• Communications for Statistical Applications and Methods
• /
• v.31 no.2
• /
• pp.235-246
• /
• 2024

In high-dimensional data analysis, sufficient dimension reduction (SDR) has been considered as an attractive tool for reducing the dimensionality of predictors while preserving regression information. The principal support vector machine (PSVM) (Li et al., 2011) offers a unified approach for both linear and nonlinear SDR. This article comprehensively explores a variety of SDR methods based on the PSVM, which we call principal machines (PM) for SDR. The PM achieves SDR by solving a sequence of convex optimizations akin to popular supervised learning methods, such as the support vector machine, logistic regression, and quantile regression, to name a few. This makes the PM straightforward to handle and extend in both theoretical and computational aspects, as we will see throughout this article.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.10
• /
• pp.45-52
• /
• 1999

The online realtime positioning error compensation system 'SKY-PACS' is developed to correct geometric errors, thermal errors and tool deflection errors induced by cutting forces on the vertical machining center. 'SKY-PACS' communicates position commands and position compensation signals with the CNC controller at 100Hz, which is CNC control frequency. So the compensation procedure can be applied during axis movement. Using 'SKY-PACS', Maximum 1 axis positioning accuracy was corrected from 5{\mu}m$ to 2{\mu}m$and the squareness error of X-Y table was corrected from 51{\mu}m$/m to below 4{\mu}m$/m. The error compensation under the cutting condition is carried out by ISO10791-7. And the measurement of test-pieces shows that the roundness is corrected rom 8{\mu}m$ to below 5{\mu}m$.

• Agricultural and Biosystems Engineering
• /
• v.5 no.2
• /
• pp.50-54
• /
• 2004

The study aimed to develop a mechanized mushroom growing system for the substrate materials mixing and wetting, materials fermentation and pasteurisation through the design of integrated cultivation machine system for oyster mushroom. The power requirement of the prototype during fermentation operation was measured in the range of 31$\~$33 kg-m and the torque has not so much differ by the kinds and quantity of materials. The work efficiency of conventional method for stacking the heap and turning the heap of cotton waste by tractor rotavator and manual wetting required 78 hours. But the watering, fermentation and sterilisation by the prototype use same operation required 25.5 hours, which can save the operation labour by $67\%$. The machine can be saved the requirement of heating energy by $63\%$, and the machine can also be saved the material cost by $44\%$. It is envisaged that the machine can effectively be used for large mushroom growing farms or joint use mushroom growing group-farmers in a village.

• Journal of Power Electronics
• /
• v.3 no.2
• /
• pp.115-123
• /
• 2003

This paper presents analysis, design and simulation for the indirect field orientation control (IFOC) of induction machine drive system. The dynamic performance of the IFOC under nominal and detuned parameters of the induction machine is established. A conventional proportional plus integral-derivative (PI-D) two-degree-of-freedom controller (2DOFC) is designed and analysed for an ideal IFOC induction machine drive at nominal parameters with the desired dynamic response. Varying the induction machine parameters causes a degredation in the dynamic response for disturbance rejection and tracking performance with PI-D 2DOF speed controller. Therefore, conventional controllers can nut meet a wide range of speed tracking performance under parameter variations. To achieve high- dynamic performance, a proposed robust fuzzy logic controllers (RFLC) for d-axis rotor flux, d-q axis stator currents and rotor speed have been designed and analysed. These controllers provide robust tracking and disturbance rejection performance when detuning occurres and improve the dynamic behavior. The proposed REL controllers provide a fast and accurate dynamic response in tracking and disturbance rejection characteristics under parameter variations. Computer simulation results demonstrate the effectiveness of the proposed REL controllers and a robust performance is obtained fur IFOC induction machine drive system.

• Transactions of Materials Processing
• /
• v.32 no.2
• /
• pp.74-80
• /
• 2023

A deformation behavior of commercially pure titanium (CP-Ti) is highly dependent on material and processing parameters, such as deformation temperature, deformation direction, and strain rate. This study aims to predict the multivariable and nonlinear tensile behavior of CP-Ti using machine learning based on three algorithms: artificial neural network (ANN), light gradient boosting machine (LGBM), and long short-term memory (LSTM). The predictivity for tensile behaviors at the cryogenic temperature was lower than those in the room temperature due to the larger data scattering in the train dataset used in the machine learning. Although LGBM showed the lowest value of root mean squared error, it was not the best strategy owing to the overfitting and step-function morphology different from the actual data. LSTM performed the best as it effectively learned the continuous characteristics of a flow curve as well as it spent the reduced time for machine learning, even without sufficient database and hyperparameter tuning.

• Textile Coloration and Finishing
• /
• v.10 no.4
• /
• pp.37-44
• /
• 1998

The purpose of this study was to elucidate the effect of weight loss of polyethylene terephthalate(PET) fabrics on the mechanical properties such as bending and shear. In order to compare the effect of treatment machine on the mechanical properies of treated PET fabrics, PET fabrics were hydrolyzed with NaOH aqueous solution using Tank machine and Liquor flow machine, respectively. The results were as follows ： 1. The bending rigidity and shear stiffness of hydrolyzed PET fabric decreased markedly up to about 10％ weight loss regardless of treatment machines. At the above 10％ weight loss, the variation of these properties is nearly unchanged. In addition, the bending hysteresis and shear hysteresis also showed similar trend. 2. Weft density change of PET fabrics treated with Liquor flow machine decreased by 1pick/inch. It is assumed that this is attributed to the tension during the treatment of Liquor flow machine. On the other hand, the weft density change of PET fabrics treated with Tank machine is scarcely influeneced by the weight loss. While warp density of PET fabrics treated with Liquor flow machine had no change with weight loss, warp density of PET fabrics treated with Tank machine decreased by 6pick/inch due to the tension. 3. The bending rigidity and shear stiffness of PET fabrics hydrolyzed with liquor flow machine slightly higher than with Tank m/c at the above 10％ weight loss. It is assumed that this is caused by the increasement of the crossing pressure of warp and weft yarn and contact points of filaments in the yarns. Also, the bending and shear hysteresis of PET fabrics treated with Tank machine were higher than that of liquor flow machine.

• Journal of the Korean Graphic Arts Communication Society
• /
• v.16 no.2
• /
• pp.1-10
• /
• 1998

Even if some kinds of software for halftoning such as raster image process program are on the market, most of them couldn`t apply to the new laser gravure cylinder making machine because they are closed the source program. In order to develop new laser gravure engraving machine, we were investigated new suitable halftoning software based on the mapping and equal density expansion algorithm that we are mapped. As the results of actual practice with Microsoft Visiul C++2.0 in 133Khz 64M ram IBM personal computer, we found that the new software for halftone generation for laser gravure engraving machine are available in new machine, and easily load and processing the graphic image for gravure hardcopy.

• Physical Therapy Korea
• /
• v.10 no.3
• /
• pp.81-90
• /
• 2003

This study was conducted to assess the effects of the gait training method in incomplete spinal cord injured persons using an auto-walking machine. Persons with incomplete spinal cord injury level C or D on the American Spinal Injury Association impairment scale participated for eight weeks in an auto-walking training program. The gait training program was carried out for 15 minutes, three times per day for 8 weeks with an auto-walking machine. The foot rests of the auto-walking machine can be moved forward, downward, backward and upward to make the gait pattern with fixed on crank. The patient's body weight is supported by a harness during waking training. We evaluated the gait speed, physiologic cost index, motor score of lower extremities and the WISCI (walking index for spinal cord injury) level before the training and after the forth and eighth week of walking training. 1. The mean gait speed was significantly increased from .22 m/s at pre-training to .28 m/s after 4 weeks of training and .31 m/s after 8 weeks of training (p=.004). 2. The mean physiologic cost index was decreased from 4.6 beats/min at pre-training to 3.0 beats/min after 4 weeks and 2.0 beats/min after 8 weeks of training, but it was not statistically significant (p=.140). 3. The mean motor score of lower extrernities was significantly increased from 29.8 to 35.8 after 8 weeks of training (p=.043). 4. The mean WISCI level was significantly increased from level 10 to level 19 after 8 weeks of training (p=.007). The results of this study suggest that the gait training program using the auto-walking machine increased the gait speed, muscle strength and galt pattern (WISCI level) in persons with incomplete spinal cord injury. A large, controlled study of this technique is warranted.

• Journal of the Korean Society for Precision Engineering
• /
• v.17 no.1
• /
• pp.120-128
• /
• 2000

One of the major limitations of productivity and quality in metal cutting is the machining accuracy of machine tools. The machining accuracy is affected by geometric errors, thermally-induced errors, and the deterioration of the machine tools. Geometric and thermal errors of machine tools should be measured and compensated to manufacture high quality products. In metal cutting, the machining accuracy is more affected by thermal errors than by geometric errors. This paper models of the thermal errors for error analysis and develops on-the-machine measurement system by which the volumetric error are measured and compensated. The thermal error is modeled by means of angularity errors of a column and thermal drift error of the spindle unit which are measured by the touch probe unit with a star type styluses and a designed spherical ball artifact (SBA). Experiments, performed with the developed measurement system, show that the system provides a high measuring accuracy, with repeatability of $\pm$2${\mu}{\textrm}{m}$ in X, Y and Z directions. It is believed that the developed measurement system can be also applied to the machine tools with CNC controller. In addition, machining accuracy and product quality can be improved by using the developed measurement system when the spherical ball artifact is mounted on the modular fixture.

• Journal of Korean Institute of Industrial Engineers
• /
• v.29 no.3
• /
• pp.190-196
• /
• 2003

We consider the problem of scheduling n jobs on m machines with the objective of minimizing makespan. Each job cannot be eligible to all the machines but to its consecutively eligible set of machines. For this problem, a 2-approximation algorithm, MFFH, is developed. In addition, an example is presented to show the tightness of the algorithm.