• Proceedings of the KIPE Conference
• /
• 1998.07a
• /
• pp.384-387
• /
• 1998

This paper presents a newly developed speed sensorless drive using RLS(Recursive Least Squares) based on Neural Network Training Algorithm. The proposed algorithm based on the RLS has just the time-varying learning rate, while the well-known back-propagation (or generalized delta rule) algorithm based on gradient descent has a constant learning rate. The number of iterations required by the new algorithm to converge is less than that of the back-propagation algorithm. The RLS based on NN is used to adjust the motor speed so that the neural model output follows the desired trajectory. This mechanism forces the estimated speed to follow precisely the actual motor speed. In this paper, a flux estimation strategy using filter concept is discussed. The theoretical analysis and experimental results to verify the effectiveness of the proposed analysis and the proposed control strategy are described.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.23 no.3
• /
• pp.185-207
• /
• 1998

This research investigates computer generated hybrid second-order model of two numerically based approaches to risk classification : discriminant analysis and neural networks. The hybrid second-order models are derived by rule induction using the ID3 and tested in the several different kinds of data. This new hybrid approach is designed to combine the high prediction accuracy and robustness of DA or NN with perspicuity of ID3. The hybrid model also eliminates the problem of contradictory inputs of ID3. After doing empirical test for the validity of hybrid model using small and medium companies' bankrupt data, hybrid model shows high perspicuity, high prediction accuracy for bankrupt, and simplicity for rules. The hybrid model also shows high performance regardless the type of data such as numeric data, non-numeric data, and combined data.

• Journal of Information Technology Services
• /
• v.2 no.2
• /
• pp.97-109
• /
• 2003

As the importance and the need for network security is increased, many organization uses the various security systems. They enable to construct the consistent integrated security environment by sharing the vulnerable information among firewall, intrusion detection system, and vulnerable scanner. And Policy-based network provides a means by which the management process can be simplified and largely automated. In this article we build a foundation of policy-based network modeling environment. The procedure and structure for policy rule induction from vulnerabilities stored in SVDB (Simulation based Vulnerability Data Based) is conducted. It also transforms the policy rules into PCIM (Policy Core Information Model).

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.3
• /
• pp.461-466
• /
• 2024

Korean local governments operates the participatory budgeting system autonomously. This study is to classify these entities into clusters. Among the diverse machine learning methodologies(Neural Network, Rule Induction(CN2), KNN, Decision Tree, Random Forest, Gradient Boosting, SVM, Naïve Bayes), the Support Vector Machine technique emerged as the most efficacious in the analysis of 2022 Korean municipalities data. The first cluster C1 is characterized by minimal committee activity but a substantial allocation of participatory budgeting; another cluster C3 comprises cities that exhibit a passive stance. The majority of cities falls into the final cluster C2 which is noted for its proactive engagement in. Overall, most Korean local government operates the participatory busgeting system in good shape. Only a small number of cities is less active in this system. We anticipate that analyzing time-series data from the past decade in follow-up studies will further enhance the reliability of classifying local government types regarding participatory budgeting.

• Journal of the Korea Computer Industry Society
• /
• v.2 no.2
• /
• pp.151-156
• /
• 2001

We describe a new representation for learning concepts that differs from the traditional decision tree and rule induction algorithms. Our algorithm PROLEARN learns one or more prototype per class and follows instance based classification with them. Prototype here differs from psychological term in that we can have more than one prototype per concept and also differs from other instance based algorithms since the prototype is a "ficticious ideal example". We show that PROLEARN is as good as the traditional machine learning algorithms but much move stable than them in an environment that has noise or changing training set, what we call 'stability’.tability’.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.2 no.1
• /
• pp.13-17
• /
• 2001

The configuration design of kinematic mechanisms of industrial sewing machine has been studied using a functional approach. The configuration design methodology has been applied to shorten the development cycle time of mechanisms and to manage design data efficiently Expert system has been used to embody the decomposition of functional requirements. It has been interfaced with a CAD system through the API program to show the assembly and parts of the mechanism. Constraints also can be handled by the expert system through the rule induction and the case based reasoning process. The configuration design system includes the kinematical analysis and optimization of the mechanisms of an industrial sewing machine by the interface between the expert system and an analysis program by means of API Program supplied by expert system. The conceptual design of sewing machine mechanism can be Performed rapidly and efficiently.

• Journal of Trauma and Injury
• /
• v.27 no.2
• /
• pp.33-37
• /
• 2014

Central venous catheterization through a subclavian approach is indicated for some special purposes but it may cause many complications such as infection, bleeding, pneumothorax, thrombosis, air embolization, arrhythmia, myocardial perforation, and nerve injury. A case involving a mistaken central venous catheterization into the right vertebral artery through the subclavian artery is presented. A 33-year-old man who had deteriorated mentality after head injury underwent an emergency craniotomy for acute epidural hematomas on the right frontal and temporal convexities. His mentality improved rapidly, but he complained of continuous severe pain in the right posterior neck even though he had no previous symptom or past medical history of such pain. Three-dimensional cervical spine computed tomography (3D-CT) was performed first to rule out unconfirmed cervical injuries and it revealed a linear radiopaque material intrathoracically from the level of the 1st rib up to the level of C6 in the right vertebral foramen. An additional neck CT was performed, and the subclavian catheter was indwelling in the right vertebral artery through right subclavian artery. For the purpose of proper fluid infusion and central venous pressure monitoring, the subclavian vein catheterization had been performed in the operation room after general anesthesia induction before the craniotomy. Sufficient anatomical consideration and prudence is essential because inadvertent arterial cannulation at a non-compressible site is a highly risky iatrogenic complication of central venous line placement.

• Geomechanics and Engineering
• /
• v.14 no.3
• /
• pp.257-269
• /
• 2018

Analysis of slope stability failures, as one of the complex natural hazards, is one of the important research issues in the field of civil engineering. Present paper adopts and investigates four soft computing-based techniques for this problem: Patient Rule-Induction Method (PRIM), M5' algorithm, Group Method of data Handling (GMDH) and Multivariate Adaptive Regression Splines (MARS). A comprehensive database consisting of 168 case histories is used to calibrate and test the developed models. Six predictive variables including slope height, slope angle, bulk density, cohesion, angle of internal friction, and pore water pressure ratio were considered to generate new models. The results of test studies are used for feasibility, effectiveness and practicality comparison of techniques with each other, and with the other available well-known methods in the literature. Results show that all methods not only are feasible but also result in better performance than previously developed soft computing based predictive models and tools. It is shown that M5' and PRIM algorithms are the most effective and practical prediction models.

• Journal of Korea Foundry Society
• /
• v.13 no.4
• /
• pp.359-368
• /
• 1993

Mg-9wt.%Al and Mg-9wt.%-1.6wt%Zn/SiCp(particle size $40{\mu}m$) metal-matrix-composite specimens were manufactured by rheo-compocasting method, known for its effect of improving the wettability. The ceramic reinforcement particles(SiCp) were dispersed in the semi-solid magnesium alloy matrix slurry being vigorously stirred in a high frequency induction furnace under inert atmosphere. A microstructural study of the dispersed particles in the specimens, prepared under different conditions as regards the time(10min, 20min, 30min) and temperature of the stirring, was made with the aid of optical microscope and SEM. The effect of superheating was also observed. It is revealed that 30 minutes' stirring time of the semi-solid at 40% solid fraction temperature(Mg-9wt.%Al : $590^{\circ}C$, AZ91 : $576^{\circ}C$), as determined by the lever rule, gives a satisfactorily uniform distribution of the particles. The superheating is observed to enhance further the uniformity.

• The KIPS Transactions:PartD
• /
• v.15D no.1
• /
• pp.139-146
• /
• 2008

It is very important to identify useful web user group and induce their behavior pattern in eCRM domain. Inducing user group with a similar inclination, a reliability of user group decreases because there is an uncertainty in online user data. In this paper, we have applied the 2-tier clustering, which uses the outcome of interaction with data from other tiers. Also we propose a method which induces user behavior pattern from a cluster and compare C4.5 with our method.