• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.801-803
• /
• 2014

In the modern society, image processing is utilized in various fields. Edge detection used for image processing as such is essential for most of the applications. Accordingly, there are studies conducted both in and out of Korea in order to detect edge. Representative edge detection methods include Sobel, Prewitt and Roberts. However, these methods are rather limited when it comes to the edge detection characteristics when used for the image with damaged AWGN(additive white Gaussian noise). Thus, this paper presented edge detection method utilizing local mask in order to overcome the shortcomings of the existing methods.

• Electronics and Telecommunications Trends
• /
• v.36 no.5
• /
• pp.82-91
• /
• 2021

This study reviews application of data-driven anomaly detection techniques to the aviation domain. Recent advances in deep learning have inspired significant anomaly detection research, and numerous methods have been proposed. However, some of these advances have not yet been explored in aviation systems. After briefly introducing aviation safety issues, data-driven anomaly detection models are introduced. Along with traditional statistical and well-established machine learning models, the state-of-the-art deep learning models for anomaly detection are reviewed. In particular, the pros and cons of hybrid techniques that incorporate an existing model and a deep model are reviewed. The characteristics and applications of deep learning models are described, and the possibility of applying deep learning methods in the aviation field is discussed.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.13 no.1
• /
• pp.49-57
• /
• 2017

IoT can be connected through a single network not only objects which can be connected to existing internet but also objects which has communication capability. This IoT environment will be a huge change to the existing communication paradigm. However, the big security problem must be solved in order to develop further IoT. Security mechanisms reflecting these characteristics should be applied because devices participating in the IoT have low processing ability and low power. In addition, devices which perform abnormal behaviors between objects should be also detected. Therefore, in this paper, we proposed D-IDS technique for efficient detection of malicious attack nodes between devices participating in the IoT. The proposed technique performs the central detection and distribution detection to improve the performance of attack detection. The central detection monitors the entire network traffic at the boundary router using SVM technique and detects abnormal behavior. And the distribution detection combines RSSI value and reliability of node and detects Sybil attack node. The performance of attack detection against malicious nodes is improved through the attack detection process. The superiority of the proposed technique can be verified by experiments.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.328-330
• /
• 2015

Edge is a characteristic information that can easily obtain the size, direction and location of objects included in the image, and the edge detection is utilized as a preprocess processing in various image processing application sectors such as object detection and object recognition, etc. For the conventional edge detection methods, there are Sobel, Prewitt and Roberts. These existing edge detection methods are easy to implement but the edge detection characteristics are somewhat insufficient as fixed weighted mask is applied. Therefore, in order to compensate the problems of existing edge detection methods, in this paper, an edge detection algorithm was proposed after applying the weighted value according to the standard deviation and means within the local mask.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.13 no.2
• /
• pp.99-106
• /
• 2003

Intrusions pose a serious security risk in a network environment. For detecting the intrusion effectively, many researches have developed data mining framework for constructing intrusion detection modules. Traditional anomaly detection techniques focus on detecting anomalies in new data after training on normal data. To detect anomalous behavior, Precise normal Pattern is necessary. This training data is typically expensive to produce. For this, the understanding of the characteristics of data on network is inevitable. In this paper, we propose to use clustering and association rules as the basis for guiding anomaly detection. For applying entropy to filter noisy data, we present a technique for detecting anomalies without training on normal data. We present dynamic transaction for generating more effectively detection patterns.

• Journal of Broadcast Engineering
• /
• v.22 no.5
• /
• pp.632-642
• /
• 2017

In this paper, we propose a DNN based speech detection system using acoustic characteristics and context information of media audio. The speech detection for discriminating between speech and non-speech included in the media audio is a necessary preprocessing technique for effective speech processing. However, since the media audio signal includes various types of sound sources, it has been difficult to achieve high performance with the conventional signal processing techniques. The proposed method improves the speech detection performance by separating the harmonic and percussive components of the media audio and constructing the DNN input vector reflecting the acoustic characteristics and context information of the media audio. In order to verify the performance of the proposed system, a data set for speech detection was made using more than 20 hours of drama, and an 8-hour Hollywood movie data set, which was publicly available, was further acquired and used for experiments. In the experiment, it is shown that the proposed system provides better performance than the conventional method through the cross validation for two data sets.

• Journal of Microbiology and Biotechnology
• /
• v.28 no.3
• /
• pp.465-472
• /
• 2018

Our aim was to determine the detection rate of respiratory viruses (RVs) in feces of patients with acute viral respiratory infection (AVRI) and the detection rate of diarrheal viruses (DVs) in nasopharyngeal samples from patients with acute viral gastroenteritis. The relationships between the presence of fecal RVs or nasopharyngeal DVs and their impacts on the clinical severity were also investigated. A total of 144 fecal specimens were collected from AVRI patients and 95 nasopharyngeal specimens were collected from acute viral gastroenteritis patients. Clinical characteristics and laboratory profiles were compared between subgroups on the basis of the presence or absence of virus in the specimens. The detection rate of RVs in feces was 17.4% (25/144), whereas the detection rate for viruses identical to the respiratory pathogen was 10.4% (identical group, 15/144). Within the identical group, adenovirus (86.7%, 13/15) was most commonly found. Patients in the identical group showed statistically higher values for C-reactive protein, mean age, increased frequency of vomiting, and decreased frequency of chest film involvement and cough (p < 0.05). The detection rate of nasopharyngeal DVs among acute viral gastroenteritis patients was 19.0% (18/95), and in the identical group it was 15.8% (15/95). Norovirus group II and enteric adenovirus were the major pathogens detected in the identical group. There were no significant differences in clinical characteristics and laboratory profiles between the subgroups. In conclusion, the major pathogens of fecal RV and nasopharyngeal DV were adenovirus and norovirus group II, respectively. However, their relationship with the clinical symptoms or disease severity is unclear.

• Journal of Biomedical Engineering Research
• /
• v.19 no.1
• /
• pp.1-8
• /
• 1998

Clustered microcalcifications on X-ray mammograms are an important sign for early detection of breast cancer. This paper proposes a computer-aided diagnosis method for the detection of clustered microcalcifications and marking their locations on digitized mammograms. The proposed detection method consists of the region of interest (ROI) selection, the film-artifact removal, the surrounding texture analysis method for the detection of clustered microcalcifications, which is based on the second-order histogram in two nested surrounding regions on the current pixel. This paper also describes the effectiveness of the proposed film-artifact removal filter in terms of the classification performance with the receiver operating-characteristics(ROC) analysis. A three-layer backpropagation neural network is employed as a classifier. The appropriate marking for the locations of clustered microcalcifications can be used to alert radiologists to locations of suspicious lesions.

• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.3
• /
• pp.204-211
• /
• 2011

Embedded systems require intensively complex and high power dissipating modules that have the capability of real-time high performance data processing, wide bandwidth communication, and low power consumption. However, the current battery technology has not been developed as much as meeting the requirements of portable embedded systems for long system lifetime. In this paper, new approach that operates with low energy consumption is proposed to overcome the situation while guaranteeing detection accuracy. The designed method associates a variety of detection algorithms hierarchically to detect events happening around the system. The Change for energy consumption characteristics is shown with change for probabilistic characteristics and those relationships are analytically explained from experiments. Furthermore, several techniques to consume low energy and achieve high detection accuracy are described, depending on the event static or dynamic characteristics.

• Journal of Information Technology Services
• /
• v.12 no.4
• /
• pp.435-447
• /
• 2013

If we use a smartphone to analyze and detect falling, it is a huge advantage that the person with a sensor attached to one's body is free from awareness of difference and limitation of space, unlike attaching sensors on certain fixed areas. In this paper, we suggested effective posture analysis of smartphone users, and fall detecting system. Suggested algorithm enables to detect falling accurately by using the fact that instantaneous change of acceleration sensor is different according to user's posture. Since mobile applications working on smart phones are low in compatibility according to mobile platforms, it is a constraint that new development is needed which is suitable for sensor equipment's characteristics. In this paper, we suggested posture analysis algorithm using smartphones to solve the problems related to user's inconvenience and limitation of development according to sensor equipment's characteristics. Also, we developed fall detection system with the suggested algorithm, using hybrid mobile application which is not limited to platform.