• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.38 no.1
• /
• pp.58-63
• /
• 2010

In this paper, we propose a simple technique for the detection of a frequency jump in the GPS clock behavior. GPS satellite atomic clocks have characteristics of a second order polynomial in the long term and a non-periodic frequency drift in the short term, showing a sudden frequency jump occasionally. As satellite clock anomalies influence on GPS measurements, it requires to develop a real time technique for the detection of the clock anomaly on the real-time GPS precise point positioning. The proposed technique is based on Teager energy which is mainly used in the field of various signal processing for the detection of a specific signal or symptom. Therefore, we employed the Teager energy for the detection of the jump phenomenon of GPS satellite atomic clocks, and it showed that the proposed clock anomaly detection strategy outperforms a conventional detection methodology.

• Journal of Internet Computing and Services
• /
• v.17 no.3
• /
• pp.11-18
• /
• 2016

Accessing unauthorized rogue APs in WiFi environments is a very dangerous behavior which may lead WiFi users to be exposed to the various cyber attacks such as sniffing, phishing, and pharming attacks. Therefore, prompt and precise detection of rogue APs and properly alarming to the corresponding users has become one of most essential requirements for the WiFi security. This paper proposes a new rogue AP detection method which is mainly using the installation information of authorized APs and the DHCP snooping information of the corresponding switches. The proposed method detects rogue APs promptly and precisely, and notify in realtime to the corresponding users. Since the proposed method is simple and does not require any special devices, it is very cost-effective comparing to the wireless intrusion prevention systems which are normally based on a number of detection sensors and servers. And it is highly precise and prompt in rogue AP detection and flexible in deployment comparing to the existing rogue AP detection methods based on the timing information, location information, and white list information.

• Journal of KIISE:Information Networking
• /
• v.32 no.3
• /
• pp.301-309
• /
• 2005

Learning program's behavior using machine learning techniques based on system call audit data is an effective intrusion detection method. Rule teaming, neural network, statistical technique, and hidden Markov model are representative methods for intrusion detection. Among them neural networks are known for its good performance in teaming system call sequences. In order to apply it to real world problems successfully, it is important to determine their structure. However, finding appropriate structure requires very long time because there are no formal solutions for determining the structure of networks. In this paper, a novel intrusion detection technique using evolutionary neural networks is proposed. Evolutionary neural networks have the advantage that superior neural networks can be obtained in shorter time than the conventional neural networks because it leams the structure and weights of neural network simultaneously Experimental results against 1999 DARPA IDEVAL data confirm that evolutionary neural networks are effective for intrusion detection.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.25 no.3
• /
• pp.615-625
• /
• 2015

This paper proposes new methods and examples for improving fraud detection rules based on banking customer's transaction behaviors focused on anomaly detection method. This study investigates real example that FDS(Fraud Detection System) regards fraudulent transaction as legitimate transaction and figures out fraudulent types and transaction patterns. To understanding the cases that FDS regard legitimate transaction as fraudulent transaction, it investigates all transactions that requied additional authentications or outbound call. We infered additional facts to refine detection rules in progress of outbound calling and applied to existing detection rules to improve. The main results of this study is the following: (a) Type I error is decreased (b) Type II errors are also decreased. The major contribution of this paper is the improvement of effectiveness in detecting fraudulent transaction using transaction behaviors and providing a continuous method that elevate fraud detection rules.

• Smart Structures and Systems
• /
• v.29 no.6
• /
• pp.757-766
• /
• 2022

To train deep learning algorithms, a sufficient number of data are required. However, in most engineering systems, the acquisition of fault data is difficult or sometimes not feasible, while normal data are secured. The dearth of data is one of the major challenges to developing deep learning models, and fault diagnosis in particular cannot be made in the absence of fault data. With this context, this paper proposes an anomaly detection methodology for rotating machines using only normal data with self-labeling. Since only normal data are used for anomaly detection, a self-labeling method is used to generate a new labeled dataset. The overall procedure includes the following three steps: (1) transformation of normal data to self-labeled data based on a pretext task, (2) training the convolutional neural networks (CNN), and (3) anomaly detection using defined anomaly score based on the softmax output of the trained CNN. The softmax value of the abnormal sample shows different behavior from the normal softmax values. To verify the proposed method, four case studies were conducted, on the Case Western Reserve University (CWRU) bearing dataset, IEEE PHM 2012 data challenge dataset, PHMAP 2021 data challenge dataset, and laboratory bearing testbed; and the results were compared to those of existing machine learning and deep learning methods. The results showed that the proposed algorithm could detect faults in the bearing testbed and compressor with over 99.7% accuracy. In particular, it was possible to detect not only bearing faults but also structural faults such as unbalance and belt looseness with very high accuracy. Compared with the existing GAN, the autoencoder-based anomaly detection algorithm, the proposed method showed high anomaly detection performance.

• Journal of Navigation and Port Research
• /
• v.36 no.4
• /
• pp.279-284
• /
• 2012

This study aims to identify the degree of safety when mariners take their actions in several different situations. We have carried out many experiments to observe mariners' behavior and then measured the safety level based on their actions to avoid dangerous situations of ships collision. One of the most important actions that mariners have to take, either as their daily routine or when they are in a collision situation and then want to avoid that situation is the lookout. In this paper, behaviors on the lookout have been defined as a standard sequence of three steps which are "time of first detection", "time of recognition as risky vessel" and "time of starting avoiding action", and the suitability and applicability of the definition have been shown. And also we propose the risk assessment on ships collision and the recommendation for reducing ships collision at sea. Some analyzing results and the application of the results are reported. By combining these knowledge and some systematic studies, we propose the risk assessment on ships collision and the recommendation for reducing ships collision at sea.

• The KIPS Transactions:PartC
• /
• v.19C no.3
• /
• pp.185-190
• /
• 2012

The recent trends in malwares show the most widely used for the distribution of malwares that the targeted computer is infected while the user is accessing to the website, without being aware of the fact that, in which the harmful codes are concealed. In this thesis, we propose a new malicious web page detection system based on a real time analysis of normal/abnormal behaviors in client-side. By means of this new approach, it is not only the limitation of conventional methods can be overcome, but also the risk of infection from malwares is mitigated.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.4
• /
• pp.477-481
• /
• 2010

In this paper, we try to classify behavior patterns of a person around a bed based on a wireless sensor network system. We define five behavioral patterns and three states of a person around a bed which is described by a state machine. We collected data sensed by motion detection and vibration sensors installed around a bed from which a feature vector was extracted. Based on feature vector corresponding to behavioral patterns and the state machine, we established a model for behavioral patterns. To validate the model, experiments on subjects were performed and the model was fixed. These experimental results revealed that behavior patterns of a person around a bed can be classified well.

• International Journal of Advanced Culture Technology
• /
• v.12 no.3
• /
• pp.148-158
• /
• 2024

We investigate Autism Spectrum Disorder (ASD), which is typified by deficits in social interaction, repetitive behaviors, limited vocabulary, and cognitive delays. Traditional diagnostic methodologies, reliant on expert evaluations, frequently result in deferred detection and intervention, particularly in South Korea, where there is a dearth of qualified professionals and limited public awareness. In this study, we employ advanced deep learning algorithms to enhance early ASD screening through automated video analysis. Utilizing architectures such as Convolutional Long Short-Term Memory (ConvLSTM), Long-term Recurrent Convolutional Network (LRCN), and Convolutional Neural Networks with Gated Recurrent Units (CNN+GRU), we analyze video data from platforms like YouTube and TikTok to identify stereotypic behaviors (arm flapping, head banging, spinning). Our results indicate that the LRCN model exhibited superior performance with 79.61% accuracy on the augmented platform video dataset and 79.37% on the original SSBD dataset. The ConvLSTM and CNN+GRU models also achieved higher accuracy than the original SSBD dataset. Through this research, we underscore AI's potential in early ASD detection by automating the identification of stereotypic behaviors, thereby enabling timely intervention. We also emphasize the significance of utilizing expanded datasets from social media platform videos in augmenting model accuracy and robustness, thus paving the way for more accessible diagnostic methods.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.7
• /
• pp.3147-3153
• /
• 2016

Background: Many strategies are required for cervical cancer reduction e.g. provision of education cautious sexual behavior, HPV vaccination, and early detection of pre-invasive cervical lesions and invasive cancer. Basic health data for cervical cytology/ HPV DNA and associated factors are important to make an appropriate policy to fight against cervical cancer. Aims: To assess the prevalence of abnormal cervical cytology and/or HPV DNA and associated factors, including sexual behavior, among Bangkok Metropolitan women. Materials and Methods: Thai women, aged 25-to-65 years old, had lived in Bangkok for ${\geq}5$ years were invited into the study. Liquid-based cervical cytology and HPV DNA tests were performed. Personal data were collected. Main Outcomes Measures: Rates of abnormal cytology and/ or high-risk HPV (HR-HPV) and factors associated with abnormal test (s) were studied. Results: Abnormal cytology and positive HR-HPV were found in 6.3% (279/4442 women) and 6.7% (295/4428), respectively. The most common abnormal cytology was ASC-US (3.5%) while the most common HR-HPV genotype was HPV 16 (1.4%) followed by HPV 52 (1.0%), HPV 58 (0.9%), and HPV 18 and HPV 51 at equal frequency (0.7%). Both tests were abnormal in 1.6% (71/4428 women). Rates of HR-HPV detection were directly associated with severity of abnormal cytology: 5.4% among normal cytology and 13.0%, 30.8%, 40.0%, 39.5%, 56.3% and 100.0% among ASC-US, ASC-H, AGC-NOS, LSIL, HSIL, and SCC, respectively. Some 5% of women who had no HR-HPV had abnormal cytology, in which 0.3% had ${\geq}$ HSIL. Factors associated with abnormal cytology or HR-HPV were: age ${\leq}40$ years, education lower than (for cytology) or higher than bachelor for HR-HPV), history of sexual intercourse, and sexual partners ${\geq}2$. Conclusions: Rates for abnormal cytology and HR-HPV detection were 6.3% and 6.7% HR-HPV detection was directly associated with severity of abnormal cytology. Significant associated factors were age ${\leq}40$ years, lower education, history of sexual intercourse, and sexual partners ${\geq}2$.