• The KIPS Transactions:PartB
• /
• v.15B no.5
• /
• pp.457-464
• /
• 2008

In the real-world operational environment, most of text classification systems have the problems of insufficient training documents and no prior knowledge of feature space. In this regard, $Na{\ddot{i}ve$ Bayes is known to be an appropriate algorithm of operational text classification since the classification model can be evolved easily by incrementally updating its pre-learned classification model and feature space. This paper proposes the improving technique of $Na{\ddot{i}ve$ Bayes classifier through feature weighting strategy. The basic idea is that parameter estimation of $Na{\ddot{i}ve$ Bayes considers the degree of feature importance as well as feature distribution. We can develop a more accurate classification model by incorporating feature weights into Naive Bayes learning algorithm, not performing a learning process with a reduced feature set. In addition, we have extended a conventional feature update algorithm for incremental feature weighting in a dynamic operational environment. To evaluate the proposed method, we perform the experiments using the various document collections, and show that the traditional $Na{\ddot{i}ve$ Bayes classifier can be significantly improved by the proposed technique.

• Korean Journal of Remote Sensing
• /
• v.34 no.3
• /
• pp.481-494
• /
• 2018

The accurate radiative transfer model simulation is essential for an accurate ozone profile retrieval using optimal estimation from backscattered ultraviolet (BUV) measurement. The input parameters of the radiative transfer model are the main factors that determine the model accuracy. In particular, meteorological parameters such as temperature and surface pressure have a direct effect on simulating radiation spectrum as a component for calculating ozone absorption cross section and Rayleigh scattering. Hence, a sensitivity of UV ozone profile retrievals to these parameters has been investigated using radiative transfer model. The surface pressure shows an average error within 100 hPa in the daily / monthly climatological data based on the numerical weather prediction model, and the calculated ozone retrieval error is less than 0.2 DU for each layer. On the other hand, the temperature shows an error of 1-7K depending on the observation station and altitude for the same daily / monthly climatological data, and the calculated ozone retrieval error is about 4 DU for each layer. These results can help to understand the obtained vertical ozone information from satellite. In addition, they are expected to be used effectively in selecting the meteorological input data and establishing the system design direction in the process of applying the algorithm to satellite operation.

• Journal of Korean Society of Environmental Engineers
• /
• v.28 no.4
• /
• pp.429-437
• /
• 2006

To establish the efficient treatment technology of chemical cleaning wastewater from power plant, several AOPs($UV/H_2O_2,\;UV/TiO_2/H_2O_2$, Photo-Fenton oxidation) were investigated. Treatment efficiencies and the electrical energy requirements based on the EE/O parameter(the electrical energy, required per order of pollutant removal in $1m^3$ wastewater) were evaluated. TOC removal efficiencies of $UV/H_2O_2,\;UV/TiO_2/H_2O_2$, Photo-Fenton oxidation at the optimum conditions were 95.5%, 92.3%, 91.5%, respectively. The electrical energy requirements of $UV/H_2O_2,\;UV/TiO_2/H_2O_2$, Photo-Fenton oxidation were $11.26kWh/m^3,\;3.85kWh/m^3,\;0.799kWh/m^3$, respectively. From these results, it could be concluded that all of the three oxidation processes were effective for the degradation of citric acid. Considering the treatment efficiency and economical aspect, photo-Fenton oxidation was the most efficient treatment process among the three processes tested.

• Journal of Korean Society of Environmental Engineers
• /
• v.22 no.11
• /
• pp.2037-2046
• /
• 2000

It has been reported that the inhibition effect of pH on activated sludge follows noncompetitive inhibition kinetics. However. the noncompetitive inhibition kinetic equation can not be directly applied to pH inhibition because of the difficulty in quantification of pH in terms of inhibitor concentration. So, many empirical equations have been developed to describe the pH inhibition effect especially for acidic condition. In this research. the pseudo toxic concentration ($C_{PT}$) concept model to quantify pH inhibition effect on activated sludge was proposed and compared to other existing models. The $C_{PT}$ concept model can explain the reduction of the maximum specific growth rate (${\mu}_{max}$) caused by the pH inhibition more accurately than any other models, at a wide range of pH. The only model parameter. $K_I$ can be easily estimated by Lineweaver-Burk linearization method.

• Journal of the Korean Society of Food Culture
• /
• v.3 no.3
• /
• pp.309-317
• /
• 1988

The effects of $CaCl_2$, K-sorbate, and fermented fish sauces and blanching on the texture of Chinese cabbage of Kimchi were evaluated. The addition of salt-fermented shrimp or salt-fermented anchovy accelerated the pH reduction, acidity increase and reducing sugar consumption, but K-sorbate, Ca-chloride and blanching suppressed the ripening process of Kimchi. The latter retarded the softening rate of Chinese cabbage during Kimchi fermentation, as demonstrated by the cutting force, compression force, recovered height and work ratio. The sensory evaluation confirmed the results of instrumental texture measurments. The instrumental measurements, i.e. pH, acidity cutting thickness, cutting force and compression test parameters, showed acidity acidity was calculated as % lactic acid attributes, i.e. the preferences for taste, appearance and texture, and the level of crispiness, hardness, chewiness and fibrousness. The pH of Kimchi was appeared to be an important quality parameter, whiih had significant correlations with the taste, appearance, chewiness, hardness, fibrousness and crispiness.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.1
• /
• pp.114-123
• /
• 2018

This paper concerns a design and learning method of softmax function neural networks based on K-means clustering. The partial discharge data Information is preliminarily processed through simulation using an Epoxy Mica Coupling sensor and an internal Phase Resolved Partial Discharge Analysis algorithm. The obtained information is processed according to the characteristics of the pattern using a Motor Insulation Monitoring System program. At this time, the processed data are total 4 types that void discharge, corona discharge, surface discharge and slot discharge. The partial discharge data with high dimensional input variables are secondarily processed by principal component analysis method and reduced with keeping the characteristics of pattern as low dimensional input variables. And therefore, the pattern classifier processing speed exhibits improved effects. In addition, in the process of extracting the partial discharge data through the MIMS program, the magnitude of amplitude is divided into the maximum value and the average value, and two pattern characteristics are set and compared and analyzed. In the first half of the proposed partial discharge pattern classifier, the input and hidden layers are classified by using the K-means clustering method and the output of the hidden layer is obtained. In the latter part, the cross entropy error function is used for parameter learning between the hidden layer and the output layer. The final output layer is output as a normalized probability value between 0 and 1 using the softmax function. The advantage of using the softmax function is that it allows access and application of multiple class problems and stochastic interpretation. First of all, there is an advantage that one output value affects the remaining output value and its accompanying learning is accelerated. Also, to solve the overfitting problem, L2-normalization is applied. To prove the superiority of the proposed pattern classifier, we compare and analyze the classification rate with conventional radial basis function neural networks.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.11
• /
• pp.1423-1433
• /
• 2018

Recently, a permanent magnet synchronous motor of middle and small-capacity has high torque, high precision control and acceleration / deceleration characteristics. But existing control has several problems that include unpredictable disturbances and parameter changes in the high accuracy and rigidity control industry or nonlinear dynamic characteristics not considered in the driving part. In addition, in the drive method for the control of low-vibration and high-precision, the process of connecting the permanent magnet synchronous motor and the load may cause the response characteristic of the system to become very unstable, to cause vibration, and to overload the system. In order to solve these problems, various studies such as adaptive control, optimal control, robust control and artificial neural network have been actively conducted. In this paper, an incremental encoder of the permanent magnet synchronous motor is used to detect the position of the rotor. And the position of the detected rotor is used for low vibration and high precision position control. As the controller, we propose augmented state feedback control with a speed observer and first order deadbeat disturbance observer. The augmented state feedback controller performs control that the position of the rotor reaches the reference position quickly and precisely. The addition of the speed observer to this augmented state feedback controller compensates for the drop in speed response characteristics by using the previously calculated speed value for the control. The first order deadbeat disturbance observer performs control to reduce the vibration of the motor by compensating for the vibrating component or disturbance that the mechanism has. Since the deadbeat disturbance observer has a characteristic of being vulnerable to noise, it is supplemented by moving average filter method to reduce the influence of the noise. Thus, the new controller with the first order deadbeat disturbance observer can perform more robustness and precise the position control for the influence of large inertial load and natural frequency. The simulation stability and efficiency has been obtained through C language and Matlab Simulink. In addition, the experiment of actual 2.5[kW] permanent magnet synchronous motor was verified.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.2
• /
• pp.8-18
• /
• 2020

An Exponential Bandwidth Harmony Search with Centralized Global Search (EBHS-CGS) was developed to enhance the performance of a Harmony Search (HS). EBHS-CGS added two methods to improve the performance of HS. The first method is an improvement of bandwidth (bw) that enhances the local search. This method replaces the existing bw with an exponential bw and reduces the bw value as the iteration proceeds. This form of bw allows for an accurate local search, which enables the algorithm to obtain more accurate values. The second method is to reduce the search range for an efficient global search. This method reduces the search space by considering the best decision variable in Harmony Memory (HM). This process is carried out separately from the global search of the HS by the new parameter, Centralized Global Search Rate (CGSR). The reduced search space enables an effective global search, which improves the performance of the algorithm. The proposed algorithm was applied to a representative optimization problem (math and engineering), and the results of the application were compared with the HS and better Improved Harmony Search (IHS).

• The Journal of the Korea Contents Association
• /
• v.12 no.4
• /
• pp.390-400
• /
• 2012

The satisfaction of customers, who are in a servicescape, will be subject to many environmental stimulations. In particularly, the servicescapes of the store and the customer characteristics are important factors that affecting the emotional commitment of consumers. In this study, the servicescape that consumers evaluated can be divided into physical and social factors. Furthermore, how these factors can affect the emotional commitment through perceived service quality and social interaction will be studied as well. In addition, the moderating effects of the individual characteristics at the perception of servicescape, such as optimum stimulation level and social appropriateness will be studied together. The results show that the physical factor of servicescape is one of the most important elements that affect "emotional commitment" and under this process; the perceived service quality is performed as a parameter. Besides, the social factor of servicescape, such as the other customer and companion affect can also affect emotional commitment through social interaction. On the other hand, through the analysis of optimum stimulation level and social appropriateness, we found that the higher the social appropriateness, the greater the effect of servicescape. Overall, in order to enhance the customer's emotional commitment, we must build high quality servicescape, meanwhile; the management of other customers and the companion are needed at the same time.

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.10 no.3
• /
• pp.161-170
• /
• 2012

To provide domestic values of input parameters in a safety assessment of radioactive waste disposal under domestic deep underground environments, various kinds of experiments have been carried out under KURT (KAERI Underground Research Tunnel) conditions. The input parameters were classified, and some of them were selected for this study by the criteria of importance. The domestic experimental data under KURT environments were given top priority in the data review process. Foreign data under similar conditions to KURT were also gathered. The collected data were arranged and the statistical calculations were processed. The properties and distribution of the data were explained and compared to foreign values in view of their validity. The following parameters were analysed: failure time and early time failure rate of a container, solubility of nuclides, porosity and density of the buffer, and distribution coefficients of nuclides in the geomedia, hydraulic conductivity, diffusion depth of nuclides, groundwater flow rate, fracture aperture, length of internal fracture, and width of faulted rock mass in the host rock.