• Journal of Korea Multimedia Society
• /
• v.21 no.2
• /
• pp.98-107
• /
• 2018

In this paper, we propose a method to classify the skeletal maturity with a small amount of hand wrist X-ray image using deep learning-based meta-learning. General deep-learning techniques require large amounts of data, but in many cases, these data sets are not available for practical application. Lack of learning data is usually solved through transfer learning using pre-trained models with large data sets. However, transfer learning performance may be degraded due to over fitting for unknown new task with small data, which results in poor generalization capability. In addition, medical images require high cost resources such as a professional manpower and mcuh time to obtain labeled data. Therefore, in this paper, we use meta-learning that can classify using only a small amount of new data by pre-trained models trained with various learning tasks. First, we train the meta-model by using a separate data set composed of various learning tasks. The network learns to classify the bone maturity using the bone maturity data composed of the radiographs of the wrist. Then, we compare the results of the classification using the conventional learning algorithm with the results of the meta learning by the same number of learning data sets.

• Journal of Multimedia Information System
• /
• v.6 no.4
• /
• pp.209-216
• /
• 2019

Over the past decade, researchers were able to solve complex medical problems as well as acquire deeper understanding of entire issue due to the availability of machine learning techniques, particularly predictive algorithms and automatic recognition of patterns in medical imaging. In this study, a technique called transfer learning has been utilized to classify Magnetic Resonance (MR) images by a pre-trained Convolutional Neural Network (CNN). Rather than training an entire model from scratch, transfer learning approach uses the CNN model by fine-tuning them, to classify MR images into Alzheimer's disease (AD), mild cognitive impairment (MCI) and normal control (NC). The performance of this method has been evaluated over Alzheimer's Disease Neuroimaging (ADNI) dataset by changing the learning rate of the model. Moreover, in this study, in order to demonstrate the transfer learning approach we utilize different pre-trained deep learning models such as GoogLeNet, VGG-16, AlexNet and ResNet-18, and compare their efficiency to classify AD. The overall classification accuracy resulted by GoogLeNet for training and testing was 99.84% and 98.25% respectively, which was exceptionally more than other models training and testing accuracies.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2004.11a
• /
• pp.653-657
• /
• 2004

In this study, PD(partial discharge) signals which occurrs at stator coil of traction Motor are acquired. these data are used for classifying the PD sources. W(Neural Network) has recently applied to classify the PB pattern. The PD data are used for the learning process to classify PD sources. The PD data come from normal specimen and defective specimens such as internal void discharges, slot discharges and surface discharges. PD distribution parameters are calculated from a set of the data, which is used to realize diagnostic algorithm. NN which applies distribution parameters is useful to classify the PD patterns of defective sources generating in stator coil of traction motor.

• Journal of IKEEE
• /
• v.22 no.2
• /
• pp.350-355
• /
• 2018

In this paper, a system that can classify the objects in the image according to their sizes using the reference points is proposed. The object is studied with samples. The proposed system recognizes and classifies objects by the size in images acquired using a mobile phone camera. Conventional object recognition systems classify objects using only object size. As the size of the object varies depending on the distance, such systems have the disadvantage that an error may occurs if the image is not acquired with a certain distance. In order to overcome the limitation of the conventional object recognition system, the object recognition system proposed in this paper can classify the object regardless of the distance with comparing the size of the reference point by placing it at the upper left corner of the image.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.7
• /
• pp.2261-2280
• /
• 2014

Recently, network traffic has become more complex and diverse due to the emergence of new applications and services. Therefore, the importance of application-level traffic classification is increasing rapidly, and it has become a very popular research area. Although a lot of methods for traffic classification have been introduced in literature, they have some limitations to achieve an acceptable level of performance in real-time application-level traffic classification. In this paper, we propose a novel application-level traffic classification method using payload size sequence (PSS) signature. The proposed method generates unique PSS signatures for each application using packet order, direction and payload size of the first N packets in a flow, and uses them to classify application traffic. The evaluation shows that this method can classify application traffic easily and quickly with high accuracy rates, over 99.97%. Furthermore, the method can also classify application traffic that uses the same application protocol or is encrypted.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.1
• /
• pp.454-475
• /
• 2018

This paper presents a novel Android malware classification model planned to classify and categorize Android malicious code at Drebin dataset. The amount of malicious mobile application targeting Android based smartphones has increased rapidly. In this paper, Restricted Boltzmann Machine and Deep Belief Network are used to classify malware into families of Android application. A texture-fingerprint based approach is proposed to extract or detect the feature of malware content. A malware has a unique "image texture" in feature spatial relations. The method uses information on texture image extracted from malicious or benign code, which are mapped to uncompressed gray-scale according to the texture image-based approach. By studying and extracting the implicit features of the API call from a large number of training samples, we get the original dynamic activity features sets. In order to improve the accuracy of classification algorithm on the features selection, on the basis of which, it combines the implicit features of the texture image and API call in malicious code, to train Restricted Boltzmann Machine and Back Propagation. In an evaluation with different malware and benign samples, the experimental results suggest that the usability of this method---using Deep Belief Network to classify Android malware by their texture images and API calls, it detects more than 94% of the malware with few false alarms. Which is higher than shallow machine learning algorithm clearly.

• KCID journal
• /
• v.17 no.2
• /
• pp.17-27
• /
• 2010

In order to manage the water quality in reservoir, it is necessary to understand the temporal and spatial variation of reservoirs and to classify the reservoirs. In this research, agricultural reservoirs are classified according to physical characteristics (depth, residence time, shape of the reservoir etc) and water quality using multivatriate analysis (PCA and CA). CA (Cluster Analysis) method classify reservoirs into several groups as a similarity of the reservoirs, but it is difficult to indicate a full list to the one table. In case of PCA (Principle Component Analysis) method, it has the advantage for the classification on the reservoirs depending on the water quality similarity and also it is useful to analyze the relationship between related factors through correlation analysis. However PCA is limited to classify into several groups based on the characteristics of the reservoirs and each user should be classified as randomly subjective according to the relative position of the reservoir in the figure. In conclusions, compared to conventional reservoirs classification methods, both CA and PCA methods are considered to be a classification method that describes the nature of the reservoir well, but classification results has a restriction on use, so further research will be needed to complement.

• Journal of Information Processing Systems
• /
• v.9 no.3
• /
• pp.395-404
• /
• 2013

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.

• The Korean Journal of Applied Statistics
• /
• v.30 no.6
• /
• pp.851-865
• /
• 2017

Ransomware such as WannaCry is a global issue and methods to defend against malware attacks are important. We have to be able to classify the malware types efficiently in order to minimize the damage from malwares. This study makes models to classify malware properly with various statistical techniques. Several classification techniques such as logistic regression, random forest, gradient boosting, and support vector machine are used to construct models. This study also helps us understand key variables to classify the type of malicious software.

• Journal of Biosystems Engineering
• /
• v.29 no.3
• /
• pp.261-266
• /
• 2004

This study was Performed to classify the acoustic emission(AE) signal due to surface cracking and moisture movement in the flat-sawn boards of oak(Quercus Variablilis) during drying using the principal component analysis(PCA) and artificial neural network(ANN). To reduce the multicollinearity among AE parameters such as peak amplitude, ring-down count event duration, ring-down count divided by event duration, energy, rise time, and peak amplitude divided by rise time and to extract the significant AE parameters, correlation analysis was performed. Over 96 of the variance of AE parameters could be accounted for by the first and second principal components. An ANN analysis was successfully used to classify the Af signals into two patterns. The ANN classifier based on PCA appeared to be a promising tool to classify the AE signals from wood drying.