• Journal of Korea Society of Industrial Information Systems
• /
• v.4 no.2
• /
• pp.1-6
• /
• 1999

We propose a new algorithm for pattern classification by extracting feature vectors based on Gibbs distributions which are well suited for representing the characteristic of an images. The extracted feature vectors are comprised of 2-D moments which are invariant under translation rotation, and scale of the image less sensitive to noise. This implementation contains two puts: feature extraction and pattern classification First of all, we extract feature vector which consists of an improved 2-D moments on the basis of estimated Gibbs distribution Next, in the classification phase the minimization of the discrimination cost function for a specific pattern determines the corresponding template pattern. In order to evaluate the performance of the proposed scheme, classification experiments with training document sets of characters have been carried out on SUN ULTRA 10 Workstation Experiment results reveal that the proposed scheme had high classification rate over 98%.

• Korean Journal of Remote Sensing
• /
• v.24 no.5
• /
• pp.507-515
• /
• 2008

Many studies have generally used a large number of pure pixels as an approach to training set design. The training set are used, however, varies between classifiers. In the recent research, it was reported that small mixed pixels between classes are actually more useful than larger pure pixels of each class in Support Vector Machine (SVM) classification. We evaluated a usability of small mixed pixels as a training set for the classification of high-resolution satellite imagery. We presented an advanced approach to obtain a mixed pixel readily, and evaluated the appropriateness with the land cover classification from IKONOS satellite imagery. The results showed that the accuracy of the classification based on small mixed pixels is nearly identical to the accuracy of the classification based on large pure pixels. However, it also showed a limitation that small mixed pixels used may provide insufficient information to separate the classes. Small mixed pixels of the class border region provide cost-effective training sets, but its use with other pixels must be considered in use of high-resolution satellite imagery or relatively complex land cover situations.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.45-55
• /
• 2022

Recently, large-scale language models (LPLM) have been shown state-of-the-art performances in various tasks of natural language processing including intent classification. However, fine-tuning LPLM requires much computational cost for training and inference which is not appropriate for dialog system. In this paper, we propose compressed intent classification model for multi-agent in low-resource like CPU. Our method consists of two stages. First, we trained sentence encoder from LPLM then compressed it through knowledge distillation. Second, we trained agent-specific adapter for intent classification. The results of three intent classification datasets show that our method achieved 98% of the accuracy of LPLM with only 21% size of it.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.1D
• /
• pp.149-156
• /
• 2006

Existing method of landuse classification using aerial photographs or field survey requires relatively higher amount of time and cost due to necessary manual work. Especially in urban area where the pattern of landuse is densely aggregated, a landuse classification using satellite image is more complex. In this background, this study proposes a landuse classification method to utilize 1:1,000 digital topographic data and IKONOS satellite image. To prove the possibility of this method, the method was applied to Seoul metropolitan area. The results shows the total accuracy of approximately 95% and 14 landuse classes extracted. Based on the results from the pilot study, this method is applicable to landuse classification in urban area.

• Journal of Aerospace System Engineering
• /
• v.12 no.5
• /
• pp.76-88
• /
• 2018

Space agencies such as NASA, ESA, and the US military provide guidelines and standards for PA(product assurance) requirements and plans. In recent years, major satellite manufacturers around the world have been mitigating PA requirements and processes by tailoring. PA tailoring has been implemented to improve the cost and schedule efficiency. PA tailoring can be accomplished based on various factors such as mission, classification of mission risk, complexity, development cost, life cycle, etc. In this study, PA tasks according to the mission risk classification proposed by NASA are investigated, and the tailoring method is suggested for the optimization of the development cost and schedule. In particular, the classification of mission risk for the satellites under development or operation in Korea is performed, and PA characteristics in accordance with mission risk are analyzed.

• International Journal of Highway Engineering
• /
• v.17 no.2
• /
• pp.143-150
• /
• 2015

PURPOSES : The authors set out to estimate the related carbon emissions, energy use, and costs of the national freeways and highways in Korea. To achieve this goal, a macro-level methodology for estimating those amounts by road type, road structure type, and road life cycle was developed. METHODS : The carbon emissions, energy use, and costs associated with roads vary according to the road type, road structure type, and road life cycle. Therefore, in this study, the road type, road structure type, and road life cycle were classified into two or three categories based on criteria determined by the authors. The unit amounts of carbon emissions and energy use per unit road length by classification were estimated using data gathered from actual road samples. The unit amounts of cost per unit road length by classification were acquired from the standard cost values provided in the 2013 road business manual. The total carbon emissions, energy use, and cost of the national freeways and highways were calculated by multiplying the road length by the corresponding unit amounts. RESULTS: The total carbon emissions, energy use, and costs associated with the national freeways and highways in Korea were estimated by applying the estimated unit amounts and the developed method. CONCLUSIONS: The developed method can be employed in the road planning and design stage when decision makers need to consider the impact of road construction from an environmental and economic point of view.

• Journal of Korean Society for Geospatial Information Science
• /
• v.22 no.1
• /
• pp.13-22
• /
• 2014

Recently, many civil appeals have been occurred in land management work because of discord between cadastral records and actual land use pattern. it is important to select parcels for land alternation exactly using land information and to evaluate compensation cost according to scenarios for advancing this problem. This study operated GIS spatial overlay based on serial cadastral maps and actual-width of the road and analyzed the number and area of the parcels for land alternation by the land classification and ownership applying fuzzy membership function according to occupation ratio to road. Also compensation cost was calculated according to scenarios using individual public land price information of the parcels for land alternation and was arranged by district as Eup and Myeon according to land classification and ownership. This study can efficiently support the work of the parcels for land alternation complying with the financial condition of local government, by supplying compensation cost according to scenarios to the parcels of land alternation by district as Eup and Myeon.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.157-173
• /
• 2011

As the Internet use explodes recently, the malicious attacks and hacking for a system connected to network occur frequently. This means the fatal damage can be caused by these intrusions in the government agency, public office, and company operating various systems. For such reasons, there are growing interests and demand about the intrusion detection systems (IDS)-the security systems for detecting, identifying and responding to unauthorized or abnormal activities appropriately. The intrusion detection models that have been applied in conventional IDS are generally designed by modeling the experts' implicit knowledge on the network intrusions or the hackers' abnormal behaviors. These kinds of intrusion detection models perform well under the normal situations. However, they show poor performance when they meet a new or unknown pattern of the network attacks. For this reason, several recent studies try to adopt various artificial intelligence techniques, which can proactively respond to the unknown threats. Especially, artificial neural networks (ANNs) have popularly been applied in the prior studies because of its superior prediction accuracy. However, ANNs have some intrinsic limitations such as the risk of overfitting, the requirement of the large sample size, and the lack of understanding the prediction process (i.e. black box theory). As a result, the most recent studies on IDS have started to adopt support vector machine (SVM), the classification technique that is more stable and powerful compared to ANNs. SVM is known as a relatively high predictive power and generalization capability. Under this background, this study proposes a novel intelligent intrusion detection model that uses SVM as the classification model in order to improve the predictive ability of IDS. Also, our model is designed to consider the asymmetric error cost by optimizing the classification threshold. Generally, there are two common forms of errors in intrusion detection. The first error type is the False-Positive Error (FPE). In the case of FPE, the wrong judgment on it may result in the unnecessary fixation. The second error type is the False-Negative Error (FNE) that mainly misjudges the malware of the program as normal. Compared to FPE, FNE is more fatal. Thus, when considering total cost of misclassification in IDS, it is more reasonable to assign heavier weights on FNE rather than FPE. Therefore, we designed our proposed intrusion detection model to optimize the classification threshold in order to minimize the total misclassification cost. In this case, conventional SVM cannot be applied because it is designed to generate discrete output (i.e. a class). To resolve this problem, we used the revised SVM technique proposed by Platt(2000), which is able to generate the probability estimate. To validate the practical applicability of our model, we applied it to the real-world dataset for network intrusion detection. The experimental dataset was collected from the IDS sensor of an official institution in Korea from January to June 2010. We collected 15,000 log data in total, and selected 1,000 samples from them by using random sampling method. In addition, the SVM model was compared with the logistic regression (LOGIT), decision trees (DT), and ANN to confirm the superiority of the proposed model. LOGIT and DT was experimented using PASW Statistics v18.0, and ANN was experimented using Neuroshell 4.0. For SVM, LIBSVM v2.90-a freeware for training SVM classifier-was used. Empirical results showed that our proposed model based on SVM outperformed all the other comparative models in detecting network intrusions from the accuracy perspective. They also showed that our model reduced the total misclassification cost compared to the ANN-based intrusion detection model. As a result, it is expected that the intrusion detection model proposed in this paper would not only enhance the performance of IDS, but also lead to better management of FNE.

• Korean Journal of Construction Engineering and Management
• /
• v.25 no.1
• /
• pp.32-41
• /
• 2024

In the construction industry, not only safety accidents, but also various complex risks such as construction delays, cost increases, and environmental pollution occur, and management technologies are needed to solve them. Among them, process risk management, which directly affects the project, lacks related information compared to its importance. This study tried to develop a MATM tunnel process risk classification system to solve the difficulty of risk information retrieval due to the use of different classification systems for each project. Risk collection used existing literature review and experience mining techniques, and DB construction utilized the concept of natural language processing. For the structure of the classification system, the existing WBS structure was adopted in consideration of compatibility of data, and an RBS linked to the work species of the WBS was established. As a result of the research, a risk classification system was completed that easily identifies risks by work type and intuitively reveals risk characteristics and risk factors linked to risks. As a result of verifying the usability of the established classification system, it was found that the classification system was effective as risks and risk factors for each work type were easily identified by user input of keywords. Through this study, it is expected to contribute to preventing an increase in cost and construction period by identifying risks according to work types in advance when planning and designing NATM tunnels and establishing countermeasures suitable for those factors.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.2
• /
• pp.233-242
• /
• 2018

Previous works for detecting arrhythmia have mostly used nonlinear method such as artificial neural network, fuzzy theory, support vector machine to increase classification accuracy. Most methods require higher computational cost and larger processing time. Therefore it is necessary to design efficient algorithm that classifies PVC(premature ventricular contraction) and decreases computational cost by accurately detecting feature point based on only R peak through optimal R wave. For this purpose, we detected R wave through optimal threshold value and extracted RR interval and R peak pattern from noise-free ECG signal through the preprocessing method. Also, we classified PVC in realtime through RR interval and R peak pattern. The performance of R wave detection and PVC classification is evaluated by using 9 record of MIT-BIH arrhythmia database that included over 30. The achieved scores indicate the average of 99.02% in R wave detection and the rate of 94.85% in PVC classification.