• The Journal of the Acoustical Society of Korea
• /
• v.25 no.7
• /
• pp.312-318
• /
• 2006

The conventional lip-synch system has a two-step process, speech segmentation and recognition. However, the difficulty of speech segmentation procedure and the inaccuracy of training data set due to the segmentation lead to a significant Performance degradation in the system. To cope with that, the connected vowel recognition method using Head-Body-Tail (HBT) model is proposed. The HBT model which is appropriate for handling relatively small sized vocabulary tasks reflects co-articulation effect efficiently. Moreover the 7 vowels are merged into 3 classes having similar lip shape while the system is optimized by employing a class dependent SCHMM structure. Additionally in both end sides of each word which has large variations, 8 components Gaussian mixture model is directly used to improve the ability of representation. Though the proposed method reveals similar performance with respect to the CHMM based on the HBT structure. the number of parameters is reduced by 33.92%. This reduction makes it a computationally efficient method enabling real time operation.

• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.92-96
• /
• 2004

The researches of the emotions are currently great interest in speech processing as well as in human-machine interaction domain. In the recent years, more and more of researches relating to emotion synthesis or emotion recognition are developed for the different purposes. Each approach uses its methods and its various parameters measured on the speech signal. In this paper, we proposed using a short-time parameter: MFCC coefficients (Mel­Frequency Cepstrum Coefficients) and a simple but efficient classifying method: Vector Quantification (VQ) for speaker-dependent emotion recognition. Many other features: energy, pitch, zero crossing, phonetic rate, LPC... and their derivatives are also tested and combined with MFCC coefficients in order to find the best combination. The other models: GMM and HMM (Discrete and Continuous Hidden Markov Model) are studied as well in the hope that the usage of continuous distribution and the temporal behaviour of this set of features will improve the quality of emotion recognition. The maximum accuracy recognizing five different emotions exceeds $88\%$ by using only MFCC coefficients with VQ model. This is a simple but efficient approach, the result is even much better than those obtained with the same database in human evaluation by listening and judging without returning permission nor comparison between sentences [8]; And this result is positively comparable with the other approaches.

• Geomechanics and Engineering
• /
• v.8 no.4
• /
• pp.559-594
• /
• 2015

A nonlinear creep function incorporated into the elastic visco-plastic model may describe the long-term soil deformation more accurately. However, by applying the conventional procedure, there are challenges to determine the model parameters due to limitation of suitable data points. This paper presents a numerical solution to obtain several parameters simultaneously for a nonlinear elastic visco-plastic (EVP) model using the available consolidation data. The finite difference scheme using the Crank-Nicolson procedure is applied to solve a set of coupled partial differential equations of the time dependent strain and pore water pressure dissipation. The model parameters are determined by applying the algorithm of trust-region reflective optimisation in conjunction with the finite difference solution. The proposed method utilises all available consolidation data during dissipation of the excess pore water pressure to determine the required model parameters. Moreover, the reference time in the elastic visco-plastic model can readily be adopted as a unit of time; denoting creep is included in the numerical predictions explicitly from the very first time steps. In this paper, the settlement predictions of thick soft clay layers are presented and discussed to evaluate and compare the accuracy and reliability of the proposed method against the graphical procedure to obtain the model parameters. In addition, comparison of the available experimental results to the numerical predictions confirms the accuracy of the numerical procedure.

• Water Engineering Research
• /
• v.3 no.2
• /
• pp.143-153
• /
• 2002

As the natural flows in rivers dramatically decrease during drought season in Korea, a deterioration of river water quality is accelerated. Thus, consideration of downstream water quality responding to changes in reservoir release is essential for an integrated watershed management with regards to water quantity and quality. In this study, water quality models based on artificial neural networks (ANNs) method were developed using historical downstream water quality (rm $\NH_3$-N) data obtained from a water treatment plant in Geum river and reservoir release data from Daechung dam. A nonlinear multiple regression model was developed and compared with the ANN models. In the models, the rm NH$_3$-N concentration for next time step is dependent on dam outflow, river water quality data such as pH, alkalinity, temperature, and rm $\NH_3$-N of previous time step. The model parameters were estimated using monthly data from Jan. 1993 to Dec. 1998, then another set of monthly data between Jan. 1999 and Dec. 2000 were used for verification. The predictive performance of the models was evaluated by comparing the statistical characteristics of predicted data with those of observed data. According to the results, the ANN models showed a better performance than the regression model in the applied cases.

• Journal of Construction Engineering and Project Management
• /
• v.3 no.3
• /
• pp.35-41
• /
• 2013

All infrastructure projects are said to be inter-dependent, uncertain and labour-intensive in nature. There is no exception for building services sub sector. For a real time project such as 'The construction, extension and refurbishment of Employees' State Insurance Corporation (ESIC) Hospital at Tirupathy, India with total area of 45,000 square feet at an estimated cost of 1100 million rupees, a generic process model is developed to simulate the effect of set of identified variables on construction project. The 'Stocks and Flows' of dynamic model affords relevant insights to project managers, who apply this knowledge when designing better performance through more appropriate project planning. It is concluded from the model-based approach that building services works can be improved through specific better focussed managerial efforts, such as an increasing coordination effectiveness at the planning stage, clarifying prerequisite conditions prior to installations. Otherwise, pending works arising from work clashes can lead to knock-on effects resulting in productivity constraints and pressures, as well as more rework and demolition. Current study reveals that the model enables deep insight into various interdependent processes, their by improving construction performance levels, by addressing the dynamics of design errors and defective works, and recovering delayed schedule.

• Journal of the Korea Society of Computer and Information
• /
• v.4 no.4
• /
• pp.101-112
• /
• 1999

In this paper variable bit rate VBR Moving Picture Experts Group (MPEG) coded full-motion video traffic is modeled by a nonlinear time-series process. The threshold autoregressive (TAR) process is of particular interest. The TAR model is comprised of a set of autoregressive (AR) processes that are switched between amplitude sub-regions. To model the dynamics of the switching between the sub-regions a selection of amplitude dependent thresholds and a delay value is required. To this end, an efficient and accurate TAR model construction algorithm is developed to model VBR MPEG-coded video traffic. The TAR model is shown to accurately represent statistical characteristics of the actual full-motion video trace. Furthermore. in simulations for the bit-loss rate actual and TAR traces show good agreement.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.16 no.2
• /
• pp.8-17
• /
• 2008

This paper presents the Matlab/Simulink-based software-in-the-loop simulation(SILS) environment which is the co-simulator for temporal and functional simulations of control systems. The temporal behavior of a control system is strongly dependent on the implemented software and hardware such as the real-time operating system, the target CPU, and the communication protocol. The proposed SILS abstracts the system with tasks, task executions, real-time schedulers, and real-time networks close to the implementation. Methods to realize these components in graphical block representations are investigated with Matlab/Simulink, which is most commonly used tool for designing and simulating control algorithms in control engineering. In order to achieve a seamless development from SILS to rapid control prototyping (RCP), the SILS block-set is designed to support automatic code generation without tool changes and block modifications.

• Wind and Structures
• /
• v.9 no.2
• /
• pp.95-108
• /
• 2006

Wind turbines are highly complex structures for numerical flow simulation. They normally comprise of a turbine mounted on a tower thus the movement of the turbine blades and the blade/tower interaction must be captured. In addition the ground effect should also be included. There are many more important features of wind turbines and it is difficult to include all of them. A simplified set of features is chosen here for both the turbine and the tower to show how the method can begin to identify the main points connected with wind turbine wake generation and tip vortex tower interaction. An approach to modelling the rotating blades of a turbine is proposed here. The model uses point forces based on blade element theory to model the blades and takes into account their time dependent motion. This means that local instantaneous velocities can be used as a basis for the blade element theory. The model is incorporated into a large eddy simulation code and, although many important features are left out of the model, the velocity/power performance relation is generally of the correct order of magnitude. Suggested improvements to the method are discussed.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1614-1614
• /
• 2001

The sweetness (。Bix) of fruit is the main quality factor contributing to the fruit taste. The brix of the apple fruit can be measured non-destructively by near infrared (NIR) spectroscopy, allowing the sweetness grading of individual apple fruit. However, the fruit quality is influenced by various factors such as growing location, producing year, variety and harvest time etc., accordingly the robust NIR calibration is required. In this experimental results are presented the influence of two variations such as growing location and producing year of apple fruit in establishing of calibrations for sweetness, and developed a stable and highly accurate calibration. Apple fruit (Fuji) was collected every year from 1995 to 1997 in 3 different growing locations (Andong, Youngchun and Chungsong) of Kyungpook in Korea. NIR reflectance spectra of apple fruit were scanned in wavelength range of 1100∼2500nm using an InfraAlyzer 500C (Bran+Luebbe) with halogen lamp and PbS detector. The multiple linear regression and stepwise was carried out between the NIR raw spectra and the brix measured by refractometer to select the best regression equations. The calibration models by each growing district were well predicted to dependent sample set, but poorly predicted to independent sample set. Combined calibration model using data of three growing districts predicted reasonable well to a population set drawn from all growing districts(SEP = 0.69%, Bias=-0.075). The calibration models by each harvest year were not transferable across harvest year, however a combined calibration model using data of three harvest years was sufficiently robust to predict each sample sets(SEP = 0.53%, Bias = 0.004).

• Journal of Information Technology Applications and Management
• /
• v.9 no.3
• /
• pp.113-127
• /
• 2002

The effort for software process improvement is lately surging its interest though it does not satisfy both developer and receiver In terms of low productivity, quality, delay and increasing cost. According to current research, software process improvement contributes to improvement of productivity, its Duality, reduction of development time and cost, and the prediction of the time limit for delivery, which means software process improvement affects competitive advantage among developers. The latest research is whether the investment for information technology substantially had effect on improvement of productivity. That is, software process improvement and maturity of software industries has influence upon economic efficiency and as a result, it plays an important role in whole industries. This research is that how does software process improvement using CMM (Capability Maturity Model) and SPICE (Software Process Improvement and Capability dEtermination) have a effect on factors of software engineering, and how does it have influence upon competitive advantage among SI firms. For this research, reusability, customizability, participation, and review & inspection are set to independent variable and process flexibility and process predictability are set to mediate Variable. Finally, competitive advantage among SI firms Is set to dependent variable. The targets for survey are laborers who work for SI firms. The result of this research is as follows: 1 ) Reusability, Customizability and participation is not rejected but review and Inspection is rejected in process flexibility which has significant level 0.05. 2) Reusability, Customizability and participation is not rejected but review and inspection Is rejected in process predictability which has significant level 0.05. 3) Process flexibility is not rejected and process predictability Is rejected in the competitive advantage of 51 industries which has significant level 0.05