• The Journal of the Acoustical Society of Korea
• /
• v.28 no.6
• /
• pp.566-571
• /
• 2009

This paper proposes noise-robust fast speaker adaptation method based on the eigenvoice framework in various noisy environments. The proposed method is focused on de-noising and environment clustering. Since the de-noised adaptation DB still has residual noise in itself, environment clustering divides the noisy adaptation data into similar environments by a clustering method using the cepstral mean of non-speech segments as a feature vector. Then each adaptation data in the same cluster is used to build an environment-clustered speaker adapted (SA) model. After selecting multiple environmentally clustered SA models which are similar to test environment, the speaker adaptation based on an appropriate linear combination of clustered SA models is conducted. According to our experiments, we observe that the proposed method provides error rate reduction of $40{\sim}59%$ over baseline with speaker independent model.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.4
• /
• pp.57-63
• /
• 1997

In this paper, we study the efficient feature vector extraction method and front-end processing to improve the performance of the speech recognition system using KT(Korea Telecommunication) database collected through various telephone channels. First of all, we compare the recognition performances of the feature vectors known to be robust to noise and environmental variation and verify the performance enhancement of the recognition system using weighted cepstral distance measure methods. The experiment result shows that the recognition rate is increasedby using both PLP(Perceptual Linear Prediction) and MFCC(Mel Frequency Cepstral Coefficient) in comparison with LPC cepstrum used in KT recognition system. In cepstral distance measure, the weighted cepstral distance measure functions such as RPS(Root Power Sums) and BPL(Band-Pass Lifter) help the recognition enhancement. The application of the spectral subtraction method decrease the recognition rate because of the effect of distortion. However, RASTA(RelAtive SpecTrAl) processing, CMS(Cepstral Mean Subtraction) and SBR(Signal Bias Removal) enhance the recognition performance. Especially, the CMS method is simple but shows high recognition enhancement. Finally, the performances of the modified methods for the real-time implementation of CMS are compared and the improved method is suggested to prevent the performance degradation.

• KDI Journal of Economic Policy
• /
• v.14 no.1
• /
• pp.121-145
• /
• 1992

This paper examines characteristics of time series data related to the construction investment(stationarity and time series components such as secular trend, cyclical fluctuation, seasonal variation, and random change) and surveys predictibility, fitness, and explicability of independent variables of various models to build a short-term construction investment forecasting model suitable for current economic circumstances. Unit root test, autocorrelation coefficient and spectral density function analysis show that related time series data do not have unit roots, fluctuate cyclically, and are largely explicated by lagged variables. Moreover it is very important for the short-term construction investment forecasting to grasp time lag relation between construction investment series and leading indicators such as building construction permits and value of construction orders received. In chapter 3, we explicate 7 forecasting models; Univariate time series model (ARIMA and multiplicative linear trend model), multivariate time series model using leading indicators (1st order autoregressive model, vector autoregressive model and error correction model) and multivariate time series model using National Accounts data (simple reduced form model disconnected from simultaneous macroeconomic model and VAR model). These models are examined by 4 statistical tools that are average absolute error, root mean square error, adjusted coefficient of determination, and Durbin-Watson statistic. This analysis proves two facts. First, multivariate models are more suitable than univariate models in the point that forecasting error of multivariate models tend to decrease in contrast to the case of latter. Second, VAR model is superior than any other multivariate models; average absolute prediction error and root mean square error of VAR model are quitely low and adjusted coefficient of determination is higher. This conclusion is reasonable when we consider current construction investment has sustained overheating growth more than secular trend.

• Journal of Korea Multimedia Society
• /
• v.8 no.4
• /
• pp.473-481
• /
• 2005

In this paper, we propose an image segmentation method preserving object's boundaries by using the number of quantized colors and merging regions using adaptive threshold values. First of all, the proposed method quantizes an original image by a vector quantization and the number of quantized colors is determined differently using PSNR each image. We obtain initial regions from the quantized image, merge initial regions in CIE Lab color space and RGB color space step by step and segment the image into semantic regions. In each merging step, we use color distance between adjacent regions as similarity-measure. Threshold values for region-merging are determined adaptively according to the global mean of the color difference between the original image and its split-regions and the mean of those variations. Also, if the segmented image of RGB color space doesn't split into semantic objects, we merge the image again in the CIE Lab color space as post-processing. Whether the post-processing is done is determined by using the color distance between initial regions of the image and the segmented image of RGB color space. Experiment results show that the proposed method splits an original image into main objects and boundaries of the segmented image are preserved. Also, the proposed method provides better results for objective measure than the conventional method.

• Korean journal of applied entomology
• /
• v.16 no.2 s.31
• /
• pp.79-86
• /
• 1977

Four experiments were carried out under farmer's field conditions to determine economic threshold levels of major rice pests aad attempt a reduction in the number of insecticide applications. In the experiments were included check treatments, insecticide schedules representing the official recommendations to farmers, and several corrective treatments. A careful record was kept of insect pest densities and disease incidence. i) In the north at Suweon and Icheon where Chilo suppresalis. (Walk.), the striped rice borer, was active in the first generation, no significant yield differences were obtained between plots receiving several insecticide applications and those left totally unprotected. The mean yields were high (5.2-7.6t/ha). ii) First generation borer activity rising to $8.6\%$ injured tillers was below the economic threshold since no yield reduction was recorded in either japonica varieties or the high-yielding Tongil variety. iii) Evidence was obtained thst berer damage was made good by replacement of infested tillers (compensatory growth), C. suppressalis populations were always low in the second generation. iv) The experimental results obtained at Suweon and Icheon do not justify the present official recommendations of 6-7 pesticide applications. v) further south at Iri a substantial yield reduction occurred due to an early outbreak of stripe disease transmitted by Laodelphax striatellus (Fallen), the small brown planthopper; a mean of 1-2 individuals/hill was recorded immediately after transplanting. C. suppressalis probably contributed to this yield reduction. vi) Several applications against the vector failed to prevent the rapid spread of stripe to the susceptible variety in the Iri experiment: in surrounding fields the resistant Tonsil varivety was ralatively unaffected. vii) Pests of lesser importance were Nephotettix cinctieps (Uhler), Nilaparvata lugens (Stil), Sogatella furcifera (Horv..), and leaf miners.

• Safety and Health at Work
• /
• v.10 no.4
• /
• pp.452-460
• /
• 2019

Background: Monitoring and control of PM_2.5 are being recognized as key to address health issues attributed to PM_2.5. Availability of low-cost PM_2.5 sensors made it possible to introduce a number of portable PM_2.5 monitors based on light scattering to the consumer market at an affordable price. Accuracy of light scatteringe-based PM_2.5 monitors significantly depends on the method of calibration. Static calibration curve is used as the most popular calibration method for low-cost PM_2.5 sensors particularly because of ease of application. Drawback in this approach is, however, the lack of accuracy. Methods: This study discussed the calibration of a low-cost PM_2.5-monitoring device (PMD) to improve the accuracy and reliability for practical use. The proposed method is based on construction of the PM_2.5 sensor network using Message Queuing Telemetry Transport (MQTT) protocol and web query of reference measurement data available at government-authorized PM monitoring station (GAMS) in the republic of Korea. Four machine learning (ML) algorithms such as support vector machine, k-nearest neighbors, random forest, and extreme gradient boosting were used as regression models to calibrate the PMD measurements of PM_2.5. Performance of each ML algorithm was evaluated using stratified K-fold cross-validation, and a linear regression model was used as a reference. Results: Based on the performance of ML algorithms used, regression of the output of the PMD to PM_2.5 concentrations data available from the GAMS through web query was effective. The extreme gradient boosting algorithm showed the best performance with a mean coefficient of determination (R²) of 0.78 and standard error of 5.0 ㎍/㎥, corresponding to 8% increase in R² and 12% decrease in root mean square error in comparison with the linear regression model. Minimum 100 hours of calibration period was found required to calibrate the PMD to its full capacity. Calibration method proposed poses a limitation on the location of the PMD being in the vicinity of the GAMS. As the number of the PMD participating in the sensor network increases, however, calibrated PMDs can be used as reference devices to nearby PMDs that require calibration, forming a calibration chain through MQTT protocol. Conclusions: Calibration of a low-cost PMD, which is based on construction of PM_2.5 sensor network using MQTT protocol and web query of reference measurement data available at a GAMS, significantly improves the accuracy and reliability of a PMD, thereby making practical use of the low-cost PMD possible.

• Journal of Environmental Health Sciences
• /
• v.42 no.1
• /
• pp.41-52
• /
• 2016

Objectives: Scrub typhus is one of the most prevalent vector-borne diseases. It is caused by Orientia tsutsugamushi, which is transmitted when people are bitten by infected chigger mites. This study aims at quantifying the association between the incidence of scrub typhus and meteorological factors in Jeollabuk-do Province over the period 2001-2015. Methods: Reported cases of scrub typhus were collected from the website of the Disease Web Statistical System supported by the Korea Centers for Disease Control and Prevention (KCDC). Simultaneous meteorological data, including temperature, rainfall, relative humidity, and sunshine duration were collected from the website of the National Climate Data Service System by the Korea Meteorological Administration. Correlation and regression analyses were applied to identify the association between the incidence of scrub typhus and meteorological factors. Results: The general epidemiological characteristics of scrub typhus in Jeollabuk-do Province were similar to those nationwide for sex, age, and geographical distribution. However, the annual incidence rate (i.e., cases per 100,000) of scrub typhus in Jeollabuk-do Province was approximately four times higher than all Korea's 0.9. The number of total cases was the highest proportion at 13.3% in Jeonbuk compared to other regions in Korea. The results of correlation analysis showed that there were significant correlations between annual cases of scrub typhus and monthly data for meteorological factors such as temperature and relative humidity in late spring and summer, especially in the case of temperature in May and June. The results of regression analysis showed that determining factors in the regression equation explaining the incidence of scrub typhus reached 46.2% and 43.5% in May and June. Using the regression equation, each 1oC rise in the monthly mean temperature in May or June may lead to an increase of 38 patients with scrub typhus compared to the annual mean of incidence cases in Jeollabuk-do Province. Conclusion: The result of our novel attempts provided rational evidence that meteorological factors are associated with the occurrence of scrub typhus in Jeollabuk-do. It should therefore be necessary to observe the trends and predict patterns of scrub typhus transmission in relation to global-scale climate change. Also, action is urgently needed in all areas, especially critical regions, toward taking steps to come up with preventive measures against scrub typhus transmission.

• Journal of KIISE
• /
• v.43 no.10
• /
• pp.1085-1093
• /
• 2016

Community-based Question Answering system is a system which provides answers for each question from the documents uploaded on web communities. In order to enhance the capacity of question analysis, former methods have developed specific rules suitable for a target region or have applied machine learning to partial processes. However, these methods incur an excessive cost for expanding fields or lead to cases in which system is overfitted for a specific field. This paper proposes a multiple machine learning method which automates the overall process by adapting appropriate machine learning in each procedure for efficient processing of community-based Question Answering system. This system can be divided into question analysis part and answer selection part. The question analysis part consists of the question focus extractor, which analyzes the focused phrases in questions and uses conditional random fields, and the question type classifier, which classifies topics of questions and uses support vector machine. In the answer selection part, the we trains weights that are used by the similarity estimation models through an artificial neural network. Also these are a number of cases in which the results of morphological analysis are not reliable for the data uploaded on web communities. Therefore, we suggest a method that minimizes the impact of morphological analysis by using character features in the stage of question analysis. The proposed system outperforms the former system by showing a Mean Average Precision criteria of 0.765 and R-Precision criteria of 0.872.

• Journal of the Korean Society of Radiology
• /
• v.14 no.2
• /
• pp.121-127
• /
• 2020

The era of the Fourth Industrial Revolution is increasingly demanding mathematical competencies for virtual reality (VR), artificial intelligence (AI) and the like. In this context, this study intended to identify the basic mathematical competency levels of university freshman students in radiology department and to provide basic data thereon. For this, the diagnostic assessment of basic learning competencies for the domain of mathematics was conducted from June 17, 2019 to June 28, 2019 among 78 freshman students of radiology department at S university and D university. As a result, the university students' overall basic mathematical competency levels were diagnosed to be excellent. However, their levels in the sectors of the geometry and vector and the probability and statistics were diagnosed to be moderate, with the mean scores of 2.61 points and 2.64 points, respectively, which were found to be lower than those of the other sections. As for basic mathematical competency levels according to genders, the levels of male students and female students were diagnosed to be excellent, with the mean scores of 17.48 points and 16.29 points, respectively, showing no statistically significant difference (p>0.05). Given the small number of subjects and regional restriction, there might be some limitations in the generalization of the findings of the present study to all university freshman students and all departments. The above results suggest that it is necessary to implement various programs such as student level-based special lectures for enhancing basic mathematical competencies relating to major in order to improve the basic mathematical competencies of freshman students in radiology department, and that it is necessary to increase the students' mathematical competencies by offering major math courses in the curriculum and applying teaching-learning methods matching students' levels.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.11
• /
• pp.245-253
• /
• 2011

Due to the imprudent spending of the fossil fuels, the environment was contaminated seriously and the exhaustion problems of the fossil fuels loomed large. Therefore people become taking a great interest in alternative energy resources which can solve problems of fossil fuels. The wind power energy is one of the most interested energy in the new and renewable energy. However, the plants of wind power energy and the traditional power plants should be balanced between the power generation and the power consumption. Therefore, we need analysis and prediction to generate power efficiently using wind energy. In this paper, we have performed a research to predict power generation patterns using the wind power data. Prediction approaches of datamining area can be used for building a prediction model. The research steps are as follows: 1) we performed preprocessing to handle the missing values and anomalous data. And we extracted the characteristic vector data. 2) The representative patterns were found by the MIA(Mean Index Adequacy) measure and the SOM(Self-Organizing Feature Map) clustering approach using the normalized dataset. We assigned the class labels to each data. 3) We built a new predicting model about the wind power generation with classification approach. In this experiment, we built a forecasting model to predict wind power generation patterns using the decision tree.