• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06c
• /
• pp.67-70
• /
• 1998

본 논문에서는 단어독립 음성인식 시스템을 위한 음성인식 거절(rejection)기능에 대해 기술한다. 음성인식 거절 기능은 음성인식기를 제작할 때 정해놓은 인식대상 단어 이외의 단어가 입력되었을 때 그 단어가 인식할 수 없는 단어임을 알려주는 기능이다. 본 연구에서는 단어독립 음성인식 시스템에 적용될 수 있는 발화 검증 방식에 의해 음성인식 거절 기능을 구현하였다. 특히 유사도를 결정함에 있어서 산술평균, 기하평균, 조화평균을 사용하고 각각을 비교하여, 기하 평균을 사용하는 방식이 우수한 성능을 보임을 알 수 있었다. 음성의 신뢰도(confidence score)를 정규화하기 위해서 Sigmoid 함수를 사용하는데 이 함수의 가중치(weight) 상수의 변화에 대해 인식률을 비교함으로써 가장 적절한 가중치 상수값을 결정하였다. 음성인식 테스트 결과에서는 신뢰도 임계치 값을 구하고 이 값을 사용하여 인식률을 계산하였으며, 거절의 오류까지 포함된 음성인식률은 약 76%였다. 이 연구결과는 현재 한국통신에서 시험 서비스 중인 음성인식 증권정보 안내 시스템에 적용될 예정이다.

• The Journal of the Korea Contents Association
• /
• v.10 no.10
• /
• pp.86-93
• /
• 2010

With the introduction of smart phones, the augmented reality became popular and is increasingly drawing attention. The augmented reality in the mobile devices is becoming an individual area to study. Many applications of the augmented reality have been studied, but there are just a few studies on its combination with artificial intelligence in games. In this study, an artificial intelligence algorithm was proposed, which dynamically converts the state of the 3D agent in the augmented reality environment using the 3-Axis acceleration sensor in the smart phone. To control the state of the agent to which the artificial intelligence is applied, users used to directly enter the data or use markers to detect them. The critical values, which were determined via test, were given to the acceleration sensor to ensure accurate state conversion. In this paper, makerless tracking technology was used to implement the augmented reality, and the state of the agent was dynamically converted using the 3-Axis acceleration seonsor.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.613-614
• /
• 2017

Recently, research on the automation of home IoT has been carried out in which IoT (Internet of Things) is applied inside the home. However, the conventional IoT automation system has a problem that the operation of the device is limited only by the threshold value of the sensor, so that the device may collide and interfere with each other and the efficiency of the Task is low due to the malfunction of the device. In this paper, we propose a Situation-specific task classification algorithm to solve these problems. Using the sensor threshold and the current date as classification values in the decision tree, the task according to the internal situation of the home is classified and the corresponding device is selected and proceeded. Therefore, it is expected that the users will be provided with a service that changes flexibly according to changes in the internal situation of the home, and the accuracy of the operation will be increased by reducing the malfunction of the device and the collision between the devices.

• Journal of Korea Water Resources Association
• /
• v.53 no.4
• /
• pp.293-301
• /
• 2020

This study determined appropriate threshold level (cumulative period and percentage) of precipitation for drought management in dam basin. The 5 dam basins were selected, the daily dam storage level and daily precipitation data were collected. MAP (Mean Areal Precipitation was calculated by using Thiessen polygon method, and MAP were converted to accumulated values for 6 cumulative periods (30-, 60-, 90-, 180-, 270-, and 360-day). The correlation coefficient and ratio of variation coefficient between storage level and MAP for 6 cumulative periods were used to determine the appropriate cumulative period. Correlation of cumulative precipitation below 90-day was low, and that of 270-day was high. Correlation was high when the past precipitation during the flood period was included within the cumulative period. The ratio of variation coefficient was higher for the shorter cumulative period and lower for the longer in all dam, and that of 270-day precipitation was closed to 1.0 in every month. ROC (Receiver Operating Characteristics) analysis with TLWSA (Threshold Line of Water Supply Adjustment) was used to determine the percentage of precipitation shortages. It is showed that the percentage of 270-day cumulative precipitation on Boryung dam and other 4-dam were less than 90% and 80% as threshold level respectively, when the storage was below the attention level. The relationship between storage and percentage of dam outflow and precipitation were analyzed to evaluate the impact of artificial dam operations on drought analysis, and the magnitude of dam outflow caused uncertainty in the analysis between precipitation and storage data. It is concluded that threshold level should be considered for dam drought analysis using based on precipitation.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2008.04a
• /
• pp.497-500
• /
• 2008

In order to prevent deterioration of reinforced concrete structures exposed to marine environment, performance based durability design than the design by conventional deemed-to-satisfy rule should be concerned. For example, even though chloride threshold level, which is a major parameter for durability design, is defined as a 1.2 $kg/m^3$ in the Korean concrete specification, it shows that the chloride threshold level leads to over design in its real application so that realistic value should be determined for the performance design. In this paper, not only the probabilistic properties of chloride threshold level obtained from published data are taken into account, but also the experimental results of the probabilistic properties using surface chloride content, diffusion coefficient, cover depth are considered in the assessment utilizing the concept of performance based durability design. In computation, the Monte Carlo Simulation (MCS) is used to perform an assessment due to chloride attack for a target submerged tunnel box. This study found that the specification on current chloride threshold level should be modified for more rational and accurate assessment and design.

• Journal of Advanced Navigation Technology
• /
• v.18 no.4
• /
• pp.304-311
• /
• 2014

In this paper, we propose a ultra sound inspection technique for automatic defect detection and classification in aircraft composite materials. Using local maximum values of ultra sound wave, we choose peak values for defect detection. Distance data among peak values are used to construct histogram and to determine surface and back-wall echo from the floor of composite materials. C-scan image is then composed through this method. A threshold value is determined by average and variance of the peak values, and defects are detected by the values. PCA(principal component analysis) and QDA(quadratic discriminant analysis) are carried out to classify the types of defects. In PCA, 512 dimensional data are converted into 30 PCs(Principal Components), which is 99% of total variances. Computational cost and misclassification rate are reduced by limiting the number of PCs. A decision boundary equation is obtained by QDA, and defects are classified by the equation. Experimental result shows that our proposed method is able to detect and classify the defects automatically.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.6
• /
• pp.485-492
• /
• 2016

A role of the binarization is very important in separating the foreground and the background in the field of the computer vision. In this study, an adaptive fuzzy binarization is proposed. An ${\alpha}$-cut control ratio is obtained by the distribution of grey level of pixels in a sliding window, and binarization is performed using the value. To obtain the ${\alpha}$-cut, existing thresholding methods which execution speed is fast are used. The threshold values are set as the center of each membership function and the fuzzy intervals of the functions are specified with the distribution of grey level of the pixel. Then ${\alpha}$-control ratio is calculated using the specified function and binarization is performed according to the membership degree of the pixels. The experimental results show the proposed method can segment the foreground and the background well than existing binarization methods and decrease loss of the foreground.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.3
• /
• pp.304-310
• /
• 2009

In this paper, target extraction method in FLIR(forward-looking infrared) images based on fuzzy thresholding which used bi-modality and adjacency to determine membership value is proposed. The bi-modality represents how a pixel is classified into a part of target using distribution of pixel values in a local region, and The adjacency is a measure to represent how each pixel is far from the target region. First, membership value is calculated using above two measures, and then fuzzy thresholding is performed to extract the target. To evaluate performance of proposed target extraction method, we compare other segmentation methods using various FLIR tank image. Experimental results show that the proposed algorithm is a good segmentation performance.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.601-601
• /
• 2015

비홍수기 하천유량관리는 정해진 기준 이상으로 유량을 유지하는 데 목적을 두며 유량관리를 위한 기준유량으로는 하천유지유량이나 하천관리유량이 주로 사용되고 있다. 이들 기준유량과 함께 최근에는 하천 유량 변화를 효과적으로 파악하고 유량변화에 따른 갈수상황을 객관적으로 판단하기 위한 의사결정 도구로 갈수지표가 활용되고 있다. 본 연구에서는 낙동강 주요 홍수예보지점의 하나인 진동지점을 대상으로 유량자료를 수집하고 갈수지표를 이용한 유량평가를 실시하였다. 다양한 갈수지표 중 특정기간을 대상으로 일정시간 가장 낮은 유량을 갈수지표로 활용하는 기법과 동일기간 유량자료의 저유량백분위 기준을 적용하여 이를 갈수임계값으로 활용하는 기법을 적용하였다. 전자는 7Q10(Singh, 1974)이 대표적이며 이는 10년 중 가장 낮은 값을 갖는 7일의 유량이 갈수의 기준이 된다. 본 연구에서는 7Q10의 기간을 20년으로 확대한 7Q20을 적용하였다. 후자는 WMO(2008)에서 적용된 바 있으며 본 연구에서는 1~12월의 월별 저유량90분위(Q90)를 갈수임계값으로 선정하였다. 신뢰할 수 있는 장기유량자료의 활용을 위해 "장기 수문자료 검증 및 평가연구"(한강홍수통제소, 2011)를 통해 수정, 보완된 진동지점의 과거 20년간(1994~2013) 유량자료를 활용하였으며 갈수지표와 함께 유량관리를 위한 기준유량으로 활용되는 하천유지유량(2006년 고시)과 하천관리유량(2013년 기준)의 유량만족도를 비교하였다. 과거 가뭄발생 및 제한급수시기, 강수량 등과 비교했을 때 월별 갈수임계값(Q90)을 갈수지표로 활용한 경우가 갈수관리에 효과적이라 판단되었다. 해당 기법은 통계학적 유의성을 갖기 위해서 장기수문자료의 활용이 필요하나 유량의 시계열 변동특성 반영이 가능하므로 우리나라와 같이 갈수기와 홍수기의 구분이 명확하고 하상계수가 큰 지역에서는 장점을 갖는 것으로 판단된다.

• Land and Housing Review
• /
• v.3 no.1
• /
• pp.69-78
• /
• 2012

This study proposes an approach to improve the accuracy of land assessment result focused on the Land Suitability Assessment. The detailed analysis processes are; (a) that they are analyzed considering resistance in distance measurement on the space characteristics of location, and; (b) that an assessment result is measured according to the threshold definition of membership function, which is applied in estimating conservation suitability. The assessment results are; firstly, the method considering resistance better reflects the local characteristics of area with worse accessibility including rivers and mountains than one by linear distance; secondly, the existing method that the maximum value of a target area is defined as the maximum threshold may draw a value evaluated lower than a threshold definition considering the distribution of measured indices. Finally, satellite images are overlapped with the assessed results, the applicability level from the approach proposed by this study is more coincident with the present status. The assessment method proposed by this study can be meaningful in view of that it improves the accuracy of Land Suitability Assessment. Furthermore, it can be applied as SDSS, which can support effective establishment of urban policies, in case of complementing the problems in executing the assessment system.