• Smart Structures and Systems
• /
• v.8 no.1
• /
• pp.119-137
• /
• 2011

A bio-inspired two-mode structural health monitoring (SHM) system based on the Na$\ddot{i}$ve Bayes (NB) classification method is discussed in this paper. To implement the molecular biology based Deoxyribonucleic acid (DNA) array concept in structural health monitoring, which has been demonstrated to be superior in disease detection, two types of array expression data have been proposed for the development of the SHM algorithm. For the micro-vibration mode, a two-tier auto-regression with exogenous (AR-ARX) process is used to extract the expression array from the recorded structural time history while an ARX process is applied for the analysis of the earthquake mode. The health condition of the structure is then determined using the NB classification method. In addition, the union concept in probability is used to improve the accuracy of the system. To verify the performance and reliability of the SHM algorithm, a downscaled eight-storey steel building located at the shaking table of the National Center for Research on Earthquake Engineering (NCREE) was used as the benchmark structure. The structural response from different damage levels and locations was collected and incorporated in the database to aid the structural health monitoring process. Preliminary verification has demonstrated that the structure health condition can be precisely detected by the proposed algorithm. To implement the developed SHM system in a practical application, a SHM prototype consisting of the input sensing module, the transmission module, and the SHM platform was developed. The vibration data were first measured by the deployed sensor, and subsequently the SHM mode corresponding to the desired excitation is chosen automatically to quickly evaluate the health condition of the structure. Test results from the ambient vibration and shaking table test showed that the condition and location of the benchmark structure damage can be successfully detected by the proposed SHM prototype system, and the information is instantaneously transmitted to a remote server to facilitate real-time monitoring. Implementing the bio-inspired two-mode SHM practically has been successfully demonstrated.

• Journal of the Korean Society of Tobacco Science
• /
• v.28 no.2
• /
• pp.124-129
• /
• 2006

The grades of burley tobacco stems and scraps were classified followed by the nicotine and nitrate contents by using the cluster analysis. The chemical components of the burley tobacco stems and scraps gathered from 2002 to 2005 were analyzed with auto analyzer. According to the nicotine contents and the nitrate contents, the burley stems and scraps could be classified three groups, respectively. In case of the burley scraps, the AB3T, AB4TR, B1T and B2T grades belonged to the $1^{st}$ a group. The C1W and C2W grades belonged to the $2^{nd}$ group and the CD3W and CD4TR belonged to the $3^{rd}$. In case of the burley stems, the AB3T and AB4TR grades belonged to the $1^{st}$ group. The B1T, B2T, C1W and C2W grades belonged to the $2^{nd}$ group and the CD3W and CD4TR belonged to the $3^{rd}$ group. This classification of raw materials depending on the similarity in the chemical components might be helpful to control the properties of the Reconstituted Tobacco sheet.

• Journal of KIISE:Software and Applications
• /
• v.32 no.12
• /
• pp.1247-1259
• /
• 2005

This paper proposes a real-time face recognition system which detects multiple faces from low resolution video such as web-camera video. Face recognition system consists of the face detection step and the face classification step. At First, it finds face region candidates by using AdaBoost based object detection method which have fast speed and robust performance. It generates reduced feature vector for each face region candidate by using principle component analysis. At Second, Face classification used Principle Component Analysis and multi-SVM. Experimental result shows that the proposed method achieves real-time face detection and face recognition from low resolution video. Additionally, We implement the auto-tracking face recognition system using the Pan-Tilt Web-camera and radio On/Off digital door-lock system with face recognition system.

• Journal of the Korean Institute of Gas
• /
• v.23 no.5
• /
• pp.52-58
• /
• 2019

In this study, we have developed a forecasting model for city- gas acceptance. City-gas corporations have to report about city-gas sale volume next year to KOGAS. So it is a important thing to them. Factors influenced city-gas have differences corresponding to usage classification, however, in city-gas acceptence, it is hard to classificate. So we have considered tha outside temperature as factor that influence regardless of usage classification and the model development was carried out. ARIMA, one of the traditional time series analysis, and LSTM, a deep running technique, were used to construct forecasting models, and various Ensemble techniques were used to minimize the disadvantages of these two methods.Experiments and validation were conducted using data from JB Corp. from 2008 to 2018 for 11 years.The average of the error rate of the daily forecast was 0.48% for Ensemble LSTM, the average of the error rate of the monthly forecast was 2.46% for Ensemble LSTM, And the absolute value of the error rate is 5.24% for Ensemble LSTM.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.9 no.5
• /
• pp.103-113
• /
• 2009

In this study, we separated the precipitation zones using the geographic location of stations and precipitation characteristics (monthly, seasonal, annual) in Gangwon province. Precipitation data of 66 weather stations (meterological office: 11 locations, auto weather system (AWS): 55 places) were used, and statistical method, K-means cluster method, was conducted for division of the precipitation regions. As the results of regional classification, the five zones of precipitation (Yongdong: 1 region, Youngseo: 4 regions) were separated. Seasonal average precipitation in spring is similar throughout Gangwon Province, seasonal average precipitation in summer has high values at Youngseo, and seasonal average precipitation in autumn and winter have high values at Youngdong. The some areas, the vicinity of Misiryeong and Daegwallyeong, happens the orographic precipitation in spatial analysis, but the orographic effects didn't occur for the whole Gangwon areas. However, to achieve more accurate results, the expansion of observatories per elevation and AWS data are demanded.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.4008-4023
• /
• 2022

Since machine learning was introduced into cross-site scripting (XSS) attack detection, many researchers have conducted related studies and achieved significant results, such as saving time and labor costs by not maintaining a rule database, which is required by traditional XSS attack detection methods. However, this topic came across some problems, such as poor generalization ability, significant false negative rate (FNR) and false positive rate (FPR). Moreover, the automatic clustering property of graph convolutional networks (GCN) has attracted the attention of researchers. In the field of natural language process (NLP), the results of graph embedding based on GCN are automatically clustered in space without any training, which means that text data can be classified just by the embedding process based on GCN. Previously, other methods required training with the help of labeled data after embedding to complete data classification. With the help of the GCN auto-clustering feature and labeled data, this research proposes an approach to detect XSS attacks (called GCNXSS) to mine the dependencies between the units that constitute an XSS payload. First, GCNXSS transforms a URL into a word homogeneous graph based on word co-occurrence relationships. Then, GCNXSS inputs the graph into the GCN model for graph embedding and gets the classification results. Experimental results show that GCNXSS achieved successful results with accuracy, precision, recall, F1-score, FNR, FPR, and predicted time scores of 99.97%, 99.75%, 99.97%, 99.86%, 0.03%, 0.03%, and 0.0461ms. Compared with existing methods, GCNXSS has a lower FNR and FPR with stronger generalization ability.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.21-30
• /
• 2024

This research aims to design a system capable of generating real web pages based on deep learning and big data, in three stages. First, a classification system was established based on the industry type and functionality of e-commerce websites. Second, the types of components of web pages were systematically categorized. Third, the entire web page auto-generation system, applicable for deep learning, was designed. By re-engineering the deep learning model, which was trained with actual industrial data, to analyze and automatically generate existing websites, a directly usable solution for the field was proposed. This research is expected to contribute technically and policy-wise to the field of generative AI-based complete website creation and industrial sectors.

• Journal of Korea Multimedia Society
• /
• v.6 no.1
• /
• pp.97-104
• /
• 2003

The appearance of various portal web sites that have individual customers, customizing information operate importantly upon a content. But most current portal sites that has a goal for international electronic commerce use information for customer to a simply individual profile and don't create more and new information that customizing. In this paper, we propose a system that generates a new customizing information with classification and analysis in detail and provides automatically to individual customers. The goal of our research is the development of personalizing auto generation agent that composed form of e-mail from preference of each individual user using open rate and mouse event Information for e-mail.

• Proceedings of the KIEE Conference
• /
• 2005.11b
• /
• pp.283-285
• /
• 2005

This paper presents a new two-terminal numerical algorithm for fault location estimation and for faults recognition using the synchronized phasor in time-domain. The proposed algorithm is also based on the synchronized voltage and current phasor measured from the PMUs(Phasor Measurement Units) installed at both ends of the transmission lines. Also the arc voltage wave shape is modeled numerically on the basis of a great number of arc voltage records obtained by transient recorder. From the calculated arc voltage amplitude it can make a decision whether the fault is permanent or transient. In this paper the algorithm is given and estimated using DFT(Discrete Fourier Transform) and the LES(Least Error Squares Method). The algorithm uses a very short data window and enables fast fault detection and classification for real-time transmission line protection. To test the validity of the proposed algorithm, the Electro-Magnetic Transient Program(EMTP/ATP) and MATLAB is used.

• Spatial Information Research
• /
• v.8 no.1
• /
• pp.69-83
• /
• 2000

Cadastral map is the basic data that prescribe a lot number, the classification of land category, a boundary and ownerships of the parcels. Because the analogue cadastral map is not appropriate for the Parcel Based Land Information System, computerization of cadastral map is needed. When considering other automatic vectorizing softwares, we conclude that they can not satisfy the accuracy needed in cadastral map. Also screen digitizing methods demand lots of time. So we developed semi-automatic vectorizing program that realized almost capacities, such as overlay display which is needed for screen digitizing , window link, vector file generation , and so forth. As comparing screen digitizing method using AutoCAD with our developed program, we could obtain not only almost same accuracy , but also 35 minute reduction in vectorizing.