• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.1
• /
• pp.8-14
• /
• 2002

In this paper, we realized a real-time text-independent speaker recognition system using gaussian mixture model, and applied frame level likelihood normalization method which shows its effects in verification system. The system has three parts as front-end, training, recognition. In front-end part, cepstral mean normalization and silence removal method were applied to consider speaker's speaking variations. In training, gaussian mixture model was used for speaker's acoustic feature modeling, and maximum likelihood estimation was used for GMM parameter optimization. In recognition, likelihood score was calculated with speaker models and test data at frame level. As test sentences, we used text-independent sentences. ETRI 445 and KLE 452 database were used for training and test, and cepstrum coefficient and regressive coefficient were used as feature parameters. The experiment results show that the frame-level likelihood method's recognition result is higher than conventional method's, independently the number of registered speakers.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.38 no.12
• /
• pp.1441-1446
• /
• 2014

In the present paper, the effects of the thickness and width of a curved wide-plate, the crack length, and the strain hardening exponent on the crack-tip constraint of the curved wide-plate were investigated. To accomplish this, detailed three-dimensional elastic-plastic finite element (FE) analyses were performed considering various geometric and material variables. The material was characterized by the Ramberg-Osgood relationship, and the Q-stress was employed as a crack-tip constraint parameter. Based on the present FE results, the variations in the Q-stress of the curved wide-plate with the geometric variables and material properties were evaluated. This revealed that the effect of out-of-plane constraint conditions on the crack-tip constraint was closely related to the in-plane constraint conditions, and out-of-plane constraint conditions affected the crack-tip constraint more than in-plane constraint conditions.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.37 no.6
• /
• pp.607-614
• /
• 2013

Nowadays, automotive manufacturers have developed various technologies to improve fuel economy and reduce harmful emissions. The ultra-lean direct injection engine is a promising technology because it has the advantage of improving thermal efficiency through the deliberate control of fuel and ignition. This study aims to investigate the development of a spray-guided-type lean-burn LPG direct injection engine through the redesign of the combustion system. This engine uses a central-injection-type cylinder head in which the injector is installed adjacent to the spark plug. Fuel consumption and combustion stability were estimated depending on the ignition timing and injection timing at various air-fuel ratios. The optimal injection timing and ignition timing were based on the best fuel consumption and combustion stability.

• Journal of IKEEE
• /
• v.8 no.1 s.14
• /
• pp.96-107
• /
• 2004

In this paper, a new integral variable structure regulation controller(IVSRC) is designed by using a special integral sliding surface and a disturbance observer for the improved regulation control of highly nonlinear robot manipulators with prescribed output performance. The sliding surface having the integral state with a special initial condition is employed in this paper to exactly predetermine the ideal sliding trajectory from a given initial condition to origin without any reaching phase. And a continuous sliding mode input using the disturbance observer is also introduced in oder to effectively follow the predetermined sliding trajectory within the prescribed accuracy without large computation burden. The performance of the prescribed tracking accuracy to the predetermined sliding trajectory is clearly investigated in detail through the two theorems together with the closed loop stability. The design of the proposed IVSRC is separated into the performance design and robustness design in each independent link. The usefulness of the algorithm has been demonstrated through simulation studies on the regulation control of a two link manipulator under parameter uncertainties and payload variations, in view of no reaching phase, no overshoot, predetermined response with prescribed accuracy, easy change of output performance, separation of design phase, and so on.

• Journal of Environmental Policy
• /
• v.11 no.4
• /
• pp.85-105
• /
• 2012

In this paper, the energy efficiency of wastewater utilities was evaluated to explore ways to save energy via operational measures. The correlation of each wastewater characteristic parameter to energy was assessed to find a set of parameters that explained most of the variations in energy use among utilities. The results show that increases in inflow, influent COD concentration, and ratio of advanced treatment generally increased the energy use. On the other hand, increases in load factor (influentaverage flow/design flow) reduced the energy use. In the regression analysis, the energy efficiency was highest in the A2O advanced process. On the other hand, the membrane process (among the advanced processes) and the contacted aeration process (among the secondary processes) require more efforts in saving energy. However, the data base system related to energy use must be supplemented in order for more accurate analysis of energy consumption in wastewater treatment facilities. In particular, i) electricity consumption of relay pumps and, ii) energy usage per unit process, iii) pump power usage to discharge treated wastewater in a long distance, if necessary, and iv) alternative energy production and utilization status must be recorded. By utilizing the results of the analysis conducted in this study, it is possible to quantify a level of energy savings needed and establish customized energy saving measures to achieve a certain target level for benchmarking a successful case of wastewater utilities.

• Journal of Intelligence and Information Systems
• /
• v.22 no.1
• /
• pp.139-157
• /
• 2016

Bankruptcy involves considerable costs, so it can have significant effects on a country's economy. Thus, bankruptcy prediction is an important issue. Over the past several decades, many researchers have addressed topics associated with bankruptcy prediction. Early research on bankruptcy prediction employed conventional statistical methods such as univariate analysis, discriminant analysis, multiple regression, and logistic regression. Later on, many studies began utilizing artificial intelligence techniques such as inductive learning, neural networks, and case-based reasoning. Currently, ensemble models are being utilized to enhance the accuracy of bankruptcy prediction. Ensemble classification involves combining multiple classifiers to obtain more accurate predictions than those obtained using individual models. Ensemble learning techniques are known to be very useful for improving the generalization ability of the classifier. Base classifiers in the ensemble must be as accurate and diverse as possible in order to enhance the generalization ability of an ensemble model. Commonly used methods for constructing ensemble classifiers include bagging, boosting, and random subspace. The random subspace method selects a random feature subset for each classifier from the original feature space to diversify the base classifiers of an ensemble. Each ensemble member is trained by a randomly chosen feature subspace from the original feature set, and predictions from each ensemble member are combined by an aggregation method. The k-nearest neighbors (KNN) classifier is robust with respect to variations in the dataset but is very sensitive to changes in the feature space. For this reason, KNN is a good classifier for the random subspace method. The KNN random subspace ensemble model has been shown to be very effective for improving an individual KNN model. The k parameter of KNN base classifiers and selected feature subsets for base classifiers play an important role in determining the performance of the KNN ensemble model. However, few studies have focused on optimizing the k parameter and feature subsets of base classifiers in the ensemble. This study proposed a new ensemble method that improves upon the performance KNN ensemble model by optimizing both k parameters and feature subsets of base classifiers. A genetic algorithm was used to optimize the KNN ensemble model and improve the prediction accuracy of the ensemble model. The proposed model was applied to a bankruptcy prediction problem by using a real dataset from Korean companies. The research data included 1800 externally non-audited firms that filed for bankruptcy (900 cases) or non-bankruptcy (900 cases). Initially, the dataset consisted of 134 financial ratios. Prior to the experiments, 75 financial ratios were selected based on an independent sample t-test of each financial ratio as an input variable and bankruptcy or non-bankruptcy as an output variable. Of these, 24 financial ratios were selected by using a logistic regression backward feature selection method. The complete dataset was separated into two parts: training and validation. The training dataset was further divided into two portions: one for the training model and the other to avoid overfitting. The prediction accuracy against this dataset was used to determine the fitness value in order to avoid overfitting. The validation dataset was used to evaluate the effectiveness of the final model. A 10-fold cross-validation was implemented to compare the performances of the proposed model and other models. To evaluate the effectiveness of the proposed model, the classification accuracy of the proposed model was compared with that of other models. The Q-statistic values and average classification accuracies of base classifiers were investigated. The experimental results showed that the proposed model outperformed other models, such as the single model and random subspace ensemble model.

• Korean Journal of Acupuncture
• /
• v.30 no.4
• /
• pp.252-263
• /
• 2013

Objectives : Skin color deformation by cupping has been widely used as a diagnostic parameter in Traditional Korean Medicine(TKM). Skin color deformation such as ecchymoses and purpura is induced by local vacuum in a suction cup. Since existing studies have relied on a visual diagnostic method, there is a need to use the quantitative measurement method. Methods : We conducted an analysis of cross-polarization photographic images to assess the changes in skin color deformation. The skin color variation was analyzed using $L^*a^*b^*$ space and the skin erythema index(E.I.). The meridian theory in TKM indicates that the condition of primary internal organs is closely related to the skin color deformation at special acupoints. Before conducting these studies, it is necessary to evaluate whether or not skin color deformation is influenced by muscle condition. Hence, we applied cupping at BL13, BL15, BL18, BL20 and BL23 at Bladder Meridian(BL) and measured blood lactate at every acupoint. Results : We confirmed the high system measurement accuracy, and observed the diverse skin color deformations. Moreover, we confirmed that the $L^*$, $a^*$ and E.I. had not changed after 40 minutes(p>0.05). The distribution of blood lactate levels at each part was observed differently. Blood lactate level and skin color deformation at each part was independent of each other. Conclusions : The negative pressure produced by the suction cup induces a reduction in the volumetric fraction of melanosomes and subsequent reduction in epidermal thickness. The relationship between variations of tissue and skin properties and skin color deformation degree must be investigated prior to considering the relationship between internal organ dysfunction and skin color deformation.

• The Journal of Korean Society for Radiation Therapy
• /
• v.33
• /
• pp.89-97
• /
• 2021

Purpose: The purpose of this study is to compare and evaluate the dose change according to the gas volume variations in the rectum, which was not included in the treatment plan during radiation therapy for cervical cancer. Materials and methods: Static Intensity Modulated Radiation Therapy (S-IMRT) using a 9-field and Volumetric Modulated Arc Therapy (VMAT) using 2 full-arcs were established with treatment planning system on Computed Tomography images of a human phantom. Random gas parameters were included in the Planning Target Volume(PTV) with a maximum change of 2.0 cm in increments of 0.5 cm. Then, the Conformity Index (CI), Homogeneity Index (HI) and PTV D_max for the target volume were calculated, and the minimum dose (D_min), mean dose (D_mean) and Maximum Dose (D_max) were calculated and compared for OAR(organs at risk). For statistical analysis, T-test was performed to obtain a p-value, where the significance level was set to 0.05. Result: The HI coefficients of determination(R²) of S-IMRT and VMAT were 0.9423 and 0.8223, respectively, indicating a relatively clear correlation, and PTV D_max was found to increase up to 2.8% as the volume of a given gas parameter increased. In case of OAR evaluation, the dose in the bladder did not change with gas volume while a significant dose difference of more than D_mean 700 cGy was confirmed in rectum using both treatment plans at gas volumes of 1.0 cm or more. In all values except for D_mean of bladder, p-value was less than 0.05, confirming a statistically significant difference. Conclusion: In the case of gas generation not considered in the reference treatment plan, as the amount of gas increased, the dose difference at PTV and the dose delivered to the rectum increased. Therefore, during radiation therapy, it is necessary to make efforts to minimize the dose transmission error caused by a large amount of gas volumes in the rectum. Further studies will be necessary to evaluate dose transmission by not only varying the gas volume but also where the gas was located in the treatment field.

• Radiation Oncology Journal
• /
• v.20 no.4
• /
• pp.381-390
• /
• 2002

Purpose : To develop a dose calibration program for the IAEA TRS-277 and AAPM TG-21, based on the air kerma calibration factor (or the cavity-gas calibration factor), as well as for the IAEA TRS-398 and the AAPM TG-51, based on the absorbed dose to water calibration factor, so as to avoid the unwanted error associated with these calculation procedures. Materials and Methods : Currently, the most widely used dosimetry Protocols of high energy photon beams are the air kerma calibration factor based on the IAEA TRS-277 and the AAPM TG-21. However, this has somewhat complex formalism and limitations for the improvement of the accuracy due to uncertainties of the physical quantities. Recently, the IAEA and the AAPM published the absorbed dose to water calibration factor based, on the IAEA TRS-398 and the AAPM TG-51. The formalism and physical parameters were strictly applied to these four dose calibration programs. The tables and graphs of physical data and the information for ion chambers were numericalized for their incorporation into a database. These programs were developed user to be friendly, with the Visual $C^{++}$ language for their ease of use in a Windows environment according to the recommendation of each protocols. Results : The dose calibration programs for the high energy photon beams, developed for the four protocols, allow the input of informations about a dosimetry system, the characteristics of the beam quality, the measurement conditions and dosimetry results, to enable the minimization of any inter-user variations and errors, during the calculation procedure. Also, it was possible to compare the absorbed dose to water data of the four different protocols at a single reference points. Conclusion : Since this program expressed information in numerical and data-based forms for the physical parameter tables, graphs and of the ion chambers, the error associated with the procedures and different user could be solved. It was possible to analyze and compare the major difference for each dosimetry protocol, since the program was designed to be user friendly and to accurately calculate the correction factors and absorbed dose. It is expected that accurate dose calculations in high energy photon beams can be made by the users for selecting and performing the appropriate dosimetry protocol.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.16 no.4
• /
• pp.34-43
• /
• 2012

The behaviors of the curved bridges which has been constructed in the RAMP or Interchange are very complicate and different than orthogonal bridges according to the variations of radius of curvature, skew angle and spacing of shoes. Occasionally, the camber of girder and negative reactions can be occurred due to bending and torsional moment. In this study, the effects on the negative reaction in the curved bridge were investigated on the basis of design variables such as radius of curvature, skew angle, and spacing of shoes. For this study, the twin-steel box girder curved bridge with single span which is applicable for the RAMP bridges with span length(L) of 50.0m and width of 9.0m was chosen and the structural analysis to calculate the reactions was conducted using 3-dimensional equivalent grillage system. The value of negative reaction in curved bridges depends on the plan structures of bridges, the formations of structural systems, and the boundary conditions of bearing, so, radius of curvature, skew angle, and spacing of shoes among of design variables were chosen as the parameter and the load combination according to the design standard were considered. According to the results of numerical analysis, the negative reaction in curved bridge increased with an decrease of radius of curvature, skew angle, and spacing of shoes, respectively. Also, in case of skew angle of $60^{\circ}$ the negative reaction has been always occurred without regard to ${\theta}/B$, and in case of skew angle of $75^{\circ}$ the negative reaction hasn't been occurred in ${\theta}/B$ below 0.27 with the radius of curvature of 180m and in ${\theta}/B$ below 0.32 with the radius of curvature of 250m, and in case of skew angle of $90^{\circ}$ the negative reaction hasn't been occurred in the radius of curvature over 180m and in ${\theta}/B$ below 0.38 with the radius of curvature of 130m, The results from this study indicated that occurrence of negative reaction was related to design variables such as radius of curvature, skew angle, and spacing of shoes, and the problems with the stability including negative reaction will be expected to be solved as taken into consideration of the proper combinations of design variables in design of curved bridge.