• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.6
• /
• pp.19-25
• /
• 2019

The CleanSYS(Clean SYStem) is operated to monitor air pollutants emitted from specific industrial complexes in Korea. So the industrial complexes without the system are directly monitored by the control officers. For efficient monitoring, studies using various sensors have been conducted to monitor air pollutants emitted from industrial complex. In this study, hyperspectral sensors were used to model and verify the equations for estimating the concentration of $NO_2$(nitrogen dioxide) in air pollutants emitted. For development of the equations, spectral radiance were observed for $NO_2$ at various concentrations with different SZA(Solar Zenith Angle), VZA(Viewing Zenith Angle), and RAA(Relative Azimuth Angle). From the observed spectral radiance, the calculated value of the difference between the values of the specific wavelengths was taken as an absorption depth, and the equations were developed using the relationship between the depth and the $NO_2$ concentration. The spectral radiance mixed gas of $NO_2$ and $SO_2$(sulfur dioxide) was used to verify the equations. As a result, the $R^2$(coefficient of determination) and RMSE(Root Mean Square Error) were different from 0.71~0.88 and 72~23 ppm according to the form of the equation, and $R^2$ of the exponential form was the highest among the equations. Depending on the type of the equations, the accuracy of the estimated concentration with varying concentrations is not constant. However, if the equations are advanced in the future, hyperspectral sensors can be used to monitor the $NO_2$ emitted from the industrial complex.

• 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.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.57-78
• /
• 2020

With the development of the Internet, consumers have had an opportunity to check product information easily through E-Commerce. Product reviews used in the process of purchasing goods are based on user experience, allowing consumers to engage as producers of information as well as refer to information. This can be a way to increase the efficiency of purchasing decisions from the perspective of consumers, and from the seller's point of view, it can help develop products and strengthen their competitiveness. However, it takes a lot of time and effort to understand the overall assessment and assessment dimensions of the products that I think are important in reading the vast amount of product reviews offered by E-Commerce for the products consumers want to compare. This is because product reviews are unstructured information and it is difficult to read sentiment of reviews and assessment dimension immediately. For example, consumers who want to purchase a laptop would like to check the assessment of comparative products at each dimension, such as performance, weight, delivery, speed, and design. Therefore, in this paper, we would like to propose a method to automatically generate multi-dimensional product assessment scores in product reviews that we would like to compare. The methods presented in this study consist largely of two phases. One is the pre-preparation phase and the second is the individual product scoring phase. In the pre-preparation phase, a dimensioned classification model and a sentiment analysis model are created based on a review of the large category product group review. By combining word embedding and association analysis, the dimensioned classification model complements the limitation that word embedding methods for finding relevance between dimensions and words in existing studies see only the distance of words in sentences. Sentiment analysis models generate CNN models by organizing learning data tagged with positives and negatives on a phrase unit for accurate polarity detection. Through this, the individual product scoring phase applies the models pre-prepared for the phrase unit review. Multi-dimensional assessment scores can be obtained by aggregating them by assessment dimension according to the proportion of reviews organized like this, which are grouped among those that are judged to describe a specific dimension for each phrase. In the experiment of this paper, approximately 260,000 reviews of the large category product group are collected to form a dimensioned classification model and a sentiment analysis model. In addition, reviews of the laptops of S and L companies selling at E-Commerce are collected and used as experimental data, respectively. The dimensioned classification model classified individual product reviews broken down into phrases into six assessment dimensions and combined the existing word embedding method with an association analysis indicating frequency between words and dimensions. As a result of combining word embedding and association analysis, the accuracy of the model increased by 13.7%. The sentiment analysis models could be seen to closely analyze the assessment when they were taught in a phrase unit rather than in sentences. As a result, it was confirmed that the accuracy was 29.4% higher than the sentence-based model. Through this study, both sellers and consumers can expect efficient decision making in purchasing and product development, given that they can make multi-dimensional comparisons of products. In addition, text reviews, which are unstructured data, were transformed into objective values such as frequency and morpheme, and they were analysed together using word embedding and association analysis to improve the objectivity aspects of more precise multi-dimensional analysis and research. This will be an attractive analysis model in terms of not only enabling more effective service deployment during the evolving E-Commerce market and fierce competition, but also satisfying both customers.

• Journal of Science of Art and Design
• /
• v.11
• /
• pp.221-249
• /
• 2007

Today, photography is facing to the crisis of identity and dilemma of ontology from the digital imaging process in the new technology form. It is very important points to say rethinking of the traditional photographic medium, that has changed the way we view the world and ourselves is perhaps an understatement and that photography has transformed our essential understanding of reality. Now, no longer are photographic images regarded as the true automatic recording, innocent evidence and the mirror to the reality. Rather, photography constructs the world for our entertainment, helping to create the comforting illusions by which we live. The recognition that photographs are not constructions and reflections of reality, is the basis for the actual presence within the contemporary photographic world. It is shock. This thesis's aim is to look for the problems of photographic identity and ontological crisis that is controlling and regulating digital photographic imagery, allowing the reproduction of the electronic simulations era. Photography loses its special aesthetic status and becomes no more true information and, exclusively evidence by traditional film and paper that appeared both as a technological accuracy and as a medium-specific aesthetic. The result, photography is facing two crises, one is the photographic ontology(the introduction of computerized digital images) and the other is photographic epistemology(having to do broader changes in ethics, knowledge and culture). Taken together, these crises apparently threaten us with the death of photography, with the 'end' of photography and the culture it sustains. The thesis's meaning is to look into the dilemma of photography's ontology and epistemology, especially, automatical index and digital codes from its origin, meaning, and identity as the technological medium. Thus, in particular, thesis focuses on the analog imagery presence, from the nature in the material world, and the digital imagery presence from the cultural situations in our society. And also thesis's aim is to examine the main issues of the history of photography has been concentrated on the ontological arguments since the discovery of photography in 1839. Photography has never been only one static technology form. Rather, its nearly two centuries of technological development have been marked by numerous, competing of technological innovation and self revolution from the dual aspects. This thesis examines recent account of photography by the analysis of the medium's concept, meaning, identity between film base image and digital base image from the aspects of photographic ontology and epistemology. Thus, the structure of thesis is fairy straightforward to examine what appear to be two opposing view of photographic conditions and ontological situations. Thesis' view contrasts that figure out the value of photography according to its fundamental characteristic as a medium. Also, it seeks a possible solution to the dilemma of photographic ontology through the medium's origin from the early years of the nineteenth century to the raising questions about the different meaning(analog/digital) of photography, now. Finally, this thesis emphasizes and concludes that the photographic ontological crisis reflects to the paradoxical dynamic structure, that unsolved the origins of the medium, itself. Moreover, even photography is not single identity of the photographic ontology, and also can not be understood as having a static identity or singular status from the dynamic field of technologies, practices, and images.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.183-203
• /
• 2018

News articles are the most suitable medium for examining the events occurring at home and abroad. Especially, as the development of information and communication technology has brought various kinds of online news media, the news about the events occurring in society has increased greatly. So automatically summarizing key events from massive amounts of news data will help users to look at many of the events at a glance. In addition, if we build and provide an event network based on the relevance of events, it will be able to greatly help the reader in understanding the current events. In this study, we propose a method for extracting event networks from large news text data. To this end, we first collected Korean political and social articles from March 2016 to March 2017, and integrated the synonyms by leaving only meaningful words through preprocessing using NPMI and Word2Vec. Latent Dirichlet allocation (LDA) topic modeling was used to calculate the subject distribution by date and to find the peak of the subject distribution and to detect the event. A total of 32 topics were extracted from the topic modeling, and the point of occurrence of the event was deduced by looking at the point at which each subject distribution surged. As a result, a total of 85 events were detected, but the final 16 events were filtered and presented using the Gaussian smoothing technique. We also calculated the relevance score between events detected to construct the event network. Using the cosine coefficient between the co-occurred events, we calculated the relevance between the events and connected the events to construct the event network. Finally, we set up the event network by setting each event to each vertex and the relevance score between events to the vertices connecting the vertices. The event network constructed in our methods helped us to sort out major events in the political and social fields in Korea that occurred in the last one year in chronological order and at the same time identify which events are related to certain events. Our approach differs from existing event detection methods in that LDA topic modeling makes it possible to easily analyze large amounts of data and to identify the relevance of events that were difficult to detect in existing event detection. We applied various text mining techniques and Word2vec technique in the text preprocessing to improve the accuracy of the extraction of proper nouns and synthetic nouns, which have been difficult in analyzing existing Korean texts, can be found. In this study, the detection and network configuration techniques of the event have the following advantages in practical application. First, LDA topic modeling, which is unsupervised learning, can easily analyze subject and topic words and distribution from huge amount of data. Also, by using the date information of the collected news articles, it is possible to express the distribution by topic in a time series. Second, we can find out the connection of events in the form of present and summarized form by calculating relevance score and constructing event network by using simultaneous occurrence of topics that are difficult to grasp in existing event detection. It can be seen from the fact that the inter-event relevance-based event network proposed in this study was actually constructed in order of occurrence time. It is also possible to identify what happened as a starting point for a series of events through the event network. The limitation of this study is that the characteristics of LDA topic modeling have different results according to the initial parameters and the number of subjects, and the subject and event name of the analysis result should be given by the subjective judgment of the researcher. Also, since each topic is assumed to be exclusive and independent, it does not take into account the relevance between themes. Subsequent studies need to calculate the relevance between events that are not covered in this study or those that belong to the same subject.

• Journal of Food Hygiene and Safety
• /
• v.32 no.4
• /
• pp.267-274
• /
• 2017

This paper deals with the natural occurrence of total aflatoxins ($B_1$, $B_2$, $G_1$, and $G_2$) in commercial herbs for food and medicine. To monitor aflatoxins in commercial herbs for food and medicine not included in the specifications of Food Code, a total of 62 samples of 6 different herbs (Bombycis Corpus, Glycyrrhizae Radix et Rhizoma, Menthae Herba, Nelumbinis Semen, Polygalae Radix, Zizyphi Semen) were collected from Yangnyeong market in Seoul, Korea. The samples were treated by the immunoaffinity column clean-up method and quantified by high performance liquid chromatography (HPLC) with on-line post column photochemical derivatization (PHRED) and fluorescence detection (FLD). The analytical method for aflatoxins was validated by accuracy, precision and detection limits. The method showed recovery values in the 86.9~114.0% range and the values of percent coefficient of variaton (CV%) in the 0.9~9.8% range. The limits of detection (LOD) and quantitation (LOQ) in herb were ranged from 0.020 to $0.363{\mu}g/kg$ and from 0.059 to $1.101{\mu}g/kg$, respectively. Of 62 samples analyzed, 6 semens (the original form of 2 Nelumbinis Semen and 2 Zizyphi Semen, the powder of 1 Nelumbinis Semen and 1 Zizyphi Semen) were aflatoxin positive. Aflatoxins $B_1$ or $B_2$ were detected in all positive samples, and the presence of aflatoxins $G_1$ and $G_2$ were not detected. The amount of total aflatoxins ($B_1$, $B_2$, $G_1$, and $G_2$) in the powder and original form of Nelumbinis Semen and Zizyphi Semen were observed around $ND{\sim}21.8{\mu}g/kg$, which is not regulated presently in Korea. The 56 samples presented levels below the limits of detection and quantitation.

• Tuberculosis and Respiratory Diseases
• /
• v.62 no.5
• /
• pp.406-416
• /
• 2007

Background: Single nucleotide polymorphisms (SNPs), which consist of a substitution of a single nucleotide pair, are the most abundant form of genetic variations occurring with a frequency of approximately 1 per 1000 base pairs. SNPs by themselves do not cause disease but can predispose humans to disease, modify the extent or severity of the disease or influence the drug response and treatment efficacy. Single nucleotide polymorphisms (SNPs), particularly those within the regulatory regions of the genes often influence the expression levels and can modify the disease. Studies examining the associations between SNP and the disease outcome have provided valuable insight into the disease etiology and potential therapeutic intervention. Traditionally, the genotyping of SNPs has been carried out using polymerase chain reaction-restriction fragment length polymorphism(PCR-RFLP), which is a low throughput technique not amenable for use in large-scale SNP studies. Recently, TaqMan real-time PCR chemistry was adapted for use in allelic discrimination assays. This study validated the accuracy and utility of real-time PCR technology for SNPs genotyping Methods: The SNPs in promoter sequence (-37 and -524) of lung cancer suppressor gene, RRM1 (ribonucleotide reductase M1 subunit) with the genomic DNA samples of 89 subjects were genotyped using both real-time PCR and PCR-RFLP. Results: The discordance rates were 2.2% (2 mismatches) in -37 and 16.3% (15 mismatches) in -524. Auto-direct sequencing of all the mismatched samples(17 cases) were in accord with the genotypes read by real-time PCR. In addition, 138 genomic DNAs were genotyped using real-time PCR in a duplicate manner (two separated assays). Ninety-eight percent of the samples showed concordance between the two assays. Conclusion: Real-time PCR allelic discrimination assays are amenable to high-throughput genotyping and overcome many of the problematic features associated with PCR-RFLP.

• Journal of Gastric Cancer
• /
• v.9 no.2
• /
• pp.51-56
• /
• 2009

Purpose: Peritoneal recurrence has been reported to be the most common form of recurrence of gastric cancer. Peritoneal recurrence can generally be suggested by several types of image studies and also if there is evidence of ascites or Bloomer's rectal shelf. It can be confirmed by explorative laparotomy, but diagnostic laparoscopy is a good alternative method and laparoscopic surgery has also been widely used. We reviewed and analyzed the ability of diagnostic laparoscopy to detect peritoneal recurrence or carcinomatosis, and especially for gastric cancer. Materials and Methods: We performed a retrospective review the 45 gastric cancer patients who were operated via diagnostic laparoscopy between 2004. 2. and 2009. 3. We analyzed the perioperative clinical characteristics and the accuracy of the diagnostic methods. Results: The study groups included 14 patients who had confirmed gastric cancer, but they suspected to have carcinomatosis, and 31 patients who had previously underwent gastric resection, but they suspected to have recurrence. The mean operation time was $44.1\pm26.9$ minutes and the mean postoperative hospital stay was $2.7\pm2.8$ days. There was one case of operation-related complication and no postoperative mortality occurred. The sensitivities for detecting peritoneal recurrence or carcinomatosis were 92.1% for diagnostic laparoscopy, 29.7% for detecting ascites and rectal shelf on the physical examination, 86.5% for abdominal computed tomography, 69.2% for PET CT and 18.8% for CEA. Conclusion: Diagnostic laparoscopy does not require a long operation time or a long hospital stay, and it showed a low complication rate in our study. It has high sensitivity for detecting peritoneal recurrence of gastric cancer. It can be an alternative diagnostic confirmative method and it is useful for deciding on further treatment.

• Journal of Korean Academy of Nursing Administration
• /
• v.2 no.1
• /
• pp.97-114
• /
• 1996

INSTRODUCTION Service quality is, unlike goods quality, an abstract and elusive constuct. Service quality and its requirements are not easily understood by consumers, and also present some critical research problems. However, quality is very important to marketers and consumers in that it has many strategic benefits in contributing to profitability of marketing activities and consumers' problem-solving activities. Moreover, despite the phenomenal growth of medical service sector, few researchers have attempted to define and model medical service quality. Especially, little research has focused on the evaluation of medical service quality and patient satisfaction from the perspectives of both the provider and the patient. As competition intensifies and patients are demanding higher quality of medical service, medical service quality and patient satisfaction has emerged as a critical research topic. The major purpose of this article is to explore the concept of medical service quality and its evaluation from both nurse and patient perspectives. This article attempts to achieve its purpose by (1)classfying critical service attibutes into threecategories(satisfiers, hygiene factors, and performance factors). (2)measuring the relative importance of need criteria, (3)evaluating SERVPERF model and SERVQUAL model in medical service sector, and (4)identifying the relationship between perceived quality and overall patient satisfaction. METHOD Data were gathered from a sample of 217 patients and 179 nurses in Seoul-area general hospitals. From the review of previous literature, 50 survey items representing various facets of the medical service quality were developed to form a questionnaire. A five-point scale ranging from "Strongly Agree"(5) to "Strongly Disagree"(1) accompanied each statement(expectation statements, perception statements, and importance statements). To measure overall satisfaction, a seven-point scale was used, ranging from "Very Satisfied"(7) to "Very Dissatisfied"(1) with no verbal labels for scale points 2 through 6 RESULTS In explaining the relationship between perceived performance and overall satisfaction, only 31 variables out of original 50 survey items were proven to be statistically significant. Hence, a penalty-reward analysis was performed on theses 31 critical attributes to find out 17 satisfiers, 8 hygiene factors, and 4 performance factors in patient perspective. The role(category) of each service quality attribute in relation to patient satisfaction was com pared across two groups, that is, patients and nurses. They were little overlapped, suggesting that two groups had different sets of 'perceived quality' attributes. Principal components factor analyses of the patients' and nurses' responses were performed to identify the underlying dimensions for the set of performance(experience) statements. 28 variables were analyzed by using a varimax rotation after deleting three obscure variables. The number of factors to be extracted was determined by evaluating the eigenvalue scores. Six factors wereextracted, accounting for 57.1% of the total variance. Reliability analysis was performed to refine the factors further. Using coefficient alpha, scores of .84 to .65 were obtained. Individual-item analysis indicated that all statements in each of the factors should remain. On 26 attributes of 31 critical service quality attributes, there were gaps between actual patient's importance of need criteria and nurse perceptions of them. Those critical attributes could be classified into four categories based on the relative importance of need criteria and perceived performance from the perspective of patient. This analysis is useful in developing strategic plans for performance improvement. (1) top priorities(high importance and low performance) (in this study)- more health-related information -accuracy in billing - quality of food - appointments at my convenience - information about tests and treatments - prompt service of business office -adequacy of accommodations(elevators, etc) (2) current strengths(high importance and high performance) (3)unnecessary strengths(low importance and high performance) (4) low priorities(low importance and low performance) While 26 service quality attributes of SERPERF model were significantly related to patient satisfation, only 13 attributes of SERVQUAL model were significantly related. This result suggested that only experience-based norms(SERVPERF model) were more appropriate than expectations to serve as a benchmark against which service experiences were compared(SERVQUAL model). However, it must be noted that the degree of association to overall satisfaction was not consistent. There were some gaps between nurse percetions and patient perception of medical service performance. From the patient's viewpoint, "personal likability", "technical skill/trust", and "cares about me" were most significant positioning factors that contributed patient satisfaction. DISCUSSION This study shows that there are inconsistencies between nurse perceptions and patient perceptions of medical service attributes. Also, for service quality improvement, it is most important for nurses to understand what satisfiers, hygiene factors, and performance factors are through two-way communications. Patient satisfaction should be measured, and problems identified should be resolved for survival in intense competitive market conditions. Hence, patient satisfaction monitoring is now becoming a standard marketing tool for healthcare providers and its role is expected to increase.

• The Journal of Korean Society for Radiation Therapy
• /
• v.25 no.1
• /
• pp.77-85
• /
• 2013

Purpose: The accurate movement of gantry rotation, collimator and correct application of dose rate are very important to approach the successful performance of Volumetric Modulated Arc Therapy (VMAT), because it is tightly interlocked with a complex treatment plan. The interruption and restart of dose delivery, however, are able to occur on treatment by various factors of a treatment machine and treatment plan. If unexpected problems of a treat machine or a patient interrupt the VMAT, the movement of treatment machine for delivering the remaining dose will be restarted at the start point. In this investigation, We would like to know the effect of interruptions and restart regarding dose delivery at VMAT. Materials and Methods: Treatment plans of 10 patients who had been treated at our center were used to measure and compare the dose distribution of each VMAT after converting to a form of digital image and communications in Medicine (DICOM) with treatment planning system (Eclipse V 10.0, Varian, USA). We selected the 6 MV photon energy of Trilogy (Varian, USA) and used OmniPro I'mRT system (V 1.7b, IBA dosimetry, Germany) to analyze the data that were acquired through this measurement with two types of interruptions four times for each case. The door interlock and the beam-off were used to stop and then to restart the dose delivery of VMAT. The gamma index in OmniPro I'mRT system and T-test in Microsoft Excel 2007 were used to evaluate the result of this investigation. Results: The deviations of average gamma index in cases with door interlock, beam-off and without interruption on VMAT are 0.141, 0.128 and 0.1. The standard deviations of acquired gamma values are 0.099, 0.091, 0.071 and The maximum gamma value in each case is 0.413, 0.379, 0.286, respectively. This analysis has a 95-percent confidence level and the P-value of T-test is under 0.05. Gamma pass rate (3%, 3 mm) is acceptable in all of measurements. Conclusion: As a result, We could make sure that the interruption of this investgation are not enough to seriously affect dose delivery of VMAT by analyzing the measured data. But this investigation did not reflect all cases about interruptions and errors regarding the movement of a gantry rotation, collimator and patient So, We should continuously maintain a treatment machine and program to deliver the accurate dose when we perform the VMAT for the many kinds of cancer patients.