• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.10
• /
• pp.927-932
• /
• 2010

Estimation methods of motion intention from bio-signal present challenges in man machine interaction(MMI) to offer user's command to machine without control of any devices. Measurements of meaningful bio-signals that contain the motion intention and motion estimation methods from bio-signal are important issues for accurate and safe interaction. This paper proposes a novel motion estimation sensor based on a geometrical muscle changes, and a motion estimation method using the sensor. For estimation of the motion, we measure the circumference change of the muscle which is proportional to muscle activation level using a flexible piezoelectric cable (pMAS, piezo muscle activation sensor), designed in band type. The pMAS measures variations of the cable band that originate from circumference changes of muscle bundles. Moreover, we estimate the elbow motion by applying the sensor to upper limb with least square method. The proposed sensor and prediction method are simple to use so that they can be used to motion prediction device and methods in rehabilitation and sports fields.

• Journal of information and communication convergence engineering
• /
• v.14 no.4
• /
• pp.258-267
• /
• 2016

Three-dimensional integrated circuits (3D ICs) experience die-to-die variations in addition to the already challenging within-die variations. This adds an additional design complexity and makes variation estimation and full-chip optimization even more challenging. In this paper, we show that the industry standard on-chip variation (AOCV) tables cannot be applied directly to 3D paths that are spanning multiple dies. We develop a new machine learning-based model and methodology for an accurate variation estimation of logic paths in 3D designs. Our model makes use of key parameters extracted from existing GDSII 3D IC design and sign-off simulation database. Thus, it requires no runtime overhead when compared to AOCV analysis while achieving an average accuracy of 90% in variation evaluation. By using our model in a full-chip variation-aware 3D IC physical design flow, we obtain up to 16% improvement in critical path delay under variations, which is verified with detailed Monte Carlo simulations.

• Proceedings of the Korea Technical Association of the Pulp and Paper Industry Conference
• /
• 1999.11b
• /
• pp.61-69
• /
• 1999

Contaminants such as fatty acids, triglycerides, resin acids and foam collected from a high yield sulfite weak liquor storage tank lowered the water surface tension and reduced inter-fibre bonding but also tended to benefit sheet opacity. Some common wet end additives such as defoamers and dispersants gave similar results. Lignosulfonate and naphthalene sulfonate showed little if any negative effect on both surface tension and sheet strength properties. Among the natural wood extractives. fatty acids were identified to be most detrimental followed by triglycerides and then resin acids. In order to alleviate the detrimental impact of these contaminants, membrane separation, air floatation and ozone treatment were carried out on paper machine white water samples. The effect of these treatments on removal of fatty and resin acids was quantified by a GC-Mass analysis. Reverse osmosis with a 1000 molecular weight cut off membrane failed to totally reject fatty and resin acids, but markedly reduced losses of sheet properties due to contaminants. Ozone treatment resulted in a significant increase of the surface tension and air floatation was considered to be a practical and useful method for removing fatty and resin acids from the machine white water.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.441-444
• /
• 2016

Peace on the Korean Peninsula is threatened by physical aggressions and cyber terrors such as nuclear tests, missile launchings, senior government officials' smart phone hackings and DDos attacks to banking systems. Cyber attacks such as vulnerability for the hackings, malware distributions are generally defended by passive defense through the detecting signs of first invasion and attack, data analysis, adding library and updating vaccine programs. In this paper the concept of security program based on Google TensorFlow machine learning ability to perform adding libraries and solving security vulnerabilities by itself is researched and proposed.

• Fashion & Textile Research Journal
• /
• v.2 no.3
• /
• pp.227-233
• /
• 2000

The purpose of this study was to develop the High Functional Covering machine and the Compound Twister to produce the high value added textile goods and to meet the consumer's needs. For the study, 8 yarns and 12 fabrics were made with two developed machines and the tensile characteristics of the samples were tested and analysed. The result indicated that the sample fabrics kept their elongation regardless of buffering process. Elongation of the sample yarns was higher than those of yarns made with a traditional covering method. Elastic recovery of the sample fabrics was more effected by the recovery rate than by the number of extension and the characteristics of the sample yarns and fabrics were comparable to the yarns and fabrics made with a traditional covering method in terms of the position of Spandex yarns in their yarn structure and buffering effect.

• 제어로봇시스템학회:학술대회논문집
• /
• 1998.10a
• /
• pp.391-394
• /
• 1998

The man-machine interface Is an important factor in the computer system, and it is thought that line-of-sight (LOS) detection technology will allow significant advances in this field. Techniques for detecting LOS for use in human interfaces have been studied［1]［2］. In earlier studies, however, LOS was detected with a head piece, goggles, or through fixing the position of the head. The limitations imposed by these fixed conditions render them unsuitable far use in interfaces, as they have adverse mental or physical effects on humans. Therefore. they have not been sufficiently developed for practical application. Research on non-contact LOS detection is expected to result in a usable LOS man-machine interface［3］［4］, and the current study is intended to be a step in that direction. The authors used color contact lenses for LOS detection, and applied this new method to a computer interface. The use of color contact lenses simplifies image processing. The algorithm used in this study is sufficiently accurate for practical applications. This technique can be used in input devices, in virtual reality applications, and in human engineering research.

• Nuclear Engineering and Technology
• /
• v.52 no.5
• /
• pp.1008-1012
• /
• 2020

In order to make reasonable design for the improvement of comprehensive mechanical properties of RAFM steels, the design system with both machine learning and high-throughput optimization algorithm was established. As the basis of the design system, a dataset of RAFM steels was compiled from previous literatures. Then, feature engineering guided random forests regressors were trained by the dataset and NSGA II algorithm were used for the selection of the optimal solutions from the large-scale solution set with nine composition features and two treatment processing features. The selected optimal solutions by this design system showed prospective mechanical properties, which was also consistent with the physical metallurgy theory. This efficiency design mode could give the enlightenment for the design of other metal structural materials with the requirement of multi-properties.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.27 no.6
• /
• pp.507-514
• /
• 2022

This study proposes an optimal design process for a high-frequency transformer that has a large leakage inductance for dual-active-bridge converters. Notably, conventional design processes have large errors in designing leakage transformers because mathematically modeling the leakage inductance of such transformers is difficult. In this work, the geometric parameters of a shell-type transformer are identified, and finite element analysis(FEA) simulation is performed to determine the magnetization inductance, leakage inductance, and copper loss of various shapes of shell-type transformers. Regression models for magnetization and leakage inductances and copper loss are established using the simulation results and the machine learning technique. In addition, to improve the regression models' performance, the regression models are tuned by adding featured parameters that consider the physical characteristics of the transformer. With the regression models, optimal high-frequency transformer designs and the Pareto front (in terms of volume and loss) are determined using NSGA-II. In the Pareto front, a desirable optimal design is selected and verified by FEA simulation and experimentation. The simulated and measured leakage inductances of the selected design match well, and this result shows the validity of the proposed design process.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.207-209
• /
• 2022

In the IoT environment, it is possible to collect life pattern data by recognizing human physical activity from smart devices. In this paper, the proposed model consists of a prediction stage and a recommendation stage. The prediction stage predicts the scale of anxiety and depression by using logistic regression and k-nearest neighbor algorithm through machine learning on the dataset collected from life pattern data. In the recommendation step, if the symptoms of anxiety and depression are classified, the principal component analysis algorithm is applied to recommend food and light exercise that can improve them. It is expected that the proposed anxiety/depression prediction and food/exercise recommendations will have a ripple effect on improving the quality of life of individuals.

• Journal of Sensor Science and Technology
• /
• v.33 no.3
• /
• pp.139-146
• /
• 2024

Surface-enhanced Raman scattering (SERS) enables the detection of various types of π-conjugated biological and chemical molecules owing to its exceptional sensitivity in obtaining unique spectra, offering nondestructive classification capabilities for target analytes. Herein, we demonstrate an innovative strategy that provides significant machine learning (ML)-enabled predictive SERS platforms through surface-engineered graphene via complementary hybridization with Au nanoparticles (NPs). The hybridized Au NPs/graphene SERS platforms showed exceptional sensitivity (10^-7 M) due to the collaborative strong correlation between the localized electromagnetic effect and the enhanced chemical bonding reactivity. The chemical and physical properties of the demonstrated SERS platform were systematically investigated using microscopy and spectroscopic analysis. Furthermore, an innovative strategy employing ML is proposed to predict various analytes based on a featured Raman spectral database. Using a customized data-preprocessing algorithm, the feature data for ML were extracted from the Raman peak characteristic information, such as intensity, position, and width, from the SERS spectrum data. Additionally, sophisticated evaluations of various types of ML classification models were conducted using k-fold cross-validation (k = 5), showing 99% prediction accuracy.