• Sleep Medicine and Psychophysiology
• /
• v.10 no.1
• /
• pp.52-60
• /
• 2003

Objectives: Stage 1 sleep provides important information regarding interpretation of nocturnal polysomnography, particularly sleep onset. It is a short transition period from wakeful consciousness to sleep. The lack of prominent sleep events characterizing stage 1 sleep is a major obstacle in automatic sleep stage scoring. In this study, utilization of simultaneous EEG and EOG processing and analyses to detect stage 1 sleep automatically were attempted. Methods: Relative powers of the alpha waves and the theta waves were calculated from spectral estimation. A relative power of alpha waves less than 50% or relative power of theta waves more than 23% was regarded as stage 1 sleep. SEM(slow eye movement) was defined as the duration of both-eye movement ranging from 1.5 to 4 seconds, and was also regarded as stage 1 sleep. If one of these three criteria was met, the epoch was regarded as stage 1 sleep. Results were compared to the manual rating results done by two polysomnography experts. Results: A total of 169 epochs were analyzed. The agreement rate for stage 1 sleep between automatic detection and manual scoring was 79.3% and Cohen’s Kappa was 0.586 (p<0.01). A significant portion (32%) of automatically detected stage 1 sleep included SEM. Conclusion: Generally, digitally-scored sleep staging shows accuracy up to 70%. Considering potential difficulty in stage 1 sleep scoring, accuracy of 79.3% in this study seems to be strong enough. Simultaneous analysis of EOG differentiates this study from previous ones which mainly depended on EEG analysis. The issue of close relationship between SEM and stage 1 sleep raised by Kinnari remains a valid one in this study.

• Journal of Food Hygiene and Safety
• /
• v.31 no.1
• /
• pp.28-35
• /
• 2016

Species identification of animal tissues in meat products is an important issue to protect the consumer from illegal and/or undesirable adulteration; for economic, religious and health reasons. In this reason, accurate analytical methods are needed for the labeling of meat products with requiring simple and fast procedure. Recently, applications of PCR in food analysis have been increased because of their simplicity, specificity and sensitivity. Therefore, in this study, a multiplex PCR assay was developed for the simultaneous identification of eight species of cow, pig, chicken, duck, goat, sheep, horse and turkey from raw meats. The primers were designed in different regions of mitochondrial 16S RNA after alignment of the available sequences in the GenBank database. Two multiplex primer sets were designed as Set 1 (cow, pig, chicken, duck) and Set 2 (goat, sheep, horse, turkey), respectively. Total 274 samples from cow (n = 55), pig (n = 30), chicken (n=30), and duck (n = 30), goat (n = 40), sheep (n = 33), horse (n = 41), and turkey (n = 15) were tested. The primers generated specific fragments of 94, 192, 279, 477 bp (pig, chicken, cow, duck), 670, 271, 152, 469 bp (goat, sheep, horse, turkey) lengths for eight species, respectively. The animal species specificity was 100% in all eight samples in the multiplex PCR assay. The detection limit of the multiplex PCR assay showed from 100 fg to 1 pg of template DNA from extracted from raw meats. When applying multiplex PCR assays to sample from pork/beef and pork/chicken, beef/chicken tested raw mixed meats and heat-treated ($83^{\circ}C$ for 30min, $100^{\circ}C$ for 20min, and $121^{\circ}C$ for 10min) mixtures, detection limit was 0.1% level beef, pork and pork in beef and chicken in pork and 1.0% level pork in chicken. This study suggest that the developed multiplex PCR assay can be used for rapid and simultaneous species identification of cow, pig, chicken, duck, goat, sheep, horse and turkey from meats.

• Journal of Biomedical Engineering Research
• /
• v.25 no.1
• /
• pp.11-19
• /
• 2004

Stage 1 sleep provides important information regarding interpretation of nocturnal polysomnography, particularly sleep onset. It is a short transition period from wakeful consciousness to sleep. Lack of prominent sleep events characterizing stage 1 sleep is a major obstacle in automatic sleep stage scoring. In this study, we attempted to utilize simultaneous EEC and EOG processing and analyses to detect stage 1 sleep automatically. Relative powers of the alpha waves and the theta waves were calculated from spectral estimation. Either the relative power of alpha waves less than 50％ or the relative power of theta waves more than 23％ was regarded as stage 1 sleep. SEM (slow eye movement) was defined as the duration of both eye movement ranging from 1.5 to 4 seconds and regarded also as stage 1 sleep. If one of these three criteria was met, the epoch was regarded as stage 1 sleep. Results f ere compared to the manual rating results done by two polysomnography experts. Total of 169 epochs was analyzed. Agreement rate for stage 1 sleep between automatic detection and manual scoring was 79.3％ and Cohen's Kappa was 0.586 (p＜0.01). A significant portion (32％) of automatically detected stage 1 sleep included SEM. Generally, digitally-scored sleep s1aging shows the accuracy up to 70％. Considering potential difficulties in stage 1 sleep scoring, the accuracy of 79.3％ in this study seems to be robust enough. Simultaneous analysis of EOG provides differential value to the present study from previous oneswhich mainly depended on EEG analysis. The issue of close relationship between SEM and stage 1 sleep raised by Kinnariet at. remains to be a valid one in this study.

• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.29-45
• /
• 2015

Response modeling is a well-known research issue for those who have tried to get more superior performance in the capability of predicting the customers' response for the marketing promotion. The response model for customers would reduce the marketing cost by identifying prospective customers from very large customer database and predicting the purchasing intention of the selected customers while the promotion which is derived from an undifferentiated marketing strategy results in unnecessary cost. In addition, the big data environment has accelerated developing the response model with data mining techniques such as CBR, neural networks and support vector machines. And CBR is one of the most major tools in business because it is known as simple and robust to apply to the response model. However, CBR is an attractive data mining technique for data mining applications in business even though it hasn't shown high performance compared to other machine learning techniques. Thus many studies have tried to improve CBR and utilized in business data mining with the enhanced algorithms or the support of other techniques such as genetic algorithm, decision tree and AHP (Analytic Process Hierarchy). Ahn and Kim(2008) utilized logit, neural networks, CBR to predict that which customers would purchase the items promoted by marketing department and tried to optimized the number of k for k-nearest neighbor with genetic algorithm for the purpose of improving the performance of the integrated model. Hong and Park(2009) noted that the integrated approach with CBR for logit, neural networks, and Support Vector Machine (SVM) showed more improved prediction ability for response of customers to marketing promotion than each data mining models such as logit, neural networks, and SVM. This paper presented an approach to predict customers' response of marketing promotion with Case Based Reasoning. The proposed model was developed by applying different weights to each feature. We deployed logit model with a database including the promotion and the purchasing data of bath soap. After that, the coefficients were used to give different weights of CBR. We analyzed the performance of proposed weighted CBR based model compared to neural networks and pure CBR based model empirically and found that the proposed weighted CBR based model showed more superior performance than pure CBR model. Imbalanced data is a common problem to build data mining model to classify a class with real data such as bankruptcy prediction, intrusion detection, fraud detection, churn management, and response modeling. Imbalanced data means that the number of instance in one class is remarkably small or large compared to the number of instance in other classes. The classification model such as response modeling has a lot of trouble to recognize the pattern from data through learning because the model tends to ignore a small number of classes while classifying a large number of classes correctly. To resolve the problem caused from imbalanced data distribution, sampling method is one of the most representative approach. The sampling method could be categorized to under sampling and over sampling. However, CBR is not sensitive to data distribution because it doesn't learn from data unlike machine learning algorithm. In this study, we investigated the robustness of our proposed model while changing the ratio of response customers and nonresponse customers to the promotion program because the response customers for the suggested promotion is always a small part of nonresponse customers in the real world. We simulated the proposed model 100 times to validate the robustness with different ratio of response customers to response customers under the imbalanced data distribution. Finally, we found that our proposed CBR based model showed superior performance than compared models under the imbalanced data sets. Our study is expected to improve the performance of response model for the promotion program with CBR under imbalanced data distribution in the real world.

• Journal of the Korean Society of Radiology
• /
• v.18 no.3
• /
• pp.187-201
• /
• 2024

Osteoporosis is a major health issue globally, often remaining undetected until a fracture occurs. To facilitate early detection, deep learning (DL) models were developed to classify osteoporosis using abdominal computed tomography (CT) scans. This study was conducted using retrospectively collected data from 3,012 contrast-enhanced abdominal CT scans. The DL models developed in this study were constructed for using image data, demographic/clinical information, and multi-modality data, respectively. Patients were categorized into the normal, osteopenia, and osteoporosis groups based on their T-scores, obtained from dual-energy X-ray absorptiometry, into normal, osteopenia, and osteoporosis groups. The models showed high accuracy and effectiveness, with the combined data model performing the best, achieving an area under the receiver operating characteristic curve of 0.94 and an accuracy of 0.80. The image-based model also performed well, while the demographic data model had lower accuracy and effectiveness. In addition, the DL model was interpreted by gradient-weighted class activation mapping (Grad-CAM) to highlight clinically relevant features in the images, revealing the femoral neck as a common site for fractures. The study shows that DL can accurately identify osteoporosis stages from clinical data, indicating the potential of abdominal CT scans in early osteoporosis detection and reducing fracture risks with prompt treatment.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.1-23
• /
• 2018

From the 21st century, various high-quality services have come up with the growth of the internet or 'Information and Communication Technologies'. Especially, the scale of E-commerce industry in which Amazon and E-bay are standing out is exploding in a large way. As E-commerce grows, Customers could get what they want to buy easily while comparing various products because more products have been registered at online shopping malls. However, a problem has arisen with the growth of E-commerce. As too many products have been registered, it has become difficult for customers to search what they really need in the flood of products. When customers search for desired products with a generalized keyword, too many products have come out as a result. On the contrary, few products have been searched if customers type in details of products because concrete product-attributes have been registered rarely. In this situation, recognizing texts in images automatically with a machine can be a solution. Because bulk of product details are written in catalogs as image format, most of product information are not searched with text inputs in the current text-based searching system. It means if information in images can be converted to text format, customers can search products with product-details, which make them shop more conveniently. There are various existing OCR(Optical Character Recognition) programs which can recognize texts in images. But existing OCR programs are hard to be applied to catalog because they have problems in recognizing texts in certain circumstances, like texts are not big enough or fonts are not consistent. Therefore, this research suggests the way to recognize keywords in catalog with the Deep Learning algorithm which is state of the art in image-recognition area from 2010s. Single Shot Multibox Detector(SSD), which is a credited model for object-detection performance, can be used with structures re-designed to take into account the difference of text from object. But there is an issue that SSD model needs a lot of labeled-train data to be trained, because of the characteristic of deep learning algorithms, that it should be trained by supervised-learning. To collect data, we can try labelling location and classification information to texts in catalog manually. But if data are collected manually, many problems would come up. Some keywords would be missed because human can make mistakes while labelling train data. And it becomes too time-consuming to collect train data considering the scale of data needed or costly if a lot of workers are hired to shorten the time. Furthermore, if some specific keywords are needed to be trained, searching images that have the words would be difficult, as well. To solve the data issue, this research developed a program which create train data automatically. This program can make images which have various keywords and pictures like catalog and save location-information of keywords at the same time. With this program, not only data can be collected efficiently, but also the performance of SSD model becomes better. The SSD model recorded 81.99% of recognition rate with 20,000 data created by the program. Moreover, this research had an efficiency test of SSD model according to data differences to analyze what feature of data exert influence upon the performance of recognizing texts in images. As a result, it is figured out that the number of labeled keywords, the addition of overlapped keyword label, the existence of keywords that is not labeled, the spaces among keywords and the differences of background images are related to the performance of SSD model. This test can lead performance improvement of SSD model or other text-recognizing machine based on deep learning algorithm with high-quality data. SSD model which is re-designed to recognize texts in images and the program developed for creating train data are expected to contribute to improvement of searching system in E-commerce. Suppliers can put less time to register keywords for products and customers can search products with product-details which is written on the catalog.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.9 no.2
• /
• pp.138-147
• /
• 1998

Authors surveyed intrafamilial child sexual abuse in the children under 15years old in clinical. We sent the semi-structured child sexual abuse questionnaires to 7055 board certified pediatrics, obstetrics and gynecology, family medicine and emergency medicine. Total respondents were 1205. The results from these respondents were as follows. 1) The numbers of respondents who have had the experience of treating victims of intrafamilial child sexual abuses were 157(13.0% of total respondents). 2) Among the perpetrators, 58(36.9%) were siblings and 32(20.4%) 26(16.6%) were step-fathers, and respectively. The most common age bracket was 10s(39.5%), and the next was 40s and 50s (33.7%) Almost all(98.7%) of the perpetrators were male. 3) The mean age of victims was $12.1{\pm}3.3$ years old, and all of the victims were female, and the number of victims who had previous mental or physical handicaps and behavior problems were 5(3.2%) and 8(5.1%) respectively. 4) The ways by which intrafamilial child sexual abuses were found were abnormal behaviors 45(28.7%), victim's own report 40(25.5%), pregnancy 18(11.5%), pain complaint 13(8.3%), other person's report 13(8.3%), and detection during examination 12(7.6%). 5) Time lags between intrafamilial child sexual abuses and hospital visits were after 1 month 97(61.8%), from 1 day to 1 week 29(18.5%), within 1 day 21(13.4%), and from 1 week to 1 month 10(6.4%). 6) Physical complications were perineal wound 93(59.2%), hymen rupture 90(57.3%), pregnancy 68(43.3%), wound of other part of body 11(7.0%), and sexually transmitted disease 4(4.5%). 7) Treatment for victims were discharge 92(58.6%), admission, operation or transfer to a bigger hospital 25(15.9%), psychiatry consult 19(12.1%), report to police(10.9%) and social work consult 3(1.9%). These results suggest that considerable numbers of physicians have had the experience of treating victims of intrafamilial child sexual abuses, and intrafamilial child sexual abuses are the major medical as well as social issue in children in Korea.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.9 no.2
• /
• pp.127-137
• /
• 1998

The authors surveyed extrafamilial sexual abuse in the children under 15years old by the physician's reports. We sent the semi-structured child sexual abuse questionnaires to 7055 board certified pediatrics, obstetrics and gynecology, family medicine and emergency medicine. Total respondents were 1205. The results from these respondents were as followings. 1) The number of respondents who have had the experience of treating victims of extraf/amilial child sexual abuse were 641(53.2% of total respondents). 2) 338(52.7%) of the perpetrators were known persons and 277(43.2%) were strangers, the most common age bracket were 20s, 30s and 10s, and almost all(99.8%) of the perpetrators were male. 3) The mean age of victims was $9.7{\pm}3.5$ years old, and almost all(98.6%) of the victims were female. 4) The ways by which extrafamilial child sexual abuses were found were victim’s own reports：273(62.6%), pain complaint, 156(24.3%) and abnormal behavior 96(15.0%), other person’s report 72(11.2%), detection during examination 19(3.0%), and pregnancy 4(0.6%). 5) Time lags between extrafamilial child sexual abuses and hospital visits were within 24 hours 332 (51.8%) and from 1 day to 1 week 232(36.2%), victims were rather quickly 6) Physical complications were perineal wound 571(89.1%), hymen rupture 349(54.4%), wound of other part of body 124(19.3%), pregnancy 37(5.8%), and sexually transmitted disease 18(2.8%), and other serious complications such as vaginal-rectal lacerations 8, intastinal bleeding 7, death 2, hypotensive shock 1. These results suggest considerable numbers of physicians have had the experience of treating victims of extrafamilial child sexual abuses, and extrafamilial child sexual abuses are the major medical as well as social issue in children in Korea.

• Journal of the Korean Society of Radiology
• /
• v.9 no.4
• /
• pp.205-211
• /
• 2015

At a recent medical imaging technology, the major issue of X-ray diagnosis in breast cancer is the early detection of breast cancer and low patient's exposure dose. As one of studies to acquire a monochromatic X-ray, Technologies using multilayer mirror had been preceded. However, a uniform multilayer mirror that consists of uniform thin-film thickness can acquire a monochromatic X-ray only in the partial area corresponds to angle of incidence of white X-ray, so there are limits for X-ray imaging technology applications. In this study, we designed laterally graded multilayer mirror(below GML) that reflects same monochromatic X-ray over the entire area of thin-film mirror, which have the the thickness of the linear gradient that correspond to angle of incidence of white X-ray. By using ion-beam sputtering system added the mask control system we fabricated a GML which has size of $100{\times}100mm^2$. The GML is designed to achieve the monochromatic X-ray of 17.5kev energy and has thin-film thickness change from 4.62nm to 6.57nm(3.87nm at center). It reflects the monochromatic X-ray with reflectivity of more than 60 percent, FWHM of below 2.6keV and X-ray beam width of about 3mm. The monochromatic X-ray corresponded to 17.5keV using GML would have wide application in development of mammography system with high contrast and low dose.

• Journal of Korean Society of Environmental Engineers
• /
• v.28 no.2
• /
• pp.158-164
• /
• 2006

Offensive odor from CAFO(concentrated animal feeding operation) and its control have become a significant issue in Korea. Control of odors from the CAFO requires to identify major odorant and their generation mechanisms. In this study, an easy method to collect gas sample and to quantify its odorants is proposed. The method involves on-site odorant extraction with solid-phase microextraction and quantitation with GC/MSD or GC/FID. Analytes of the current study include: trimethylamine(TMA), carbon disulfide($CS_2$), dimethyl sulfide(DMS), dimethyl disulfide(DMDS), acetic acid(AA), propionic acid(PA) and n-butyric acid(BA). The resulting linearity($R^2$) of calibration curve for each analyte was good over the range from several ppbv to ppmv; 0.984 for TMA(0.056-1.437), 0.996 for $CS_2$(0.039-0.999), 0.994 for DMS(0.029-0.756), 0.995 for DMDS(0.024-0.623), 0.992 for AA(0.068-1.314), 0.955 for PA(0.047-0.940), and 0.976 for BA(0.036-0.712). Method detection limits were 5.67, 6.39, 5.78, 25.2, 0.098, 0.363 and 0.099 ppbv for AA, PA, BA, TMA, DMS, $CS_2$, and DMDS, respectively. With the developed method, odorants from poultry, swine, and cattle barns were analysed. All the compounds but DMDS were detected from the sample collected in the poultry barn, and their levels exceeded the representative published human olfactory threshold.