated NLP and ML-based system that classifies the Resumes according to job categories with performance guarantees. This study employs various ML algorithms and NLP techniques to measure the accuracy of Resume Classification Systems and proposes a solution with better accuracy and reliability in different settings. To demonstrate the significance of NLP & ML techniques for processing & classification of Resumes, the extracted features were tested on nine machine learning models Support Vector Machine - SVM (Linear, SGD, SVC & NuSVC), Naïve Bayes (Bernoulli, Multinomial & Gaussian), K-Nearest Neighbor (KNN) and Logistic Regression (LR). The Term-Frequency Inverse Document (TF-IDF) feature representation scheme proven suitable for Resume Classification Task. The developed models were evaluated using F-Score_M, Recall_M, Precission_M, and overall Accuracy. The experimental results indicate that using the One-Vs-Rest-Classification strategy for this multi-class Resume Classification task, the SVM class of Machine Learning algorithms performed better on the study dataset with over 96% overall accuracy. The promising results suggest that NLP & ML techniques employed in this study could be used for the Resume Classification task.

• 한국통신학회논문지
• /
• 제32권4C호
• /
• pp.425-432
• /
• 2007

본 논문에서는 사전정보 없이 입사하는 신호의 변조 형태를 자동 식별하기 위해 변조타입에 대한 민감도가 우수하고, SNR에 대한 변화가 적은 속성을 가진 7개의 특징(key features)들을 선정하였다. 또한 선정된 특징들을 이용하여 총 9종의 변조 신호(아날로그와 디지털 신호 포함)를 분류하기 위한 시뮬레이션을 수행하였다. 소프트웨어 라디오의 고속 변조 인식기 탑재를 고려하여, 4 타입의 변조인식기에 대한 인식 정확도 및 수행시간을 검토하였다. 시뮬레이션 결과 인식시간은 DTC(Decision Tree Classifier)가 가장 빠르게 수행되었고, 인식정확도는 SVC(Support Vector Machine Classifier)과 MDC(Minimum Distance Classifier)가 우수하게 제시되었다. 변조 인식기의 프로토타입은 처리 속도가 가장 우수한 DTC로 구현되었다. 필드 실험 결과, 인식 성능은 DTC 시뮬레이션 결과와 일치하는 것을 확인하였다.

• 산업경영시스템학회지
• /
• 제37권1호
• /
• pp.1-8
• /
• 2014

This paper proposes an emotion classifier from EEG signals based on Bayes' theorem and a machine learning using a perceptron convergence algorithm. The emotions are represented on the valence and arousal dimensions. The fast Fourier transform spectrum analysis is used to extract features from the EEG signals. To verify the proposed method, we use an open database for emotion analysis using physiological signal (DEAP) and compare it with C-SVC which is one of the support vector machines. An emotion is defined as two-level class and three-level class in both valence and arousal dimensions. For the two-level class case, the accuracy of the valence and arousal estimation is 67% and 66%, respectively. For the three-level class case, the accuracy is 53% and 51%, respectively. Compared with the best case of the C-SVC, the proposed classifier gave 4% and 8% more accurate estimations of valence and arousal for the two-level class. In estimation of three-level class, the proposed method showed a similar performance to the best case of the C-SVC.

• 대한의용생체공학회:의공학회지
• /
• 제28권4호
• /
• pp.556-568
• /
• 2007

Unsatisfied results of return of spontaneous circulation (ROSC) estimates were caused by the fact that the predictability of the predictors was insufficient. This unmet estimate of the predictors may be affected by transitional events due to behaviors which occur during cardiopulmonary resuscitation (CPR). We thus hypothesized that the discrepancy of ROSC estimates found in statistical characteristics due to transitional CPR events, may affect the performance of the predictors, and that the performance of the classifier dichotomizing between ROSC and No-ROSC might be different during CPR. In a canine model (n=18) of prolonged ventricular fibrillation (VF), standard CPR was provided with administration of two doses of epinephrine 0 min or 3 min later of the onset of CPR. For the analysis of the likelihood of a successful defibrillation during CPR, Support Vector Classification was adopted to evaluate statistical peculiarity combining time and frequency based predictors: median frequency, frequency band-limited power spectrum, mean segment amplitude, and zero crossing rates. The worst predictable period showed below about 1 min after the onset of CPR, and the best predictable period could be observed from about 1.5 min later of the administering epinephrine through 2.0-2.2 min. As hypothesized, the discrepancy of statistical characteristics of the predictors was reflected in the differences of the classification performance during CPR. These results represent a major improvement in defibrillation prediction can be achieved by a specific timing of the analysis, as a change in CPR transition.

• 한국산학기술학회논문지
• /
• 제21권1호
• /
• pp.169-177
• /
• 2020

과학기술 분야의 연구·개발 결과는 연구보고서 형태로 국가과학기술정보서비스(NTIS)에 제출된다. 각 연구보고서는 국가과학기술 표준 분류체계 (K-NSCC)에 따른 분류코드를 가지고 있는데, 보고서 작성자가 제출 시에 수동으로 입력하게끔 되어있다. 하지만 2000여 개가 넘는 세분류를 가지고 있기에, 분류체계에 대한 정확한 이해가 없이는 부정확한 분류코드를 선택하기 십상이다. 새로이 수집되는 연구보고서의 양과 다양성을 고려해 볼 때, 이들을 기계적으로 보다 정확하게 분류할 수 있다면 보고서 제출자의 수고를 덜어줄 수 있을 뿐만 아니라, 다른 부가 가치적인 분석 서비스들과의 연계가 수월할 것이다. 하지만, 국내에서 과학기술표준 분류체계에 기반을 둔 문서 자동 분류 연구 사례는 거의 없으며 공개된 학습데이터도 전무하다. 본 연구는 KISTI가 보유하고 있는 최근 5년간 (2013년~2017년) NTIS 연구보고서 메타정보를 활용한 최초의 시도로써, 방대한 과학기술표준 분류체계를 기반으로 하는 국내 연구보고서들을 대상으로 높은 성능을 보이는 문서 자동 분류기법을 도출하는 연구를 진행하였다. 이를 위해, 과학기술 표준분류 체계에서 과학기술 분야의 연구보고서를 분류하기에 적합한 중분류 210여 개를 선별하였으며, 연구보고서 메타 데이터의 특성을 고려한 전처리를 진행하였다. 특히, 가장 영향력 있는 필드인 과제명(제목)과 키워드만을 이용한 TK_CNN 기반의 딥러닝 기법을 제안한다. 제안 모델은 텍스트 분류에서 좋은 성능을 보이고 있는 기계학습법들 (예, Linear SVC, CNN, GRU등)과 비교하였으며, Top-3 F1점수 기준으로 1~7%에 이르는 성능 우위를 확인하였다.