• 한국융합학회논문지
• /
• 제7권6호
• /
• pp.35-41
• /
• 2016

소프트웨어의 중요성이 높아지면서 소프트웨어 품질평가에 대한 관심이 높아지고 있다. 본 연구에서는 소프트웨어 품질 평가를 위한 국제 표준 문서를 비교 분석하고 테스트 데이터 분석을 통한 평가 방안을 제시한다. 국제표준 ISO/IEC 9126-2의 평가 모델과 ISO/IEC 25023의 평가 모델에 대한 차이점을 비교했다. ISO/IEC 25023의 평가모델인 8가지 품질 특성, 즉 기능성, 신뢰성, 사용성, 유지보수성, 이식성, 효율성, 상호운영성, 보안성적인 측면에서 평가 메트릭을 제시했다. 실제 테스트를 통해 얻어진 331개 자료를 분석해서 테스트 데이터의 발견된 오류 특징을 파악했다. 또한 결함 자료를 분석하고 차이점을 파악했다. 테스트데이터가 남녀에 따라서 시험 일수나 발견하는 품질 특성별 오류의 수에는 차이가 있음을 증명하고 시험일수를 기능성, 사용성, 성별을 가지고 예측했으며, 제품의 종류에 따라서도 오류수에 차이가 있음을 증명했다.

• 경영정보학연구
• /
• 제18권1호
• /
• pp.25-39
• /
• 2016

본 연구의 목적은 데이터 분석에 익숙하지 않은 일반인도 공개된 빅 데이터를 사용하여 복잡한 프로그래밍 없이 비교적 쉽게 빅 데이터를 활용할 수 있도록 참고할 수 있는 분석 사례를 제시하는 것이다. 이를 위해 본 연구에서는 SKT Data Hub에서 공개한 '배달 업종 이용 현황 분석' 데이터를 이용하여, 음식을 주제로 한 방송이 실제로 배달음식 주문량에 긍정적인 영향을 미치는지를 이중차이(DID: Difference In Differences) 방법을 적용한 다중 회귀분석을 통해 확인하였다. 분석결과, 배달음식을 주제로 한 TV 프로그램의 5개 회 차 중 4개 회 차의 방영 후 배달음식의 주문량이 유의하게 증가한 것으로 나타났다. 본 연구의 결과는 음식을 주제로 한 방송으로 인해, 해당 방송이 진행된 점포 뿐아니라 해당 점포와 같은 음식 업종 전반에서 긍정적인 영향을 받을 수 있다는 가능성을 확인했다는 점에서 학문적 의의가 있다. 또한 공개된 빅 데이터를 이용하여 일반에서 쉽게 활용하고 분석할 수 있도록 참고사례를 제공했다는 점에서 실무적 의의를 갖는다.

• 한국지능시스템학회논문지
• /
• 제20권3호
• /
• pp.447-454
• /
• 2010

본 논문은 예측 시스템의 성능을 개선하기 위해 비선형데이터의 내재된 특성이나 불확실성을 보다 효과적으로 반영할 수 있는 Interval Type-2 TSK 퍼지논리 시스템 기반 다중 퍼지 예측시스템의 설계를 다룬다. 본 논문에 제시된 다중 예측시스템들은 데이터의 비선형적 특성들을 효과적으로 고려하기 위해 설계되며, 각각의 시스템은 Type-1 TSK 퍼지논리나 다른 방법들에 비해 데이터의 불확실성을 충분히 반영할 수 있는 Interval Type-2 TSK 퍼지논리를 기반으로 구현된다. 또한, 1차 차분변환 과정을 통해, 데이터의 원형으로부터 최적의 차분데이터를 생성하고, 이들을 각 시스템의 입력으로 사용함으로써 시스템 설계 시 보다 안정된 통계적 정보를 제공할 수 있도록 한다. 마지막으로, 두 개의 전형적인 시계열 데이터의 예측 시뮬레이션을 통해 제안된 방법의 효용성을 검증한다.

• 한국보건간호학회지
• /
• 제13권2호
• /
• pp.59-69
• /
• 1999

This study was conducted to investigate dental caries according to obesity in order to provide basic data for efficient dental health program for elementary school students. Data were obtained from a health record book of 668 elementary school students in Chun Cheon city in 1998. Obesity was categorized into overweight. normal and under weight groups by Rohrer index. Dental caries was classified into decayed. filled and missed teeth. The result were as follow: 1. Prevalence rate of dental caries(dft) was $78.7\%$ and mean dft was 2.96; decayed and filled teeth was 1.01 and 1.95. respectively. As for mean dft. a siginificant difference were shown according to obesity and age. while no siginificant difference was shown between boys and girls. 2. Prevalence rate of dental caries including missed teeth (dmft) rate was $83.9\%$ and mean dmft was 3.64. As for mean dmft. a siginificant difference were shown according to obesity and age. while no siginificant difference was shown between boys and girls.

• 기술혁신학회지
• /
• 제3권3호
• /
• pp.36-52
• /
• 2000

This study takes an issue of efficiency analysis in the presence of network effect utilizing the DEA (Data Envelopment Analysis) framework. Network effect has important policy implication for the regulation of local monopolies which undertake their business through physical network, such as electricity, natural gas, local telephony, etc. If the difference in spatial condition between companies is not controlled properly, the performance comparison and associated incentive regulation bear significant bias. In this study, we propose a methodology to measure the true managerial or technical efficiency apart from efficiency difference accruing from the difference in spatial condition. A series of modified DEA efficiency models are combined to investigate the extent of exogenous and endogenous efficiency component in the Korean natural gas distribution companies. Empirical results show that the network effect plays significant role in determining superficial performance difference.

• Journal of the Korean Data and Information Science Society
• /
• 제19권4호
• /
• pp.1123-1131
• /
• 2008

A considerable amount of research has focused on the dimensionality of service failure and recovery construct. This paper is focused on service failure and recovery in the Korean native cattle and imported beef restaurant industry in the Korea. So, this paper has adapted Kau and Loh's Service recovery measurement scale so that restaurant managers can use it to determine how customers perceive the service quality in Korean native cattle beef restaurant and imported beef restaurant. The purpose of this research is to test the difference in pre-purchase expectation and post-purchase actual performance of 4 dimensions between the restaurants that sell the beef of Korean native cattle and imported cattle. The paired t -test is used to test difference of pre-purchase expectation and post-purchase actual performance for service recovery measurement scale's 4 dimensions of the 2 restaurant types. But, there is significant difference between pre-purchase expectation and post-purchase actual performance in the 2 restaurant types.

• Journal of the Korean Data and Information Science Society
• /
• 제19권4호
• /
• pp.1165-1172
• /
• 2008

A considerable amount of research has focused on the dimensionality of service quality construct. To achieve and maintain their comprehensiveness and profitability, restaurant managers should manage and aim to continuously improve the level of service quality offered to their customers. This paper is focused on service quality in the Korean native cattle and imported beef restaurant industry in the Korea. So, this paper has adapted DINESERV scale so that restaurant managers can use it to determine how customers perceive the service quality in Korean native cattle beef restaurant and imported beef restaurant. The purpose of this research is to test the difference in importance and actual performance of 5 dimensions between the restaurants that sell the beef of Korean native cattle and imported cattle. The t-value is used to test difference of the importance and actual performance for DINESERV's 5 dimensions of the 2 restaurant types. But, there is no difference between Korean native cattle and imported beef restaurant.

• Ocean and Polar Research
• /
• 제35권3호
• /
• pp.239-247
• /
• 2013

Digital image processing is a process to analyze a large volume of information on digital images. In this study, Artemia hatching rate was measured by automatically classifying and counting cysts and larvae based on color imaging data from cyst hatching experiments using an image processing technique. The Artemia hatching rate estimation consists of a series of processes; a step to convert the scanned image data to a binary image data, a process to detect objects and to extract their shape information in the converted image data, an analysis step to choose an optimal discriminant function, and a step to recognize and classify the objects using the function. The function to classify Artemia cysts and larvae is optimally estimated based on the classification performance using the areas and the plan-form factors of the detected objects. The hatching rate using the image data obtained under the different experimental conditions was estimated in the range of 34-48%. It was shown that the maximum difference is about 19.7% and the average root-mean squared difference is about 10.9% as the difference between the results using an automatic counting (this study) and a manual counting were compared. This technique can be applied to biological specimen analysis using similar imaging information.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume I
• /
• pp.394-397
• /
• 2006

Gridded products of surface wind/wind-stress over the world ocean have been constructed by using satellite scatterometer as the Japanese Ocean Flux data sets with Use of Remote-sensing Observation (J-OFURO) data. Our previous validation study in the tropical Pacific using TAO/Triton and NDBC buoys revealed high reliability of our products. In this study, the Kuroshio Extension Observatory (KEO) buoy data are used for validation of other gridded wind-stress products including the NCEP-1 and 2 in the western North Pacific region where there have been few in-situ data. Results reveal that our J-OFURO product has almost zero mean difference and smallest root-mean-square (RMS) difference, while the NCEP-1 and 2 ones significantly positive biases and relatively high RMS difference. Intercomparison between the J-OFURO and NCEP products in a wide region of the North Pacific covered by the westerly winds exhibits that the NCEPs have larger magnitudes in the wind stress than the J-OFURO's, suggesting overestimation of the NCEPs.

• 대한의용생체공학회:의공학회지
• /
• 제28권4호
• /
• pp.530-538
• /
• 2007

Magnetocardiography (MCG) is a device to measure the magnetic field from the heart. It is a noninvasive device and takes only few minutes to record magnetocardiogram from a subject. In this study, we compared the difference of MCG data recorded from 56 normal subjects in early twenties (28 males and 28 females, mean $age=21.0{\pm}1.6$ years) and 36 elderly subjects (20 males and 16 females, mean $age=61.9{\pm}6.9$ years) for the analysis of the age and gender difference. A total of 24 parameters used in the analysis were derived from QRS complex, R-wave, T-wave, and ST-T period. As a result, seven parameters including maximum current angle and map angle showed the significant difference (p<0.01 and p<0.05, respectively) between young males and young females. Significant difference (p<0.05) between elderly males and elderly females was found from a parameter, pole distance at T-wave peak. In the comparison of age difference, seven parameters regarding current moment, pole distance, and dynamics showed the significant difference between young and elderly males. Eight parameters also showed significant difference (p<0.05) between two younger and elderly female groups. Results showed that parameters regarding current moment, pole distance, and dynamics might be changed when people get older. In conclusion, gender and age difference should be considered when MCG data are analyzed for certain parameters.