• Journal of information and communication convergence engineering
• /
• v.17 no.1
• /
• pp.41-48
• /
• 2019

In recent years, sentiment analysis research has become popular. The research results of sentiment analysis have achieved remarkable results in practical applications, such as in Amazon's book recommendation system and the North American movie box office evaluation system. Analyzing big data based on user preferences and evaluations and recommending hot-selling books and hot-rated movies to users in a targeted manner greatly improve book sales and attendance rate in movies [1, 2]. However, traditional machine learning-based sentiment analysis methods such as the Classification and Regression Tree (CART), Support Vector Machine (SVM), and k-nearest neighbor classification (kNN) had performed poorly in accuracy. In this paper, an improved kNN classification method is proposed. Through the improved method and normalizing of data, the purpose of improving accuracy is achieved. Subsequently, the three classification algorithms and the improved algorithm were compared based on experimental data. Experiments show that the improved method performs best in the kNN classification method, with an accuracy rate of 11.5% and a precision rate of 20.3%.

• Honam Mathematical Journal
• /
• v.26 no.1
• /
• pp.87-103
• /
• 2004

A practical estimation method for groundwater contaminant concentration is introduced. Using geostatistical techniques and symmetry, experimental variograms show significant improved correlation compared with those from conventional techniques. Numrical experiments are performed using a field data set.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.26 no.7
• /
• pp.1348-1356
• /
• 2002

The present work concerns the optimal design for injection molding processes by using the design of experiments (DOE) and numerical analysis. The DOE approaches is planned to be able to consider two-way interaction, and have been applied progressively for both mold design and process design. Numerical analyses have been carried out as a design of experiments for mold parameters such as runner specifications and cooling channel configurations. In order to determine optimal process parameters, experiments have been performed for various process conditions with the DOE scheduling. As a result, the quality and productivity of the product have been improved, and the proposed approach can be successfully reflected on the industrial injection molding process of precision electronics parts.

• Journal of Korean Elementary Science Education
• /
• v.29 no.3
• /
• pp.316-325
• /
• 2010

The purpose of this study was to analyze elementary school teacher' expectation and reality before and after science experiment in-service training program. The surveys for before and after in-service training were conducted among 231 elementary school teachers who participated for science experiment in-service training. 5 elementary school teachers who took part in surveys were interviewed after training. The results of this study are as follows: First, teachers' interest for science increased regardless of willingness to training participation through science experiment training. Second, discussion for science teaching strategies were not enough while the training recognized with experiments and lecture of instructors mainly. Third, teachers prefered alternative experiments and practical experience of experiments to lecture and basic experiments based on textbook. Forth, assessment of teachers in training must be improved.

• The KIPS Transactions:PartB
• /
• v.18B no.1
• /
• pp.39-44
• /
• 2011

In this paper, we propose a method to improve the Firefly Algorithm(FA) introduced by Xin-She Yang, recently. We design and analyze the improved firefly algorithm based on the heuristic. We compare the FA with the Particle Swarm Optimization (PSO) which the problem domain is similar with the FA in terms of accuracy, algorithm convergence time, the motion of each particle. The compare experiments show that the accuracy of FA is not worse than PSO's, but the convergence time of FA is slower than PSO's. In this paper, we consider intuitive reasons of slow convergence time problem of FA, and propose the improved version of FA using a partial mutation heuristic based on the consideration. The experiments using benchmark functions show the accuracy and convergence time of the improved FA are better than them of PSO and original FA.

• Nuclear Engineering and Technology
• /
• v.56 no.4
• /
• pp.1165-1203
• /
• 2024

In the paper we validate theoretical models of the pulse against experimental data from the Jozef Stefan Institute TRIGA Mark II research reactor. Data from all pulse experiments since 1991 have been collected, analysed and are publicly available. This paper summarizes the validation study, which is focused on the comparison between experimental values, theoretical predictions (Fuchs-Hansen and Nordheim-Fuchs models) and calculation using computational program Improved Pulse Model. The results show that the theoretical models predicts higher maximum power but lower total released energy, full width at half maximum and the time when the maximum power is reached is shorter, compared to Improved Pulse Model. We evaluate the uncertainties in pulse physical parameters (maximum power, total released energy and full width at half maximum) due to uncertainties in reactor physical parameters (inserted reactivity, delayed neutron fraction, prompt neutron lifetime and effective temperature reactivity coefficient of fuel). It is found that taking into account overestimated correlation of reactor physical parameters does not significantly affect the estimated uncertainties of pulse physical parameters. The relative uncertainties of pulse physical parameters decrease with increasing inserted reactivity. If all reactor physical parameters feature an uncorrelated uncertainty of 10 % the estimated total uncertainty in peak pulse power at 3 $ inserted reactivity is 59 %, where significant contributions come from uncertainties in prompt neutron lifetime and effective temperature reactivity coefficient of fuel. In addition we analyse contribution of two physical mechanisms (Doppler broadening of resonances and neutron spectrum shift) that contribute to the temperature reactivity coefficient of fuel. The Doppler effect contributes around 30 %-15 % while the rest is due to the thermal spectrum hardening for a temperature range between 300 K and 800 K.

• MALSORI
• /
• no.62
• /
• pp.149-161
• /
• 2007

In this paper we proposed a modified reliability function for improving bimodal speaker identification(BSI) performance. The convectional reliability function, used by N. Fox[1], is extended by introducing an optimization factor. We evaluated the proposed method in BSI domain. A BSI system was implemented based on GMM and it was tested using VidTIMIT database. Through speaker identification experiments we verified the usefulness of our proposed method. The experiments showed the improved performance, i.e., the reduction of error rate by 39%.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2001.11a
• /
• pp.953-958
• /
• 2001

A retrofit method “Steel Ring Confinement Retrofit” was proposed and discussed on the material and member characteristics through experiments. Steel Ring Confinement Retrofit consist of confining steel ring and expansive concrete. The steel ring is set on the footing, surrounding the base of the pier. By placing expansive concrete between the pier and steel ring, chemical prestress is introduced in the members. Chemical prestressed ring concrete enlarge the pier section and enhance both the strength and ductility of the pier. It was confirmed that Various Ring Confinement Retrofit improved the strength of the pier up to 30% ~ 100% with experiments.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.852-855
• /
• 1996

A variable structure controller is developed for an AC servo motor used in CNC milling machines. The designed controller is implemented as an outer loop controller to a factory designed motor-servopack system. The robustness parameter is tuned for a fast response when the speed tracking error is large, while it is tuned for small oscillations when the speed tracking error is small. The designed controller is installed on a CNC machine using a PC. Cutting experiments show improved performance over the factory-designed controller.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.1175-1180
• /
• 1991

The purpose of this paper is to improve the matching accuracy in identifying corresponding points in the area-based matching for the processing of stereo vision. For the selection of window size, a new method is proposed based on frequency domain analysis. The effectiveness of the proposed method is confirmed through a series of experiments. To overcome disproportionate distortion in stereo image pair, a new matching method using the warped window is also proposed. In the algorithm, the window is warped according to imaging geometry. Experiments on a synthetic image show that the matching accuracy is improved by 14.1% and 4.2% over the rectangular window method and image warping method each.