• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.16 no.3
• /
• pp.115-127
• /
• 2006

The purpose of this paper is evaluation of various normalization methods and fusion algorithms in addition to pattern classification algorithms for multi-biometric systems. Experiments are performed using various normalization functions, fusion algorithms and pattern classification algorithms based on Biometric Scores Set-Releasel(BSSR1) provided by NIST. The performance results are presented by Half Total Error Rate (WTER). This study gives base data for the study on performance enhancement of multiple-biometric system by showing performance results using single database and metrics.

• International Journal of Computer Science & Network Security
• /
• v.23 no.6
• /
• pp.115-120
• /
• 2023

Plant leaf diseases and destructive insects are major challenges that affect the agriculture production of the country. Accurate and fast prediction of leaf diseases in crops could help to build-up a suitable treatment technique while considerably reducing the economic and crop losses. In this paper, Convolutional Neural Network based model is proposed to detect leaf diseases of a plant in an efficient manner. Convolutional Neural Network (CNN) is the key technique in Deep learning mainly used for object identification. This model includes an image classifier which is built using machine learning concepts. Tensor Flow runs in the backend and Python programming is used in this model. Previous methods are based on various image processing techniques which are implemented in MATLAB. These methods lack the flexibility of providing good level of accuracy. The proposed system can effectively identify different types of diseases with its ability to deal with complex scenarios from a plant's area. Predictor model is used to precise the disease and showcase the accurate problem which helps in enhancing the noble employment of the farmers. Experimental results indicate that an accuracy of around 93% can be achieved using this model on a prepared Data Set.

• Earthquakes and Structures
• /
• v.24 no.6
• /
• pp.429-437
• /
• 2023

This paper studied the prediction of structural damage indices to buildings after earthquake occurrence using Multiple Linear Regression (MLR) and Fuzzy Linear Regression (FLR) methods. Particularly, the structural damage degree, represented by the Maximum Inter Story Drift Ratio (MISDR), is an essential factor that ensures the safety of the building. Thus, the seismic response of a steel building was evaluated, utilizing 65 seismic accelerograms as input signals. Among the several response quantities, the focus is on the MISDR, which expresses the postseismic damage status. Using MLR and FLR methods and comparing the outputs with the corresponding evaluated by nonlinear dynamic analyses, it was concluded that the FLR method had the most accurate prediction results in contrast to the MLR method. A blind prediction applying a set of another 10 artificial accelerograms also examined the model's effectiveness. The results revealed that the use of the FLR method had the smallest average percentage error level for every set of applied accelerograms, and thus it is a suitable modeling tool in earthquake engineering.

• International Journal of Computer Science & Network Security
• /
• v.24 no.4
• /
• pp.107-112
• /
• 2024

Plant leaf diseases and destructive insects are major challenges that affect the agriculture production of the country. Accurate and fast prediction of leaf diseases in crops could help to build-up a suitable treatment technique while considerably reducing the economic and crop losses. In this paper, Convolutional Neural Network based model is proposed to detect leaf diseases of a plant in an efficient manner. Convolutional Neural Network (CNN) is the key technique in Deep learning mainly used for object identification. This model includes an image classifier which is built using machine learning concepts. Tensor Flow runs in the backend and Python programming is used in this model. Previous methods are based on various image processing techniques which are implemented in MATLAB. These methods lack the flexibility of providing good level of accuracy. The proposed system can effectively identify different types of diseases with its ability to deal with complex scenarios from a plant's area. Predictor model is used to precise the disease and showcase the accurate problem which helps in enhancing the noble employment of the farmers. Experimental results indicate that an accuracy of around 93% can be achieved using this model on a prepared Data Set.

• Journal of The Korean Association For Science Education
• /
• v.12 no.3
• /
• pp.91-107
• /
• 1992

The Purpose of this study was to present the procedures and methods of ordering theory,and to search for a learning hierarchy among science process skills in each Piagetian cognitive reasoning level. One of the purpose of this is not to determine the clear and exact hierarchy but rather to demonstrate how ordering theoretic methods and procedures can be used to determine the hierarchy of logical relationships among a set of test items or the testing of a hypothesized hierarchy. Ordering theory was used to analyze five science process skills collected from 509 high school students. Ordering Theory has as its primary intent either the testing of hypothesized hierarchies among items at the determination of hierchies among items. Hierarchical relationships were identified within five science process skills. The results will be helpful in giving useful inform at ions to classroom teachers and science curriculum developer.

• Journal of Korea Multimedia Society
• /
• v.15 no.9
• /
• pp.1075-1085
• /
• 2012

In clinical research using medical images, the image segmentation is one of the most important processes. Especially, the hippocampal atrophy is helpful for the clinical Alzheimer diagnosis as a specific marker of the progress of Alzheimer. In order to measure hippocampus volume exactly, segmentation of the hippocampus is essential. However, the hippocampus has some features like relatively low contrast, low signal-to-noise ratio, discreted boundary in MRI images, and these features make it difficult to segment hippocampus. To solve this problem, firstly, We selected region of interest from an experiment image, subtracted a original image from the negative image of the original image, enhanced contrast, and applied anisotropic diffusion filtering and gaussian filtering as preprocessing. Finally, We performed an image segmentation using two level set methods. Through a variety of approaches for the validation of proposed hippocampus segmentation method, We confirmed that our proposed method improved the rate and accuracy of the segmentation. Consequently, the proposed method is suitable for segmentation of the area which has similar features with the hippocampus. We believe that our method has great potential if successfully combined with other research findings.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.27 no.1
• /
• pp.1-8
• /
• 2014

Using the level set and the meshfree methods, we develop a topological shape optimization method applied to linear elasticity problems. Design gradients are computed using an efficient adjoint design sensitivity analysis(DSA) method. The boundaries are represented by an implicit moving boundary(IMB) embedded in the level set function obtainable from the "Hamilton-Jacobi type" equation with the "Up-wind scheme". Then, using the implicit function, explicit boundaries are generated to obtain the response and sensitivity of the structures. Global nodal shape function derived on a basis of the reproducing kernel(RK) method is employed to discretize the displacement field in the governing continuum equation. Thus, the material points can be located everywhere in the continuum domain, which enables to generate the explicit boundaries and leads to a precise design result. The developed method defines a Lagrangian functional for the constrained optimization. It minimizes the compliance, satisfying the constraint of allowable volume through the variations of boundary. During the optimization, the velocity to integrate the Hamilton-Jacobi equation is obtained from the optimality condition for the Lagrangian functional. Compared with the conventional shape optimization method, the developed one can easily represent the topological shape variations.

• Journal of Environmental Health Sciences
• /
• v.41 no.2
• /
• pp.133-145
• /
• 2015

Objectives: Food safety has become one of the major public-concerning issues in Korea. In order to set guidelines to create manuals for the response to a food safety crisis by food industry, this paper classified food safety crises and suggested techniques to determine crisis level. Methods: This study clarified common terminologies and definitions including in food safety crises. It reviewed various food safety crises and described characteristics, types, and states of crises. Results: The results of this study suggested that a food safety crisis implied a situation in which hazards/risk spreading in the food supply chain was widely described, causing strong public concern followed by a socioeconomic impact, and therefore, requiring the implementation of a prompt and full response regarding the situation. In terms of seeking response plans, food safety crises might be classified according to the penalties resulting from violations of laws and regulations, causative substances, stages of the food supply chain, and first contact point for incidents. The crisis level for a food safety crisis could be classified according to its severity parameters. The guideline matrix was divided into four major stages: Blue/guarded, Yellow/elevated, Orange/high, and Red/severe. This study also suggested several methods for determining the crisis level, such as the simple judgement method, scoring methods using a check-list and a weighted check-list. Conclusion: The severity of related parameters might be of great importance in understanding a crisis and determining response options/challenges for crisis levels.

• Nutritional Sciences
• /
• v.6 no.1
• /
• pp.48-52
• /
• 2003

The Dietary Reference Intakes (DRI's) are new nutrient intake standards that are being set for the United States and Canada. There are currently four types of DRI's: Estimated Average Requirements (EAR), Recommended Dietary Allowances (RDA), Adequate Intakes (AI), and Tolerable Upper Intake Levels (UL). The EAR is the nutrient intake that would be adequate for about half the population, while intake at the RDA should be adequate for 97-98% of the population. When the data are insufficient to set an EAR and RDA, then an AI is set. The UL is the highest intake level that does not pose a risk of adverse effects. The EAR, AI, and UL may be used to assess intakes of both individuals and of groups of people. For individuals, the EAR is used to calculate the probability that intake is inadequate, the AI is used to decide if the probability of inadequacy is low, and the UL is used to determine if a risk of excess intake is present. For groups. the EAR is used to estimate the prevalence of inadequacy, the AI is used to decide if the prevalence of inadequacy is low, and the UL is used to estimate the prevalence of excessive intakes. Because this approach to setting and applying nutrient standards is new, research recommendations include improving estimates of risk, improving dietary data, and improving statistical methods.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.7
• /
• pp.1117-1122
• /
• 2017

Pedestrian detection is a very important and valuable part of artificial intelligence and computer vision. It can be used in various areas for example automatic drive, video analysis and others. Many works have been done for the pedestrian detection. The accuracy of pedestrian detection on multiple pedestrian image has reached high level. It is not easily get more progress now. This paper proposes a new structure based on the idea of HOG and convolutional filters to do the pedestrian detection in single pedestrian image. It can be a method to increase the accuracy depend on the high accuracy in single pedestrian detection. In this paper, we use Multiblock HOG and magnitude of the pixel as the feature and use convolutional filter to do the to extract the feature. And then use NEWFM to be the classifier for training and testing. We use single pedestrian image of the INRIA data set as the data set. The result shows that the Convolutional Multiblock HOG we proposed get better performance which is 0.015 miss rate at 10-4 false positive than the other detection methods for example HOGLBP which is 0.03 miss rate and ChnFtrs which is 0.075 miss rate.