• International Journal of Internet, Broadcasting and Communication
• /
• v.11 no.4
• /
• pp.26-30
• /
• 2019

This paper proposes a new voice activity detection (VAD) method which is based on SNR and non-intrusive speech intelligibility estimation. In the conventional SNR-based VAD methods, voice activity probability is obtained by estimating frame-wise SNR at each spectral component. However these methods lack performance in various noisy environments. We devise a hybrid VAD method that uses non-intrusive speech intelligibility estimation as well as SNR estimation, where the speech intelligibility score is estimated based on deep neural network. In order to train model parameters of deep neural network, we use MFCC vector and the intrusive speech intelligibility score, STOI (Short-Time Objective Intelligent Measure), as input and output, respectively. We developed speech presence measure to classify each noisy frame as voice or non-voice by calculating the weighted average of the estimated STOI value and the conventional SNR-based VAD value at each frame. Experimental results show that the proposed method has better performance than the conventional VAD method in various noisy environments, especially when the SNR is very low.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.11
• /
• pp.3780-3797
• /
• 2022

The estimation of radio map (RM) is a fundamental and critical task for the network planning and optimization performance of mobile communication. In this paper, a RM estimation method is proposed based on a deep dual learning structure. This method can simultaneously and accurately reconstruct the urban building map (UBM) and estimate the RM of the whole cell by only part of the measured reference signal receiving power (RSRP). Our proposed method implements UBM reconstruction task and RM estimation task by constructing a dual U-Net-based structure, which is named RadioCycle. RadioCycle jointly trains two symmetric generators of the dual structure. Further, to solve the problem of interference negative transfer in generators trained jointly for two different tasks, RadioCycle introduces a dynamic weighted averaging method to dynamically balance the learning rate of these two generators in the joint training. Eventually, the experiments demonstrate that on the UBM reconstruction task, RadioCycle achieves an F1 score of 0.950, and on the RM estimation task, RadioCycle achieves a root mean square error of 0.069. Therefore, RadioCycle can estimate both the RM and the UBM in a cell with measured RSRP for only 20% of the whole cell.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1432-1435
• /
• 1997

This paper proposes a fault detection and isolation metho by combining the parameter estimation method[4] with the observer method[2] to use merits of both methods. To verify the performance of the method proposed some simulations applied to remotely piloted vehicle are performed.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.2
• /
• pp.125-133
• /
• 2004

Most of the way shape estimation method using reference sources assume that the reference sources are in the farfield. That is, the reference sources are assumed to be far from the array. However, in applications of the array with reference sources, the reference sources are not far from the way, so that in practical ocean environments, the conventional method using farfield source model fail to estimate the positions of the hydrophones. In this paper, based on the nearfield source model, a subspace-based array shape estimation method was proposed. In the proposed method, nearfield reference source is modeled using the differential time delay at each hydrophone, and nearfield parameters are derived. Using these parameters, a subspace-based array shape estimation method that generalizes the existing farfield subspace fitting method which can work regardless of the range of the source is proposed. The Cramer-Rao lower bound for the proposed method is investigated. The results of the numerical experiments indicate that the proposed method performs well in estimating the shape of a perturbed way regardless of the ranges of the reference sources.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.14 no.6
• /
• pp.1679-1688
• /
• 1990

The method of nonlinear parameter estimation(NPE), which is a statistical and an inverse method, is used to estimate the thermal diffusivity of the porous insulation material. In order to apply the NPE method for measuring the thermal diffusivity, and algorithm for programing suitable to IBM personal computer is established, and is studied the statistical treatment of experimental data and theory of estimation. The experimental data obtained by discrete measurement using a constant heat flux technique are used to find the boundary conditions, initial conditions, and the thermal diffusivity, and then the final values are compared with the values obtained by some different methods. The results are presented as follows:(1) NPE method is used to establish the estimation of the thermal diffusivity and compared results with experimental output shows, that this method can be applicable to define the thermal diffusivity without considering hear flux types. (2) Because of all of the temperatures obtained by the discrete measurement on each steps of time are used to estimate the thermal diffusivity. Although some error in the temperature measurements of temperature are included in estimating process, its influences on the final value are minimzed in NPE method. (3) NPE method can reduce the experimental time including the time of data collecting in a few minutes and can take smaller specimen compared with steady state method. If the tube-type furnace is used, also the adjusting time of surrounding temperature can be reduced.

• Journal of Wetlands Research
• /
• v.7 no.3
• /
• pp.41-48
• /
• 2005

Generally the estimation of effective rainfall is important in the rainfall-runoff analysis. So, we must pay attention to selecting more accurate effective rainfall estimation method. Although there are many effective rainfall estimation methods, the NRCS method is widely used for the estimation of effective rainfall in the ungaged basin. However, the NRCS method was developed based on the characteristics of the river basin in USA. So, it may have problems to use the NRSC method in Korea without its verification. In the NRCS method, the antecedent precipitation of 5-day is usually used for the estimation of effective rainfall. The main purpose of this study is to investigate the suitable antecedent precipitation day in Korea river basin through the case study. This study performs the rainfall-runoff simulation for the Tanbu river basin by HEC-HMS model under the condition of varying the antecedent precipitation day from 1-day to 7-day and performs goodness of fit test by Monte Carlo simulation method. The antecedent precipitation of 2-day shows the most preferable result in the analysis. This result indicates that the NRCS method should be applied with caution according to the characteristics of the river basin.

• Korean Journal of Remote Sensing
• /
• v.31 no.5
• /
• pp.449-459
• /
• 2015

The conventional National Forest Inventory(NFI)-based forest carbon stock estimation method is suitable for national-scale estimation, but is not for regional-scale estimation due to the lack of NFI plots. In this study, for the purpose of regional-scale carbon stock estimation, we created grid-based forest carbon stock maps using spatial ancillary data and two types of up-scaling methods. Chungnam province was chosen to represent the study area and for which the $5^{th}$ NFI (2006~2009) data was collected. The first method (method 1) selects forest type map as ancillary data and uses regression model for forest carbon stock estimation, whereas the second method (method 2) uses satellite imagery and k-Nearest Neighbor(k-NN) algorithm. Additionally, in order to consider uncertainty effects, the final AGB carbon stock maps were generated by performing 200 iterative processes with Monte Carlo simulation. As a result, compared to the NFI-based estimation(21,136,911 tonC), the total carbon stock was over-estimated by method 1(22,948,151 tonC), but was under-estimated by method 2(19,750,315 tonC). In the paired T-test with 186 independent data, the average carbon stock estimation by the NFI-based method was statistically different from method2(p<0.01), but was not different from method1(p>0.01). In particular, by means of Monte Carlo simulation, it was found that the smoothing effect of k-NN algorithm and mis-registration error between NFI plots and satellite image can lead to large uncertainty in carbon stock estimation. Although method 1 was found suitable for carbon stock estimation of forest stands that feature heterogeneous trees in Korea, satellite-based method is still in demand to provide periodic estimates of un-investigated, large forest area. In these respects, future work will focus on spatial and temporal extent of study area and robust carbon stock estimation with various satellite images and estimation methods.

• The Korean Journal of Applied Statistics
• /
• v.29 no.5
• /
• pp.807-822
• /
• 2016

The composite lognormal-GPD models (LN-GPD) enjoys both merits from log-normality for the body of distribution and GPD for the thick tailedness of the observation. However, in the estimation perspective, LN-GPD model performs poorly due to numerical instability. Therefore, a two-stage procedure, that estimates threshold first then estimates other parameters later, is a natural method to consider. This paper considers five nonparametric threshold estimation methods widely used in extreme value theory and compares their performance in LN-GPD parameter estimation. A simulation study reveals that simultaneous maximum likelihood estimation performs good in threshold estimation, but very poor in tail index estimation. However, the nonparametric method performs good in tail index estimation, but introduced bias in threshold estimation. Our method is illustrated to the service time of an Israel bank call center and shows that the LN-GPD model fits better than LN or GPD model alone.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.3
• /
• pp.29-35
• /
• 2010

This paper discusses a method that can enhance the exactness of depth estimation of an image by PCA(Principle Component Analysis) based on feature reduction through learning algorithm. In estimation of the depth of an image, hyphen such as energy of pixels and gradient of them are found, those selves and their relationship are used for depth estimation. In such a case, many features are obtained by various filter operations. If all of the obtained features are equally used without considering their contribution for depth estimation, The efficiency of depth estimation goes down. This paper proposes a method that can enhance the exactness of depth estimation of an image and its processing speed is considered as the contribution factor through PCA. The experiment shows that the proposed method(30% of an feature vector) is more exact(average 0.4%, maximum 2.5%) than using all of an image data in depth estimation.

• Journal of the Society of Naval Architects of Korea
• /
• v.53 no.2
• /
• pp.154-161
• /
• 2016

There are several existing studies for the weight estimation of offshore plants. However, most of them were applicable at the pre-FEED (Front End Engineering Design) stage. In this paper, a preliminary study on a method for the weight estimation and calculation of offshore EPC (Engineering Procurement Construction) projects is made for the use at the estimation stage after FEED. Based on literature surveys including ISO (International Organization for Standardization) 19901-5 about weight estimation, we proposes new weight factors and a weight curve. Weight factors defined in this study include MTO (Material Take-Off), estimated weight, FEED maturity factor, allowance factor, and contingency factor. The proposed method utilizes bottom-up approach for weight estimation and it can be used for the weight estimation and calculation of offshore EPC projects at the estimation stage.