• Journal of Korean Neurosurgical Society
• /
• v.62 no.4
• /
• pp.442-449
• /
• 2019

Objective : Bone mineral density (BMD) is an important consideration during fusion surgery. Although dual X-ray absorptiometry is considered as the gold standard for assessing BMD, quantitative computed tomography (QCT) provides more accurate data in spine osteoporosis. However, QCT has the disadvantage of additional radiation hazard and cost. The present study was to demonstrate the utility of artificial intelligence and machine learning algorithm for assessing osteoporosis using Hounsfield units (HU) of preoperative lumbar CT coupling with data of QCT. Methods : We reviewed 70 patients undergoing both QCT and conventional lumbar CT for spine surgery. The T-scores of 198 lumbar vertebra was assessed in QCT and the HU of vertebral body at the same level were measured in conventional CT by the picture archiving and communication system (PACS) system. A multiple regression algorithm was applied to predict the T-score using three independent variables (age, sex, and HU of vertebral body on conventional CT) coupling with T-score of QCT. Next, a logistic regression algorithm was applied to predict osteoporotic or non-osteoporotic vertebra. The Tensor flow and Python were used as the machine learning tools. The Tensor flow user interface developed in our institute was used for easy code generation. Results : The predictive model with multiple regression algorithm estimated similar T-scores with data of QCT. HU demonstrates the similar results as QCT without the discordance in only one non-osteoporotic vertebra that indicated osteoporosis. From the training set, the predictive model classified the lumbar vertebra into two groups (osteoporotic vs. non-osteoporotic spine) with 88.0% accuracy. In a test set of 40 vertebrae, classification accuracy was 92.5% when the learning rate was 0.0001 (precision, 0.939; recall, 0.969; F1 score, 0.954; area under the curve, 0.900). Conclusion : This study is a simple machine learning model applicable in the spine research field. The machine learning model can predict the T-score and osteoporotic vertebrae solely by measuring the HU of conventional CT, and this would help spine surgeons not to under-estimate the osteoporotic spine preoperatively. If applied to a bigger data set, we believe the predictive accuracy of our model will further increase. We propose that machine learning is an important modality of the medical research field.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.5
• /
• pp.193-204
• /
• 2019

The explosion of data due to the improvement of sensor technology and computing performance has become the basis for analyzing the situation in the industrial fields, and various attempts to detect events based on such data are increasing recently. In particular, sound signals collected from sensors are used as important information to classify events in various application fields as an advantage of efficiently collecting field information at a relatively low cost. However, the performance of sound-event classification in the field cannot be guaranteed if noise can not be removed. That is, in order to implement a system that can be practically applied, robust performance should be guaranteed even in various noise conditions. In this study, we propose a system that can classify the sound event after generating the enhanced sound signal based on the deep learning algorithm. Especially, to remove noise from the sound signal itself, the enhanced sound data against the noise is generated using SEGAN applied to the GAN with a VAE technique. Then, an end-to-end based sound-event classification system is designed to classify the sound events using the enhanced sound signal as input data of CNN structure without a data conversion process. The performance of the proposed method was verified experimentally using sound data obtained from the industrial field, and the f1 score of 99.29% (railway industry) and 97.80% (livestock industry) was confirmed.

• Korean journal of applied entomology
• /
• v.4
• /
• pp.39-46
• /
• 1965

The author studied on the bionomics of Oriental moth. Cnidocampa flavescens WALKER, damaging to the persimmon tree n the southern part of Korea from 1964 to 1965. The results can be summarized as follows; 1. Emergence peak period of Oriental moth was mid-June in Taegu district and eggs are deposited on the opposite side of persimmon tree leaf. Specially most of eggs are deposited on the terminal part of opposite side and peak period s also mid-June. 2. Hatched Percentage of eggs was $84.4\%$ in 1964 while $96.1\%$ in 1965 at the rearing room. Mean egg Period was $5.984\pm0.162$ in 1964 while $6.262\pm0.094$ days in 1965. Thus during two years, the egg period was about 6 days. 3. In the growth ratio of Oriental moth fed on various host plants persimmon tree, Acer negund, Hazel-wood and Platanus, the best growth ratio was shown on the leaf of Hazel-wood from 1st till 3rd instar, but, on the contrary, persimmon tree was the best from 4th till the last instar. The growth ratio of head width was also the same tendency as the body length above mentioned. Individuals fed on the leaf of platanus were dead after 20 days. 4. Oriental moth has one generation a year and molts 6 times. The first molting occurred in 5 hours after hatched, and the other moltings were done at f days intervals. After 3 days since the last molting, larvae made the non for over-winter in it. 5. As the bristles on the process of larval body are different from each position and instar, judgement of instars are possible by the counting of bristles on the body according to the Table 8. Specially the bristle of L. 2., D. 2, 3 ,8. 10. and L. 1, 3, 4, 5, 6, 7, are perfectly different from each instar. From these bristles, instars can be recognized easily. 6. Pupation of larvae in the over-wintered cocoon on the stem of persimmon tree was done in mid-May and continued will early June when emergence will take place. 7. Mean number of eggs in the ovary was $1325.5\pm2.7182$

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.3 no.2
• /
• pp.77-92
• /
• 1970

Ueda, in the course of his systematic work on the lavers, Porphyra, in Japan and Korea in 1932, mentioned that most of the cultivated Porphyra belong to Porphyra tenera Kjellman. Then he, dividing the species into two forms, f. typica and f. kjellmani, put Korean cultivated Porphyra under the latter. From the 1930s to the early 1940s, Fujikawa, Kaneko and others worked on Physiological experiments or cultivational experiments of Porphyra in the culture-bed, but there was no mention about the cultivated Porphyra species. However, many fishermen generally recognize that the characteristics of cultivated Porphyra vary depending on their habitat or the picking season, and it is considered that these differences are due to the varieties of the species which are well adaptable to various environments. Recently, I have become aware of the predominant occurrence of P. yezoensis Ueda in most culture-beds of Korea as in the Tokyo Bay or other places in Japan. At present, since artificial seeding for the cultivation of Porphyra with Conchocelis has been carried out and peculiar species can be cultured, a study of the species of cultivated Porphyra has become an important subject. I collected the specimens from a number of culture-beds which are located in the legions shown in fig. 1 from January, 1968 to May, 1970 and found that there are five species, P. tenera Kjellman, P. yezoensis Ueda, P. kuniedai Kurogi, P. seriata Kjellman and P. suborbiculata Kjellman. Among them, P. kuniedai was treated as a round-type, a form of P. tenera, by Kunieda (1939) and Tanaka (1952) and the occurrence of this form is generally recognized by most fishermen. At present, as mentioned above, the most dominant species of cultivated Porphyra is P. yezoensis but the cultivation of P. tenera is restricted to certain culture-beds or the early half of the cultivation period. P. kunieda appears as a mixed species throughout most of the culture-beds, particulary in the later half of the period, while when it was picked in January it appeared dominantly in a place such as Gum-Dang where the 'Bal', splitted bamboo piece mat, was settled during the last of September. This is the first seeding process. The latter two species, P. suborbiculata and P. seriata appear frequently but in small amounts in the later half of the period particulary in the western region of the southern coast. However, it can not be ascertained when P. yezoensis becomes predominant, because specimens have not been available up until recent years but the process can be described as follows: We commonly recognize the ecological characteristics of P. tenera as follows; First, the conchospores of the species develop earlier and the period of its discharge is shorter than those of P. yezoensis; second, the microscopical buds discharge neutral spores which develop into new buds directly and buds develop repeatedly through a short period. Consequently, according to such above ecological characteristics, the species can grow thick on the 'Bal' exclusively. However, buds may disappear when they are harmed by disease such a 'infection by certain parasites or by other unusual environmental conditions. Thus P. yezoensis are enabled to grow on the 'Bal' instead of the former species since they not only develop later than the former but also macroscopical fronds discharge the neutral spore throughout the period from October to May. Likewise, if any disease appears in the culture-bed ill the later half of the period, the former is more severely damaged than the latter because the former have less resistance to the disease than the latter. Thus fewer frond survive and fewer carpospores which are the origin of the next generation can be discharged. However the latter by their nature can continue growing until early summer. In the case of the culture-bed where the above phenomenon occurs repeatedly P. yezoensis gradually may become the dominant species among cultivated Porphyra. In support of the validity of this process we find that according to the description and the plate of Wada (1941), P. tenera, P. yezoensis and P. kuniedai grow together in the culture-bed at the mouth of the Nakdong River where P. yezoensis occurs predominantly and mixed with P. kuniedai.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.

• Korean Journal of Animal Reproduction
• /
• v.25 no.4
• /
• pp.339-347
• /
• 2001

Sperm-mediated DNA transfer has a potential to markedly simplify techniques for the generation of transgenic animals. The exogenous DNA transfer by intracytoplasmic sperm injection (ICSI) procedure has been recently introduced in the production of transgenic animals. In this study, the developmental competence and tile expression rates of transgene were investigated after injection of spermatozoon or sperm head with enhanced green fluorescent protein (EGFP) gene into the mature porcine oocytes. The porcine oocytes were injected with intact sperm, membrane-disrupted sperm or sperm head. After injection. embryos were cultured in NCSU23 medium up to the blastocyst stage, and the developmental competence and expression rates were studied. The developmental rate (67.0%) of sperm injection group was higher than that (59.7%) of sperm head injection group, and the rates of EGFP expression were also significantly different between sperm injection and sperm head injection groups (42.1 vs 20.0%) (F＜0.05). In the porcine oocytes injected with sperm treated with different methods of membrane disruption, the removal of sperm membrane did not alter the developmental competence of embryos. The rate of blastocysts at 7 days after injection with intact and membrane disrupted sperm were 15.0 and 14.2%, respectively. The EGFP expression rates, 38.4% in embryos injected with frozen-thawed sperm was higher than that, 22.4% of embryos injected with the Triton X-100 treated sperm. Prior to injection, sperm were cultured in different EGFP gene concentrations from 0.Ol to 1ng/u${mu}ell$. However, no significant difference in developmental rates of embryos among different concentrations of EGFP gene were observed. The highest expression rate of EGFP gene, 37.4% was obtained from the embryos injected with spermatozoa treated with 0.1 ng/${mu}ell$ EGFP gene. These results suggested that exogenous DNA could be attached to the membrane disrupted sperm, and that these sperm could be used as a vector carrying foreign DNA into embryos.

• The Korean Journal of Pesticide Science
• /
• v.14 no.2
• /
• pp.123-132
• /
• 2010

Six populations of the diamondback moth, Plutella xylostella, were collected from the different national areas for resistance and reared in laboratory for two sensitive population. These populations of P. xylostella were examined the developed resistance against commercial products of Bacillus thuringiensis. There were 3 products with B. thuringiensis subsp. kurstaki including Tyuneup$^{(R)}$, Thuricide$^{(R)}$ and Geumulmang$^{(R)}$ and 2 products with B. thuringiensis subsp. aizawai including Tobagi$^{(R)}$ and Scorpion$^{(R)}$. The sensitive population of diamondback moths were provided from National Academy of Agricultural Science (NP) and Highland Agriculture Research Center (GR population) and field populations were caught from 6 different national areas. Resistance against Tyuneup$^{(R)}$ was developed 4.8 and 2.5 times in SP and HS compared with GR population of diamondback moth, respectively. In case of Geumulmang$^{(R)}$, it was developed 9.9 and 6.8 times in SP and NM population compared with NP population, respectively. Otherwise, Tobagi$^{(R)}$ was showed higher resistance in HS than any other population compared with GR population, however, Scorpion$^{(R)}$ that is a same strain with Tobagi$^{(R)}$, was showed only double resistance to SP population. It was supposed that the development of resistance to B. thuringiensis might be caused by the continuous application of the specific commercial product at the specific area. So, we need to use the commercial products of B. thuringiensis in rotation with different B. thuringiensis strains. In the other hand, when HS population with highest resistance were reared in laboratory, their resistance ratio was rapidly dropped to 1.1 times at second generation. We have to examined the resistance mechanism of the diamondback moth to B. thuringiensis strains.

• Journal of Life Science
• /
• v.16 no.1
• /
• pp.131-135
• /
• 2006

Oligopeptide is known to be an essential nitrogen nutrient for bacterial growth. Oligopeptide can be transported into cytoplasm by a specific transport system, Opp system. Opp system is composed of five proteins, which are transcribed by an operon. These are responsible for oligopeptide binding protein (OppA), permease (OppB and OppC) and energy generation system (OppD and OppF), respectively. Previously, we isolated the opp operon from Vibrio fluvialis and constructed the oppA mutant by allelic exchange method. In this study, we investigated the growth pattern and biofilm production under the different growth condition. When the cells were cultivated using brain heart infusion(BHI) medium, the wild type was faster than the mutant in growth during the exponential phase. However, it showed that the growth pattern of two strains in M9 medium is very similar. The growth of wild type showed better than that of the mutant grown at pH 8. At pH 7, there was no an obvious difference in growth. After 5 mM $H_2O_2$ was treated to the cells $(OD_{600}=1.2)$, the cell survival was examined. The oppA mutation did not affect in survivability. In the presence of $10{\mu}g/ml$ polymyxin B, the biofilm production of the oppA mutant was higher than that of the wild type.

• Korean Journal of Breeding Science
• /
• v.42 no.3
• /
• pp.262-266
• /
• 2010

'Josaengheugchal', a new blackish purple pigmented glutinous japonica rice cultivar, was developed by the rice breeding team of Department of Functional Crop, NICS, RDA in 2004. This cultivar was derived from a cross between 'Tohoku 149' as black glutinous source and 'Sx 864' as purple colored rice in 1992 and 1993 winter season, and selected by pedigree breeding method until $F_6$ generation. As a result, a promising line, YR15907-6-8-1-5, was advanced and designated as the name of 'Milyang 194' in 2001. The local adaptability test of 'Milyang 194' was carried out at seven locations from 2002 to 2004 and it was named as 'Josaengheugchal'. 'Josaengheugchal' is an early maturing cultivar and has 71 cm culm height. It has higher anthocyanian content compared with 'Heugnambyeo'. It is moderately resistant to leaf blast but susceptible to other disease and insect pests. The yield potential of 'Josaengheugchal' in brown rice was about 4.21 MT/ha at ordinary fertilizer level in local adaptability test. This cultivar would be adaptable to the plain paddy field of middle, Honam, and Yeomgnam in Korea under ordinary and double cropping system.

• Child Health Nursing Research
• /
• v.7 no.3
• /
• pp.322-341
• /
• 2001

The family value is expected to play a crucial role in adjusting a new environment for the family, especially in the critical situation as having a child with cancer in the family. The purpose of the study was to analyze the family values of the family with cancer children in order to offer descriptive data, which will facilitate family adjustment with cancer children. The survey was conducted from July 18, 2000 to August 30, 2000 and the analysis included 309 parents of the children who have been diagnosed as cancer, 18 years of age or less, and treated either hospitalized or at the outpatient clinics. Two instruments were used to measure family value. The modified form of General family value scale was 18 items with a 5 points of Likert response format (Cronbach alpha= .78) and Family value scale was developed for the study with 12 items on a 5 points of Likert response format(Cronbach alpha= .73). The data analysis utilized SAS 6.12 for percentage, frequency, Mean, and t-test of demographic characteristics and mean, F score, ANOVA, and Duncan follow-up test of variable relationships. The study findings were as follows. 1) In General family value, the fathers gave the higher scores to 'The children should live with their parents'(M=4.01), and 'A parents and their children are like one body' (M=3.91). The item with lowest score was 'Its not impossible for man to have extramarital relationship'(M=1.92). The mothers thought the most important items were 'A parents and their children are like one body'(M=3.79), and 'A wife needs to be patient to keep harmony of the family' (M=3.56), and the item with lowest score was 'Its not impossible for man to have extramarital relationship'(M=1.44). 2) The mean scores of the mothers were higher than the fathers for all items in family value with cancer children, while fathers gave more points for items in general family value. Both of parents gave the highest score to 'The health of the family is most important to me'(M=4.85 for fathers, M=4.97 for mothers), and followed by 'The husband and wife need to be patient and understand each other to overcome the difficulties'. The item with lowest scores was 'The parents can have conflicts in making decisions since their child was sick'(M=3.34 for fathers, M=3.37 for mothers). 3) There were significant differences between fathers and mothers in items of General family value; fathers gave more points to the items of 'The children should live with their parents', 'Its essential to hold the ceremony to respect their forefathers', 'Its not impossible for man to have extramarital relationship', 'A woman with two daughters should have one more baby to succeed the generation', 'The husbands are responsible for the household economy', and 'When his mother and wife dont get along, the man should be on his mothers side'. However, there was no significant difference between fathers and mothers in items of Family value with cancer children. 4) The general family value was significantly different by the birth order of cancer children, mothers age, mothers education level, and types of payment. On the other hand, the family value with cancer children was significantly different by the age of cancer children, period of illness, period after completing treatment, family type, the number of family members, and the number of total children.