• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.3
• /
• pp.297-305
• /
• 2008

Recently, kernel methods have attracted great interests in the areas of pattern classification, function approximation, and anomaly detection. The role of the kernel is particularly important in the methods such as SVM(support vector machine) and KPCA(kernel principal component analysis), for it can generalize the conventional linear machines to be capable of efficiently handling nonlinearities. This paper considers the problem of combining radar and rain gauge observations utilizing the regression approach based on the kernel-based gaussian process and support vector learning. The data-assimilation results of the considered methods are reported for the radar and rain gauge observations collected over the region covering parts of Gangwon, Kyungbuk, and Chungbuk provinces of Korea, along with performance comparison.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.10
• /
• pp.732-742
• /
• 2016

This study suggests methods of defense against low-level high-bandwidth DDoS attacks by adding a solution with a time limit factor (TLF) to an existing high-bandwidth DDoS defense system. Low-level DDoS attacks cause faults to the service requests of normal users by acting as a normal service connection and continuously positioning the connected session. Considering this, the proposed method makes it possible for users to show a down-related session by considering it as a low-level DDoS attack if the abnormal flow is detected after checking the amount of traffic. However, the service might be blocked when misjudging a low-level DDoS attack in the case of a communication fault resulting from a network fault, even with a normal connection status. Thus, we made it possible to reaccess the related information through a certain period of blocking instead of a drop through blacklist. In a test of the system, it was unable to block the session because it recognized sessions that are simply connected with a low-level DDoS attack as a normal communication.

• Journal of the Institute of Convergence Signal Processing
• /
• v.21 no.3
• /
• pp.121-126
• /
• 2020

Sound-based machine fault diagnosis is the automatic detection of abnormal sound in the acoustic emission signals of the machines. Conventional methods of using mathematical models were difficult to diagnose machine failure due to the complexity of the industry machinery system and the existence of nonlinear factors such as noises. Therefore, we want to solve the problem of machine fault diagnosis as a deep learning-based image classification problem. In the paper, we propose a CNN-based automatic machine fault diagnosis method using Spectrogram images. The proposed method uses STFT to effectively extract feature vectors from frequencies generated by machine defects, and the feature vectors detected by STFT were converted into spectrogram images and classified by CNN by machine status. The results show that the proposed method can be effectively used not only to detect defects but also to various automatic diagnosis system based on sound.

• Journal of Internet Computing and Services
• /
• v.17 no.3
• /
• pp.55-66
• /
• 2016

A local storage of HTML5 is a Web Storage, which is stored permanently on a local computer in the form of files. The contents of the storage can be easily accessed and modified because it is stored as plaintext. Moreover, because the internet browser classifies the local storages of each domain using file names, the malicious attacker can abuse victim's local storage files by changing file names. In the paper, we propose a scheme to maintain the integrity and the confidentiality of the local storage's source domain and source device. The key idea is that the client encrypts the data stored in the local storage with cipher key, which is managed by the web server. On the step of requesting the cipher key, the web server authenticates whether the client is legal source of local storage or not. Finally, we showed that our method can detect an abnormal access to the local storage through experiments according to the proposed method.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.4
• /
• pp.205-212
• /
• 2023

Among cardiac diseases, arrhythmias can lead to serious complications such as stroke, heart attack, and heart failure if left untreated, so continuous and accurate ECG monitoring is crucial for clinical care. However, the accurate interpretation of electrocardiogram (ECG) data is entirely dependent on medical doctors, which requires additional time and cost. Therefore, this paper proposes an arrhythmia recognition module for the purpose of developing a medical platform through the analysis of abnormal pulse waveforms based on Lifelogs. The proposed method is to convert ECG data into image format instead of time series data, apply visual pattern recognition technology, and then detect arrhythmia using CNN model. In order to validate the arrhythmia classification of the CNN model by image type conversion of ECG data proposed in this paper, the MIT-BIH arrhythmia dataset was used, and the result showed an accuracy of 97%.