• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.18
• /
• pp.124-155
• /
• 1975

To obtain the fundamental informations on the varietal improvement of peanut and to study the ecological variations of the important agronomic traits and to the relationship between the traits studied, an investigation was made on varietal classification of 489 introduced on the basis of their morphological and ecological differences at Crop Experiment Station, Suweon in 1968, and the other study conducted at some location as above in 1969 was to investigate the ecological variations of the materials in accordance with changes of seeding date using classified varietal group under 5 different seeding times from April 16 to July 7 with twenty days interval. The results obtained were summarized as follows: 1. Peanut varieties tested were classified into Spanish, Virginia Erect, Virginia Runner, Southeast Runner. Valencia and Semirunner, on the basis of plant type, flowering time, number of grains per pod and grain size. 2. Characteristics of varietal group classified are as followings. (1) Spanish; erect, small grained and early maturing type. (2) Virginia Erect; erect, large grained and late flowering type. (3) Virginia Runner; runner, large grained and late maturing type. (4) Southeast Runner; runner, small grained and early maturing type. (5) Valencia; erect, small grained and early flowering type with 3-4 grains per pod. (6) Semi runner; semirunner, large grained and late flowering type. 3. Flowering period in respective varietal group was consistently shorted by delayed seeding date and the degree of shortening was more serious in late flowering varietal group. 4. Number of branches per plant was generally decreased in late seeding date in respective group. However, Spanish and Virginia Runner exhibited lower number of branches in the first seeding rather than the second seeding and the lowest number of branches was found in Spanish while the highest were Virginia Erect in all seeding date. 5. Shelling ratio was high in Spanish and Southeast Runner in any seeding date and decreased remarkedly by seeding after May. 6. Number of pod per plant in all varietal groups was remarkedly decreased by delayed seeding date and the degree of decreasing was more serious in large grain varietal group. 7. The higher pod weight per plant was found in second seeding date rather than first seeding and pod weight per plant was decreased obviously in all late seeding after the second. Therefore, among the cultivars tested, Southeast Runner noted the highest pod weight per plant while Virginia Runner showed the lowest. 8. Grain number per plant expressed the similar tendency as the pod weight per plant but was low in large grain group and high in small grain group in all seeding date employed. 9. 100 grain weight was heaviest in second seeding and was decreased remarkedly after the second and even the first seeding date. 10. Yield per 10a noted considerable variations in accordance with seeding date in all groups classified. However, the yield was increased in second seeding date (May 7) and decreased in the others. 11. Length of main stem and branches were exceptionally decreased in the first seeding date compare to the second in Spanish while other varieties were tend to be same between the indicated seeding date, but. these two traits were strikingly decreased in all seeding after the second. This tendency, however, strongly suggested the importance of environmental effects on peanut growth in terms of their changes due to the different seeding date. 12. Highly significant positive correlations were showed between yield and yield componets such as pod weight per plant, 100 grain weight and the number of grains per plant in all varietal groups except, Virginia Runner. However, the other characters were almost not correlated with yield and differences in correlation coefficients among the seeding dates were found. 13. Path coefficients estimated for yield components to yield was higher in number of grains per plant pod weight per plant and 100 grain weight in terms of direct effect and the other components were negligible in all varietal groups. 14. Heritabilities estimated were generally high in pod number per plant, shelling ratio, 100 grain weights and number of grains per pod and the other traits were relatively low.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.14 no.2
• /
• pp.159-165
• /
• 2010

Purpose: Positron emission tomography scan has been growing diagnostic equipment in the development of medical imaging system. Compare to $^{99m}Tc$ emitting 140 keV, Positron emission radionuclide emits 511 keV gamma rays. Because of this high energy, it needs to reduce radioactive emitting from patients for radiotechnologist. We searched the external dose rates by changing distance from patients and measure the external dose rates when we used shielder investigate change external dose rates. In this study, the external dose distribution were analyzed in order to help managing radiation protection of radiotechnologists. Materials and Methods: Ten patients were searched (mean age: $47.7{\pm}6.6$, mean height: $165.5{\pm}3.8$ cm and mean weight: $65.9{\pm}1.4$ kg). Radiation were measured on the location of head, chest, abdomen, knees and toes at the distance of 10, 50, 100, 150 and 200 cm. Then, all the procedure was given with a portable radiation shielding on the location of head, chest and abdomen at the distance of 100, 150 and 200 cm and transmittance was calculated. Results: In 10 cm, head (105.40 ${\mu}Sv/h$) was the highest and foot (15.85 ${\mu}Sv/h$) was the lowest. In 200 cm, head, chest and abdomen showed similar. On head, the measured dose rates were 9.56 ${\mu}Sv/h$, 5.23 ${\mu}Sv/h$, and 3.40 ${\mu}Sv/h$ in 100, 150 and 200 cm respectively. When using shielder, it shows 2.24 ${\mu}Sv/h$, 1.67 ${\mu}Sv/h$, and 1.27 ${\mu}Sv/h$ in 100, 150 and 200 cm on head. On chest, the measured dose rates were 8.54 ${\mu}Sv/h$, 4.90 ${\mu}Sv/h$, 3.44 ${\mu}Sv/h$ in 100, 150 and 200 cm, respectively. When using shielder, it shows 2.27 ${\mu}Sv/h$, 1.34 ${\mu}Sv/h$, and 1.13 ${\mu}Sv/h$ in 100, 150 and 200 cm on chest. On abdomen, the measured dose rates were 9.83 ${\mu}Sv/h$, 5.15 ${\mu}Sv/h$ and 3.18 ${\mu}Sv/h$ in 100, 150 and 200cm respectively. When using shielder, it shows 2.60 ${\mu}Sv/h$, 1.75 ${\mu}Sv/h$ and 1.23 ${\mu}Sv/h$ in 100, 150 and 200 cm on abdomen. Transmittance was increased as the distance was expanded. Conclusion: As the distance was further, the radiation dose were reduced. When using shielder, the dose were reduced as one-forth of without shielder. The Radio technologists are exposed of radioactivity and there were limitations on reducing the distance with Therefore, the proper shielding will be able to decrease radiation dose to the radiotechnologists.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.20 no.2
• /
• pp.14-20
• /
• 2016

Purpose Tongue cancer is 1.8% of all cancer tumors occur in the tongue, it is known that the high incidence enough to account for 75% of oral cancer conducted a PET / CT examination for early diagnosis, metastasis, staging, etc. and. Tongue when PET / CT scan of a cancer patient and a Torso taken to close mouth lesions if the condition was caused due to the overlapping or corresponding artifacts are not clearly observed. The purpose of this study is to evaluate the changes that occur during PET / CT scan with open mouth and its usefulness under. Materials and Methods From June 2015 to March 2016 complained of herein by May 21 had received a diagnosis of tongue cancer underwent PET / CT scan patients were treated with a target (16 males, 5 female). The first was taken to close mouth Torso state, it was taken to add 1 bed open mouth condition. Tumor (T), measuring the Normal Tongue (NT), Lymph Node (LN) standard intake coefficient by setting a region of interest in the (standardized uptake value, SUV) SUVmean, the average value was measured SUVmax, drawn to each region of interest 3 times and Background (Carotid artery) was out of the SUV. In Chapter 3 of the slice to the tumor clearly visible by setting the region of interest to measure the change Tumor size was calculated average value. Gross Image resolution assessment were analyzed statistically through were divided into 1-5 points by the Radiation 7 people in 2, more than five years worked in specialized nuclear medicine compare to proceed with the blind test nonparametric test (wilcoxon signed rank test). (SPSS ver.18) Results $SUV_{mean}$ T's were in close mouth $5.01{\pm}2.70$ with open mouth $5.48{\pm}2.88$ (P<0.05), $SUV_{max}$ were respectively $8.78{\pm}5.55$ and $9.70{\pm}5.99$ (P<0.05). $SUV_{mean}$ in the NT were respectively $0.43{\pm}0.30$ and $0.34{\pm}0.24$ (P=0.20), $SUV_{max}$ was $0.56{\pm}0.34$ and $0.45{\pm}0.25$ (P=0.204). LN $SUV_{mean}$ were respectively $1.62{\pm}1.43$ and $1.69{\pm}1.49$ (P=0.161), $SUV_{mean}$ was $2.09{\pm}1.88$ and $1.99{\pm}1.74$ (P=0.131). Tumor size change is close mouth $4.96{\pm}4.66cm^2$ $5.33{\pm}4.64cm^2$ with 7.45% increase was (P<0.05), gross image resolution evaluation is $2.87{\pm}0.73$, $3.77{\pm}0.68$ with open mouth examinations 30.5% increase was (P<0.05). Conclusion Tumor SUV on the changes that had an increase in open mouth during inspection, the normal tongue and lymph node, but there was no significant difference in the change slightly. It is also one open mouth PET / CT scan will provide improved image to all patients with tongue cancer, but it could be confirmed that similar overall through the blind test, or tumor size changes and showing a high resolution image. It can be the perfect alternative method for problems that occur when the close mouth Open mouth PET / CT scan, but is believed to be through the open mouth to observe the boundary of overlapping or tumor of the oral cavity other structures a little more clearly. Tongue cancer patients how to recommend that the shooting further open mouth PET / CT.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.18 no.1
• /
• pp.40-46
• /
• 2013

The isotope ratios of $^{13}C/^{12}C$ and $^{18}O/^{16}O$ for a sample in a mass spectrometer are measured relative to those of a pure $CO_2$ reference gas (i.e., laboratory working standard). Thus, the calibration of a laboratory working standard gas to the international isotope scales (Pee Dee Belemnite (PDB) for ${\delta}^{13}C$ and Vienna Standard Mean Ocean Water (V-SMOW) for ${\delta}^{18}O$) is essential for comparisons between data sets obtained by other groups on other mass spectrometers. However, one often finds difficulties in getting well-calibrated standard gases, because of their production time and high price. Additional difficulty is that fractionation processes can occur inside the gas cylinder most likely due to pressure drop in long-term use. Therefore, studies on laboratory production of pure $CO_2$ isotope standard gas from stable solid calcium carbonate standard materials, have been performed. For this study, we propose a method to extract pure $CO_2$ gas without isotope fractionation from a solid calcium carbonate material. The method is similar to that suggested by Coplen et al., (1983), but is better optimized particularly to make a large amount of pure $CO_2$ gas from calcium carbonate material. The $CaCO_3$ releases $CO_2$ in reaction with 100% pure phosphoric acid at $25^{\circ}C$ in a custom designed, evacuated reaction vessel. Here we introduce optimal procedure, reaction conditions, and samples/reactants size for calcium carbonate-phosphoric acid reaction and also provide the details for extracting, purifying and collecting $CO_2$ gas out of the reaction vessel. The measurements for ${\delta}^{18}O$ and ${\delta}^{13}C$ of $CO_2$ were performed at Seoul National University using a stable isotope ratio mass spectrometer (VG Isotech, SIRA Series II) operated in dual-inlet mode. The entire analysis precisions for ${\delta}^{18}O$ and ${\delta}^{13}C$ were evaluated based on the standard deviations of multiple measurements on 15 separate samples of purified $CO_2$. The pure $CO_2$ samples were taken from 100-mg aliquots of a solid calcium carbonate (Solenhofen-ori $CaCO_3$) during 8-day experimental period. The multiple measurements yielded the $1{\sigma}$ precisions of ${\pm}0.01$‰ for ${\delta}^{13}C$ and ${\pm}0.05$‰ for ${\delta}^{18}O$, comparable to the internal instrumental precisions of SIRA. Therefore, we conclude the method proposed in this study can serve as a way to produce an accurate secondary and/or laboratory $CO_2$ standard gas. We hope this study helps resolve difficulties in placing a laboratory working standard onto the international isotope scales and does make accurate comparisons with other data sets from other groups.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.13 no.3
• /
• pp.56-60
• /
• 2009

Purpose: The various studies and efforts to develop program are in progress in the field of nuclear medicine for the purpose of reducing scan time. The Oncoflash is one of the programs used in whole body bone scan which allows to maintain the image quality while to reduce scan time. When Those applications are used in clinical setting, both the image quality and reduction of scan time should be considered, therefore, the purpose of this study was to determine the criteria for proper scan speed. Materials and Methods: The subjects of this study were the patients who underwent whole body bone scan at the departments of nuclear medicine in the Asan Medical Center located in Seoul from 1st to 10th, July, 2008. The whole body bone images obtained in the scan speed of 30cm/min were classified by the total counts into under 800 K, and over 800 K, 900 K, 1,000 K, 1,500 K, and 2,000 K. The image quality were assessed qualitatively and the percentages of those of 1,000K and under of total counts were calculated. The FWHM before and after applying the Oncoflash were analyzed using images obtained in $^{99m}Tc$ Flood and 4-Quadrant bar phantom in order to compare the resolution according to the amount of total counts by the application of the Oncoflash. Considering the counts of the whole body bone scan, the dosed 2~5 mCi were used. 152 patients underwent the measurement in which the counts of Patient Postioning Monitor (PPM) were measured with including head and the parts of chest which the starting point of whole body bone scan from 7th to 26th, August, 2008. The correlations with total counts obtained in the scan speed of 30cm/min among them were analyzed (The exclusion criteria were after over six hours of applying isotopes or low amount of doses). Results: The percentage of the whole body bone image which has the geometric average of total counts of under 1,000K among them obtained in the scan speed of 30cm/min were 17.6%(n=58) of 329 patients. The qualitative analysis of the image groups according to the whole body counts showed that the images of under 1,000K were assessed to have coarse particles and increased noises. The analysis on the FWHM of the images before and after applying the Oncoflash showed that, in the case of PPM counts of under 3.6 K, FWHM values after applying the Oncoflash were higher than that before applying the Oncoflash, whereas, in the case of that of over 3.6 K, the FWHM after applying the Oncoflash were not higher than that before applying the Oncoflash. The average of total counts at 2.5~3.0 K, 3.1~3.5 K, 3.6~4.0 k, 4.1~4.5 K, 4.6~5.0 K, 5.1~6.0 K, 6.1~7.0 K, and 7.1 K over (in PPM) were $965{\pm}173\;K$, $1084{\pm}154\;K$, $1242{\pm}186\;K$, $1359{\pm}170\;K$, $1405{\pm}184\;K$, $1640{\pm}376\;K$, $1,771{\pm}324\;K$, and $1,972{\pm}385\;K$, respectively and the correlations between the counts in PPM and the total counts of image obtained in the scan speed of 30 cm/min demonstrated strong correlation (r=.775, p<.01). Conclusions: In the case of PPM coefficient over 3.6 K, the image quality obtained in the scan speed of 30cm/min and after applying the Oncoflash was similar to that obtained in the scan speed of 15 cm/min. In the case of total counts over 1,000 K, it is expected to reduce scan time without any damage on the image quality. In the case of total counts under 1,000 K, however, the image quality were decreased even though the Oncoflash is applied, so it is recommended to perform the re-image in the scan speed of 15 cm/min.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.13 no.3
• /
• pp.17-23
• /
• 2009

Purpose: It has been known that PET/CT is very valuable in follow-up study of diffuse large B cell lymphoma (DLBCL). Generally, in DLBCL, radiotherapy and chemotherapy has been progressed, because the lesion hasn‘t been limited to one site. And, it has lead to the decrease of leukocyte like neutropenia, due to myelosuppression of chemotherapy. So, in that case, administration of Filgrastim (Granulocyte colony-stimulating factor; G-CSF) is universal. However, in short time after administration, PET/CT has limitation to offer accurate images, through the uptake of $^{18}F$-FDG is increased in the region that is activated bone marrow by hematopoietic growth. Therefore, the aim of this study is that PET/CT in a certain period of time after administration of Filgrastim is able to show normal degree of $^{18}F$-FDG uptake. Materials and Methods: 10 patients under follow-up study of diffuse large B cell lymphoma were examined in this study from January, 2007 to January, 2009 (Male: 4 persons; Female: 6 persons; The mean age: 53.8 years old; The mean weight: 57.3 Kg). Using PET/CT (Discovery STe; GE Healthcare, Milwaukee, WI, USA), whole body images were acquired in 1 hour after $^{18}F$-FDG injection. For image analysis, each ROI ($120\;mm^2$) was drawn on $C^6$ (the sixth C-spine), $L_4$ (the forth L-spine), liver, spleen, and lung, then SUV (Standard Uptake Value)s were measured. We compared with each uptake between in 1-day and 5~7 days after administration of Filgrastim at same patient, so confirmed significance about these by SPSS version 12. Results: In case of $C_6$, $L_4$, spleen, every SUV of 1 day later was remarkably higher than that of 5~7 days later, but liver and lung were similar. Also, the images acquired after 5~7 days distinct remarkably and show normal degree of $^{18}F$-FDG uptake, because uptake of bone was almost disappeared. Conclusions: In this study, each SUV was prominent difference as a period of time after Filgrastim’s administration. And Filgrastim makes concentrate uptake of $^{18}F$-FDG in bone, but, after 5~7 days, bone‘s uptake was greatly decreased. Therefore, we are able to infer a certain period of time that shows normal degree of uptake, by numerical value proven. Also, we consider that this study contribute to advanced study about the other agent like Pegfilgrastim, Lenograstim besides Filgrastim, afterwards.

• Investigative Magnetic Resonance Imaging
• /
• v.8 no.1
• /
• pp.32-41
• /
• 2004

Purpose : To measure the NMR relaxation properties of MnPC, to observe the characteristics of liver enhancement patterns on MR images in experimentally implanted rabbit VX2 tumor model, and to estimate the possibility of tissue specific contrast agent for MnPC in comparison with the hepatobiliary agent. Materials and Methods : Phthalocyanine (PC) was chelated with paramagnetic ions, manganese (Mn). 2.01 g (5.2 mmol) of phthalocyanine was mixed with 0.37 g (1.4 nlmol) of Mn chloride at $310^{\circ}C$ for 36 hours and then purified by chromatography ($CHCl_3:\;CH_3OH=98:2$, volume ratio) to obtain 1.04 g $(46\%)$ of MnPC (molecular weight = 2000 daltons). The T1/T2 relaxivity (R1/R2) for MnPC were determined at a 1.5 T (64 MHz) MR spectrometer. VX2 tumor model was experimentally implanted in the liver parenchyma of rabbits. All MR studies were performed on 1.5 T. The human extremity radio frequency coil of a bird cage type was employed. MR images were acquired at 17 to 24 days after VX2 carcinoma implantation.4 mmol/kg MnPC and 0.01 mmol/kg Mn-DPDP were injected via the ear vein of rabbits. T1-weighted images were obtained with spin-echo (TR/TE=516/14 msec) and fast multiplanar spoiled gradient recalled (TR/TE : 80/4 msec, $60^{\circ}$ flip angle) pulse sequence. Fast spin-echo (TR/TE=1200/85 msec) was used to obtain the T2-weighted images. Results : The value of T1/T2 relaxivity (R1/R2) of MnPC was $7.28\;mM^{-1}S^{-1}$ and $55.56\;mM^{-1}S^{-1}$ respectively at 1.5 T (64 MHz). Because the T2 relaxivity of MnPC that bonded strongly, covalently manganese with phthalocyanine was very high, the signal intensity of liver parenchyma was decreased on postcontrast T2-weighted images and we could easily distinguish the VX2 carcinoma within the liver parenchyma. When MnPC was administrated intravenously, the tumor margin delineation was more remarkable than Mn-DPDP-enhanced images. The enhancement of liver parenchyma with MnPC persisted at relatively high levels over at least one hour after injection of the contrast agents. Conclusion : The hepatic uptake and biliary excretion of MnPC, which are similar to Mn-DPDP, suggest that this agent is a new liver-specific agent. Also, MnPC seems to be used as a dual contrast agent (T1 and T2) with high T2 relaxivity. However, it is warranted that MnPC needs further investigation as a potential contrast agent for MR imaging of the liver. That is, further characterizations of MnPC are needed in vivo and in vitro before clinical trials. The diagnostic potential of MnPC will also have to be examined more in the animal models of additional types.

• The Journal of Korean Society for Radiation Therapy
• /
• v.25 no.1
• /
• pp.1-8
• /
• 2013

Purpose: A selection of proper energy in treatment planning is very important because of having different dose distribution in body as photon energy. In generally, the low energy photon has been used in intensity-modulated radiation therapy (IMRT) for head and neck (H&N) cancer. The aim of this study was to evaluate the effect of partially used high energy photon at posterior oblique fields on IMRT plan for H&N cancer. Materials and Methods: The study was carried out on 10 patients (nasopharyngeal cancer 5, tonsilar cancer 5) treated with IMRT in Seoul National University Bundang Hospital. CT images were acquired 3 mm of thickness in the same condition and the treatment plan was performed by Eclipse (Ver.7.1, Varian, Palo Alto, USA). Two plans were generated under same planing objectives, dose volume constraints, and eight fields setting: (1) The low energy plan (LEP) created using 6 MV beam alone, (2) the partially used high energy plan (PHEP) created partially using 15 MV beam at two posterior oblique fields with deeper penetration depths, while 6 MV beam was used at the rest of fields. The plans for LEP and PHEP were compared in terms of coverage, conformity index (CI) and homogeneity index (HI) for planning target volume (PTV). For organs at risk (OARs), $D_{mean}$ and $D_{50%}$ were analyzed on both parotid glands and $D_{max}$, $D_{1%}$ for spinal cord were analyzed. Integral dose (ID) and total monitor unit (MU) were compared as addition parameters. For the comparing dose to normal tissue of posterior neck, the posterior-normal tissue volume (P-NTV) was set on the patients respectively. The $D_{mean}$, $V_{20Gy}$ and $V_{25Gy}$ for P-NTV were evaluated by using dose volume histogram (DVH). Results: The dose distributions were similar with regard to coverage, CI and HI for PTV between the LEP and PHEP. No evident difference was observed in the spinal cord. However, the $D_{mean}$, $D_{50%}$ for both parotid gland were slightly reduced by 0.6%, 0.7% in PHEP. The ID was reduced by 1.1% in PHEP, and total MU for PHEP was 1.8% lower than that for LEP. In the P-NTV, the $D_{mean}$, $V_{20Gy}$ and $V_{25Gy}$ of the PHEP were 1.6%, 1.8% and 2.9% lower than those of LEP. Conclusion: Dose to some OARs and a normal tissue, total monitor unit were reduced in IMRT plan with partially used high energy photon. Although these reduction are unclear how have a clinical benefit to patient, application of the partially used high energy photon could improve the overall plan quality of IMRT for head and neck cancer.

• Applied Biological Chemistry
• /
• v.13 no.2
• /
• pp.153-170
• /
• 1970

1. Isolation and identification of amylase-producing bacteria. The powerful strain A-12 and S-8 were respectively isolated from air and soil after screening a large number of amylase-producing bacteria. Their bacterial characteristics have been investigated and it has been found that all characteristics of strain A-12 and S-8 are similar to Bac. subtilis of Bergey's manual except for the acid formation from a few carbohydrates and the citrate utilization, i.e., the strain A-12 shows negative in the citrate utilization, and the acid formation from arabinose and xylose, S-8 shows negative in the acid formation from xylose. 2. Amylase production by Liquid cultures with solid materials. Several conditions for amylase production by strain A-12 in stationary cultures have been studied. The results obtained are as follows. (1) The optimum conditions are:temperature $35^{\circ}C$, initial pH 6.5 to 7.0 and incubation time 3 to 4 days. (2) The amylase production is not affected by the preservation period of the stock cultures. (3) Among the various solid material, the defatted soy bean is found to be the best for t1e amylase production. However, the alkali treatment of the defatted soy bean gives no effect contrary to the cage of defatted rape seed. The addition of soluble starch to the alkali extract of defatted soy bean shows the increased amylase production. (4) Up to 1% addition of ethanol to carbon dificient media gives the improved amylase production, whereas the above effect is not found in the case of carbon rich media. (5) The amylase production can be increased 2.5 times when 10% of defatted soy bean is admixed to cheaply available wheat bran. (6) The excellent effect is found for amylase production when 20% of wheat bran is admixed to defatted dry milk which is a poor medium. The activity is found to be $D^{40^{\circ}}_{30'}$ 7,000(L.S.V. 1,800) in 10% medium. (7) No significant effect is observed due to the addition of various inorganic salts. 3. Amylase production by solid cultures. Several conditions for amylase production by strain A-12 in wheat bran cultures have been studied and the results obtained are as follows. (1) The optimum conditions: are temperature $33^{\circ}C$, incubation lime 2 days, water content added 150 to 175% and the thickness of the medium 1.5cm, The activity is found to be $D^{40^{\circ}}_{30'}$ 36,000(L.S.V. 15,000) (2) No significant effect is found in the case of the additions of various organic and inorganic substances.

• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.1-19
• /
• 2018

Large amount of data is now available for research and business sectors to extract knowledge from it. This data can be in the form of unstructured data such as audio, text, and image data and can be analyzed by deep learning methodology. Deep learning is now widely used for various estimation, classification, and prediction problems. Especially, fashion business adopts deep learning techniques for apparel recognition, apparel search and retrieval engine, and automatic product recommendation. The core model of these applications is the image classification using Convolutional Neural Networks (CNN). CNN is made up of neurons which learn parameters such as weights while inputs come through and reach outputs. CNN has layer structure which is best suited for image classification as it is comprised of convolutional layer for generating feature maps, pooling layer for reducing the dimensionality of feature maps, and fully-connected layer for classifying the extracted features. However, most of the classification models have been trained using online product image, which is taken under controlled situation such as apparel image itself or professional model wearing apparel. This image may not be an effective way to train the classification model considering the situation when one might want to classify street fashion image or walking image, which is taken in uncontrolled situation and involves people's movement and unexpected pose. Therefore, we propose to train the model with runway apparel image dataset which captures mobility. This will allow the classification model to be trained with far more variable data and enhance the adaptation with diverse query image. To achieve both convergence and generalization of the model, we apply Transfer Learning on our training network. As Transfer Learning in CNN is composed of pre-training and fine-tuning stages, we divide the training step into two. First, we pre-train our architecture with large-scale dataset, ImageNet dataset, which consists of 1.2 million images with 1000 categories including animals, plants, activities, materials, instrumentations, scenes, and foods. We use GoogLeNet for our main architecture as it has achieved great accuracy with efficiency in ImageNet Large Scale Visual Recognition Challenge (ILSVRC). Second, we fine-tune the network with our own runway image dataset. For the runway image dataset, we could not find any previously and publicly made dataset, so we collect the dataset from Google Image Search attaining 2426 images of 32 major fashion brands including Anna Molinari, Balenciaga, Balmain, Brioni, Burberry, Celine, Chanel, Chloe, Christian Dior, Cividini, Dolce and Gabbana, Emilio Pucci, Ermenegildo, Fendi, Giuliana Teso, Gucci, Issey Miyake, Kenzo, Leonard, Louis Vuitton, Marc Jacobs, Marni, Max Mara, Missoni, Moschino, Ralph Lauren, Roberto Cavalli, Sonia Rykiel, Stella McCartney, Valentino, Versace, and Yve Saint Laurent. We perform 10-folded experiments to consider the random generation of training data, and our proposed model has achieved accuracy of 67.2% on final test. Our research suggests several advantages over previous related studies as to our best knowledge, there haven't been any previous studies which trained the network for apparel image classification based on runway image dataset. We suggest the idea of training model with image capturing all the possible postures, which is denoted as mobility, by using our own runway apparel image dataset. Moreover, by applying Transfer Learning and using checkpoint and parameters provided by Tensorflow Slim, we could save time spent on training the classification model as taking 6 minutes per experiment to train the classifier. This model can be used in many business applications where the query image can be runway image, product image, or street fashion image. To be specific, runway query image can be used for mobile application service during fashion week to facilitate brand search, street style query image can be classified during fashion editorial task to classify and label the brand or style, and website query image can be processed by e-commerce multi-complex service providing item information or recommending similar item.