• Trans-
• /
• v.12
• /
• pp.51-79
• /
• 2022

This study investigates the methods for deriving colors which can serve as a reference to users such as designers and or contents creators who search for online images from the web portal sites using specific words for color planning and more. Two experiments were conducted in order to accomplish this. Digital scenery photos within the geographic scope of Korea were downloaded from web portal sites, and those photos were studied to find out what colors were used to describe daytime and nighttime. Machine learning was used as the study methodology to classify colors in daytime and nighttime, and KSCA was used to derive the color frequency of daytime and nighttime photos and to compare and analyze the two results. The results of classifying the colors of daytime and nighttime photos using machine learning show that, when classifying the colors by 51~100%, the area of daytime colors was approximately 2.45 times greater than that of nighttime colors. The colors of the daytime class were distributed by brightness with white as its center, while that of the nighttime class was distributed with black as its center. Colors that accounted for over 70% of the daytime class were 647, those over 70% of the nighttime class were 252, and the rest (31-69%) were 101. The number of colors in the middle area was low, while other colors were classified relatively clearly into day and night. The resulting color distributions in the daytime and nighttime classes were able to provide the borderline color values of the two classes that are classified by brightness. As a result of analyzing the frequency of digital photos using KSCA, colors around yellow were expressed in generally bright daytime photos, while colors around blue value were expressed in dark night photos. For frequency of daytime photos, colors on the upper 40% had low chroma, almost being achromatic. Also, colors that are close to white and black showed the highest frequency, indicating a large difference in brightness. Meanwhile, for colors with frequency from top 5 to 10, yellow green was expressed darkly, and navy blue was expressed brightly, partially composing a complex harmony. When examining the color band, various colors, brightness, and chroma including light blue, achromatic colors, and warm colors were shown, failing to compose a generally harmonious arrangement of colors. For the frequency of nighttime photos, colors in approximately the upper 50% are dark colors with a brightness value of 2 (Munsell signal). In comparison, the brightness of middle frequency (50-80%) is relatively higher (brightness values of 3-4), and the brightness difference of various colors was large in the lower 20%. Colors that are not cool colors could be found intermittently in the lower 8% of frequency. When examining the color band, there was a general harmonious arrangement of colors centered on navy blue. As the results of conducting the experiment using two methods in this study, machine learning could classify colors into two or more classes, and could evaluate how close an image was with certain colors to a certain class. This method cannot be used if an image cannot be classified into a certain class. The result of such color distribution would serve as a reference when determining how close a certain color is to one of the two classes when the color is used as a dominant color in the base or background color of a certain design. Also, when dividing the analyzed images into several classes, even colors that have not been used in the analyzed image can be determined to find out how close they are to a certain class according to the color distribution properties of each class. Nevertheless, the results cannot be used to find out whether a specific color was used in the class and by how much it was used. To investigate such an issue, frequency analysis was conducted using KSCA. The color frequency could be measured within the range of images used in the experiment. The resulting values of color distribution and frequency from this study would serve as references for color planning of digital design regarding natural scenery in the geographic scope of Korea. Also, the two experiments are meaningful attempts for searching the methods for deriving colors that can be a useful reference among numerous images for content creator users of the relevant field.

• Journal of radiological science and technology
• /
• v.28 no.2
• /
• pp.137-144
• /
• 2005

To find the personal radiation dose of radiological technologists, a survey was conducted to 623 radiological technologists who had been working at 44 general hospitals in Korea's 16 cities and provinces from 1998 to 2002. A total of 2,624 cases about personal radiological dose that were collected were analyzed by region, year and hospital, the results of which look as follows : 1. The average radiation dose per capita by region and year for the 5 years was 1.61 mSv. By region, Daegu showed the highest amount 4.74 mSv, followed by Gangwon 4.65 mSv and Gyeonggi 2.15 mSv. The lowest amount was recorded in Chungbuk 0.91 mSv, Jeju 0.94 mSv and Busan 0.97 mSv in order. By year, 2000 appeared to be the year showing the highest amount of radiation dose 1.80 mSv, followed by 2002 1.77 mSv, 1999 1.55 mSv, 2001 1.50 mSv and 1998 1.36 mSv. 2. In 1998, Gangwon featured the highest amount of radiological dose per capita 3.28 mSv, followed by Gwangju 2.51 mSv and Daejeon 2.25 mSv, while Jeju 0.86mSv and Chungbuk 0.85 mSv belonged to the area where the radiation dose remained less than 1.0 mSv In 1999, Gangwon also topped the list with 5.67 mSv, followed by Daegu with 4.35 mSv and Gyeonggi with 2.48 mSv. In the same year, the radiation dose was kept below 1.0 mSv. in Ulsan 0.98 mSv, Gyeongbuk 0.95 mSv and Jeju 0.91 mSv. 3. In 2000, Gangwon was again at the top of the list with 5.73 mSv. Ulsan turned out to have less than 1.0 mSv of radiation dose in the years 1998 and 1999 consecutively, whereas the amount increased relatively high to 5.20 mSv. Chungbuk remained below the level of 1.0 mSv with 0.79 mSv. 4. In 2001, Daegu recorded the highest amount of radiation dose among those ever analyzed for 5 years with 9.05 mSv, followed by Gangwon with 4.01 mSv. The area with less than 1.0 mSv included Gyeongbuk 0.99 mSv and Jeonbuk 0.92 mSv. In 2002, Gangwon also led the list with 4.65 mSv while Incheon 0.88 mSv, Jeonbuk 0.96 mSv and Jeju 0.68 mSv belonged to the regions with less than 1.0 mSv of radiation dose. 5. By hospital, KMH in Daegu showed the record high amount of average radiation dose during the period of 5 years 6.82 mSv, followed by GAH 5.88 mSv in Gangwon and CAH 3.66 mSv in Seoul. YSH in Jeonnam 0.36 mSv comes first in the order of the hospitals with least amount of radiation dose, followed by GNH in Gyeongnam 0.39 mSv and DKH in Chungnam 0.51 mSv. There is a limit to the present study in that a focus is laid on the radiological technologists who are working at the 3rd referral hospitals which are regarded to be stable in terms of working conditions while radiological technologists who are working at small-sized hospitals are excluded from the survey. Besides, there are also cases in which hospitals with less than 5 years since establishment are included in the survey and the radiological technologists who have worked for less than 5 years at a hospital are also put to survey. We can't exclude the possibility, either, of assumption that the difference of personal average radiological dose by region, hospital and year might be ascribed to the different working conditions and facilities by medical institutions. It seems therefore desirable to develop standardized instruments to measure working environment objectively and to invent device to compare and analyze them by region and hospital more accurately in the future.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.97-117
• /
• 2020

Product evaluation criteria is an indicator describing attributes or values of products, which enable users or manufacturers measure and understand the products. When companies analyze their products or compare them with competitors, appropriate criteria must be selected for objective evaluation. The criteria should show the features of products that consumers considered when they purchased, used and evaluated the products. However, current evaluation criteria do not reflect different consumers' opinion from product to product. Previous studies tried to used online reviews from e-commerce sites that reflect consumer opinions to extract the features and topics of products and use them as evaluation criteria. However, there is still a limit that they produce irrelevant criteria to products due to extracted or improper words are not refined. To overcome this limitation, this research suggests LDA-k-NN model which extracts possible criteria words from online reviews by using LDA and refines them with k-nearest neighbor. Proposed approach starts with preparation phase, which is constructed with 6 steps. At first, it collects review data from e-commerce websites. Most e-commerce websites classify their selling items by high-level, middle-level, and low-level categories. Review data for preparation phase are gathered from each middle-level category and collapsed later, which is to present single high-level category. Next, nouns, adjectives, adverbs, and verbs are extracted from reviews by getting part of speech information using morpheme analysis module. After preprocessing, words per each topic from review are shown with LDA and only nouns in topic words are chosen as potential words for criteria. Then, words are tagged based on possibility of criteria for each middle-level category. Next, every tagged word is vectorized by pre-trained word embedding model. Finally, k-nearest neighbor case-based approach is used to classify each word with tags. After setting up preparation phase, criteria extraction phase is conducted with low-level categories. This phase starts with crawling reviews in the corresponding low-level category. Same preprocessing as preparation phase is conducted using morpheme analysis module and LDA. Possible criteria words are extracted by getting nouns from the data and vectorized by pre-trained word embedding model. Finally, evaluation criteria are extracted by refining possible criteria words using k-nearest neighbor approach and reference proportion of each word in the words set. To evaluate the performance of the proposed model, an experiment was conducted with review on '11st', one of the biggest e-commerce companies in Korea. Review data were from 'Electronics/Digital' section, one of high-level categories in 11st. For performance evaluation of suggested model, three other models were used for comparing with the suggested model; actual criteria of 11st, a model that extracts nouns by morpheme analysis module and refines them according to word frequency, and a model that extracts nouns from LDA topics and refines them by word frequency. The performance evaluation was set to predict evaluation criteria of 10 low-level categories with the suggested model and 3 models above. Criteria words extracted from each model were combined into a single words set and it was used for survey questionnaires. In the survey, respondents chose every item they consider as appropriate criteria for each category. Each model got its score when chosen words were extracted from that model. The suggested model had higher scores than other models in 8 out of 10 low-level categories. By conducting paired t-tests on scores of each model, we confirmed that the suggested model shows better performance in 26 tests out of 30. In addition, the suggested model was the best model in terms of accuracy. This research proposes evaluation criteria extracting method that combines topic extraction using LDA and refinement with k-nearest neighbor approach. This method overcomes the limits of previous dictionary-based models and frequency-based refinement models. This study can contribute to improve review analysis for deriving business insights in e-commerce market.

• Sleep Medicine and Psychophysiology
• /
• v.19 no.2
• /
• pp.68-76
• /
• 2012

Objectives: Sleep disorders cause changes of autonomic nervous system (ANS) which affect cardiovascular system. Primary insomnia (PI) makes acceleration of sympathetic nervous system (SNS) tone by sleep deficiency and arousal. Obstructive sleep apnea syndrome (OSAS) sets off SNS by frequent arousals and hypoxemias during sleep. We aimed to compare the changes of heart rate variability (HRV) indices induced by insomnia or sleep apnea to analyze for ANS how much to be affected by PI or OSAS. Methods: Total 315 subjects carried out nocturnal polysomnography (NPSG) were categorized into 4 groups - PI, mild, moderate and severe OSAS. Severity of OSAS was determined by apnea-hypopnea index (AHI). Then we selected 110 subjects considering age, sex and valance of each group's size [Group 1 : PI (mean age=$41.50{\pm}13.16$ yrs, AHI <5, n=20), Group 2 : mild OSAS (mean age=$43.67{\pm}12.11$ yrs, AHI 5-15, n=30), Group 3 : moderate OSAS (mean age $44.93{\pm}12.38$ yrs, AHI 16-30, n=30), Group 4 : severe OSAS (mean age=$45.87{\pm}12.44$ yrs, AHI >30, n=30)]. Comparison of HRV indices among the four groups was performed with ANCOVA (adjusted for age and body mass index) and Sidak post-hoc test. Results: We found statistically significant differences in HRV indices between severe OSAS group and the other groups (PI, mild OSAS and moderate OSAS). And there were no significant differences in HRV indices among PI, mild and moderate OSAS group. In HRV indices of PI and severe OSAS group showing the most prominent difference in the group comparisons, average RR interval were $991.1{\pm}27.1$ and $875.8{\pm}22.0$ ms (p=0.016), standard deviation of NN interval (SDNN) was $85.4{\pm}6.6$ and $112.8{\pm}5.4$ ms (p=0.022), SDNN index was $57.5{\pm}5.2$ and $87.6{\pm}4.2$ (p<0.001), total power was $11,893.5{\pm}1,359.9$ and $18,097.0{\pm}1,107.2ms^2$(p=0.008), very low frequency (VLF) was $7,534.8{\pm}1,120.1$ and $11,883.8{\pm}912.0ms^2$ (p=0.035), low frequency (LF) was $2,724.2{\pm}327.8$ and $4,351.6{\pm}266.9ms^2$(p=0.003). Conclusions: VLF and LF which were correlated with SNS tone showed more increased differences between severe OSAS group and PI group than other group comparisons. We could suggest that severe OSAS group was more influential to increased SNS activity than PI group.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.14 no.4
• /
• pp.1-10
• /
• 2011

This study was conducted to compare the growth of Zoysia japonica depending on different soil treatments in Saemangeum sea dike, which is filled with dredged soil. Zoysia japonica was planted using sod-pitching method on the control plot. On plots which were treated with forest soil and soil improvement, Zoysia japonica seeds were sprayed mechanically. Sixteen months after planting, coverage rate, leaf length, leaf width, and root length were measured and analyzed. Also, three Zoysia japonica samples per plot were collected to analyze nutrient contents. Coverage rate was 100% in B treatment plot(dredged soil+$40kg/m^3$ soil improvement+forest soil), in C treatment plots (dredged soil+$60kg/m^3$ soil improvement+forest soil), and D treatment plots (dredged soil+$60kg/m^3$ soil improvement), while only 43% of the soil surface was covered with Zoysia japonica on control plots. The width of the leaf on C treatment plots (3.79mm) was the highest followed by D treatment (3.49mm), B treatment (2.40mm) and control plots (1.97mm). Leaf and root length of D treatment was 30.18cm and 13.18cm, which were highest among different treatments. The leaf length of D treatment was highest followed by C, B, and A treatments. The root length of D treatment was highest followed by C, A, and B treatments. The nitrogen and phosphate contents of the above ground part of Zoysia japonica were highest in C treatment, followed by D, B, and A treatments. The nitrogen and phosphate contents of the underground part of Zoysia japonica were highest in D treatment, followed by C, A, and B treatments. C and D treatments showed the best results in every aspect of grass growth. The results of this study could be used to identify the cost effective way to improve soil quality for soil surface fixation on reclaimed areas using grass species.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.13 no.1
• /
• pp.77-81
• /
• 2009

Purpose: The PET of the PET/CT (Positron Emission Tomography/Computed Tomography) quantitatively shows the biological and chemical information of the body, but has limitation of presenting the clear anatomic structure. Thus combining the PET with CT, it is not only possible to offer the higher resolution but also effectively shorten the scanning time and reduce the noises by using CT data in attenuation correction. And because, at the CT scanning, the contrast media makes it easy to determine a exact range of the lesion and distinguish the normal organs, there is a certain increase in the use of it. However, in the case of using the contrast media, it affects semi-quantitative measures of the PET/CT images. In this study, therefore, we will be to establish the reliability of the SUV (Standardized Uptake Value) with CT data correction so that it can help more accurate diagnosis. Materials and Methods: In this experiment, a total of 30 people are targeted - age range: from 27 to 72, average age : 49.6 - and DSTe (General Electric Healthcare, Milwaukee, MI, USA) is used for equipment. $^{18}F$- FDG 370~555 MBq is injected into the subjects depending on their weight and, after about 60 minutes of their stable position, a whole-body scan is taken. The CT scan is set to 140 kV and 210 mA, and the injected amount of the contrast media is 2 cc per 1 kg of the patients' weight. With the raw data from the scan, we obtain a image showing the effect of the contrast media through the attenuation correction by both of the corrected and uncorrected CT data. Then we mark out ROI (Region of Interest) in each area to measure SUV and analyze the difference. Results: According to the analysis, the SUV is decreased in the liver and heart which have more bloodstream than the others, because of the contrast media correction. On the other hand, there is no difference in the lungs. Conclusions: Whereas the CT scan images with the contrast media from the PET/CT increase the contrast of the targeted region for the test so that it can improve efficiency of diagnosis, there occurred an increase of SUV, a semi-quantitative analytical method. In this research, we measure the variation of SUV through the correction of the influence of contrast media and compare the differences. As we revise the SUV which is increasing in the image with attenuation correction by using contrast media, we can expect anatomical images of high-resolution. Furthermore, it is considered that through this trusted semi-quantitative method, it will definitely enhance the diagnostic value.

• Journal of Intelligence and Information Systems
• /
• v.20 no.3
• /
• pp.93-108
• /
• 2014

To support business decision making, interests and efforts to analyze and use transaction data in different perspectives are increasing. Such efforts are not only limited to customer management or marketing, but also used for monitoring and detecting fraud transactions. Fraud transactions are evolving into various patterns by taking advantage of information technology. To reflect the evolution of fraud transactions, there are many efforts on fraud detection methods and advanced application systems in order to improve the accuracy and ease of fraud detection. As a case of fraud detection, this study aims to provide effective fraud detection methods for auction exception agricultural products in the largest Korean agricultural wholesale market. Auction exception products policy exists to complement auction-based trades in agricultural wholesale market. That is, most trades on agricultural products are performed by auction; however, specific products are assigned as auction exception products when total volumes of products are relatively small, the number of wholesalers is small, or there are difficulties for wholesalers to purchase the products. However, auction exception products policy makes several problems on fairness and transparency of transaction, which requires help of fraud detection. In this study, to generate fraud detection rules, real huge agricultural products trade transaction data from 2008 to 2010 in the market are analyzed, which increase more than 1 million transactions and 1 billion US dollar in transaction volume. Agricultural transaction data has unique characteristics such as frequent changes in supply volumes and turbulent time-dependent changes in price. Since this was the first trial to identify fraud transactions in this domain, there was no training data set for supervised learning. So, fraud detection rules are generated using outlier detection approach. We assume that outlier transactions have more possibility of fraud transactions than normal transactions. The outlier transactions are identified to compare daily average unit price, weekly average unit price, and quarterly average unit price of product items. Also quarterly averages unit price of product items of the specific wholesalers are used to identify outlier transactions. The reliability of generated fraud detection rules are confirmed by domain experts. To determine whether a transaction is fraudulent or not, normal distribution and normalized Z-value concept are applied. That is, a unit price of a transaction is transformed to Z-value to calculate the occurrence probability when we approximate the distribution of unit prices to normal distribution. The modified Z-value of the unit price in the transaction is used rather than using the original Z-value of it. The reason is that in the case of auction exception agricultural products, Z-values are influenced by outlier fraud transactions themselves because the number of wholesalers is small. The modified Z-values are called Self-Eliminated Z-scores because they are calculated excluding the unit price of the specific transaction which is subject to check whether it is fraud transaction or not. To show the usefulness of the proposed approach, a prototype of fraud transaction detection system is developed using Delphi. The system consists of five main menus and related submenus. First functionalities of the system is to import transaction databases. Next important functions are to set up fraud detection parameters. By changing fraud detection parameters, system users can control the number of potential fraud transactions. Execution functions provide fraud detection results which are found based on fraud detection parameters. The potential fraud transactions can be viewed on screen or exported as files. The study is an initial trial to identify fraud transactions in Auction Exception Agricultural Products. There are still many remained research topics of the issue. First, the scope of analysis data was limited due to the availability of data. It is necessary to include more data on transactions, wholesalers, and producers to detect fraud transactions more accurately. Next, we need to extend the scope of fraud transaction detection to fishery products. Also there are many possibilities to apply different data mining techniques for fraud detection. For example, time series approach is a potential technique to apply the problem. Even though outlier transactions are detected based on unit prices of transactions, however it is possible to derive fraud detection rules based on transaction volumes.

• The Journal of Korean Society for Radiation Therapy
• /
• v.28 no.2
• /
• pp.179-186
• /
• 2016

Purpose : To figure out if the treatment plan for rectum, bladder and prostate that have a lot of interfraction errors satisfies dosimetric limits without adaptive plan by analyzing MR image. Materials and Methods : This study was based on 5 prostate cancer patients who had IMRT(total dose: 70Gy) Using ViewRay MRIdian System(ViewRay, ViewRay Inc., Cleveland, OH, USA) The treatment plans were made on the same CT images to compare with the plan quality according to adaptive plan, and the Eclipse(Ver 10.0.42, Varian, USA) was used. After registrate the 5 treatment MR images to the CT images for treatment plan to analyze the interfraction changes of organ, we measured the dose volume histogram and the changes of the absolute volume for each organ by appling the first treatment plan to each image. Over 5 fractions, the total dose for PTV was $V_{36.25}$ Gy $${\geq_-}$$ 95%. To confirm that the prescription dose satisfies the SBRT dose limit for prostate, we measured $V_{100%}$, $V_{95%}$, $V_{90%}$ for CTV and $V_{100%}$, $V_{90%}$, $V_{80%}$ $V_{50%}$ of rectum and bladder. Results : All dose average value of CTV, rectum and bladder satisfied dose limit, but there was a case that exceeded dose limit more than one after analyzing the each image of treatment. After measuring the changes of absolute volume comparing the MR image of the first treatment plan with the one of the interfraction treatment, the difference values were maximum 1.72 times at rectum and maximum 2.0 times at bladder. In case of rectum, the expected values were planned under the dose limit, on average, $V_{100%}=0.32%$, $V_{90%}=3.33%$, $V_{80%}=7.71%$, $V_{50%}=23.55%$ in the first treatment plan. In case of rectum, the average of absolute volume in first plan was 117.9 cc. However, the average of really treated volume was 79.2 cc. In case of CTV, the 100% prescription dose area didn't satisfy even though the margin for PTV was 5 mm because of the variation of rectal and bladder volume. Conclusion : There was no case that the value from average of five fractions is over the dosimetric limits. However, dosimetric errors of rectum and bladder in each fraction was significant. Therefore, the precise delivery is needed in case of prostate SBRT. The real-time tracking and adaptive plan is necessary to meet the precision delivery.

• The Journal of Korean Society for Radiation Therapy
• /
• v.22 no.2
• /
• pp.97-103
• /
• 2010

Purpose: Treating same region with different modalities there is a limit to evaluate the total absorbed dose of normal tissues. The reason is that it does not support to communication each modalities yet. In this article, it evaluates absorbed dose of the patients who had been treated same region by a tomotherapy and a linear accelerator. Materials and Methods: After reconstructing anatomic structure with a anthropomorphic phantom, administrate 45 Gy to a tumor in linac plan system as well as prescribe 15 Gy in tomotherapy plan system for make an ideal treatment plan. After the plan which made by tomoplan system transfers to the oncentra plan system for reproduce plan under the same condition and realize total treatment plan with summation 45 Gy linac treatment plan. To evaluate the absorbed dose of two different modalities, do a comparative study both a simple summation dose values and integration dose values. Then compare and analyze absorbed dose of normal tissues and a tumor with the patients who had been exposured radiation by above two differents modalities. Results: The result of compared data, in case of minimum dose, there are big different dose values in spleen (12.4%). On the other hand, in case of the maximum dose, it reports big different in a small bowel (10.2%) and a cord (5.8%) in head & neck cancer patients, there presents that oral (20.3%), right lens (7.7%) in minimum dose value. About maximum dose, it represents that spinal (22.5), brain stem (12%), optic chiasm (8.9%), Rt lens (11.5%), mandible (8.1%), pituitary gland (6.2%). In case of Rt abdominal cancer patients, there represents big different minimum dose as Lt kidney (20.3%), stomach (8.1%) about pelvic cancer patients, it reports there are big different in minimum dose as a bladder (15.2%) as well as big different value in maximum dose as a small bowel (5.6%), a bladder (5.5%) in addition, making treatment plan it is able us to get. Conclusion: In case of comparing both simple summation absorbed dose and integration absorbed dose, the minimum dose are represented higher as well as the maximum dose come out lower and the average dose are revealed similar with our expected values data. It is able to evaluate tumor & normal tissue absorbed dose which could had been not realized by treatment plan system. The DVH of interesting region are prescribed lower dose than expected. From now on, it needs to develop the new modality which are able to realize exact dose distribution as well as integration absorbed dose evaluation in same treatment region with different modalities.

• Clinical and Experimental Pediatrics
• /
• v.45 no.5
• /
• pp.596-602
• /
• 2002

Purpose : The purpose of this study was to analyze the association of peripheral neutrophil count with the development of respiratory failure in preterm infants. Methods : A retrospective study was conducted from January 1993 to December 1999 on 44 preterm infants, who were admitted to the neonatal intensive care unit of St. Francisco hospital. Preterm infants(birth weight 500 to 1,350 gm) who had a complete blood count obtained within 2 hours after delivery. Patients in the lowest of neutrophil count(early neutropenia, < $1.0{\times}10^9/L$) were compared with patients in the remaining group. Results : Low neutrophil count were transient in early neutropenia group. The concentration the circulating neutrophil count rose from $0.85{\pm}0.11{\times}10^9/L$ at average of 2 hours after delivery to $5.3{\pm}2.7{\times}10^9/L$ at 24 hours after delivery in the early neutropenia group and from $3.6{\pm}1.6{\times}10^9/L$ to $5.8{\pm}3.2{\times}10^9/L$ in the non-neutropenia group during the same time period. Compare to the non-neutropenia group, the neutropenia group had a lower birth weight($1,046.50{\pm}180.76gm$ Vs $1,156.70{\pm}124.99gm$), a lower Apgar score(1 min : $3.41{\pm}1.18$ Vs $4.30{\pm}1.46$, 5 min : $5.41{\pm}0.87$ Vs $6.15{\pm}0.95$), and a higher incidence of bronchopulmonary dysplasia(27.27% Vs 7.0%). Patients who had early neutropenia were more likely to require mechanical ventilation, supplemental oxygen and hospital stay. Also, main effect factors for the two groups were birth weight(Odds ratio=5.457, 95% CI=1.551-27.525), initial peripheral blood white cells(odds ratio=8.308, 95% CI=2.054-52.699), and bronchopulmonary dysplasia(odds ratio=0.099, 95% CI=0.017-0.397). Conclusion : A low count of neutrophil in the systemic circulation of premature infants within 2 hours of birth is associated with more severe respiratory distress.