• Journal of Intelligence and Information Systems
• /
• v.15 no.4
• /
• pp.99-121
• /
• 2009

Recently, there have been many studies that predict corporate bankruptcy using data mining techniques. Although various data mining techniques have been investigated, some researchers have tried to combine the results of each data mining technique in order to improve classification performance. In this study, we classify 4 types of data mining techniques via their characteristics and select representative techniques of each type then combine them using a genetic algorithm. The genetic algorithm may find optimal or near-optimal solution because it is a global optimization technique. This study compares the results of single models, typical combination models, and the proposed integration model using the genetic algorithm.

• Geomechanics and Engineering
• /
• v.21 no.6
• /
• pp.551-564
• /
• 2020

High-stress and complex geological conditions impose great challenges to maintain excavation stability during deep underground mining. In this research, large anisotropic deformation and its management by support system at a deep underground mine in Western Australia were simulated through three-dimensional finite-difference model. The ubiquitous-joint model was used and calibrated in FLAC3D to reproduce the deformation and failure characteristics of the excavation based on the field monitoring results. After modeling verification, the roles of mining depth also the intercept angle between excavation axis and foliation orientation on the deformation and damage were studied. Based on the results, quantitative relationships between key factors and damage classifications were presented, which can be used as an engineering tool. Subsequently, the performance of support system installation sequences was simulated and compared at four different scenarios. The results show that, first surface support and then reinforcement installation can obtain a better controlling effect. Finally, the influence of bolt spacing and ring spacing were also discussed. The outcomes obtained in this research may play a meaningful reference for facing the challenges in thin-bedded or foliated ground conditions.

• Journal of Intelligence and Information Systems
• /
• v.6 no.1
• /
• pp.73-82
• /
• 2000

This study examined the characteristicso f the knowledge discovery and data mining algorithms to demonstrate how they can be used to predict health outcomes and provide policy information for hypertension management using the Korea Medical Insurance Corporation database. Specifically this study validated the predictive power of data mining algorithms by comparing the performance of logistic regression and two decision tree algorithms CHAID (Chi-squared Automatic Interaction Detection) and C5.0 (a variant of C4.5) since logistic regression has assumed a major position in the healthcare field as a method for predicting or classifying health outcomes based on the specific characteristics of each individual case. This comparison was performed using the test set of 4,588 beneficiaries and the training set of 13,689 beneficiaries that were used to develop the models. On the contrary to the previous study CHAID algorithm performed better than logistic regression in predicting hypertension but C5.0 had the lowest predictive power. In addition CHAID algorithm and association rule also provided the segment characteristics for the risk factors that may be used in developing hypertension management programs. This showed that data mining approach can be a useful analytic tool for predicting and classifying health outcomes data.

• Structural Engineering and Mechanics
• /
• v.58 no.5
• /
• pp.869-886
• /
• 2016

Non-Deformable Support System (NDSS) is one of the support system analysis methods. It is likely seen as numerical analysis. Obviously, numerical modeling is the key tool for this system but not unique. Although the name of the system makes you feel that there is no deformation on the support system, it is not true. The system contains some deformation but in certain tolerance determined by the numerical analyses. The important question is what is the deformation tolerance? Zero deformation in the excavation environment is not the case, actually. However, deformation occurred after supporting is important. This deformation amount will determine the performance of the applied support. NDSS is a stronghold analysis method applied in full to make this work. While doing this, NDSS uses the properties of rock mass and material, various rock mass failure criteria, various material models, different excavation geometries, like other methods. The thing that differ NDSS method from the others is that NDSS makes analysis using the time dependent deformation properties of rock mass and engineering judgement. During the evaluation process, NDSS gives the permission of questioning the field observations, measurements and timedependent support performance. These transactions are carried out with 3-dimensional numeric modeling analysis. The goal of NDSS is to design a support system which does not allow greater deformation of the support system than that calculated by numerical modeling. In this paper, NDSS applied to the problems of Tunnel 34 of the same Project (excavated with NATM method, has a length of 2218 meters), which is driven in graphite schist, was illustrated. Results of the system analysis and insitu measurements successfully coincide with each other.

• Journal of Power Electronics
• /
• v.18 no.2
• /
• pp.511-521
• /
• 2018

Proportional capacitor current feedback active damping (CCFAD) has a limited valid damping region in the discrete time domain as (0, $f_s/6$. However, the resonance frequency ($f_r$) of an LCL-type filter is usually designed to be less than half the sampling frequency ($f_s$) with the symmetry regular sampling method. Therefore, ($f_s/6$, $f_s/2$) becomes an invalid damping region. This paper proposes an improved CCFAD method to extend the valid damping region from (0, $f_s/6$ to (0, $f_s/2$), which covers all of the possible resonance frequencies in the design procedure. The full-valid damping region is obtained and the stability margin of the system is analyzed in the discrete time domain with the Nyquist criterion. Results show that the system can operate stably with the proposed CCFAD method when the resonance frequency is in the region (0, $f_s/2$). The performances at the steady and dynamic state are enhanced by the selected feedback coefficient H and controller gain $K_p$. Finally, the feasibility and effectiveness of the proposed CCFAD method are verified by simulation and experimental results.

• Journal of Korea Spatial Information System Society
• /
• v.12 no.1
• /
• pp.49-56
• /
• 2010

Many researches of frequent pattern mining technique for detecting unknown patterns on spatial data have studied actively. Existing data structures have classified into tree-structure and array-structure, and those structures show the weakness of performance on dense or sparse data. Since spatial data have obtained the characteristics of dense and sparse patterns, it is important for us to mine quickly dense and sparse patterns using only single algorithm. In this paper, we propose novel data structure as compressed patricia frequent pattern tree and frequent pattern mining algorithm based on proposed data structure which can detect frequent patterns quickly in terms of both dense and sparse frequent patterns mining. In our experimental result, proposed algorithm proves about 10 times faster than existing FP-Growth algorithm on both dense and sparse data.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.1
• /
• pp.225-234
• /
• 2019

Bitcoin is a cryptocurrency with characteristics such as de-centralization and distributed ledger, and these features are maintained through a mining system called "proof of work". In the mining system, mining difficulty is adjusted to keep the block generation time constant. However, Bitcoin's current method to update mining difficulty does not reflect the future hash power, so the block generation time can not be kept constant and the error occurs between designed time and real time. This increases the inconsistency between block generation and real world and causes problems such as not meeting deadlines of transaction and exposing the vulnerability to coin-hopping attack. Previous studies to keep the block generation time constant still have the error. In this paper, we propose a machine-learning based method to reduce the error. By training with the previous hash power, we predict the future hash power and adjust the mining difficulty. Our experimental result shows that the error rate can be reduced by about 36% compared with the current method.

• The Korean Journal of Applied Statistics
• /
• v.19 no.3
• /
• pp.599-617
• /
• 2006

Recently many LBS(Location Based Service) systems are issued in mobile computing systems. Spatial-Temporal Moving Sequence Pattern Mining is a new mining method that mines user moving patterns from user moving path histories in a sensor network environment. The frequent pattern mining is related to the items which customers buy. But on the other hand, our mining method concerns users' moving sequence paths. In this paper, we consider the sequence of moving paths so we handle the repetition of moving paths. Also, we consider the duration that user spends on the location. We proposed new Apriori_msp based on the Apriori algorithm and evaluated its performance results.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.05a
• /
• pp.611-612
• /
• 2006

Many data mining techniques have been proved useful in revealing important patterns from large data sets. Especially, data mining techniques play an important role in a customer data analysis in a financial industry and an electronic commerce. Also, there are many data mining related research papers in a semiconductor industry and an automotive industry. In addition, data mining techniques are applied to the bioinformatics area. To satisfy customers' various requirements, each industry should develop new processes with more accurate production criteria. Also, they spend more money to guarantee their products' quality. In this manner, we apply data mining techniques to the production-related data such as a test data, a field claim data, and POP (point of production) data in the automotive parts industry. Data collection and transformation techniques should be applied to enhance the analysis results. Also, we classify various types of manufacturing processes and proposed an analysis scheme according to the type of manufacturing process. As a result, we could find inter- or intra-process relationships and critical features to monitor the current status of the each process. Finally, it helps an industry to raise their profit and reduce their failure cost.

• Journal of Ocean Engineering and Technology
• /
• v.29 no.2
• /
• pp.128-134
• /
• 2015

Axial vibration analysis is very important for a deep-seabed mining system. In this study, an axial vibration analysis was carried out to estimate the natural frequencies and tensions of the umbilical cable using experimental data obtained from the first pre-pilot mining test. The axial vibrations of the umbilical cable with a pilot mining robot at the bottom end were analytically determined. The range of the added mass coefficients of the pilot mining robot is estimated by comparing the experimental and analytical data. The natural frequencies and maximum tensions are calculated using four estimated added mass coefficients.