• 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.25 no.3
• /
• pp.161-177
• /
• 2019

In this paper, we study the performance improvement of the answer extraction in Question-Answering system by using sentence dependency parsing result. The Question-Answering (QA) system consists of query analysis, which is a method of analyzing the user's query, and answer extraction, which is a method to extract appropriate answers in the document. And various studies have been conducted on two methods. In order to improve the performance of answer extraction, it is necessary to accurately reflect the grammatical information of sentences. In Korean, because word order structure is free and omission of sentence components is frequent, dependency parsing is a good way to analyze Korean syntax. Therefore, in this study, we improved the performance of the answer extraction by adding the features generated by dependency parsing analysis to the inputs of the answer extraction model (Bidirectional LSTM-CRF). The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. In this study, we compared the performance of the answer extraction model when inputting basic word features generated without the dependency parsing and the performance of the model when inputting the addition of the Eojeol tag feature and dependency graph embedding feature. Since dependency parsing is performed on a basic unit of an Eojeol, which is a component of sentences separated by a space, the tag information of the Eojeol can be obtained as a result of the dependency parsing. The Eojeol tag feature means the tag information of the Eojeol. The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. From the dependency parsing result, a graph is generated from the Eojeol to the node, the dependency between the Eojeol to the edge, and the Eojeol tag to the node label. In this process, an undirected graph is generated or a directed graph is generated according to whether or not the dependency relation direction is considered. To obtain the embedding of the graph, we used Graph2Vec, which is a method of finding the embedding of the graph by the subgraphs constituting a graph. We can specify the maximum path length between nodes in the process of finding subgraphs of a graph. If the maximum path length between nodes is 1, graph embedding is generated only by direct dependency between Eojeol, and graph embedding is generated including indirect dependencies as the maximum path length between nodes becomes larger. In the experiment, the maximum path length between nodes is adjusted differently from 1 to 3 depending on whether direction of dependency is considered or not, and the performance of answer extraction is measured. Experimental results show that both Eojeol tag feature and dependency graph embedding feature improve the performance of answer extraction. In particular, considering the direction of the dependency relation and extracting the dependency graph generated with the maximum path length of 1 in the subgraph extraction process in Graph2Vec as the input of the model, the highest answer extraction performance was shown. As a result of these experiments, we concluded that it is better to take into account the direction of dependence and to consider only the direct connection rather than the indirect dependence between the words. The significance of this study is as follows. First, we improved the performance of answer extraction by adding features using dependency parsing results, taking into account the characteristics of Korean, which is free of word order structure and omission of sentence components. Second, we generated feature of dependency parsing result by learning - based graph embedding method without defining the pattern of dependency between Eojeol. Future research directions are as follows. In this study, the features generated as a result of the dependency parsing are applied only to the answer extraction model in order to grasp the meaning. However, in the future, if the performance is confirmed by applying the features to various natural language processing models such as sentiment analysis or name entity recognition, the validity of the features can be verified more accurately.

• Journal of Hospice and Palliative Care
• /
• v.20 no.3
• /
• pp.177-187
• /
• 2017

Purpose: From August 2017, hospice-palliative care (HPC) will be provided to patients with acquired immunodeficiency syndrome (AIDS), chronic obstructive pulmonary disease (COPD), and liver cirrhosis in Korea. To contribute to building a non-cancer (NC) hospice-palliative care model, NC specialists were interviewed regarding the goals, details, and provision methods of the model. Methods: Four physicians specializing in HPC of cancer patients formulated a semi-structured interview with questions extracted from literature review of 85 articles on NC HPC. Eleven NC disease specialists were interviewed, and their answers were analyzed according to the qualitative content analysis process. Results: The interviewees said as follows: It is difficult to define end-stage NC patients. HPC for cancer patients and that for NC patients share similar goals and content. However, emphasis should be placed on alleviating other physical symptoms and emotional care rather than pain control. Timing of the care provision should be when patients are diagnosed as "end stage". Special issues should be considered for each NC disease (e.g., use of anti-retroviral drugs for AIDS patients, oxygen supply for COPD patients suffering from dyspnea, liver transplantation for patients with liver cirrhosis) and education should be provided to healthcare professionals. NC patients tend to negatively perceive HPC, and the government's financial assistance is insufficient. Conclusion: It is necessary to define end-stage NC patients through in-depth discussion to minimize issues that will likely accompany the expansion of care recipients. This requires cooperation between medical staff caring for NC patients and HPC givers for cancer patients.

• Journal of Food Hygiene and Safety
• /
• v.8 no.1
• /
• pp.37-53
• /
• 1993

F. moniliforme MRC 826, a common fungal contaminant of com, has been known to produce a group of mycotoxins, the fumonisins. By thin layer chromatography, fumonisin $B_{1}$ was detected in the F. moniliforme MRC 826 com culture material(CM) extracts. This study was performed to compare the toxicity and carcinogenicity of F. moniliforme MRC 826 CM with those of aflatoxin $B_1(AFB_1)$ in rats. The toxicity was tested over a period of 7 days in ten female Sprague-Dawley (SD) rats. Treatment group were fed a 1 : 1 mixture(wt/wt) of ground CM and basal diet in powder form, while other negative control group were given basal diet alone. The principal pathological changes in rats treated with 50% CM were hepatocellular hydropic degeneration and renal tubular necrosis. The cancer-promoting activity of CM was evaluated in the rat liver diethylnitrosamine-two thirds partial hepatectomy(DEN-PH) model for carcinogenesis. 70 male SO rats(ca. 170 g) were randomized into 5 groups. Group I served as the positive controls and received the basal diet containing 2 ppm $AFB_{1}$ group 2 received 5% CM, group 3 received 2.5% CM, group 4 received 5% normal com and group 5 received 2.5% normal com. 5% treated group showed cancer promoting activity in rat liver using DEN as initiator and the induction of glutathione S-transferase placental form positive foci as an end point after 6 weeks of promotion.

• Korean Journal of Medicinal Crop Science
• /
• v.11 no.3
• /
• pp.246-251
• /
• 2003

Angiotensin converting enzyme(ACE) belongs to the class of zinc protease and plays an important role in the regulation of blood pressure. In this experiment, we investigated the inhibitory activities of ninety four plant extracts on ACE. The extracts were prepared by water and refluxing with 70% and 100% methanol. Among the extracts, two plant extracts such as Cassia tora, Persicaria cochinchinensis Kitagawa showed more than 60% inhibitory activities, and Foeniculum vulgare Gaertner, Scutellaria baicalensis Georgl, Caragana sinica (Buchoz) Rehder, Inula britannica var. chinensis showed $45.2{\sim}49.7%$ inhibitory activities. Twenty eight plant extracts such as Hemerocallis fulva L, Camptotheca acuminata Decne, Inula britannica var. chinensis, Xanthium strumarium, Polygonatum odoratum, Phellodendron amurense Rupr, Coix lachryma-jobi var. mayuen, Prunus ansu, Hibiscus mutabilis L, Thchosanthes kirilowii, Helianthus annuus, Juglans sinensis showed $30.3{\sim}39.7%$ Inhibitory activities. These results suggest that plant extracts which contain high ACE inhibitory activities may be useful as anti-hypertension agents and to the treatment of hypertension.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.17 no.2
• /
• pp.125-135
• /
• 1988

In recent years, the presence of N-nitrosamine, which was produced by the interaction of nitrite and secondary amine, in the fermented foods has been the subject of considerable interest and controversy. In this experiment, the levels of N-nitrosamine such as N-nitrosodimethylamine(NDMA), N-nitrosodiethylamine(NDEA) and N-nitrosodipropylamine(NDPA) in the Korean ordinary soysauce, which were added with ascorbic acid, sorbic acid, and sodium benzoate in the making of it were analyzed by low resolution mass spectrometry, and then the changes of dimethylamine(DMA), nitrate and nitrite nitrogen during the fermentation of it were observed. The contents of DMA nitrogen increased during the fermentation of Korean ordinary soysauce, continuously, but those of DMA nitrogen in the soysauce which had been added with ascorbic acid were inhibited, considerably, until the fermentation of 70days. The levels of nitrate nitrogen during the fermentation of Korean ordinary soysauee decreased, while those of nitrite nitrogen increased. The soysauce which had been incoporated with ascorbic acid in the making of it showed low amounts of nitrite. The concentration of NDMA in the control sample were 2.7 and $8.5{\mu}g/kg$ after the fermentation of 30 and 60 days, respectively, those of NDMA increased during the fermentation of Korean ordinary soysauce, but NDEA and NDPA in all of the soysauce were not detected. The samples were treated with ascorbic acid, sorbic acid, and sodium benzoate in the making of Korean ordinary soysauce were turn out to be effective in preventing the formation of NDMA. Inhibitive actions from food additives as above were, respectively, $82.2{\sim}87.0%$(ascorbic acid), $25.9{\sim}65.4%$(sorbic acid) an $13.2{\sim}63.5%$ (sodium benzoate) in comparison with control sample during the fermentation of Korean ordinary soysauce. NDMA contents were detected below $1.5{\mu}g/kg$ in the soysauce, which food additives were mixed to the pure NaCI in the brewing of it. Free amino acids such as glutamic acid, proline, and histidine were proved to be inhibiting the formation of NDMA during the fermentation of Korean ordinary soysauce. This might be due to the reaction above amino acids and nitrite by Van Slyke reaction.

• Korean Journal of Remote Sensing
• /
• v.30 no.1
• /
• pp.61-73
• /
• 2014

This study reviewed an application of water quality estimation using an Airborne Hyperspectral Imagery (A-HSI) and tested a part of Han River water quality (especially suspended solid) estimation with available in-situ data. The estimation of water quality was processed two methods. One is using observation data as downwelling radiance to water surface and as scattering and reflectance into water body. Other is linear regression analysis with water quality in-situ measurement and upwelling data as at-sensor radiance (or reflectance). Both methods drive meaningful results of RS estimation. However it has more effects on the auxiliary dataset as water quality in-situ measurement and water body scattering measurement. The test processed a part of Han River located Paldang-dam downstream. We applied linear regression analysis with AISA eagle hyperspectral sensor data and water quality measurement in-situ data. The result of linear regression for a meaningful band combination shows $-24.847+0.013L_{560}$ as 560 nm in radiance (L) with 0.985 R-square. To comparison with Multispectral Imagery (MSI) case, we make simulated Landsat TM by spectral resampling. The regression using MSI shows -55.932 + 33.881 (TM1/TM3) as radiance with 0.968 R-square. Suspended Solid (SS) concentration was about 3.75 mg/l at in-situ data and estimated SS concentration by A-HIS was about 3.65 mg/l, and about 5.85mg/l with MSI with same location. It shows overestimation trends case of estimating using MSI. In order to upgrade value for practical use and to estimate more precisely, it needs that minimizing sun glint effect into whole image, constructing elaborate flight plan considering solar altitude angle, and making good pre-processing and calibration system. We found some limitations and restrictions such as precise atmospheric correction, sample count of water quality measurement, retrieve spectral bands into A-HSI, adequate linear regression model selection, and quantitative calibration/validation method through the literature review and test adopted general methods.

• Journal of KIISE:Information Networking
• /
• v.32 no.3
• /
• pp.279-290
• /
• 2005

Recently, as the serious damage caused by DDoS attacks increases, the rapid detection and the proper response mechanisms are urgent. However, existing security mechanisms do not effectively defend against these attacks, or the defense capability of some mechanisms is only limited to specific DDoS attacks. In this paper, we propose a detection architecture against DDoS attack using data mining technology that can classify the latest types of DDoS attack, and can detect the modification of existing attacks as well as the novel attacks. This architecture consists of a Misuse Detection Module modeling to classify the existing attacks, and an Anomaly Detection Module modeling to detect the novel attacks. And it utilizes the off-line generated models in order to detect the DDoS attack using the real-time traffic. We gathered the NetFlow data generated at an access router of our network in order to model the real network traffic and test it. The NetFlow provides the useful flow-based statistical information without tremendous preprocessing. Also, we mounted the well-known DDoS attack tools to gather the attack traffic. And then, our experimental results show that our approach can provide the outstanding performance against existing attacks, and provide the possibility of detection against the novel attack.

• Journal of Intelligence and Information Systems
• /
• v.20 no.2
• /
• pp.149-162
• /
• 2014

Course guidance is a mentoring process which is performed before students register for coming classes. The course guidance plays a very important role to students in checking degree audits of students and mentoring classes which will be taken in coming semester. Also, it is intimately involved with a graduation assessment or a completion of ABEEK certification. Currently, course guidance is manually performed by some advisers at most of universities in Korea because they have no electronic systems for the course guidance. By the lack of the systems, the advisers should analyze each degree audit of students and curriculum information of their own departments. This process often causes the human error during the course guidance process due to the complexity of the process. The electronic system thus is essential to avoid the human error for the course guidance. If the relation data model-based system is applied to the mentoring process, then the problems in manual way can be solved. However, the relational data model-based systems have some limitations. Curriculums of a department and certification systems can be changed depending on a new policy of a university or surrounding environments. If the curriculums and the systems are changed, a scheme of the existing system should be changed in accordance with the variations. It is also not sufficient to provide semantic search due to the difficulty of extracting semantic relationships between subjects. In this paper, we model a course mentoring ontology based on the analysis of a curriculum of computer science department, a structure of degree audit, and ABEEK certification. Ontology-based course guidance system is also proposed to overcome the limitation of the existing methods and to provide the effectiveness of course mentoring process for both of advisors and students. In the proposed system, all data of the system consists of ontology instances. To create ontology instances, ontology population module is developed by using JENA framework which is for building semantic web and linked data applications. In the ontology population module, the mapping rules to connect parts of degree audit to certain parts of course mentoring ontology are designed. All ontology instances are generated based on degree audits of students who participate in course mentoring test. The generated instances are saved to JENA TDB as a triple repository after an inference process using JENA inference engine. A user interface for course guidance is implemented by using Java and JENA framework. Once a advisor or a student input student's information such as student name and student number at an information request form in user interface, the proposed system provides mentoring results based on a degree audit of current student and rules to check scores for each part of a curriculum such as special cultural subject, major subject, and MSC subject containing math and basic science. Recall and precision are used to evaluate the performance of the proposed system. The recall is used to check that the proposed system retrieves all relevant subjects. The precision is used to check whether the retrieved subjects are relevant to the mentoring results. An officer of computer science department attends the verification on the results derived from the proposed system. Experimental results using real data of the participating students show that the proposed course guidance system based on course mentoring ontology provides correct course mentoring results to students at all times. Advisors can also reduce their time cost to analyze a degree audit of corresponding student and to calculate each score for the each part. As a result, the proposed system based on ontology techniques solves the difficulty of mentoring methods in manual way and the proposed system derive correct mentoring results as human conduct.

• Journal of Korean Society of Archives and Records Management
• /
• v.10 no.2
• /
• pp.75-99
• /
• 2010

Digital resources are widely used in our modern society. However, we are facing fundamental problems to maintain and preserve digital resources over time. Several standard methods for preserving digital resources have been developed and are in use. It is widely recognized that metadata is one of the most important components for digital archiving and preservation. There are many metadata standards for archiving and preservation of digital resources, where each standard has its own feature in accordance with its primary application. This means that each schema has to be appropriately selected and tailored in accordance with a particular application. And, in some cases, those schemas are combined in a larger frame work and container metadata such as the DCMI application framework and METS. There are many metadata standards for archives of digital resources. We used the following metadata standards in this study for the feature analysis me metadata standards - AGLS Metadata which is defined to improve search of both digital resources and non-digital resources, ISAD(G) which is a commonly used standard for archives, EAD which is well used for digital archives, OAIS which defines a metadata framework for preserving digital objects, and PREMIS which is designed primarily for preservation of digital resources. In addition, we extracted attributes from the decision tree defined for digital preservation process by Digital Preservation Coalition (DPC) and compared the set of attributes with these metadata standards. This paper shows the features of these metadata standards obtained through the feature analysis based on the records lifecycle model. The features are shown in a single frame work which makes it easy to relate the tasks in the lifecycle to metadata elements of these standards. As a result of the detailed analysis of the metadata elements, we clarified the features of the standards from the viewpoint of relationships between the elements and the lifecycle stages. Mapping between metadata schemas is often required in the long-term preservation process because different schemes are used in the records lifecycle. Therefore, it is crucial to build a unified framework to enhance interoperability of these schemes. This study presents a basis for the interoperability of different metadata schemas used in digital archiving and preservation.