• The Korean Journal of Applied Statistics
• /
• v.34 no.3
• /
• pp.375-388
• /
• 2021

This paper aims to help prevent the spread of COVID-19 by analyzing confirmed cases of COVID-19 in Daejeon. A high volume of visitors, downtown areas, and psychological fatigue with prolonged social distancing were considered as risk factors associated with the spread of COVID-19. We considered the weekly confirmed cases in each administrative district as a response variable. Explanatory variables were the number of passengers getting off at a bus station in each administrative district and the elapsed time since the Korean government had imposed distancing in daily life. We employed a mixed-effects zero-inflated Poisson regression model because the number of cases was repeatedly measured with excess zero-count data. We conducted k-means clustering to identify three groups of administrative districts having different characteristics in terms of the number of bars, the population size, and the distance to the closest college. Considering that the number of confirmed cases might vary depending on districts' characteristics, the clustering information was incorporated as a categorical explanatory variable. We found that Covid-19 was more prevalent as population size increased and a district is downtown. As the number of passengers getting off at a downtown district increased, the confirmed cases significantly increased.

• International Commerce and Information Review
• /
• v.18 no.2
• /
• pp.27-51
• /
• 2016

The purpose of this paper is to examine correlations between the facilitating factors of the B2C e-commerce and the online shopping and the overseas direct purchase for the purpose of suggesting the successful logistics operational strategies for the domestic parcel delivery service companies. This paper conducts wide literature reviews and empirical analyses on relationships between the facilitating factors of B2C e-commerce and the online shopping and the overseas direct purchase in B2C e-commerce. We built two regression equations that dependable variables are the turnover of online shopping and the amount of imports by international postal logistics services respectively. The former equation's estimation results show that all the independable variables are affecting the dependable variable in the long-term jointly. And, the results show that the change of the turnover of online shopping is affected not only by the change of the usage count of a credit card and the real GDP, but also by the change of the error-correction variable. The latter equation's estimation results show that all the independable variables are affecting the dependable variable in the long-term jointly. Futhermore, the results show that the change of the amount of imports by international postal logistics services is affected not only by the change of the usage count of a credit card, the exchange rate and the internet protocol IPv4, but also by the change of the error-correction variable. Based on these research results, a high advanced strategic approach for optimum parcel delivery services is highly required.

• International Journal of Highway Engineering
• /
• v.7 no.4 s.26
• /
• pp.41-47
• /
• 2005

Traffic data such as traffic volume, speed, and vehicle Class are very important basic data for the plan and design of highway. Based on traffic data, the future service level of a specific highway and geometry of newly constructed or expended road is predicted and determined. The Ministry of Construction & Transportation has simultaneously surveyed coverage count and permanent count at highways since 1985. Traffic volume survey sections were determined at jointed nodes of highways and jointed nodes of highways and other roads such as freeway and local highway. Volume survey was performed at these sections. The premise to decide these sections is assumed that links between jointed nodes of main highways exhibit similar traffic characteristics. Recently, due to the change of highway geometries such as construction of detour road and installations of traffic facilities such as installation of media, traffic characteristics of the existing traffic volume survey sections was changed. To reflect these changes, traffic characteristics at homogeneous road sections was widely evaluated and analyzed. Using Genetic Algorithms, a model was developed for the evaluation of traffic characteristics at homogeneous road sections. Traffic volume survey sections were then determined through the application of the developed model for current traffic system.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.11 no.2
• /
• pp.132-147
• /
• 2008

So far ubiquitous service (u-service) priority has seldom been empirically examined based on the customer's view. It is usual to prioritize the relative importance of u-service variables by the supplier's intuition and a few specialist's experienced knowledge. Such approaches have the disadvantage that they provide only limited empirical information on the field practices in relation to u-service since customer demand of u-service is poorly defined despite abundant interest in this problem. Therefore, the aim of this research was to develop u-service priority model in the context of multi-criteria framework integrating customer and supplier's view, using high technology acceptance theory as major controlling factors. An important question was how to measure or represent criteria that is important to u-service and should be included in a priority model. The selection criteria for the model variables were derived from high technology acceptance theory and AHP approach through the analysis of frequency count, elimination of overlapping factors and brainstorming with specialists. Daegu showed top-rankings in transportation-aid service, guidance service for the eyesight disabled and u-telematics service. In contrast, disaster prevention service and industrial specialized town service ranked highly in the typical supplier's approach were not a dominant determining factor in the u-service priority. The model identified the fact that typical high priority service in terms of supplier's view did not necessarily accompany the important predictor for the u-service priority.

• The Korean Journal of Nuclear Medicine
• /
• v.30 no.4
• /
• pp.548-559
• /
• 1996

A series of performance measurements of positron emission tomography (PET) were performed following the recommendations of the Computer and Instrumentation Council of the Society of Nuclear Medicine and the National Electrical Manufacturers Association. We investigated the performance of the General Electric $Advance^{TM}$ PET. The measurements include the basic intrinsic tests of spatial resolution, scatter fraction, sensitivity, and count rate losses and randoms. They also include the tests of the accuracy of corrections: count rate linearity correction, uniformity correction, scatter correction and attenuation correction. GE $Advance^{TM}$ PET has bismuth germanate oxide crystals (4.0mm transaxial ${\times}$ 8.1mm axial ${\times}$ 30.0mm radial) in 18 rings, which form 35 imaging planes spaced by 4.25mm. The system has retractable tungsten septa 1mm thick and 12cm long. Transaxial resolution was 4.92mm FWHM in 2D and 5.14mm FWHM in 3D at the center. Average axial resolution in 2D decreased from 3.91mm FWHM at the center to 6.49mm FWHM at R=20cm. Average scatter fraction of direct and cross slices was 9.57%. Dead-time losses of 50% corresponded to a radioactivity concentration of $4.86{\mu}Ci/cc$ and a true count rate of 519 kcps in 2D. The accuracy of count rate linearity correction was 1.84% at the activity of $4.50{\mu}Ci/cc$. Non-uniformity was 2.06% in 2D and 2.93% in 3D. Remnant errors after scatter correction were 0.55% in 2D and 4.12% in 3D. The errors of attenuation correction were 6.21% (air), 0.20% (water), -6.32% (teflon) in 2D and 5.00% (air), 6.94% (water), 3.01% (teflon) in 3D. The results indicate the performance of GE $Advance^{TM}$ PET scanner to be well suited for clinical and research applications.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.15 no.2
• /
• pp.41-46
• /
• 2011

Purpose: The result of exam using an imaging device is very closely related with the image quality. Moreover, this image quality can be changed according to the condition of image acquisition and evaluation method. In this study, we evaluated the image quality according to the difference of pre-set method in PET/CT image. Materials & Methods: PET/CT Discovery STe16 (GE Healthcare, Milwaukee, USA), Chest PET phantom (Experiment 1) and 94 NEMA phantom (Experiment 2) were used. Phantom were filled with $^{18}F$-FDG maintaining hot sphere and background ratio to 4:1. In the case of experiment 1, we set the radio activity concentration on 3.5, 6.0, 8.6 kBq/mL. In the case of experiment 2, we set the radio activity concentration on 3.3, 5.5, 7.7, 9.9, 12.1, 16.5 kBq/mL. All experiments were performed with the time-set method for 2 minutes 30 seconds per frame and the count-set method with one hundred million counts in 3D mode after CT transmission scan. For the evaluation of the image quality, we compared each results by using the NECR and SNR. Results: In the experiment 1, both the NECR and SNR were increased as radioactivity concentration getting increased. The NECR was shown as 53.7, 66.9, 91.4. and SNR was shown as 7.9, 10.0, 11.7. Both the NECR and SNR were increased in time-set method. But the count-set method's pattern was not similar with the time-set method. The NECR was shown as 53.8, 69.1, 97.8, and SNR was shown as 14.1, 14.7 14.4. The SNR was not increased in count-set method. In experiment 2, results of both the NECR and SNR were shown as 45.1, 70.6, 95.3, 115.6, 134.6, 162.2 and 7.1, 8.8, 10.6, 11.5, 12.7, 14.0. These results were shown similar patten with the experiment 1. Moreover, when the count-set method was applied, the NECR was shown as 42.1, 67.3, 92.1, 112.2, 130.7, 158.7, and SNR was shown as 15.2, 15.9, 15.6, 15.4, 15.5, 14.9. The NECR was increased but SNR was not shown same pattern. Conclusion: Increment of administered radioactivity improves the quality of image unconcerned with the pre-set method. However, NECR was not influenced by increment of total acquisition counts through simple increasing scan duration without increment of administered activity. In case of count-set method, the SNR was shown similar value despite of increment of radioactivity. So, the administered activity is more important than the scan duration. And we have to consider that evaluation of image quality using only SNR may not be appropriate.

• Journal of the Economic Geographical Society of Korea
• /
• v.19 no.1
• /
• pp.1-17
• /
• 2016

This paper attempts to explore the spatial structure of inventor networks and their determinants among 230 shi-gun-gu regions in Korea by investigating the residence of co-inventors engaged in Korean patent applications to the Korean Intellectual Office and exploiting a zero inflated negative binomial model to accommodate an estimation to the count nature of a dependent variable and its excess of zeros. Several variables are found to affect the spatial linkage of inventor networks. Spatial links extend beyond the region if it has more own R&D-related specific assets (private R&D, patent productivity, population, education); if it is physically close to and has technological similarity with the other region. The assets of the other region plays a positive role if, in a similar way, the other region has more R&D-related specific assets.

• Journal of Korean Society of Transportation
• /
• v.33 no.1
• /
• pp.100-111
• /
• 2015

After empirically investigating the vehicle accident risks by age groups, various programs and policies have been imposed to reduce the old's risks in other countries. In Korea, it is little known the risk level by age groups and no policy changes has been implemented even if the number of vehicle accidents occurred by the old has been rapidly rising while the total number of vehicle accidents has been decreasing. This study empirically investigates the vehicle accident risks by age groups and the results show that the old drivers over age 65 has the highest accident risk except for the young drivers below age 25. Thus, we emphasize the necessity of reinforcing the qualifications for reissuing the drive licence and programs for educating the old drivers in Korea which is facing the most rapid population aging in the world. On the other hand, various changes are needed reflecting the old drivers such as reforming the road signs, issuing a sticker and providing them incentives such that the old drivers use the public transportation instead of self-driving.

• The Journal of Society for e-Business Studies
• /
• v.10 no.4
• /
• pp.83-100
• /
• 2005

In this paper, we investigate the concept of cyber identity built in cyberspace and analyze the effects of general perception toward cyber identity on loyalty and purchase intent. Cyber identity is classified into two types: personal and social cyber identity, and has five components. Avatars and online gaming capability make up personal cyber identity while online communities and instant messenger count as social cyber identity. We regard blog personalities as having both personal and social characteristics. In our survey, we conclude that internet users want to purchase cyber items such as avatars, online game items, and wallpaper pictures to enhance their cyber identities. Based on the survey results , we derive five factors comprising personal cyber identity and social cyber identity using factor analysis and analyze overall effects of cyber identity on loyalty and purchase intention using Structural Equation Model.

• The Korean Journal of Applied Statistics
• /
• v.37 no.2
• /
• pp.239-253
• /
• 2024

This research applies both point-wise and pair-wise learning strategies within the learning-to-rank (LTR) framework to predict horse race rankings in Seoul. Specifically, for point-wise learning, we employ a linear model and random forest. In contrast, for pair-wise learning, we utilize tools such as RankNet, and LambdaMART (XGBoost Ranker, LightGBM Ranker, and CatBoost Ranker). Furthermore, to enhance predictions, race records are standardized based on race distance, and we integrate various datasets, including race information, jockey information, horse training records, and trainer information. Our results empirically demonstrate that pair-wise learning approaches that can reflect the order information between items generally outperform point-wise learning approaches. Notably, CatBoost Ranker is the top performer. Through Shapley value analysis, we identified that the important variables for CatBoost Ranker include the performance of a horse, its previous race records, the count of its starting trainings, the total number of starting trainings, and the instances of disease diagnoses for the horse.