• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.8
• /
• pp.301-308
• /
• 2015

SNS is a web-based online platform service supporting the formation of relations between users. SNS users have usually used a desktop or laptop for this purpose so far. However, the number of SNS users is greatly increasing and their access to the web is improving with the spread of smart phones. They share their daily lives with other users through SNSs. We can detect events if we analyze the contents that are left by SNS users, where the individual acts as a sensor. Such analyses have already been attempted by many researchers. In particular, Twitter is used in related spheres in various ways, because it has structural characteristics suitable for detecting events. However, there is a limitation concerning the detection of events and their locations. Thus, we developed a system that can detect the location immediately based on the district mentioned in Twitter. We tested whether the system can function in real time and evaluated its ability to detect events that occurred in reality. We also tried to improve its detection efficiency by removing noise.

• IEIE Transactions on Smart Processing and Computing
• /
• v.5 no.4
• /
• pp.256-266
• /
• 2016

Concurrently detected and annotated abnormal events can have a significant impact on surveillance systems. By considering the specific domain of pedestrian trajectories, this paper presents two main contributions. First, as introduced in much of the work on trajectory-based anomaly detection in the literature, only information about pedestrian paths, such as direction and speed, is considered. Differing from previous work, this paper proposes a framework that deals with additional types of trajectory-based anomalies. These abnormal events take places when a person enters prohibited areas. Those restricted regions are constructed by an online learning algorithm that uses surrounding information, including detected pedestrians and background scenes. Second, a simple data-boosting technique is introduced to overcome a lack of training data; such a problem particularly challenges all previous work, owing to the significantly low frequency of abnormal events. This technique only requires normal trajectories and fundamental information about scenes to increase the amount of training data for both normal and abnormal trajectories. With the increased amount of training data, the conventional abnormal trajectory classifier is able to achieve better prediction accuracy without falling into the over-fitting problem caused by complex learning models. Finally, the proposed framework (which annotates tracks that enter prohibited areas) and a conventional abnormal trajectory detector (using the data-boosting technique) are integrated to form a united detector. Such a detector deals with different types of anomalous trajectories in a hierarchical order. The experimental results show that all proposed detectors can effectively detect anomalous trajectories in the test phase.

• The KIPS Transactions:PartC
• /
• v.10C no.7
• /
• pp.857-866
• /
• 2003

For detecting an intrusion based on the anomaly of a user's activities, previous works are concentrated on statistical techniques in order to analyze an audit data set. However. since they mainly analyze the average behavior of a user's activities, some anomalies can be detected inaccurately. In this paper, a new clustering algorithm for modeling the normal pattern of a user's activities is proposed. Since clustering can identify an arbitrary number of dense ranges in an analysis domain, it can eliminate the inaccuracy caused by statistical analysis. Also, clustering can be used to model common knowledge occurring frequently in a set of transactions. Consequently, the common activities of a user can be found more accurately. The common knowledge is represented by the occurrence frequency of similar data objects by the unit of a transaction as veil as the common repetitive ratio of similar data objects in each transaction. Furthermore, the proposed method also addresses how to maintain identified common knowledge as a concise profile. As a result, the profile can be used to detect any anomalous behavior In an online transaction.

• Smart Structures and Systems
• /
• v.17 no.2
• /
• pp.167-194
• /
• 2016

This paper investigates the Synergetics based Damage Detection Method (SDDM) for frame structures by using surface-bonded PZT (Lead Zirconate Titanate) patches. After analyzing the mechanism of pattern recognition from Synergetics, the operating framework with cooperation-competition-update process of SDDM was proposed. First, the dynamic identification equation of structural conditions was established and the adjoint vector (AV) set of original vector (OV) set was obtained by Generalized Inverse Matrix (GIM).Then, the order parameter equation and its evolution process were deduced through the strict mathematics ratiocination. Moreover, in order to complete online structural condition update feature, the iterative update algorithm was presented. Subsequently, the pathway in which SDDM was realized through the modified Synergetic Neural Network (SNN) was introduced and its assessment indices were confirmed. Finally, the experimental platform with a two-story frame structure was set up. The performances of the proposed methodology were tested for damage identifications by loosening various screw nuts group scenarios. The experiments were conducted in different damage degrees, the disturbance environment and the noisy environment, respectively. The results show the feasibility of SDDM using piezoceramic sensors and actuators, and demonstrate a strong ability of anti-disturbance and anti-noise in frame structure applications. This proposed approach can be extended to the similar structures for damage identification.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.6
• /
• pp.691-697
• /
• 2006

Induction motors are critical components in industrial process. So there are many research in the condition based maintenance, online monitoring system, and fault detection. This paper presents a scheme on the detection and diagnosis of the three-phase squirrel induction motor under unbalanced voltage, broken rotor bar, and a combination of these two faults. Actually one fault happen in operation, it influence other component in motor or cause another faults. Accordingly it is useful to diagnose and detect a combination fault in induction motor as well as each fault. The proposed fault detection and diagnosis algorithm is based on the stator currents from the squirrel induction motor and simulated with the aid of Matlab Simulink.

• Smart Media Journal
• /
• v.11 no.5
• /
• pp.63-74
• /
• 2022

Initial public offering (IPO) has a legal framework for investor protection, and because there are various quantitative evaluation factors, objective analysis is possible, and various studies have been conducted. In addition, crowdfunding also has several devices to prevent indiscriminate funding as the legal system for investor protection. On the other hand, the blockchain-based cryptocurrency white paper (ICO), which has recently been in the spotlight, has ambiguous legal means and standards to protect investors and lacks quantitative evaluation methods to evaluate ICOs objectively. Therefore, this study collects online-published ICO white papers to detect fraud in ICOs, performs ICO fraud predictions based on BERT, a text embedding technique, and compares them with existing Random Forest machine learning techniques, and shows the possibility on fraud detection. Finally, this study is expected to contribute to the study of ICO fraud detection based on quantitative methods by presenting the possibility of using a quantitative approach using unstructured data to identify frauds in ICOs.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.77-91
• /
• 2022

Various monitoring systems have been implemented in civil infrastructure to ensure structural safety and integrity. In long-term monitoring, these systems generate a large amount of data, where anomalies are not unusual and can pose unique challenges for structural health monitoring applications, such as system identification and damage detection. Therefore, developing efficient techniques is quite essential to recognize the anomalies in monitoring data. In this study, several machine learning techniques are explored and implemented to detect and classify various types of data anomalies. A field dataset, which consists of one month long acceleration data obtained from a long-span cable-stayed bridge in China, is employed to examine the machine learning techniques for automated data anomaly detection. These techniques include the statistic-based pattern recognition network, spectrogram-based convolutional neural network, image-based time history convolutional neural network, image-based time-frequency hybrid convolution neural network (GoogLeNet), and proposed ensemble neural network model. The ensemble model deliberately combines different machine learning models to enhance anomaly classification performance. The results show that all these techniques can successfully detect and classify six types of data anomalies (i.e., missing, minor, outlier, square, trend, drift). Moreover, both image-based time history convolutional neural network and GoogLeNet are further investigated for the capability of autonomous online anomaly classification and found to effectively classify anomalies with decent performance. As seen in comparison with accuracy, the proposed ensemble neural network model outperforms the other three machine learning techniques. This study also evaluates the proposed ensemble neural network model to a blind test dataset. As found in the results, this ensemble model is effective for data anomaly detection and applicable for the signal characteristics changing over time.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2000.05a
• /
• pp.242-246
• /
• 2000

본 논문은 얼굴을 이용한 인증 단계의 전처리 단계로 복잡한 배경에서 효율적인 얼굴 추출 방법을 제안한다. 먼저 색상정보를 이용하여 얼굴로 추정되는 1차 영역을 찾고 2차로 색상정보와 자기정보를 이용하여 에지 정보를 추출하여 추정된 영역을 분리한다. 3차로 각 분리된 후보 영역에 얼굴 파라미터를 이용하여 후보영역을 합치면서 얼굴 영역을 추출한다. 온라인 인증을 위한 얼굴 영역 추출이기 때문에 인증 받고자 하는 사람의 얼굴은 전체 영역에서 가운데로 치우칠 것이라는 예상과 인증을 하기 위해서는 일정 크기를 가져야 한다는 가정 하에서 얼굴을 추출하였다. 실제 실험을 통하여 본 논문에서 제안하는 방법으로 실험한 결과 유용성을 확인 할 수 있었다.

• Journal of Mechanical Science and Technology
• /
• v.19 no.spc1
• /
• pp.411-421
• /
• 2005

The development and implementation of an appropriate methodology for the accurate geometric description of track models is proposed in the framework of multibody dynamics and it includes the representation of the track spatial geometry and its irregularities. The wheel and rail surfaces are parameterized to represent any wheel and rail profiles obtained from direct measurements or design requirements. A fully generic methodology to determine, online during the dynamic simulation, the coordinates of the contact points, even when the most general three dimensional motion of the wheelset with respect to the rails is proposed. This methodology is applied to study specific issues in railway dynamics such as the flange contact problem and lead and lag contact configurations. A formulation for the description of the normal contact forces, which result from the wheel-rail interaction, is also presented. The tangential creep forces and moments that develop in the wheel-rail contact area are evaluated using : Kalker linear theory ; Heuristic force method ; Polach formulation. The methodology is implemented in a general multibody code. The discussion is supported through the application of the methodology to the railway vehicle ML95, used by the Lisbon metro company.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.208-209
• /
• 2016

APT (Advanced Persistent Threat) 공격 사례가 증가하면서, 이러한 APT 공격을 해결하고자 이상 행위 탐지 기술 관련 연구가 활발히 진행되고 있다. 최근에는 APT 공격의 탐지율을 높이기 위해서 빅데이터 기술을 활용하여 다양한 소스로부터 대규모 데이터를 수집하여 실시간 분석하는 연구들이 시도되고 있다. 본 논문은 빅데이터 기술을 활용하여 기존 시스템들의 실시간 처리 및 분석 한계를 극복하기 위한 실시간 비정상 행위 탐지 시스템에서, 파일 시스템에 수집된 오프라인 데이터 기반이 아닌 온라인 수집 데이터 기반으로 실시간 비정상 행위를 탐지하여 실시간성을 제고하고 입출력 병목 문제로 인한 처리 성능 확장성 문제를 해결하는 방법 및 시스템에 대해서 제안한다.