• Journal of Electrical Engineering and Technology
• /
• v.13 no.4
• /
• pp.1715-1723
• /
• 2018

This work investigates the performance of fully complex- valued radial basis function network(FC-RBF) and complex extreme learning machine (CELM) based neural approaches for classification of power quality disturbances. This work engages the use of S-Transform to extract the features relating to single and combined power quality disturbances. The performance of the classifiers are compared with their real valued counterparts namely extreme learning machine(ELM) and support vector machine(SVM) in terms of convergence and classification ability. The results signify the suitability of complex valued classifiers for power quality disturbance classification.

• Journal of the Korea Safety Management & Science
• /
• v.14 no.2
• /
• pp.49-54
• /
• 2012

As all kind of industry has developed, metal structure and machine instrument use bolt, pin, rivet and welding for assembly and combination. For pin and hinge, dimension accuracy is crucial to keep the operation and safety of the structure and machine instrument. In case of complex machine, the hinge for cover open-loop system is one of the significant design elements. Most of the hinges are being imported and assembled sine they give high technology development cost for its unit cost position. The reason is that the localization of hinge is inadequate. As the demand increase and the necessity of localization grow, it is now more important than ever to develop low cost structure. By the low cost structure, a new technology could be obtained for electronic product and structural hinge since it would enable for complex machine hinge to be guaranteed, technologically. Open-loop hinge is the link type and designed for the structure to keep constant open-loop. And, the hinge is examined in design stability by finite element analysis method. In this paper, the operation result is presented when the hinge for complex machine open-loop is designed for link type structure.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.4
• /
• pp.182-188
• /
• 2013

In this paper, we propose a complex-valued support vector machine (SVM) classifier which process the complex valued signal measured by pulse doppler radar (PDR) to identify moving targets from the background. SVM is widely applied in the field of pattern recognition, but features which used to classify are almost real valued data. Proposed complex-valued SVM can classify the moving target using real valued data, imaginary valued data, and cross-information data. To design complex-valued SVM, we consider slack variables of real and complex axis, and use the KKT (Karush-Kuhn-Tucker) conditions for complex data. Also we apply radial basis function (RBF) as a kernel function which use a distance of complex values. To evaluate the performance of the complex-valued SVM, complex valued data from PDR were classified using real-valued SVM and complex-valued SVM. The proposed complex-valued SVM classification was improved compared to real-valued SVM for dog and human, respectively 8%, 10%, have been improved.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.17 no.6
• /
• pp.97-103
• /
• 2008

In this paper, the Post Process for the manifold complex processing using CAD/CAM Software of two and a half Dimensions(2.5D) has been developed to maximize the application of the manifold manufacturing machine. Many companies are currently making use of high price systems to improve manufacturing process using the multi-axial complex manufacturing machine. In accordance with the requirements, the utilization of CAD/CAM Software for the manifold complex manufacturing machine is earnestly demanded. However, the experts who have experience in manifold manufacturing machine are insufficient. Consequently the outcomes of the Post Process for 2.5D CAD/CAM Systems have been dealt in order to be smoothly operated by those who have basic skills and be understood in process drawings. CNC program functions can be specially used as they are, when drawn up. The Post Process for the original point designation and transformation of coordinates has been developed and applied. The results gave proof of practical manufacturing outcomes.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.12a
• /
• pp.193-198
• /
• 2001

In the large scale B2B transaction like buying Express-Train or selling Daewoo Motor, a tremendous amount of variables and factors of chaos functionate in it directly or indirectly. To get effective information processing on the so called complex system like this, it should be possible to unite the global insight power of the human being and the local computing power of the machine. In this paper, we suggested a union model of human being and machine using Hugent concept. Hugent is defined as an agent model which allows us to chemically unite the human's component and the machine's component in terms of information processing. In this paper, we showed that some typical problems contained in the complex system can be treated more easily through the suggested Hugent concept.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.158-161
• /
• 2003

Recently, the evolution in production techniques (e.g. high-speed milling), the complex shapes involved in modem production design, and the ever increasing pressure for higher productivity demand a drastic improvement of the dynamic behavior of the machine tool axes used in production machinery. And also machine tools of multi functional and minimized parts are increasingly required as demand of higher accurate in some fields such as electronic and optical components etc. The accuracy and the productivity of machined parts are natural to depend on the linear system of machine tools. The complex workpiece surfaces encountered in present-day products and generated by CAD systems are to be transformed into tool paths for machine tools. The more complex these tool paths and the higher the speed requirements, the higher the acceleration requirements are needed to the machine tool axes and the motion control system, and the more difficult it is to meet the requirements. The traditional indirect drive design for high speed machine tools, which consists of a rotary motor with a ball-screw transmission to the slide, is limited in speed, acceleration, and accuracy. The direct drive design of machine tool axes. which is based on linear motors and which recently appeared on the market. is a viable candidate to meet the ever increasing demands, because of these advantages such as no backlash, less friction, no mechanical limitations on acceleration and velocity and mechanical simplicity. Therefore performance tests were carried out to machine tool axes based on linear motor. Especially, dynamic characteristics were investigated through circular test.

• Journal of information and communication convergence engineering
• /
• v.21 no.4
• /
• pp.281-286
• /
• 2023

Diagnosing reading disorders involves complex procedures to evaluate complex cognitive processes. For an accurate diagnosis, a series of tests and evaluations by human experts are required. In this study, we propose a quantitative tool to diagnose reading disorders based on natural reading behaviors using minimal human input. The eye movements of the third- and fourth-grade students were recorded while they read a text at their own pace. Seven machine learning models were used to evaluate the gaze patterns of the words in the presented text and classify the students as normal or having a reading disorder. The accuracy of the machine learning-based diagnosis was measured using the diagnosis by human experts as the ground truth. The highest accuracy of 0.8 was achieved by the support vector machine and random forest classifiers. This result demonstrated that machine learning-based automated diagnosis could substitute for the traditional diagnosis of reading disorders and enable large-scale screening for students at an early age.

• Journal of Digital Convergence
• /
• v.19 no.10
• /
• pp.253-263
• /
• 2021

Machine learning is the process of constructing a cost function using learning data used for learning and an artificial neural network to predict the data, and finding parameters that minimize the cost function. Parameters are changed by using the gradient-based method of the cost function. The more complex the digital signal and the more complex the problem to be learned, the more complex and deeper the structure of the artificial neural network. Such a complex and deep neural network structure can cause over-fitting problems. In order to avoid over-fitting, a weight decay regularization method of parameters is used. We additionally use the value of the cost function in this method. In this way, the accuracy of machine learning is improved, and the superiority is confirmed through numerical experiments. These results derive accurate values for a wide range of artificial intelligence data through machine learning.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.12 no.3
• /
• pp.75-81
• /
• 2003

Pocket machining is metal removal operation commonly used for creating depressions in machined parts. Numerically controlled milling is the primary means for machining complex die surface. These complex surfaces are generated by a milling cutter which removes material as it traces out pre-specified tool paths. To machine, a component on a CNC machine, part programs which define the cutting tool path are needed. This tool path is usually planned from CAD, and converted to a CAM machine input format. In this paper I proposed a new method for generating NC tool paths. This method generates automatically NC tool paths with dynamic elimination of machining errors in 2$\frac{1}{2}$ arbitrary shaped pockets. This paper generates a spiral-like tool path by dynamic computing optimal pocket of the pocket boundary contour based on the type and size of the milling cutter, the geometry of the pocket contour and surface finish tolerance requirements. This part programming system is PC based and simultaneously generates a G-code file.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.21 no.47
• /
• pp.35-45
• /
• 1998

Scheduling problem in Flexible Manufacturing Systems(FMS) is complex because of various situation of Manufacturing Systems. Especially, in case of short-term scheduling demanding high efficiency, low cost at short-period, efficient scheduling is a serious problem. To solve this problem, many dispatching rules are developed. But, it leave much to be desired, because real situation in shop floor is complex and real-time scheduling is needed in real manufacturing shop floor. In this paper, search algorithm that allocate different dispatching rules to each machine is presented to complement lack of dispatching rule and develop practical real-time scheduling system. The search algorithm is described in detail. First, algorithm detect machine breakdown, evaluate each dispatching rule. dispatching rules for each machine meeting performance criteria are ranked. The algorithm selects new dispatching nile for bottleneck machine. The effectivenes and efficiency of the mixed dispatching rule and search algorithm is demonstrated.