• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.62 no.2
• /
• pp.149-155
• /
• 2017

To establish cultivation areas for the stable production of yacon, this study investigated the productivity and functional component contents of yacon in eight regions of Korea from 2011 to 2013. The results of principal component analysis using these data were as follows. A survey of 16 agricultural traits and meteorological data in the eight yacon cultivation areas showed that five factors (average temperature, maximum temperature, minimum temperature, frost-free days, and fructooligosaccharide content) were highly significant at the p < 0.001 level. Among the 16 agricultural traits and meteorological data used in the main component analysis of yacon cultivation areas, approximately eight contributed to the first principal component, and approximately four contributed to each of the second and third principal components. In particular, factors related to productivity, fructooligosaccharide content, and temperature change were considered important criteria for the classification of cultivation areas. The cultivation areas were divided into three groups by principal component analysis. In Group I, containing the Jinbu and Bonghwa areas in the mid-highland region at 500-560 m above sea level, the product yield was the highest at 2,622-3,196 kg/10a, the fructooligosaccharide content was also the highest at 9.04-9.62%, and the mean temperature was $17.3-18.5^{\circ}C$. In Group II, the areas Suncheon, Okcheon, Yeoju, and Gangneung, at 20-180 m above sea level, had the lowest yield, relatively lower fructooligosaccharide content, and the highest temperature. The areas in Group III showed values intermediate between those of Group I and Group II. For the different yacon cultivation areas, the product quantity and fructooligosaccharide content differed according to the environmental temperature, and the temperature conditions and number of frost-free days are considered important indicators for cultivation sites. Therefore, in terms of producing yacon with high quality, cultivation at 500-560 m is considered to give a higher yield and functional fructooligosaccharide content.

• Korean Journal of Remote Sensing
• /
• v.37 no.3
• /
• pp.449-461
• /
• 2021

Analysis Ready Data (ARD) for optical satellite images represents a pre-processed product by applying spectral characteristics and viewing parameters for each sensor. The atmospheric correction is one of the fundamental and complicated topics, which helps to produce Top-of-Atmosphere (TOA) and Top-of-Canopy (TOC) reflectance from multi-spectral image sets. Most remote sensing software provides algorithms or processing schemes dedicated to those corrections of the Landsat-8 OLI sensors. Furthermore, Google Earth Engine (GEE), provides direct access to Landsat reflectance products, USGS-based ARD (USGS-ARD), on the cloud environment. We implemented the Orfeo ToolBox (OTB) atmospheric correction extension, an open-source remote sensing software for manipulating and analyzing high-resolution satellite images. This is the first tool because OTB has not provided calibration modules for any Landsat sensors. Using this extension software, we conducted the absolute atmospheric correction on the Landsat-8 OLI images of Railroad Valley, United States (RVUS) to validate their reflectance products using reflectance data sets of RVUS in the RadCalNet portal. The results showed that the reflectance products using the OTB extension for Landsat revealed a difference by less than 5% compared to RadCalNet RVUS data. In addition, we performed a comparative analysis with reflectance products obtained from other open-source tools such as a QGIS semi-automatic classification plugin and SAGA, besides USGS-ARD products. The reflectance products by the OTB extension showed a high consistency to those of USGS-ARD within the acceptable level in the measurement data range of the RadCalNet RVUS, compared to those of the other two open-source tools. In this study, the verification of the atmospheric calibration processor in OTB extension was carried out, and it proved the application possibility for other satellite sensors in the Compact Advanced Satellite (CAS)-500 or new optical satellites.

• 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 Dairy Science and Biotechnology
• /
• v.34 no.2
• /
• pp.117-135
• /
• 2016

The present study was performed to develop a functional raw food material from hydrolyzed whey protein powder (23%-GNANA) medication containing sialic acid as a marker compound that is naturally occurring at 7% concentration in GMP (glycomacropeptide). GMP is used worldwide in foodstuffs for babies and infants and is obtained from the milk protein as safe food. While the purpose of our detailed evaluation was aimed to assess preliminary NOAEL values for and above 2,000 mg/kg/day, a clinical dose allowance for 23%-GNANA (as per characteristic of a functional health product, a highly refined test substance of 23% (v/v) sialic acid combined in GMP), at the same time we also wanted to assess the safety of GMP hydrolyzate lacking sialic acid but with identical properties as GMP. Animal safety evaluation was conducted using 23%-GNANA as the test substance, produced from hydrolyzed whey protein powder (product name: HELICOBACTROL-23; provided by Medinutrol Inc. [Korea]; composed of 23% sialic acid and GMP protein) after isolating the sialic acid using enzymes approved as food additives, with GMP as a raw material, and subsequently increasing the content of xx up to 23% through 80% (v/v) ethanol soaking and concentrating, in accordance with GLP Guideline. The animal safety evaluation mentioned above was made on the basis of toxicity in SPF Sprague-Dawley female and male rats dosed with 10 mL of the test substance diluted to 0, 1,250, 2,500, and 5,000 mg/kg directly into their stomachs for 90 d. This was determined in terms of the general symptoms and animal viability, weight and amount of feed intake, eye examination, uracrasia tests, hematological and blood biochemical disorder tests, blood coagulation test, abnormal intestine weight, abnormalities during postmortem and histopathological examinations. Statistical significance was set at P<0.05. Based on the toxicity determination, a certain minor effect associated with the test substance was observed in male rats with no major effects of the tested substance, in comparison with the control group dosed with sterilized water. Nevertheless, the NOAEL value, evaluated as per toxicity criteria, was verified as 5,000 mg/kg/day (P<0.05). Similarly, for female rats, a certain minor effect associated with the test substance was observed in 5,000 mg/kg/day dosed group, with no major effect, yet the NOAEL value (as assessed as per toxicity criteria) was determined to be 5,000 mg/kg/day (P<0.05), which was the same as for male rats. Accordingly, the NOAEL values of the test substances for all female and male rats were finally verified as 5,000 mg/kg/day (P<0.05). In conclusion, it was determined that the 23%-GNANA test substance exceeds 2,000 mg/kg/day, the clinical allowance characteristic for functional health food, and was finally evaluated to cause no safety concerns when used as a raw material in functional health food production, which was the ultimate goal of the present study.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.157-173
• /
• 2021

With the development of information technology, the amount of available information increases daily. However, having access to so much information makes it difficult for users to easily find the information they seek. Users want a visualized system that reduces information retrieval and learning time, saving them from personally reading and judging all available information. As a result, recommendation systems are an increasingly important technologies that are essential to the business. Collaborative filtering is used in various fields with excellent performance because recommendations are made based on similar user interests and preferences. However, limitations do exist. Sparsity occurs when user-item preference information is insufficient, and is the main limitation of collaborative filtering. The evaluation value of the user item matrix may be distorted by the data depending on the popularity of the product, or there may be new users who have not yet evaluated the value. The lack of historical data to identify consumer preferences is referred to as data sparsity, and various methods have been studied to address these problems. However, most attempts to solve the sparsity problem are not optimal because they can only be applied when additional data such as users' personal information, social networks, or characteristics of items are included. Another problem is that real-world score data are mostly biased to high scores, resulting in severe imbalances. One cause of this imbalance distribution is the purchasing bias, in which only users with high product ratings purchase products, so those with low ratings are less likely to purchase products and thus do not leave negative product reviews. Due to these characteristics, unlike most users' actual preferences, reviews by users who purchase products are more likely to be positive. Therefore, the actual rating data is over-learned in many classes with high incidence due to its biased characteristics, distorting the market. Applying collaborative filtering to these imbalanced data leads to poor recommendation performance due to excessive learning of biased classes. Traditional oversampling techniques to address this problem are likely to cause overfitting because they repeat the same data, which acts as noise in learning, reducing recommendation performance. In addition, pre-processing methods for most existing data imbalance problems are designed and used for binary classes. Binary class imbalance techniques are difficult to apply to multi-class problems because they cannot model multi-class problems, such as objects at cross-class boundaries or objects overlapping multiple classes. To solve this problem, research has been conducted to convert and apply multi-class problems to binary class problems. However, simplification of multi-class problems can cause potential classification errors when combined with the results of classifiers learned from other sub-problems, resulting in loss of important information about relationships beyond the selected items. Therefore, it is necessary to develop more effective methods to address multi-class imbalance problems. We propose a collaborative filtering model using CGAN to generate realistic virtual data to populate the empty user-item matrix. Conditional vector y identify distributions for minority classes and generate data reflecting their characteristics. Collaborative filtering then maximizes the performance of the recommendation system via hyperparameter tuning. This process should improve the accuracy of the model by addressing the sparsity problem of collaborative filtering implementations while mitigating data imbalances arising from real data. Our model has superior recommendation performance over existing oversampling techniques and existing real-world data with data sparsity. SMOTE, Borderline SMOTE, SVM-SMOTE, ADASYN, and GAN were used as comparative models and we demonstrate the highest prediction accuracy on the RMSE and MAE evaluation scales. Through this study, oversampling based on deep learning will be able to further refine the performance of recommendation systems using actual data and be used to build business recommendation systems.

• Journal of Intelligence and Information Systems
• /
• v.27 no.2
• /
• pp.1-15
• /
• 2021

If it is difficult for us to make decisions, we ask for advice from friends or people around us. When we decide to buy products online, we read anonymous reviews and buy them. With the advent of the Data-driven era, IT technology's development is spilling out many data from individuals to objects. Companies or individuals have accumulated, processed, and analyzed such a large amount of data that they can now make decisions or execute directly using data that used to depend on experts. Nowadays, the recommender system plays a vital role in determining the user's preferences to purchase goods and uses a recommender system to induce clicks on web services (Facebook, Amazon, Netflix, Youtube). For example, Youtube's recommender system, which is used by 1 billion people worldwide every month, includes videos that users like, "like" and videos they watched. Recommended system research is deeply linked to practical business. Therefore, many researchers are interested in building better solutions. Recommender systems use the information obtained from their users to generate recommendations because the development of the provided recommender systems requires information on items that are likely to be preferred by the user. We began to trust patterns and rules derived from data rather than empirical intuition through the recommender systems. The capacity and development of data have led machine learning to develop deep learning. However, such recommender systems are not all solutions. Proceeding with the recommender systems, there should be no scarcity in all data and a sufficient amount. Also, it requires detailed information about the individual. The recommender systems work correctly when these conditions operate. The recommender systems become a complex problem for both consumers and sellers when the interaction log is insufficient. Because the seller's perspective needs to make recommendations at a personal level to the consumer and receive appropriate recommendations with reliable data from the consumer's perspective. In this paper, to improve the accuracy problem for "appropriate recommendation" to consumers, the recommender systems are proposed in combination with context-based deep learning. This research is to combine user-based data to create hybrid Recommender Systems. The hybrid approach developed is not a collaborative type of Recommender Systems, but a collaborative extension that integrates user data with deep learning. Customer review data were used for the data set. Consumers buy products in online shopping malls and then evaluate product reviews. Rating reviews are based on reviews from buyers who have already purchased, giving users confidence before purchasing the product. However, the recommendation system mainly uses scores or ratings rather than reviews to suggest items purchased by many users. In fact, consumer reviews include product opinions and user sentiment that will be spent on evaluation. By incorporating these parts into the study, this paper aims to improve the recommendation system. This study is an algorithm used when individuals have difficulty in selecting an item. Consumer reviews and record patterns made it possible to rely on recommendations appropriately. The algorithm implements a recommendation system through collaborative filtering. This study's predictive accuracy is measured by Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). Netflix is strategically using the referral system in its programs through competitions that reduce RMSE every year, making fair use of predictive accuracy. Research on hybrid recommender systems combining the NLP approach for personalization recommender systems, deep learning base, etc. has been increasing. Among NLP studies, sentiment analysis began to take shape in the mid-2000s as user review data increased. Sentiment analysis is a text classification task based on machine learning. The machine learning-based sentiment analysis has a disadvantage in that it is difficult to identify the review's information expression because it is challenging to consider the text's characteristics. In this study, we propose a deep learning recommender system that utilizes BERT's sentiment analysis by minimizing the disadvantages of machine learning. This study offers a deep learning recommender system that uses BERT's sentiment analysis by reducing the disadvantages of machine learning. The comparison model was performed through a recommender system based on Naive-CF(collaborative filtering), SVD(singular value decomposition)-CF, MF(matrix factorization)-CF, BPR-MF(Bayesian personalized ranking matrix factorization)-CF, LSTM, CNN-LSTM, GRU(Gated Recurrent Units). As a result of the experiment, the recommender system based on BERT was the best.

• Journal of Intelligence and Information Systems
• /
• v.19 no.3
• /
• pp.113-125
• /
• 2013

Every company wants to know customer's requirement and makes an effort to meet them. Cause that, communication between customer and company became core competition of business and that important is increasing continuously. There are several strategies to find customer's needs, but VOC (Voice of customer) is one of most powerful communication tools and VOC gathering by several channels as telephone, post, e-mail, website and so on is so meaningful. So, almost company is gathering VOC and operating VOC system. VOC is important not only to business organization but also public organization such as government, education institute, and medical center that should drive up public service quality and customer satisfaction. Accordingly, they make a VOC gathering and analyzing System and then use for making a new product and service, and upgrade. In recent years, innovations in internet and ICT have made diverse channels such as SNS, mobile, website and call-center to collect VOC data. Although a lot of VOC data is collected through diverse channel, the proper utilization is still difficult. It is because the VOC data is made of very emotional contents by voice or text of informal style and the volume of the VOC data are so big. These unstructured big data make a difficult to store and analyze for use by human. So that, the organization need to automatic collecting, storing, classifying and analyzing system for unstructured big VOC data. This study propose an intelligent VOC analyzing system based on opinion mining to classify the unstructured VOC data automatically and determine the polarity as well as the type of VOC. And then, the basis of the VOC opinion analyzing system, called domain-oriented sentiment dictionary is created and corresponding stages are presented in detail. The experiment is conducted with 4,300 VOC data collected from a medical website to measure the effectiveness of the proposed system and utilized them to develop the sensitive data dictionary by determining the special sentiment vocabulary and their polarity value in a medical domain. Through the experiment, it comes out that positive terms such as "칭찬, 친절함, 감사, 무사히, 잘해, 감동, 미소" have high positive opinion value, and negative terms such as "퉁명, 뭡니까, 말하더군요, 무시하는" have strong negative opinion. These terms are in general use and the experiment result seems to be a high probability of opinion polarity. Furthermore, the accuracy of proposed VOC classification model has been compared and the highest classification accuracy of 77.8% is conformed at threshold with -0.50 of opinion classification of VOC. Through the proposed intelligent VOC analyzing system, the real time opinion classification and response priority of VOC can be predicted. Ultimately the positive effectiveness is expected to catch the customer complains at early stage and deal with it quickly with the lower number of staff to operate the VOC system. It can be made available human resource and time of customer service part. Above all, this study is new try to automatic analyzing the unstructured VOC data using opinion mining, and shows that the system could be used as variable to classify the positive or negative polarity of VOC opinion. It is expected to suggest practical framework of the VOC analysis to diverse use and the model can be used as real VOC analyzing system if it is implemented as system. Despite experiment results and expectation, this study has several limits. First of all, the sample data is only collected from a hospital web-site. It means that the sentimental dictionary made by sample data can be lean too much towards on that hospital and web-site. Therefore, next research has to take several channels such as call-center and SNS, and other domain like government, financial company, and education institute.

• 대한공업교육학회지
• /
• v.40 no.2
• /
• pp.155-174
• /
• 2015

The purposes of this study were to analyze the property of educational needs of teachers for educational contents of invention and intellectual property in secondary vocational education and provide fundamental data for the development of job training programs so as to develop the capabilities of teachers, the base for effective education of invention intellectual property in secondary vocational education. To achieve them, educational needs for the educational contents of invention intellectual property and the priority of the educational needs in secondary vocational education based on the recognition of the teachers were analyzed and suggested. Concrete results of this study can be suggested as follows. First, the average of educational needs of the teachers for the educational contents of invention intellectual property in secondary vocational education was 5.02. There were 23 items of the educational contents whose educational needs were higher than the average of the whole items and for those items and the average of each item, there were F4(The average of patent applications) 6.72, F5(Modification and supplementation of specification sheets) 6.46, F2(Writing of patent floor plans) 6.39, F3(Writing of patent specification sheets and abstraction) 6.31, A5(Invention method and activity) 6.27, E6(Invention design project) 6.15, H3(Invention commercialization) 5.97, F1(Patent information and application) 5.90, E5(Design obligation) 5.78, E3(Designing process of inventional design) 5.77, A4(Invention and problem solving) 5.57, G2(Patent investigation and classification) 5.47, C2(Thinking method of inventional problem solution) 5.45, E4(Production of inventional design product) 5.45, B5(Inventional patent project) 5.42, A2(Creativity development) 5.26, C4(Inventional problem solving project) 5.26, H4(Invention marketing) 5.26, H2(Analysis on invention commercialization) 5.20, D4(Invention and management) 5.16, C3(Problem solving activity) 5.14, E2(Inventional design devise and expression) 5.11, B3(Actuality of inventional method) 5.08 in order. Second, for the priority of educational needs of the teachers for the educational contents of invention intellectual property in secondary vocational education, there were 13 items of the educational contents for the first rank, 10 for the second rank and 17 for the third rank. The items of the educational contents for the first rank were A4(invention and problem solving), A5(inventional method and activity), B5(Invention patent project), C2(Thinking method of inventional problem solution), C4(Inventional problem solving project), E3(Inventional design process), E4(Production of inventional design product), E5(Design obligation), E6(Invention design project), F1(Patent information and application), F2(Writing of patent floor plan), F3(Writing of patent specification sheet and abstract), and H3(Invention commercialization. The items of the educational contents for the second rank were A2(Creativity development), B3(Actuality of inventional method), C3(Problem solving activity), D4(Invention and management), E2(Invention design devise and expression), F4(Range of patent demand), F5(Modification and supplementation of specification sheet), G2(Patent investigation and classification), H2(Analysis on invention commercialization), and H4(Invention marketing). The items for the third rank were the educational contents except the ones of the first rank and the second rank.

• Journal of Digital Convergence
• /
• v.18 no.6
• /
• pp.53-63
• /
• 2020

Electronic financial transactions are also actively increasing due to the rapid spread of information communication media such as the Internet, smart devices, and IoT, but as a derivative by-product, threats of financial security such as leakage of various personal information and hacking are also increasing. Therefore, the importance of financial security against this is increasing, but in Korea, financial security technology is relatively insufficient compared to advanced countries in the field of financial security, such as Active-X. Therefore, this study aims to present the major development direction in the domestic financial security field by comparing key technology trends with IPC classification frequency analysis, keyword frequency analysis, and keyword network analysis based on domestic and foreign financial security-related patent data. In conclusion, it seems that recent domestic and foreign trends have focused on the development of related technologies according to the development of smart device-based electronic financial services. Accordingly, it is intended to be used as the basis data for technology development of financial security by mapping the trend of financial security research trend and technology trend analysis through thesis data analysis that reflects the research of the preceding aspect as the technology of commercialization in the future.

• Korean Journal of Clinical Pharmacy
• /
• v.23 no.4
• /
• pp.327-333
• /
• 2013

Background: Antihistamine and anti-allergy medications are widely used during pregnancy. Reading label information is one of the easiest ways to get safety information. But there are content gaps among countries. Objective: To compare the risk level and the recommendation level of antihistamine/anti-allergy drug's label information in pregnant women among Korea, the USA, the UK, and Japan. Method: Study drugs of antihistamine/anti-allergy medications were selected according to Korea drug classification codes. Based on the label information of selected product, risk level was classified into 5 categories as follows: 'Definite', 'Probable', 'Possible', and 'Unlikely', 'Unclassified' according to the level of evidence. Recommendation level was classified into 4 categories as follows: 'Contraindicated', 'Cautious', 'Compatible', and 'Unclassified'. Frequency and proportion were presented according to the each category. To estimate agreement of each category among 4 countries, percent agreement and kappa (k) coefficient were calculated. Results: Total 13 drug ingredients were selected for antihistamine/anti-allergy medications. In risk level, Korea (46%) and Japan (69%) were mostly classified in the category of 'Unclassified', but 'Unlikely' category was more frequent in the UK (62%) and the USA (46%). In recommendation level, the proportion of 'Contraindicated' was highest in Korea (46%) compared to other countries. In contrast, the category of 'Cautious' was 77%-85% in the USA, the UK, and Japan. The percent agreement for risk level was highest in the USA-UK (54%). The recommendation level of Korea-USA showed lowest agreement for percent agreement (46%) and kappa coefficient (k=0.02). Conclusion: We confirmed the differences among safety information provided by four different countries. 'Contraindicated' was more likely in Korea compared with other countries.