• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.4
• /
• pp.328-337
• /
• 2021

Air pollution, which is a class 1 carcinogen, such as asbestos and benzene, is the cause of various diseases. The spread of ultra-air pollution is one of the important causes of the spread of the corona virus. This paper analyzes and predicts fine dust and ultra-air pollution from 2015 to 2019 based on weather data such as average temperature, precipitation, and average wind speed in Seoul and atmospheric environment data such as SO2, NO2, and O3. Linear regression, SVM, and ensemble models among machine learning models were compared and analyzed to predict fine dust by grasping and analyzing the status of air pollution and ultra-air pollution by season and month. In addition, important features(attributes) that affect the generation of fine dust and ultra-air pollution are identified. The highest ultra-air pollution was found in March, and the lowest ultra-air pollution was observed from August to September. In the case of meteorological data, the data that has the most influence on ultra-air pollution is average temperature, and in the case of meteorological data and atmospheric environment data, NO2 has the greatest effect on ultra-air pollution generation.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.3
• /
• pp.47-56
• /
• 2015

Automated detection of interesting web pages could be used in many different application domains. Determining a user's interesting web pages can be performed implicitly by observing the user's behavior. The task of distinguishing interesting web pages belongs to a classification problem, and we choose white box learning methods (fixed effect logit regression and support vector machine) to test empirically. The result indicated that (1) fixed effect logit regression, fixed effect SVMs with both polynomial and radial basis kernels showed higher performance than the linear kernel model, (2) a personalization is a critical issue for improving the performance of a model, (3) when asking a user explicit grading of web pages, the scale could be as simple as yes/no answer, (4) every second the duration in a web page increases, the ratio of the probability to be interesting increased 1.004 times, but the number of scrollbar clicks (p=0.56) and the number of mouse clicks (p=0.36) did not have statistically significant relations with the interest.

• Journal of the Korea Convergence Society
• /
• v.8 no.2
• /
• pp.53-62
• /
• 2017

This study was to find the factors influencing satisfaction of Korean medical tour services of Chinese college students. Structured questionnaire was developed to collect data. The data were collected from the 175 students between May 1 and May 15 in 2015 in an international college in China. The expectations and the evaluations on the Korean medical tour services were compare by t-test. To find the factors influencing satisfaction on Korean medical tour services, diverse linear regression models were estimated. According to the best fit regression model, technologies, quality of medical tour services, and health care cost significantly and positively influenced satisfaction on the Korean medical tour services. The results of the study suggested that we need to prepare marketing strategies to improve understandings on Korean medical tour services for the Chinese college students. Improvement of technology, improvement of quality of health service, and setting of reasonable price are important to attract more Chinese patients to Korea.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.6
• /
• pp.1075-1083
• /
• 2009

The scientific research method went through construction of hypothesis and collection of data by experiment or observation and abstracting the hypothesis based on the experience which uses the data. The statistical methodology plays an important role in this process. The method which acquires a data becomes an initial process of abstraction and a survey research using structured questionnaires is a basic tool. After the data is acquired, the high-class statistical techniques such as the regression analysis and the linear structural equation model are used to abstract a hypothesis. By the way, from time to time the concepts which have become abstractive do not help us to understand an actual phenomena, rather it is need to extract some knowledge from questions themselves. In this article, we review the well known statistical methods providing the ways of finding core questions which possibly answer a researcher wants to know. We deal with course evaluation data as an example and try to set up the strategy for improving course evaluation.

• Journal of the Korea Convergence Society
• /
• v.10 no.3
• /
• pp.73-79
• /
• 2019

This study simulated external ear canal modeling with different external ear canal lengths, vertical flexion angles, and inner/outer diameter ratios using digital imaging and communications in medicine(DICOM) of the head temporal region and measured the acoustic sensitivity. The experiment was performed by increasing the audible frequency for humans by 200 Hz and expressing the frequency constantly transmitted at 1 Pa as the eardrum acoustic volume and presented the measurements by linear and quadratic curve regression analysis. The results showed that the longer the external ear canal length and the higher the ratio of the outer/inner diameter, the faster the acoustic response at lower frequencies. The acoustic sensitivity correlation of the meta-model using regression analysis showed a 77% influence by the external ear canal length and 5% by the external/internal diameter ratio, while the vertical flexion angle did not show a significant relationship. This showed that auditory acoustic sensitivity of humans is a factor that reacts faster at a low frequency when the external ear canal length is longer and when the difference between the outer and inner diameter is higher.

• Journal of the Korea Society of Computer and Information
• /
• v.4 no.4
• /
• pp.101-112
• /
• 1999

In this paper variable bit rate VBR Moving Picture Experts Group (MPEG) coded full-motion video traffic is modeled by a nonlinear time-series process. The threshold autoregressive (TAR) process is of particular interest. The TAR model is comprised of a set of autoregressive (AR) processes that are switched between amplitude sub-regions. To model the dynamics of the switching between the sub-regions a selection of amplitude dependent thresholds and a delay value is required. To this end, an efficient and accurate TAR model construction algorithm is developed to model VBR MPEG-coded video traffic. The TAR model is shown to accurately represent statistical characteristics of the actual full-motion video trace. Furthermore. in simulations for the bit-loss rate actual and TAR traces show good agreement.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2002.02a
• /
• pp.471-478
• /
• 2002

초음파를 사과의 비파괴 품질판정에 이용하기 위한 기초연구로서 계측된 저장기간에 따른 사과의 초음파 특성과 본 연구에서 계측된 사과의 기계적 특성을 이용하여 초음파에 의한 사과의 탄성계수 및 생물체항복강도 예측모델을 개발하고자 하였으며, 결론은 다음과 같다. 1. UTM을 이용하여 사과의 기계적 특성치를 분석하여 생물체항복점, 생물체항복변형량, 생물체항복강도, 파괴점, 극한변형량, 극한강도 및 탄성계수 등을 구하였다. 2. 사과의 기본 물성, 초음파 특성과 기계적 특성값 들을 분석한 결과 사과의 질량, 체적, 시간영역의 진폭(PTP), 제3영역 에너지 스펙트럼 밀도함수가 기계적 특성 중 생물체항복강도, 탄성계수와 높은 상관성이 있는 것으로 나타났다. 3. 사과의 저장 기간, 질량, 체적, Peak-to-peak, 제3영역의 에너지값 등 5개의 독립변수를 가지는 다중선형회귀모형으로 사과의 탄성계수 및 생물체 항복강도 예측모형을 개발하였다.

• Journal of Biomedical Engineering Research
• /
• v.20 no.5
• /
• pp.573-579
• /
• 1999

본 논문은 2채널 센서를 이용한 펄스 옥시메터의 산소포화도 계산 모델의 설계 및 분석에 관한 것이었다. 또한 Beer Lambert 법칙에 의거하여 기존 알고리즘 및 새로운 알고리즘들을 이론적으로 분석하였다. 제안된 알고리즘은 손가락을 투과한 2개의 채널에서 나온 광신호를 각각 직류성분 Adc 와 맥동성문 Aasin wt. 잡음성분 Ahnoise , ALnoise 등으로 모델링한다. 모델링 되어진 광신호를 맥동성분이 적분비를 사용하여 고주파 동잡음인 AHnoise 를 제거한 후 각각 산소포화도 계산을 위한 상관계수 그래프를 구한다. 또한 2개의 채널에서 적분비를 사용하여 구해진 상관계수 그래프를 사용하여 산소농도를 추출하는 방법에 관하여 기술하였다. 맥동성분비와 관혈적인 측정에 의한 혈중 산소포화도와의 상관관계 그래프의 선형성을 확보하기 위하여 펄스 옥시메터 시뮬레이터 오차범위를 고려해 75~100%상이의 산소포화도를 중점적으로 관측하였고, 4주기로 면적계산주기를 결정하여 실험하였다. 본 연구에서 제안된 알고리즘의 성능평가는 맥동성분의 적분비를 이용한 방법과 비교하였다. 비교결과는 4주기의 면적계산 주기를 가졌을 때 기존의 방식보다 평균오차가 0.7%정도 향상되었으며, 회귀적선의 신뢰도를 보여주는 결정계수 ${\gamma}$$^2$도 0.995로 기존의 방식에서 나온 0.979보다 더 좋은 결과를 얻을 수 있었다. 따라서 2채널을 이용한 방법이 A Lnoise 제거와 성능면에서 우수하다는 결론을 얻을 수 있었다.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.25 no.3
• /
• pp.74-99
• /
• 2022

Surface ozone is produced by photochemical reactions of nitrogen oxides(NOx) and volatile organic compounds(VOCs) emitted from vehicles and industrial sites, adversely affecting vegetation and the human body. In South Korea, ozone is monitored in real-time at stations(i.e., point measurements), but it is difficult to monitor and analyze its continuous spatial distribution. In this study, surface ozone concentrations were interpolated to have a spatial resolution of 1.5km every hour using the stacking ensemble technique, followed by a 5-fold cross-validation. Base models for the stacking ensemble were cokriging, multi-linear regression(MLR), random forest(RF), and support vector regression(SVR), while MLR was used as the meta model, having all base model results as additional input variables. The results showed that the stacking ensemble model yielded the better performance than the individual base models, resulting in an averaged R of 0.76 and RMSE of 0.0065ppm during the study period of 2020. The surface ozone concentration distribution generated by the stacking ensemble model had a wider range with a spatial pattern similar with terrain and urbanization variables, compared to those by the base models. Not only should the proposed model be capable of producing the hourly spatial distribution of ozone, but it should also be highly applicable for calculating the daily maximum 8-hour ozone concentrations.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_1
• /
• pp.1435-1447
• /
• 2020

The seasonal variations in weather parameters can significantly affect the atmospheric transmission characteristics. Herein, we propose a novel augmented multiple regression algorithm for the accurate estimation of atmospheric transmittance and solar irradiance over highly localized areas. The algorithm employs 1) adaptive atmospheric model selection using measured meteorological data and 2) multiple linear regression computation augmented with the conventional application of MODerate resolution atmospheric TRANsmission (MODTRAN). In this study, the proposed algorithm was employed to estimate the solar irradiance over Taean coastal area using the 2018 clear days' meteorological data of the area, and the results were compared with the measurement data. The difference between the measured and computed solar irradiance significantly improved from 89.27 ± 48.08σ W/㎡ (with standard MODTRAN) to 21.35 ± 16.54σ W/㎡ (with augmented multiple regression algorithm). The novel method proposed herein can be a useful tool for the accurate estimation of solar irradiance and atmospheric transmission characteristics of highly localized areas with various weather conditions; it can also be used to correct remotely sensed atmospheric data of such areas.