• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.6
• /
• pp.524-533
• /
• 2021

Recently, due to the increasing necessity of developing core parts for weapons systems, the project for localization of parts for weapons systems is expanding. In order to apply the developed core parts to the domestic weapon system and advance into the overseas market, it is necessary to plan a project that reflects the technology trends in advance. This study derived trend of technology development through conducting the patent research and analysis. Also, suggested plan for applying the analysis results when project planning and selecting. As a detailed method, patents related to the 2019 year selection project were investigated. The number of patent applications by year and number of applicants from the time of the first application to the present were analyzed. And the growth stage of the technology market was derived. The comprehensive result was derieved through the portfolio analysis by arranging the parts localization technology in each area of the matrix consisting of market growth stage and the criteria for the selection of parts localization project. This research suggested the applying plan for improving project selection process. we expect the promotion of defense industry and the effective task planning.

• Analytical Science and Technology
• /
• v.31 no.3
• /
• pp.134-142
• /
• 2018

The uranium isotopic ratio in environmental samples around nuclear facilities is important because it reveals information regarding illegal activities or anthropogenic pollution. Determination of uranium isotopes, however, is a challenging task requiring much labor and time because of the complex separation procedures and lengthy process. In this study, a rapid determination method for uranium isotopes in environmental samples was developed using. The sample was completely decomposed using the alkali fusion method. The separation procedure using extraction chromatography (UTEVA) was simplified in a single step without any further removal process for Si and major matrix elements. The established method can be completed within 3 h from sample dissolution to ICP-MS measurement. Most matrix elements and uranium isotopes in the soil samples were well separated and purified. Five types of were used to assess the method's accuracy and precision for a rapid uranium analysis method. The analytical accuracy for all CRM samples ranged from 95.1 % to 97.8 %, and the relative standard deviation was below 3.9 %. From the analytical results, one may draw conclusions that the evaluated method for uranium isotopes using alkali-fusion, the extraction chromatography process, and ICP-MS measurements is fast and fairly reliable owing to its recovering efficiencies. Thus, it is expected that the evaluated method can contribute to the improvement of environmental monitoring ability.

• Journal of Software Assessment and Valuation
• /
• v.17 no.2
• /
• pp.1-10
• /
• 2021

The ability to recognize human emotions by computer vision is a very important task, with many potential applications. Therefore the demand for emotion recognition using not only RGB images but also thermal images is increasing. Compared to RGB images, thermal images has the advantage of being less affected by lighting conditions but require a more sophisticated recognition method with low-resolution sources. In this paper, we propose a Divide and Conquer-based CNN training strategy to improve the performance of facial thermal image-based emotion recognition. The proposed method first trains to classify difficult-to-classify similar emotion classes into the same class group by confusion matrix analysis and then divides and solves the problem so that the emotion group classified into the same class group is recognized again as actual emotions. In experiments, the proposed method has improved accuracy in all the tests than when recognizing all the presented emotions with a single CNN model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.5
• /
• pp.1413-1432
• /
• 2023

Recommender systems aim to recommend items to users by taking into account their probable interests. This study focuses on creating a model that utilizes multiple sources of information about users and items by employing a multimodality approach. The study addresses the task of how to gather information from different sources (modalities) and transform them into a uniform format, resulting in a multi-modal feature description for users and items. This work also aims to transform and represent the features extracted from different modalities so that the information is in a compatible format for integration and contains important, useful information for the prediction model. To achieve this goal, we propose a novel multi-modal recommendation model, which involves extracting latent features of users and items from a utility matrix using matrix factorization techniques. Various transformation techniques are utilized to extract features from other sources of information such as user reviews, item descriptions, and item categories. We also proposed the use of Principal Component Analysis (PCA) and Feature Selection techniques to reduce the data dimension and extract important features as well as remove noisy features to increase the accuracy of the model. We conducted several different experimental models based on different subsets of modalities on the MovieLens and Amazon sub-category datasets. According to the experimental results, the proposed model significantly enhances the accuracy of recommendations when compared to SVD, which is acknowledged as one of the most effective models for recommender systems. Specifically, the proposed model reduces the RMSE by a range of 4.8% to 21.43% and increases the Precision by a range of 2.07% to 26.49% for the Amazon datasets. Similarly, for the MovieLens dataset, the proposed model reduces the RMSE by 45.61% and increases the Precision by 14.06%. Additionally, the experimental results on both datasets demonstrate that combining information from multiple modalities in the proposed model leads to superior outcomes compared to relying on a single type of information.

• Journal of Intelligence and Information Systems
• /
• v.16 no.4
• /
• pp.67-84
• /
• 2010

In terms of business, forecasting is a work of what is expected to happen in the future to make managerial decisions and plans. Therefore, the accurate forecasting is very important for major managerial decision making and is the basis for making various strategies of business. But it is very difficult to make an unbiased and consistent estimate because of uncertainty and complexity in the future business environment. That is why we should use scientific forecasting model to support business decision making, and make an effort to minimize the model's forecasting error which is difference between observation and estimator. Nevertheless, minimizing the error is not an easy task. Case-based reasoning is a problem solving method that utilizes the past similar case to solve the current problem. To build the successful case-based reasoning models, retrieving the case not only the most similar case but also the most relevant case is very important. To retrieve the similar and relevant case from past cases, the measurement of similarities between cases is an important key factor. Especially, if the cases contain symbolic data, it is more difficult to measure the distances. The purpose of this study is to improve the forecasting accuracy of case-based reasoning approach using fuzzy relation and composition. Especially, two methods are adopted to measure the similarity between cases containing symbolic data. One is to deduct the similarity matrix following binary logic(the judgment of sameness between two symbolic data), the other is to deduct the similarity matrix following fuzzy relation and composition. This study is conducted in the following order; data gathering and preprocessing, model building and analysis, validation analysis, conclusion. First, in the progress of data gathering and preprocessing we collect data set including categorical dependent variables. Also, the data set gathered is cross-section data and independent variables of the data set include several qualitative variables expressed symbolic data. The research data consists of many financial ratios and the corresponding bond ratings of Korean companies. The ratings we employ in this study cover all bonds rated by one of the bond rating agencies in Korea. Our total sample includes 1,816 companies whose commercial papers have been rated in the period 1997~2000. Credit grades are defined as outputs and classified into 5 rating categories(A1, A2, A3, B, C) according to credit levels. Second, in the progress of model building and analysis we deduct the similarity matrix following binary logic and fuzzy composition to measure the similarity between cases containing symbolic data. In this process, the used types of fuzzy composition are max-min, max-product, max-average. And then, the analysis is carried out by case-based reasoning approach with the deducted similarity matrix. Third, in the progress of validation analysis we verify the validation of model through McNemar test based on hit ratio. Finally, we draw a conclusion from the study. As a result, the similarity measuring method using fuzzy relation and composition shows good forecasting performance compared to the similarity measuring method using binary logic for similarity measurement between two symbolic data. But the results of the analysis are not statistically significant in forecasting performance among the types of fuzzy composition. The contributions of this study are as follows. We propose another methodology that fuzzy relation and fuzzy composition could be applied for the similarity measurement between two symbolic data. That is the most important factor to build case-based reasoning model.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.2066-2071
• /
• 2003

In this paper, we identify the isotropic configurations of an omnidirectional mobile robot with three caster wheels, depending on the selection of actuated joints. First, We obtain the kinematic model of a caster wheeled omnidirectional mobile robot(COMR) without matrix inversion. For a given task velocity, the instantaneous motion of each wheel is decomposed into two orthogonal instantaneous motions of the steering and the rotating joints. Second, with the characteristic length introduced, we derive the isotropy conditions of a COMR having $n({\ge}3)$ actuated joints, which are imposed on two Jacobian matrices, $A{\in}R^{n{\times}3}$ and $B{\in}R^{6{\times}6}$. Under the condition of $B{\propto}I_6$, three caster wheels should have identical structure with the length of the steering link equal to the radius of the wheel. Third, depending on the selection of actuated joints, we derive the conditions for $A^t$ $A{\propto}I_3$ and identify the isotropic configurations of a COMR. All possible actuation sets with different number of actuated joints and different combination of rotating and steering joins are considered.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.6
• /
• pp.786-791
• /
• 2011

An optimal feature selection and extraction procedure is an important task that significantly affects the success of brain activity analysis in brain-computer interface (BCI) research area. In this paper, a novel method for extracting the optimal feature from electroencephalogram (EEG) signal is proposed. At first, a student's-t-statistic method is used to normalize and to minimize statistical error between EEG measurements. And, 2D time-frequency data set from the raw EEG signal was extracted using discrete wavelet transform (DWT) as a raw feature, standard deviations and mean of 2D time-frequency matrix were extracted as a optimal EEG feature vector along with other basis feature of sub-band signals. In the experiment, data set 1 of BCI competition IV are used and classification using SVM to prove strength of our new method.

• International Journal of Aeronautical and Space Sciences
• /
• v.18 no.4
• /
• pp.807-815
• /
• 2017

For liquid rocket engine(LRE)-based space launch vehicles, longitudinal instability, often referred to as the pogo phenomenon in the literature is predicted. In the building block of system-level task, accurate dynamic modeling of a fluid-filled tank is an essential. This paper attempts to apply the virtual mass method that accounts for the interaction of the vehicle structure and the enclosed liquid oxygen to LOX-filled tanks. The virtual mass method is applied in a modal analysis considering the hydroelastic effect of the launch vehicle tank. This method involves an analysis of the fluid in the tank in the form of mass matrix. To verify the accuracy of this method, the experimental modal data of a small hemispherical tank is used. Finally, the virtual mass method is applied to a 1/8-scale space shuttle external tank. In addition, the LOX tank bottom pressure in the external tank model is estimated. The LOX tank bottom pressure is the factor required for the coupling of the LOX tank with the propulsion system. The small hemispherical tank analysis provides relatively accurate results, and the 1/8-scale space shuttle external tank provides reasonable results. The LOX tank bottom pressure is also similar to that in the numerical results of a previous analysis.

• Korean Journal of Occupational Health Nursing
• /
• v.22 no.2
• /
• pp.159-170
• /
• 2013

Purpose: To provide the data of health manager education program in order to improve the quality of work-sites health management with qualification based job analysis of health managers (Occupational Health Nursing, Industrial Hygienist, Environmental Engineer). Methods: A descriptive research on 132 health managers using IPA and SPSS/WIN. Results: The overall average of importance of health management job was 8.0 (10 being the maximum score). Nurses had significantly higher score in the level of importance per areas and health management jobs. The overall average of performance of health management job was 6.7 (10 being the maximum score). Nurses had higher score in the area of health management. IPA matrix distributions per health management job area showed the correlations in qualification backgrounds and all of 3 main areas. Conclusion: There was difference in the level of importance and performance on health management jobs based on the qualification backgrounds of health managers. To improve the health of workers, an integrated health management must be provided. And to provide this, it is necessary to offer the additional education to health managers with an institutional complementary plan.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.13 no.3
• /
• pp.21-28
• /
• 2009

The precise analysis of soil-pile-structure interaction requires a proper description of soil layer, pile, and structure. In commonly used finite element simulations, mesh boundaries should match the material discontinuity line. However, in practice, the geometry of soil profiles and piles may be so complex that mesh alignment becomes a wasteful and difficult task. To overcome these difficulties, a different integration method is adopted in this paper, which enables easy integration over a regular element with material discontinuity regardless of the location of the discontinuity line. By applying this integration method, the mesh can be generated rapidly and in a highly structured manner, leading to a very regular stiffness matrix. The influence of the shape of the soil profile and piles on the response is examined, and the validity of the proposed soil-pile structure interaction analysis method is demonstrated through several examples. It is seen that the proposed analysis method can be easily used on soil-pile-structure interaction problems with complex interfaces between materials to produce reliable results regardless of the material discontinuity line.