• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.49 no.3
• /
• pp.145-151
• /
• 2000

The topological investigations regarding magnetic circuit geometry and winding form of the transverse flux machine have brought up a variety of constructable arrangements with different features for several types of application[1, 2]. Here with, a novel PM-exited linear motor with inner mover, based on the transverse flux configuration leads to a considerable increase in power density for moving part. In this study we designed PM-exited transverse flux linear motor for ropeless elevator, whose output power density is higher and weight is lighter than conventional linear synchronous motors. When the designed motor in this study is applied to ropeless elevator, it is possible to increase power density more than 400% comparing with PM exited linear synchronous motor. The result of this study can be utilized for ropeless elevator or gearless direct linear moving system with high output[3].

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.8
• /
• pp.1164-1171
• /
• 2012

Recently, machine olfactory systems as an artificial substitute of the human olfactory system are being studied actively because they can scent dangerous gases and identify the type of gases in contamination areas instead of the human. In this paper, we present an effective design method for the gas identification system. Even though dimensionality reduction is the very important part, in pattern analysis, We handled effectively the dimensionality reduction by grouping the sensors of which the measured patterns are similar each other, where genetic algorithms were used for combination optimization. To identify the gas type, we constructed the hierarchical rule base with two frames by using rough set theory. The first frame is to accept measurement characteristics of each sensor and the other one is to reflect the identification patterns of each group. Thus, the proposed methods was able to accomplish effectively dimensionality reduction as well as accurate gas identification. In simulation, we demonstrated the effectiveness of the proposed methods by identifying five types of gases.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.42 no.3
• /
• pp.562-565
• /
• 2017

In this letter, we consider a 7-step transmission procedure of a large number of machine nodes when they simultaneously request random access to transmit uplink data. We model the radio resource utilization of LTE systems, and analyze the overloaded resources. From the simulation results, we show that the resource of PDCCH becomes significantly overloaded as the number of machine nodes increases in a cell. To alleviate the overload of PDCCH, we allocate radio resource of PDSCH to PDCCH. The result shows that the resource utilization of PDCCH is improved.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2004.11a
• /
• pp.461-464
• /
• 2004

The reduction effect of floor impact noise depends on the various factors such as stiffness and thickness of the concrete slab, finishing If ceiling materials and the composition method. Among the rest it is well known that floating floor system is more effective. Standard floating floor(SFF) type-2 consisted of 50mm lightweight aerated concrete(LAC) and 20mm damping material has been widely used. But LAC construction problem on dry damping material occurred and the reduction effect of floor impact noise has bare minimum qualifications. Thus the aim of this study is to develop 40mm composite damping material(Soundzero Plus) for SFF type-5 which substitute LAC and damping material. 'Soundzero Plus' is satisfied with quality requirement for damping material for SFF. The heat transition rate, $0.45W/m^2{\cdot}K$ is more effective 55% about than the regulation. The test results of floor impact noise by using 'Soundzero Plus' are showed good improvement about 12dB (tested by tapping machine) and 4dB (tested by bang machine) between before and after.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2005.11a
• /
• pp.950-953
• /
• 2005

Floor impact sounds from two different floor systems were measured. One of the two floor systems is a dry floor system (with 150mm concrete slab) and the other is a standard floor system (210mm concrete slab). Real impact sources such as jumping and running of children were used as well as standard impact sources (bang machine, impact ball and tapping machine) to evaluate sound Isolation of the two floor systems. Subjective evaluations of the floor impact sound isolation performance for the two systems were also conducted by the methods of 3 scales & 9 categories, paired comparison and semantic differentials. Measurement results indicate that floor impact sound isolation performance of the dry floor was better than that of standard floor in both cases of real and standard impact sources. The subjects in auditory experiments also evaluated the dry floor as a better sound isolation system.

• The Korean Journal of Applied Statistics
• /
• v.29 no.5
• /
• pp.961-975
• /
• 2016

The hierarchically penalized support vector machine (H-SVM) has been developed to perform simultaneous classification and input variable selection when input variables are naturally grouped or generated by factors. However, the H-SVM may suffer from estimation inefficiency because it applies the same amount of shrinkage to each variable without assessing its relative importance. In addition, when analyzing imbalanced data with uneven class sizes, the classification accuracy of the H-SVM may drop significantly in predicting minority class because its classifiers are undesirably biased toward the majority class. To remedy such problems, we propose the weighted adaptive H-SVM (WAH-SVM) method, which uses a adaptive tuning parameters to improve the performance of variable selection and the weights to differentiate the misclassification of data points between classes. Numerical results are presented to demonstrate the competitive performance of the proposed WAH-SVM over existing SVM methods.

• The Korean Journal of Applied Statistics
• /
• v.28 no.1
• /
• pp.9-21
• /
• 2015

The support vector machine has been successfully applied to various classification areas due to its flexibility and a high level of classification accuracy. However, when analyzing imbalanced data with uneven class sizes, the classification accuracy of SVM may drop significantly in predicting minority class because the SVM classifiers are undesirably biased toward the majority class. The weighted $L_2$-norm SVM was developed for the analysis of imbalanced data; however, it cannot identify irrelevant input variables due to the characteristics of the ridge penalty. Therefore, we propose the weighted $L_1$-norm SVM, which uses lasso penalty to select important input variables and weights to differentiate the misclassification of data points between classes. We demonstrate the satisfactory performance of the proposed method through simulation studies and a real data analysis.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.26 no.1
• /
• pp.1-10
• /
• 2021

In this study, Information for the case of seawater flooding and observation data over a period of 10 years (2009~2018) was collected. Using machine learning algorithms, the characteristics of the types of seawater flooding and observations by type were classified. Information for the case of seawater flooding was collected from the reports of the Korea Hydrographic and Oceanographic Agency (KHOA) and the Korea Land and Geospatial Informatics Corporation. Observation data for ocean and meteorological were collected from the KHOA and the Korea Meteorological Agency (KMA). The classification of seawater flooding incidence types is largely categorized into four types, and into 5 development types through combination of 4 types. These types were able to distinguish the types of seawater flooding according to the marine weather environment. The main characteristics of each was classified into the following groups: tidal movement, low pressure system, strong wind, and typhoon. Besides, in consideration of the geographical characteristics of the ocean, the thresholds of ocean factors for seawater flooding by region and type were derived.

• Smart Media Journal
• /
• v.11 no.1
• /
• pp.58-66
• /
• 2022

As Internet technology develops, SNS users are increasing. As SNS becomes popular, SNS-type crimes using the influence and anonymity of social networks are increasing day by day. In this paper, we propose a fake account classification method that applies machine learning and deep learning to statistical and image data for fake accounts classification. SNS account data used for training was collected by itself, and the collected data is based on statistical data and image data. In the case of statistical data, machine learning and multi-layer perceptron were employed to train. Furthermore in the case of image data, a convolutional neural network (CNN) was utilized. Accordingly, it was confirmed that the overall performance of account classification was significantly meaningful.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.3
• /
• pp.531-538
• /
• 2024

While the importance of the water quality environment is being emphasized, the water quality index for improving the water quality of urban rivers in Gwangju Metropolitan City is an important factor affecting the aquatic ecosystem and requires accurate prediction. In this paper, the XGBoost and LightGBM machine learning algorithms were used to compare the performance of the water quality inspection items of the downstream Pyeongchon Bridge and upstream BanghakBr_Gwangjucheon1 water systems, which are important points of Gwangju Stream, as a result of statistical verification, three water quality indicators, Nitrogen(TN), Nitrate(NO3), and Ammonia amount(NH3) were predicted, and the performance of the predictive model was evaluated by using RMSE, a regression model evaluation index. As a result of comparing the performance after cross-validation by implementing individual models for each water system, the XGBoost model showed excellent predictive ability.