• Journal of KIISE:Software and Applications
• /
• v.27 no.8
• /
• pp.864-876
• /
• 2000

This paper proposes a new scene boundary detection scheme for the MPEG System stream using MPEG Audio information and proves its usefulness by extensive experiments. A scene boundary has a characteristic that the audio as well as video information are changed rapidly. This paper first classifies this scene boundary into three cases ; Radical, Gradual, Micro Changes, with respect to the audio changes. The Radical change has a large-scale changing of decibel value and pitch value at a scene boundary, the Gradual change shows the long-time transition of decibel and pitch values from max to min or vice versa, and the Micro change displays a some change of pitch or frequency distribution without decibel changes. Upon this analysis, a new scene change detection algorithm detecting these three cases is proposed in which a progressive window with a time line is used to trace the changes in the audio information. Some experiments with various movies show that proposed algorithm could produce a high detection ratio for Radical change that is the most popular scene change in the movies, while producing a moderate detection ratio for Gradual and Micro changes. The proposed scene boundary detection scheme could be used to build a database for visual information like MPEG System stream.

• KIPS Transactions on Computer and Communication Systems
• /
• v.6 no.8
• /
• pp.353-358
• /
• 2017

An electrical power utility, like an electrical power pole, includes various kinds of sensors for smart services. Temperature data is considered one of the important factors that can influence the smart operations of this utility. This study suggests a method for temperature data analysis for deciding the status of the smart electrical power utilities by using Kalman Filter and Ensemble Model. The suggested approach separates the temperature data according to the different positions of the temperature sensors of a utility, then uses Kalman Filter and Ensemble Model to analyse the characteristics of the temperature variation. With detailed processes, method explains the variation between an external temperature factor like weather temperature data and the sensed temperature data, and then, analysis the temperature data from each position of electrical power utilities. In this process, the suggested method uses Kalman Filter to remove error data and the ensemble model to find out mean value of every hour of electrical data. The result and discussion of temperature analysis were described clearly with the analysed results of electrical data. Finally, we were able to check the working condition of the power devices and the range of the temperature data foe each devices, which may help to indicate any causalities with respect to the devices in the utility pole.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.7
• /
• pp.221-228
• /
• 2020

Part-of-Speech (POS) tagged corpus is a collection of electronic text in which each word is annotated with a tag as the corresponding POS and is widely used for various training data for natural language processing. The training data generally assumes that there are no errors, but in reality they include various types of errors, which cause performance degradation of systems trained using the data. To alleviate this problem, we propose a novel method for detecting errors in the existing POS tagged corpus using the classifier of XGBoost and cross-validation as evaluation techniques. We first train a classifier of a POS tagger using the POS-tagged corpus with some errors and then detect errors from the POS-tagged corpus using cross-validation, but the classifier cannot detect errors because there is no training data for detecting POS tagged errors. We thus detect errors by comparing the outputs (probabilities of POS) of the classifier, adjusting hyperparameters. The hyperparameters is estimated by a small scale error-tagged corpus, in which text is sampled from a POS-tagged corpus and which is marked up POS errors by experts. In this paper, we use recall and precision as evaluation metrics which are widely used in information retrieval. We have shown that the proposed method is valid by comparing two distributions of the sample (the error-tagged corpus) and the population (the POS-tagged corpus) because all detected errors cannot be checked. In the near future, we will apply the proposed method to a dependency tree-tagged corpus and a semantic role tagged corpus.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.4
• /
• pp.79-86
• /
• 2016

About 75% of software security incidents are caused by software vulnerability. In addition, the after-market repairing cost of the software is higher by more than 30 times than that in the design stage. In this background, the secure coding has been proposed as one of the ways to solve this kind of maintenance problems. Various institutions have addressed the weakness patterns of the standard software. A new Korean programming language Saesark has been proposed to resolve the security weakness on the language level. However, the previous study on Saesark can not resolve the security weakness caused by the API. This paper proposes a way to resolve the security weakness due to the API. It adopts a static analyzer inspecting dangerous methods. It classifies the dangerous methods of the API into two groups: the methods of using tainted data and those accepting in-flowing tainted data. It analyses the security weakness in four steps: searching for the dangerous methods, configuring a call graph, navigating a path between the method for in-flowing tainted data and that uses tainted data on the call graph, and reporting the security weakness detected. To measure the effectiveness of this method, two experiments have been performed on the new version of Saesark adopting the static analysis. The first experiment is the comparison of it with the previous version of Saesark according to the Java Secure Coding Guide. The second experiment is the comparison of the improved Saesark with FindBugs, a Java program vulnerability analysis tool. According to the result, the improved Saesark is 15% more safe than the previous version of Saesark and the F-measure of it 68%, which shows the improvement of 9% point compared to 59%, that of FindBugs.

• The Korean Journal of Blood Transfusion
• /
• v.23 no.2
• /
• pp.136-144
• /
• 2012

Background: Fresh frozen plasma (FFP) transfusion is administered primarily for management of acquired bleeding disorders. However, in practice, FFP transfusion is increasing without a solid rationale. Methods: We conducted an audit to evaluate the appropriateness of the indications for FFP transfusion during the period from July 2010 through June 2011. Assessment of the appropriateness of the indications was based on the national transfusion guidelines and the transfusion criteria promulgated by the Severance Hospital. Results: In total, 17,733 units of plasma were transfused to 1,949 patients over 4,982 events. We found that administration of FFP was not in compliance with the recommended guidelines in 1,990 events. The number of total FFP transfusions was higher in medical departments (Gastroenterology) than in surgical departments (Thoracic and cardiovascular surgery, General surgery). However, the proportion of cases of inappropriate transfusion was higher in surgical departments than in medical departments. Both the total number of FFP transfusion and the proportion of inappropriate transfusion were high in patient with neoplasm, disease of the digestive system, and diseases of the circulatory system. Conclusion: Continuous monitoring on appropriateness for FFP transfusion and feedback to the physician are critical in securing the transfusion safety as well as maintaining the quality of FFP transfusion. New-found indication for FFP transfusion should be investigated and applied in timely manner.

• Journal of agriculture & life science
• /
• v.43 no.2
• /
• pp.39-46
• /
• 2009

Ten animal hospitals in Seoul were selected, and of which 41,305 practice in total for recent 1 year were analyzed based on international classification of disease(ICD) of WHO. Of the entire practice, prophylaxis cases accounted for 42.2%. Of the 9,376 cases of internal diseases, digestive system diseases accounted for 4,957 cases(52.9%), respiratory system diseases 1,776 cases(18.9%), circulatory system diseases 1,239 cases(13.2%), and neoplasms diseases 413 cases(4.4%), respectively. In the estate investment expenses, to be specific, rental guarantee deposit accounted for about 50% of the entire estate cost, foregift(48%), and monthly rent(2%). Dividing the income of animal hospitals into medical service, articles selling, and pet-dog beauty, medical service accounted for 71.6% of the entire sales, selling of articles 16.7%, and pet-dog beauty 11.6%. Publicity work for the animal hospital was done mostly through web sites on internet(47%), then through local advertising papers(23.5%), and through bulletins and telemarketing(11.8%). Manpower of the animal hospitals in this study was mostly composed of veterinarians(45.5%) up to about half of the entire staffs, while there was no veterinary technician who had specialized education in that area.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.186-186
• /
• 2015

본 연구에서는 해안도시(부산광역시 수영구) 지역의 토지이용도와 미기상인자를 고려하여 증발산량을 산정하였으며, 증발산량 변동에 대한 미기상인자의 영향성을 구명하였다. 수영구 지역의 토지이용도와 미기상인자는 2001년 12월부터 2011년 11월에 관측된 일별 자료를 사용하였다. 토지이용도는 불투수(건물, 도로 등) 및 산림(임야), 초지(논밭, 공원 등), 수계(하천, 호수 등) 지역으로 분류하였으며, 4개 지역 특성을 고려한 최적의 추정식을 적용하여 증발산량을 산정하였다. 수영구 지역의 전체 증발산량은 4개 지역에서 산정된 증발산량에 토지이용 비율을 곱하여 구하였다. 연간 증발산량 변동은 1월부터 7월까지 증가하다가 8월부터 12월까지 감소하는 형태를 보였다. 수영구 지역에서 증발산량은 강수량의 약 13.3% 정도이었으며, 이는 연구지역의 72%에 해당하는 불투수 지역에서 배수로를 통한 물의 유출이 강우 발생 후 짧은 시간 동안 다량 발생하였기에 지속적인 증발산이 가능한 잠재수량의 저유량이 적었기 때문이다. 증발산량과 미기상인자 간의 상관분석을 수행하였으며, 증발산량과 이슬점 온도의 상관계수가 0.63으로 가장 높았다. 증발산량에 대한 기온 및 강수량, 순복사 인자의 상관계수는 0.5 이상으로 양의 상관성을, 기압 및 일조시간은 0.5 이상의 음의 상관성을 보였다. 증발산량에 대한 상관계수가 0.5 이상인 미기상인자(이슬점온도와 기온, 순복사, 기압, 강수량)에 대한 회귀 분석을 수행하였다. 이슬점온도와 기온, 순복사, 기압에 대한 증발산량 회귀함수 그래프는 강수의 유무에 따라 2가지 경향을 보였다. 이슬점온도에 따른 증발산량 회귀함수는 강수 발생 시에는 $ET=0.004x+0.7$, 무강수 시에는 $ET=0.25{\times}e^{0.04x}$로 추정되었으며, 결정계수는 각각 0.48과 0.96 정도로서 무강수 시에 높게 나타났다. 기온에 따른 증발산량 회귀함수는 강수 발생 시에는 $ET=0.004x+0.53$, 무강수 시에는 $ET=0.13{\times}e^{0.06x}$로 추정되었으며, 결정계수는 각각 0.39와 0.89 정도로서 무강수 시에 높게 나타났다. 순복사에 따른 증발산량 회귀함수는 강수 발생 시에는 $ET=0.79x+0.49$, 무강수 시에는 $ET=0.22x+0.03$로 추정되었으며, 결정계수는 각각 0.34와 0.89 정도로서 무강수 시에 높게 나타났다. 기압에 따른 증발산량 회귀함수는 강수 발생 시에는 $ET=-0.04x+37.91$, 무강수 시에는 $ET=5.18{\times}10^{22}{\times}e^{-0.05x}$로 추정되었으며, 결정계수는 각각 0.25와 0.45 정도로 나타났다. 강수량에 따른 증발산량 회귀함수는 $ET=0.23lnx+0.90$으로 추정되었으며, 결정계수 0.61정도 나타났다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.55-55
• /
• 2017

가뭄은 국민생활 및 경제 등에 막대한 손실을 초래하며, 지역사회 공동체나 사회기능에 심각한 영향을 끼칠 수 있는 재해이다. 가뭄피해 최소화를 위해서는 단기대응, 복구지원 등의 사후대책에서 사전대비 및 예방으로의 정책 전환이 필요하며, 이러한 정책 수립을 뒷받침하기 위해서는 가뭄에 따른 정량적인 피해영향 평가가 우선적으로 필요하다. 하지만 가뭄 피해의 범위 및 형태는 워낙 광범위하기 때문에, 피해추정을 위한 잣대라 할 수 있는 영향평가 기법조차 제대로 정립되지 못하고 있는 실정이다. 국내에서는 분야별(기상, 농업, 수문)로 지수화 된 지표를 이용한 가뭄 평가가 주로 수행되고 있으며, 경제적 영향평가는 방법론에 대한 시범 연구 수준이다. 가뭄기록조사 등 과거 가뭄피해 자료에서도 피해액의 금액환산이 되지 않은 사례가 대부분이며 급수차지원, 관정개발 등 사후복구비 위주의 일부 자료만이 피해금액으로 제시되어 있을 뿐이다. 댐, 저수지 등에 의한 용수공급 안정성으로 인해, 기상학적인 가뭄이 즉시 물부족으로 인한 피해로 이어지지는 않지만, 물부족이 발생하거나 부족량이 예측되는 상황에서 피해규모를 시스템적으로 추정 및 비교할 수 있는 기법 개발의 필요성에 의해 잠재피해액 개념의 공급지장비용 추정기법을 개발하였다. 공급지장비용 또는 편익 도출을 위한 이론적 배경으로, 경제적 가치 또는 파급효과를 분석하기 위한 방법은 경제학적 접근법과 비경제학적 접근법으로 구분된다. 경제학적 접근법에서 사용하는 진술선호 기법의 경우 전국을 대상으로 설문 등의 과정을 거쳐 지불의사액을 도출하는 과정이 필요하기 때문에 많은 조사비용이 소요된다. 비경제학적 또는 공학적 접근법으로 분류되는 대체비용법은 이론적 배경이 약하고 대체항목의 선택에 주의가 필요하다는 단점이 있으나, 물가자료, 산업통계, 수자원통계 등 기초자료의 주기적 업데이트가 유리하며, 정신적 피해를 제외할 경우 피해비용 추정결과의 편차가 진술선호기법 보다는 작은 장점이 있다. 본 연구에서는 피해비용의 과대추정에 유의하여 대체비용법에 기반한 일본 후생노동성의 감 단수피해추정기법을 우리나라 자료에 맞게 수정하여 공급지장비용을 추정하였으며, 경제학적 접근법에 의한 용수의 한계가치비용 등과 비교를 통해 적용성을 검토하였다.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.6
• /
• pp.583-598
• /
• 2022

As human-based tunnel inspections are affected by the subjective judgment of the inspector, making continuous history management difficult. There is a lot of deep learning-based automatic crack detection research recently. However, the large public crack datasets used in most studies differ significantly from those in tunnels. Also, additional work is required to build sophisticated crack labels in current tunnel evaluation. Therefore, we present a method to improve crack detection performance by inputting existing datasets into a deep learning model. We evaluate and compare the performance of deep learning models trained by combining existing tunnel datasets, high-quality tunnel datasets, and public crack datasets. As a result, DeepLabv3+ with Cross-Entropy loss function performed best when trained on both public datasets, patchwise classification, and oversampled tunnel datasets. In the future, we expect to contribute to establishing a plan to efficiently utilize the tunnel image acquisition system's data for deep learning model learning.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_3
• /
• pp.2027-2034
• /
• 2021

Using multi-temporal KOMPSAT-3/3A high-resolution satellite images, the Normalized Difference Vegetation Index (NDVI) for the area around the Fukushima daiichi nuclear power plant was determined, and the pattern of vegetation changes was analyzed. To calculate the NDVI, surface reflectance from the KOMPSAT-3/3A satellite image was used. Satellite images from four years were used, and the zones where the images overlap was designated as the area of interest (AOI) for the study, and by setting a profile passing through highly vegetated area as a data analysis method, the changes by year were examined. In addition, random points were extracted within the AOI and displayed as a box plot to quantitatively indicate change of NDVI distribution pattern. The main results of this study showed that the NDVI in 2014 was low within AOI in the vicinity of the nuclear power plant, but vegetated area continued to expand until 2021. These results were also confirmed in the change monitoring results shown in a profile or box plot. In disaster areas where access is restricted, such as the Fukushima nuclear power plant area, where it is difficult to collect field data, obtaining land cover classification products with high accuracy using satellite images is challenging, so it is appropriate to analyze them using primary outputs such as vegetation indices obtained from high-resolution satellite imagery. It is necessary to establish an international cooperation system for jointly utilizing satellite images. Meanwhile, to periodically monitor environmental changes in neighboring countries that may affect the Korean peninsula, it is necessary to establish utilization models and systems using high-resolution satellite images.