• The Journal of the Acoustical Society of Korea
• /
• v.21 no.6
• /
• pp.552-558
• /
• 2002

Recently, based on the human speech recognition (HSR) model of Fletcher, the multi-band speech recognition has been intensively studied by many researchers. As a new automatic speech recognition (ASR) technique, the multi-band speech recognition splits the frequency domain into several sub-bands and recognizes each sub-band independently. The likelihood scores of sub-bands are weighted according to reliabilities of sub-bands and re-combined to make a final decision. This approach is known to be robust under noisy environments. When the noise is stationary a sub-band SNR can be estimated using the noise information in non-speech interval. However, if the noise is non-stationary it is not feasible to obtain the sub-band SNR. This paper proposes the inverse sub-band distance (ISD) weighting, where a distance of each sub-band is calculated by a stochastic matching of input feature vectors and hidden Markov models. The inverse distance is used as a sub-band weight. Experiments on 1500∼1800㎐ band-limited white noise and classical guitar sound revealed that the proposed method could represent the sub-band reliability effectively and improve the performance under both stationary and non-stationary band-limited noise environments.

• Korean Journal of Construction Engineering and Management
• /
• v.24 no.3
• /
• pp.3-11
• /
• 2023

This research examines the need for a quantitative and objective method of calculating baseline productivity in the construction industry, which is known for its high volatility in performance and productivity. The existing literature's baseline productivity calculation methods rely heavily on subjective criteria, limiting their effectiveness. Additionally, data collection methods such as the "Five-minute Rating" are costly and time-consuming, making it challenging to collect detailed data at construction sites. To address these issues, this study proposes an objective baseline calculation method using unimpacted productivity BP, a work check sheet to systematically record detailed data, and a data collection and utilization process that minimizes cost and time requirements. This paper also suggests using unimpacted productivity BP and comparative analysis to address the objectivity and reliability issues of existing baseline productivity calculation methods.

• Journal of the Korea Concrete Institute
• /
• v.15 no.4
• /
• pp.574-584
• /
• 2003

The most common deterioration cause of concrete structures in urban environment is carbonation. Recently, the $CO_2$ concentration and temperature at atmosphere is sharply increased with time due to global warming phenomena. In this study, the climate scenario IS92a, which was suggested by the IPCC, is used to consider temperature and atmospheric $CO_2$ concentration change in the model of service life prediction. The modified mathematical solution, which was based on the Fick's 1st law of diffusion, was used to reflect concrete materials properties such as the degree of hydration of concrete with elapsed time, and important parameters, which associated with deterioration rate. The techniques of service life prediction are developed introducing the method of reliability and stochastic concept to consider microclimatic condition in Seoul, South Korea. From the result of service life prediction, concrete containing high W/C ratio is shown fast carbonation rate due to $CO_2$ concentration increase. It is concluded that the deterioration of concrete structures due to carbonation is insignificant problem on the conditions that below W/C 55%, well curing concrete.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.5
• /
• pp.757-764
• /
• 2017

As the reduction of greenhouse gases(GHGs) emission has become a global issue, the microgrid markets are growing rapidly. With the sudden changes in the market, Korean government suggested a new business model called 'Self-Sufficient Energy Islands'. Its main concern is a stand-alone microgrid composed of Distributed Energy Resources(DERs) such as Renewable Energy Sources(RESs), Energy Storage System(ESS) and Fuel Cell, in order to minimize the emission of GHGs. According to these trend, this paper is written to propose an optimal sizing method of DERs in a stand-alone microgrid by using Genetic Algorithm(GA), one of the representative stochastic methods. It is to minimize the net present cost with the variables, size of RESs and ESS. In the process for optimization, the sunless days are considered as additional constraints. Through the case study analysis, the size of DERs installed in a microgrid system has been computed using the proposed method in MATLAB. And the result of MATLAB is compared with that of HOMER(Hybrid Optimization of Multiple Energy Resources), a well-known energy modeling software.

• Journal of Korea Water Resources Association
• /
• v.42 no.8
• /
• pp.591-605
• /
• 2009

In this study the risk integrated erosion and seepage failure factor and combined risk of the levee embankment were assessed. For the research of the reliability, the risk assessment of erosion, seepage and both of them combined for the levee embankment were conducted using discharge curve and stage hydrograph generated by stochastic rainfall variation method during typhoon and monsoon season. The risk of erosion was evaluated using tractive force and the seepage analysis was performed by selecting representative cross sections for SEEP/W model analysis. And the probability of seepage failure was assessed with MFOSM analysis using critical hydraulic gradient method. Unlike deterministic analysis method, quantitative risk could be obtained and the characteristics of realistic rainfall variation patterns as well as a variety of factors contributing to levee failure could be reflected in this research. The results of this study show significantly enhanced applicability for the combined risk. As this model can be employed to determine dangerous spots for levee failure and to establish flood insurance linked with flood risk map, it will dramatically contribute to the establishment of both efficient and systematic measures for integrated flood management on a watershed.

• Journal of Korea Water Resources Association
• /
• v.43 no.8
• /
• pp.721-731
• /
• 2010

The rainfall-runoff relationship is very difficult to predict because it is complicate factor affected by many temporal and spatial parameters of the basin. In recent, models which is based on artificial intelligent such as neural network, genetic algorithm fuzzy etc., are frequently used to predict discharge while stochastic or deterministic or empirical models are used in the past. However, the discharge data which are generally used for prediction as training and validation set are often estimated from rating curve which has potential error in its estimation that makes a problem in reliability. Therefore, in this study, water stage is predicted from antecedent rainfall and water stage data for short term using three models of neural network which trained by error back propagation algorithm and optimized by genetic algorithm and training error back propagation after it is optimized by genetic algorithm respectively. As the result, the model optimized by Genetic Algorithm gives the best forecasting ability which is not much decreased as the forecasting time increase. Moreover, the models using stage data only as the input data give better results than the models using precipitation data with stage data.