Earticle

This study aims to identify an AI classification model that is optimal for the classification of linguistic data. For this purpose, three commonly used classification models (XGBoost classifier, Random Forest Classifier, and SVM classifier) are compared in terms of their performance. Specifically, the three models are trained to classify the input data into essays and dialogues based on the syntactic complexity-related characteristics that distinguish between essays and dialogues. To determine if a model performing well on balanced data also performs well on imbalanced data, the three models’ performances are measured under two conditions: when the training dataset is balanced and when it is imbalanced. The performances of the trained models on the first test dataset are evaluated using accuracy, F1-score, normalized confusion matrix, and the area under the receiver operating characteristic curve. The performances on the second test dataset are assessed in terms of accuracy, confusion matrix, precision, and recall. The results demonstrate that the Random Forest Classifier has the best performance among the three models regardless of the balance of training data.

Breast cancer is reported as the second most deadly cancer in the world and the main of mortality among the women, on which public awareness has been increasing during the last few decades. This is why several works are made to develop help tools for disease diagnosis. Computer-Assisted Diagnosis (CAD) is based on 3 main steps: segmentation, feature extraction and classification in order to generate a final decision. Classification phase is the key step in this process; for that, many research have been accentuated in this domain and many techniques were be proposed. Kernel combination is a current active topic in the field of machine learning. It takes benefit of classifier algorithms. it allows to choose the kernel functions according to the features vectors. The combination of Kernel-based classifiers was proposed as a research way allowing reliability recognition by using the complementarily which can exist between classifiers. This study investigated a computer-aided diagnosis system for breast cancer by developing a novel classifier fusion scheme based on fusion of three support vector machine classifier. Each one is associated with an homogenous family of features (Hu moments; central moments, Haralick moment) as efficient learning algorithm and diversity between features family as fusion criteria to ensure best performance. Our experiments demonstrated that developed system using Database for Screening Mammography (DDSM) database achieve very encouraging results when compared with past works using the same information.

Epilepsy is a perilous neurological disease covering about 4-5% of total population of the world. Its main characteristics are seizures which occur due to certain disturbance in brain function. During epileptic seizures the patient is unaware of their physical as well as mental condition and hence physical injury may occur. Proper health care must be provided to the patients and this can be achieved only if the seizures are detected correctly in time. In this dissertation work, a system is designed using wavelet decomposition method and different training algorithms to train the neural network for classification of the EEG signals. The system was tested and compared with Support Vector Machine (SVM) classifier. The system accuracy comes out to be 99.97%.

$\textbullet$ Lane detection by TFALDA $\textbullet$ SVM for large scale data and multiclass classification problem $\textbullet$ TLC Classification $\textbullet$ Lateral offset estimation by IPT $\textbullet$ Lane departure warning by a fuzzy system $\textbullet$ Experimental results by HiLS $\textbullet$ Conclusion

It is important that the training stage of a supervised classification is designed to provide the spectral information. On the design of the training stage of a classification typically calls for the use of a large sample of randomly selected pure pixels in order to characterize the classes. Such guidance is generally made without regard to the specific nature of the application in-hand, including the classifier to be used. An approach to the training of a support vector machine (SVM) classifier that is the opposite of that generally promoted for training set design is suggested. This approach uses a small sample of mixed spectral responses drawn from purposefully selected locations (geographical boundaries) in training. A sample of such data should, however, be easier and cheaper to acquire than that suggested by traditional approaches. In this research, we evaluated them against traditional approaches with high-resolution satellite data. The results proved that it can be used small mixed pixels to derive a classification with similar accuracy using a large number of pure pixels. The approach can also reduce substantial costs in training data acquisition because the sampling locations used are commonly easy to observe.

본 논문은 비 접근 지역에 존재하는 관심물체의 위치를 고해상도 광학 위성영상을 이용하여 찾아내기 위한 방법을 제안한다. 관심물체는 정확하게 규정된 크기와 모양을 갖는 것이 아니라, 개념적으로 유사한 패턴을 가진 물체들의 집합이다. 본 논문에서는 유사 객체 검색에서 Histogram of Gradients (HOG) feature를 이용하여 입력 영상의 관심물체의 특징을 추출하고, 추출된 특징 데이터를 이용하여 다른 영상들의 관심물체를 탐색하는 Support Vector Machine (SVM) 학습 및 분류기를 개발하였다. 제안한 방법은 관심물체를 자동으로 찾아줌으로써, 넓은 영역에서 수동으로 관심물체를 탐색하는데 소요되는 시간과 노력을 줄일 수 있는 효과가 있음을 확인하였다.

In this paper, we propose a method to detect interesting objects in inaccessible areas using high resolution satellite images. We define the interesting objects as a set of objects which have conceptually similar image patterns, not having exact sizes or shapes. In this paper, we developed a learning and classifier of Support Vector Machine (SVM) that extracts characteristic data for inputted images using Histogram of Gradients (HOG) feature and detects similar objects in other images using the characteristic data. As automatic search of interesting objects in our proposed method, we identify that our method provides reduced time and efforts for manual searching similar objects.

This paper proposes a support vector machine (SVM) based power system voltage stability classifier using local measurement data. The excellent performance of the SVM in the classification related to time-series prediction matches the real-time data of PMU for monitoring power system dynamics. The methodology for fast monitoring of the system is initiated locally which aims to leave sufficient time to perform immediate corrective actions to stop system degradation by the effect of major disturbances. This paper briefly describes the mathematical background of SVM, and explains the procedure for fast classification of voltage stability using the SVM algorithm. To illustrate the effectiveness of the classifier, this paper includes numerical examples with a 11-bus test system.

This paper proposes a new concept of support vector machine (SVM) based voltage stability classifier using time-series phasor data. The classifier, based on a linear SVM, can provide very effective signals for identification of long-term voltage stability. In addition, the SVM output is applicable as an voltage stability indicator when an amount of corrective controls are performed just to make the system reach around at the maximum deliverable point.

고성능의 질의응답 시스템을 구현하기 위해서는 사용자의 질의 유형의 난이도에 관계없이 의도를 파악할 수 있는 질의유형 분류기가 필요하다. 본 논문에서는 문서 범주화 기법을 이용한 질의 유형 분류기를 제안한다. 본 논문에서 제안하는 질의 유형 분류기의 분류 과정은 다음과 같다. 우선, 사용자 질의에 포함된 어휘, 품사, 의미표지와 같은 다양한 정보를 이용하여 사용자 질의로부터 자질들을 추출한다. 이 과정에서 질의의 구문 특성을 반영하기 위해서 슬라이딩 윈도 기법을 이용한다. 또한, 다량의 자질들 중에서 유용한 것들만을 선택하기 위해서 카이 제곱 통계량을 이용한다. 추출된 자질들은 벡터 공간 모델로 표현되고, 문서 범주화 기법 중 하나인 지지 벡터 기계(support vector machine, SVM)는 이 정보들을 이용하여 질의 유형을 분류한다. 본 논문에서 제안하는 시스템은 질의 유형 분류 문제에지지 벡터 기계를 이용한 자동문서 범주화 기법을 도입하여 86.4%의 높은 분류 정확도를 보였다. 또한 질의 유형 분류기를 통계적 방법으로 구축함으로써 lexico-syntactic 패턴과 같은 규칙을 기술하는 수작업을 배제할 수 있으며, 응용 영역의 변화에 대해서도 안정적인 처리와 빠른 이식성을 보장한다.