• 한국통신학회논문지
• /
• 제33권8B호
• /
• pp.707-718
• /
• 2008

Traffic classification의 방법은 동적으로 변하는 application의 변화에 대처하기 위하여 페이로드나 port를 기반으로 하는 것에서 ML 알고리즘을 기반으로 하는 것으로 변하여 가고 있다. 그러나 현재의 ML 알고리즘을 이용한 traffic classification 연구는 offline 환경에 맞추어 진행되고 있다. 특히, 현재의 기존 연구들은 testing 방법으로 cross validation을 이용하여 traffic classification을 수행하고 있으며, traffic flow를 기반으로 classification 결과를 제시하고 있다. 본 논문에서는 testing방법으로 cross validation과 split validation을 이용했을 때, traffic classification의 정확도 결과를 비교한다. 또한 바이트를 기반으로 한 classification의 결과와 flow를 기반으로 한 classification의 결과를 비교해 본다. 본 논문에서는 J48, REPTree, RBFNetwork, Multilayer perceptron, BayesNet, NaiveBayes와 같은 ML 알고리즘과 다양한 feature set을 이용하여 트래픽을 분류한다. 그리고 split validation을 이용한 traffic classification에 적합한 최적의 ML 알고리즘과 feature set을 제시한다.

• 한국정보통신학회논문지
• /
• 제24권10호
• /
• pp.1341-1347
• /
• 2020

부정맥 분류를 위한 기존 연구들은 분류의 정확성을 높이기 위해 신경회로망(Artificial Neural Network), 기계학습(Machine Learning) 등을 이용한 방법이 연구되어 왔다. 특히 딥러닝은 신경회로망의 문제인 은닉층 개수의 한계를 해결함으로 인해 인공 지능 기반의 부정맥 분류에 많이 사용되고 있다. 본 연구에서는 AR 기반의 특징점 추출과 딥러닝을 통한 부정맥 분류 방법을 제안한다. 이를 위해 먼저 잡음을 제거한 ECG 신호에서 R파를 검출하고 자기 회귀 모델을 통하여 최적의 QRS와 RR간격을 추출하였다. 이후 딥러닝을 통한 지도학습 방법으로 가중치를 학습시키고 부정맥을 분류하였다. 제안된 방법의 타당성 평가를 위해 MIT-BIH 부정맥 데이터베이스를 통해 각 파라미터에 따른 훈련 및 분류 정확도를 확인하였다. 성능 평가 결과 PVC는 약 97% 이상의 평균 분류율을 나타내었다.

• 디지털융복합연구
• /
• 제19권8호
• /
• pp.59-73
• /
• 2021

본 연구는 2020학년도 1학기에 원격강의를 수강한 일반대학의 대학생들이 인식하는 학습실재감이 학습성과에 미치는 영향 및 학습몰입의 매개효과를 실증적으로 규명하였다. 서울·경기지역 소재 일반대학을 다니는 대학생들을 대상으로 2020년 9월 15일부터 약 1달 간 온라인 설문을 실시하여, 총 293명의 자료를 분석하였다. 연구결과, 첫째, 학습 실재감은 학습몰입과 학습성과에 영향을 미쳤으며, 학습몰입은 학습성과에 영향을 미치는 것으로 나타났다. 둘째, 학습 몰입은 학습실재감과 학습성과의 관계에서 매개효과가 있는 것으로 나타났다. 본 연구는 코로나 19 대응차원으로 전환한 원격강의를 수강한 일반대학의 대학생들이 인식한 학습실재감이 학습성과에 미치는 영향과 학습몰입의 매개효과를 검증하였다는데 의의가 있다.

• Journal of information and communication convergence engineering
• /
• 제19권2호
• /
• pp.79-83
• /
• 2021

This paper proposes a novel image classification method based on few-shot learning, which is mainly used to solve model overfitting and non-convergence in image classification tasks of small datasets and improve the accuracy of classification. This method uses model structure optimization to extend the basic convolutional neural network (CNN) model and extracts more image features by adding convolutional layers, thereby improving the classification accuracy. We incorporated certain measures to improve the performance of the model. First, we used general methods such as setting a lower learning rate and shuffling to promote the rapid convergence of the model. Second, we used the data expansion technology to preprocess small datasets to increase the number of training data sets and suppress over-fitting. We applied the model to 10 monkey species and achieved outstanding performances. Experiments indicated that our proposed method achieved an accuracy of 87.92%, which is 26.1% higher than that of the traditional CNN method and 1.1% higher than that of the deep convolutional neural network ResNet50.

• International Journal of Computer Science & Network Security
• /
• 제23권8호
• /
• pp.49-62
• /
• 2023

There has been a rapid increase in the creation and alteration of new malware samples which is a huge financial risk for many organizations. There is a huge demand for improvement in classification and detection mechanisms available today, as some of the old strategies like classification using mac learning algorithms were proved to be useful but cannot perform well in the scalable auto feature extraction scenario. To overcome this there must be a mechanism to automatically analyze malware based on the automatic feature extraction process. For this purpose, the dynamic analysis of real malware executable files has been done to extract useful features like API call sequence and opcode sequence. The use of different hashing techniques has been analyzed to further generate images and convert them into image representable form which will allow us to use more advanced classification approaches to classify huge amounts of images using deep learning approaches. The use of deep learning algorithms like convolutional neural networks enables the classification of malware by converting it into images. These images when fed into the CNN after being converted into the grayscale image will perform comparatively well in case of dynamic changes in malware code as image samples will be changed by few pixels when classified based on a greyscale image. In this work, we used VGG-16 architecture of CNN for experimentation.

• Geomechanics and Engineering
• /
• 제37권6호
• /
• pp.539-554
• /
• 2024

This study explores development of prediction model for seismic site classification through the integration of machine learning techniques with horizontal-to-vertical spectral ratio (HVSR) methodologies. To improve model accuracy, the research employs outlier detection methods and, synthetic minority over-sampling technique (SMOTE) for data balance, and evaluates using seven machine learning models using seismic data from KiK-net. Notably, light gradient boosting method (LGBM), gradient boosting, and decision tree models exhibit improved performance when coupled with SMOTE, while Multiple linear regression (MLR) and Support vector machine (SVM) models show reduced efficacy. Outlier detection techniques significantly enhance accuracy, particularly for LGBM, gradient boosting, and voting boosting. The ensemble of LGBM with the isolation forest and SMOTE achieves the highest accuracy of 0.91, with LGBM and local outlier factor yielding the highest F1-score of 0.79. Consistently outperforming other models, LGBM proves most efficient for seismic site classification when supported by appropriate preprocessing procedures. These findings show the significance of outlier detection and data balancing for precise seismic soil classification prediction, offering insights and highlighting the potential of machine learning in optimizing site classification accuracy.

• Journal of Information Processing Systems
• /
• 제18권2호
• /
• pp.197-207
• /
• 2022

The applications and user interfaces (UIs) of smart mobile devices are constantly diversifying. For example, deep learning can be an innovative solution to classify widgets in screen images for increasing convenience. To this end, the present research leverages captured images and the ReDraw dataset to write deep learning datasets for image classification purposes. First, as the validation for datasets using ResNet50 and EfficientNet, the experiments show that the dataset composed in this study is helpful for classification according to a widget's functionality. An implementation for widget detection and classification on RetinaNet and EfficientNet is then executed. Finally, the research suggests the Widg-C and Widg-D datasets-a deep learning dataset for identifying the widgets of smart devices-and implementing them for use with representative convolutional neural network models.

• Journal of information and communication convergence engineering
• /
• 제21권1호
• /
• pp.9-16
• /
• 2023

The natural language on social network platforms has a certain front-to-back dependency in structure, and the direct conversion of Chinese text into a vector makes the dimensionality very high, thereby resulting in the low accuracy of existing text classification methods. To this end, this study establishes a deep learning model that combines a big data ultra-deep convolutional neural network (UDCNN) and long short-term memory network (LSTM). The deep structure of UDCNN is used to extract the features of text vector classification. The LSTM stores historical information to extract the context dependency of long texts, and word embedding is introduced to convert the text into low-dimensional vectors. Experiments are conducted on the social network platforms Sogou corpus and the University HowNet Chinese corpus. The research results show that compared with CNN + rand, LSTM, and other models, the neural network deep learning hybrid model can effectively improve the accuracy of text classification.

• Journal of Positioning, Navigation, and Timing
• /
• 제12권2호
• /
• pp.149-155
• /
• 2023

In urban areas it can be difficult to utilize global navigation satellite systems (GNSS) due to signal reflections and blockages. It is thus crucial to detect reflected or blocked signals because they lead to significant degradation of GNSS positioning accuracy. In a previous study, a classifier for global positioning system (GPS) signal reception conditions was developed using three features and the support vector machine (SVM) algorithm. However, this classifier had limitations in its classification performance. Therefore, in this study, we developed an improved machine learning based method of classifying GPS signal reception conditions by including an additional feature with the existing features. Furthermore, we applied various machine learning classification algorithms. As a result, when tested with datasets collected in different environments than the training environment, the classification accuracy improved by nine percentage points compared to the existing method, reaching up to 58%.

• International Journal of Computer Science & Network Security
• /
• 제24권3호
• /
• pp.107-112
• /
• 2024

Nowadays the deadly virus famous as COVID-19 spread all over the world starts from the Wuhan China in 2019. This disease COVID-19 Virus effect millions of people in very short time. There are so many symptoms of COVID19 perhaps the Identification of a person infected with COVID-19 virus is really a difficult task. Moreover it's a challenging task to identify whether a person or individual have covid test positive or negative. We are developing a framework in which we used machine learning techniques..The proposed method uses DecisionTree, KNearestNeighbors, GaussianNB, LogisticRegression, BernoulliNB , RandomForest , Machine Learning methods as the classifier for diagnosis of covid ,however, 5-fold and 10-fold cross-validations were applied through the classification process. The experimental results showed that the best accuracy obtained from Decision Tree classifiers. The data preprocessing techniques have been applied for improving the classification performance. Recall, accuracy, precision, and F-score metrics were used to evaluate the classification performance. In future we will improve model accuracy more than we achieved now that is 93 percent by applying different techniques