• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.757-770
• /
• 2022

Palmprint recognition has drawn increasingly attentions in the past decade due to its uniqueness and reliability. Traditional palmprint recognition methods usually use high-resolution images as the identification basis so that they can achieve relatively high precision. However, high-resolution images mean more computation cost in the recognition process, which usually cannot be guaranteed in mobile computing. Therefore, this paper proposes an improved low-resolution palmprint image recognition method based on residual networks. The main contributions include: 1) We introduce a channel attention mechanism to refactor the extracted feature maps, which can pay more attention to the informative feature maps and suppress the useless ones. 2) The ResStage group structure proposed by us divides the original residual block into three stages, and we stabilize the signal characteristics before each stage by means of BN normalization operation to enhance the feature channel. Comparison experiments are conducted on a public dataset provided by the Hong Kong Polytechnic University. Experimental results show that the proposed method achieve a rank-1 accuracy of 98.17% when tested on low-resolution images with the size of 12dpi, which outperforms all the compared methods obviously.

• Journal of Distribution Science
• /
• v.20 no.2
• /
• pp.55-64
• /
• 2022

Purpose: This research is aimed to study the level of the intellectual potential distribution, as well as the correlation between economic growth and key indicators of intellectual potential in each region of Kazakhstan. A review of the conceptual framework shows that there is a large body of research evaluating the level of intellectual potential in different ways based on different factors. Research design, data, and methodology: The research methodology is divided into two groups the integral index method using the normalization of indicators, weighting, and ranking; the method of correlation analysis. By the proposed methodological approaches, were calculated a set of factors affect the distribution of the intellectual potential. Statistics are taken for indicators of development of the intellectual potential for 2011-2020 from the Bureau of National Statistics. Results: Ranking results showed gaps between regions in Kazakhstan by the level of intellectual potential. Correlation analysis results revealed a statistically significant relationship on expenditures on R&D, computer literacy, innovative products, number of PhD students, and cultural and leisure indicators. Conclusions: Based on the obtained results of the intellectual potential level development there were given recommendations for the reproduction and regulation of the intellectual potential in the future.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.5
• /
• pp.530-538
• /
• 2022

Recently, the R&D of weapon systems has been strengthened in terms of economic cost management throughout the entire life cycle from performance. This study proposes the method for setting the optimal maintenance concept based on RAM-C in weapon system acquisition stage by calculating the operation & maintenance cost as well as reliability, availability, and maintainability. First, we design a simulation model for analysis of weapon system logistic supportability. In addition, information such as weapon system Part Breakdown Structure, operation & maintenance system, cost, and etc for simulation analysis, is applied. Based on the obtained simulation results, the optimal plan is selected among alternatives designed with various maintenance concepts through normalization and weight setting. It is expected to be of technical help in the application of RAM-C in the weapon system acquisition stage.

• Tribology and Lubricants
• /
• v.39 no.2
• /
• pp.61-71
• /
• 2023

This study proposes a procedure for designing a labyrinth seal that meets both leakage flow rate and rotordynamic performance criteria (effective damping, amplification factor, separation margin, logarithmic decrement, and vibration amplitude). The seal is modeled using a one control volume (1CV) bulk flow approach to predict the leakage flow rate and rotordynamic coefficients. The rotating shaft is modeled with the finite element (FE) method and is assumed to be supported by two linearized bearings. Geometry, material and operating conditions of the rotating shaft, and the supporting characteristics of the bearings were fixed. A single labyrinth seal is placed at the center of the rotor, and the linearized dynamic coefficients predicted by the seal numerical model are inserted as linear springs and dampers at the seal position. Seal designs that satisfy both leakage and rotordynamic performance are searched by modifying five seal design parameters using the multi-grid method. The five design parameters include pre-swirl ratio, number of teeth, tooth pitch, tooth height and tooth tip width. In total, 12500 seal models are examined and the optimal seal design is selected. Finally, normalization was performed to select the optimal labyrinth seal designs that satisfy the system performance requirements.

• Geomechanics and Engineering
• /
• v.29 no.5
• /
• pp.523-533
• /
• 2022

Several prediction model of penetration rate (PR) of tunnel boring machines (TBMs) have been focused on applying to design stage. In construction stage, however, the expected PR and its trends are changed during tunneling owing to TBM excavation skills and the gap between the investigated and actual geological conditions. Monitoring the PR during tunneling is crucial to rescheduling the excavation plan in real-time. This study proposes a sequential prediction method applicable in the construction stage. Geological and TBM operating data are collected from Gunpo cable tunnel in Korea, and preprocessed through normalization and augmentation. The results show that the sequential prediction for 1 ring unit prediction distance (UPD) is R²≥0.79; whereas, a one-step prediction is R²≤0.30. In modeling algorithm, a gradient boosted regression tree (GBRT) outperformed a least square-based linear regression in sequential prediction method. For practical use, a simple equation between the R² and UPD is proposed. When UPD increases R² decreases exponentially; In particular, UPD at R²=0.60 is calculated as 28 rings using the equation. Such a time interval will provide enough time for decision-making. Evidently, the UPD can be adjusted depending on other project and the R² value targeted by an operator. Therefore, a calculation process for the equation between the R² and UPD is addressed.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.25 no.1
• /
• pp.133-146
• /
• 2015

Ever sophisticated e-finance fraud techniques have led to an increasing number of reported phishing incidents. Financial authorities, in response, have recommended that we enhance existing Fraud Detection Systems (FDS) of banks and other financial institutions. FDSs are systems designed to prevent e-finance accidents through real-time access and validity checks on client transactions. The effectiveness of an FDS depends largely on how fast it can analyze and detect abnormalities in large amounts of customer transaction data. In this study we detect fraudulent transaction patterns and establish detection rules through e-finance accident data analyses. Abnormalities are flagged by comparing individual client transaction patterns with client profiles, using the ruleset. We propose an effective flagging method that uses decision trees to normalize detection rules. In demonstration, we extracted customer usage patterns, customer profile informations and detection rules from the e-finance accident data of an actual domestic(Korean) bank. We then compared the results of our decision tree-normalized detection rules with the results of a sequential detection and confirmed the efficiency of our methods.

• Journal of Korea Multimedia Society
• /
• v.14 no.4
• /
• pp.494-503
• /
• 2011

In this paper, we propose a recognition application of facial expression for laughter theraphy on smartphone. It detects face region by using AdaBoost face detection algorithm from the front camera image of a smartphone. After detecting the face image, it detects the lip region from the detected face image. From the next frame, it doesn't detect the face image but tracks the lip region which were detected in the previous frame by using the three step block matching algorithm. The size of the detected lip image varies according to the distance between camera and user. So, it scales the detected lip image with a fixed size. After that, it minimizes the effect of illumination variation by applying the bilateral symmetry and histogram matching illumination normalization. After that, it computes lip eigen vector by using PCA(Principal Component Analysis) and recognizes laughter expression by using a multilayer perceptron artificial network. The experiment results show that the proposed method could deal with 16.7 frame/s and the proposed illumination normalization method could reduce the variations of illumination better than the existing methods for better recognition performance.

• Journal of the Korean Geotechnical Society
• /
• v.18 no.4
• /
• pp.85-93
• /
• 2002

This study presented a new method for evaluating the coefficient of consolidation by using inflection point method which was based on the fact that time factor, T corresponding to the inflection point of a semi-logarithmic plot of a time curve is fixed and equals to T = 0.405 at 70.03% consolidation. In the proposed method, as the next load increment is applied as soon as the inflection point is confirmed, the time required to identify the inflection point can be shortened. Thus, the coefficient of consolidation may be easily evaluated. The time required to complete the testing using this rapid consolidation method could be as low as 0.5~9 hours compared with 1 or 2 weeks in the case of the conventional consolidation test. For this study, we designed settlement equipment for normalization of test samples. In test results, the factors of consolidation agreed with undisturbed samples results.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.29 no.3
• /
• pp.138-144
• /
• 1987

This study was conducted to pursue the normalization of frequency distribution by making approach the coefficient of skewness to nearly zero tbrough SMEMAX transformation and to get probable minimum flows can be acquired by means of transforrnation equation which has been derivated by SMEMAX method to the annual minimum flow series of five watersheds along Geum river basin. The results obtained through SMEMAX method were compared with probable minimum flows according to return periods by Type III extremal distribution which has been determined as the best fitted one among probablility distributions for the analysis of minimum flow. All the results obtained through this study are summarized as follows. 1.SMEMAX transformation based on median value was proved to be the best method when the coefficient of skewness has less reliability because of the short duration for the observation and were not affected by accidental outliers. 2.SMEMAX transformation has found to be the best one for the coefficient of skewness to be made nearly zero in comparison with log and cubic root transformation. 3.Probable minimum flows according to the return periods were derivated by transformation equations obtained through theoretical analysis of SMEM AX transformation. 4.In general, probable minimum flows by SMEMAX method were appeared as higher values in the range of five and twenty years and as lower ones in the range of below than five and more than fifty years in return periods respectively, in comparison with the results of type III extremal distribution. 5.Relative errors in the probable minimum flows of SMEMAX method to the results of type III extremal distribution were shown to be within ten percent except those of one hundred years in return periods. 6.SMEMAX method was also confirmed to be useful for the analysis of minimum flow frequency as well as flood frequency analysis.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.11
• /
• pp.67-73
• /
• 2010

In this paper, a new face detection method that is more accurate than the conventional methods is proposed. This method utilizes a hybrid of Hausdorff distance based on the geometric similarity between the two sets of points and the LBP distance based on the distribution of local micro texture of an image. The parameters for normalization and the optimal blending factor of the two different metrics were calculated from training sample images. Popularly used face database was used to show that the proposed method is more effective and robust to the variation of the pose, illumination, and back ground than the methods based on the Hausdorff distance or LBP distance. In the particular case, the average error distance between the detected and the true face location was reduced to 47.9% of the result of LBP method, and 22.8% of the result of Hausdorff method.