• Title/Summary/Keyword: 대학기반

Search Result 4,172, Processing Time 0.031 seconds

Conditional Generative Adversarial Network based Collaborative Filtering Recommendation System (Conditional Generative Adversarial Network(CGAN) 기반 협업 필터링 추천 시스템)

  • Kang, Soyi;Shin, Kyung-shik
    • 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.

Determination of Proper Irrigation Scheduling for Automated Irrigation System based on Substrate Capacitance Measurement Device in Tomato Rockwool Hydroponics (토마토 암면재배에서 정전용량 측정장치를 기반으로 한 급액방법 구명)

  • Han, Dongsup;Baek, Jeonghyeon;Park, Juseong;Shin, Wonkyo;Cho, Ilhwan;Choi, Eunyoung
    • Journal of Bio-Environment Control
    • /
    • v.28 no.4
    • /
    • pp.366-375
    • /
    • 2019
  • This experiment aims to determine the proper irrigation scheduling based on a whole-substrate capacitance using a newly developed device (SCMD) by comparing with the integrated solar radiation automated irrigation system (ISR) and sap flow sensor automated irrigation system (SF) for the cultivation of tomato (Solanum lycopersicum L. 'Hoyong' 'Super Doterang') during spring to winter season. For the SCMD system, irrigation was conducted every 10 minutes after the first irrigation was started until the first run-off was occurred, of which the substrate capacitance was considered to be 100%. When the capacitance threshold (CT) was reached to the target point, irrigation was re-conducted. After that, when the target drain volume (TDV) was occurred, the irrigation stopped. The irrigation volume per event for the SCMD was set to 50, 75, or 100 mL at CT 0.9 and TDV 100 mL during the spring to summer cultivation, and the CT was set to 0.65, 0.75, 0.80, or 0.90 in the winter cultivation. When the irrigation volume per event was set to 50, 75, or 100 mL, the irrigation frequency in a day was 39, 29, and 19, respectively, and the drain rate was 3.04, 9.25, and 20.18%, respectively. When the CT was set to 0.65, 0.75, or 0.90 in winter, the irrigation frequency was about 6, 7, 15 times, respectively and the drain rate was 9.9, 10.8, 35.3% respectively. The signal of stem sap flow at the beginning of irrigation starting time did not correspond to that of solar irradiance when the irrigation volume per event was set to 50 or 75 mL, compared to that of 100 mL. In winter cultivation, the stem sap flow rate and substrate volumetric water content at the CT 0.65 treatment were very low, while they were very high at CT 0.90 was high. All the integrated data suggest that the proper range of irrigation volume per event is from 75 to 100 mL under at CT 0.9 and TDV 100 mL during the spring to summer cultivation, and the proper CT seems to be higher than 0.75 and lower than 0.90 under at 75 mL of the irrigation volume per event and TDV 70 mL during the winter cultivation. It is going to be necessary to investigate the relationship between capacitance value and substrate volumetric water content by determining the correction coefficient.

Estimation of Soil Moisture Using Sentinel-1 SAR Images and Multiple Linear Regression Model Considering Antecedent Precipitations (선행 강우를 고려한 Sentinel-1 SAR 위성영상과 다중선형회귀모형을 활용한 토양수분 산정)

  • Chung, Jeehun;Son, Moobeen;Lee, Yonggwan;Kim, Seongjoon
    • Korean Journal of Remote Sensing
    • /
    • v.37 no.3
    • /
    • pp.515-530
    • /
    • 2021
  • This study is to estimate soil moisture (SM) using Sentinel-1A/B C-band SAR (synthetic aperture radar) images and Multiple Linear Regression Model(MLRM) in the Yongdam-Dam watershed of South Korea. Both the Sentinel-1A and -1B images (6 days interval and 10 m resolution) were collected for 5 years from 2015 to 2019. The geometric, radiometric, and noise corrections were performed using the SNAP (SentiNel Application Platform) software and converted to backscattering coefficient of VV and VH polarization. The in-situ SM data measured at 6 locations using TDR were used to validate the estimated SM results. The 5 days antecedent precipitation data were also collected to overcome the estimation difficulty for the vegetated area not reaching the ground. The MLRM modeling was performed using yearly data and seasonal data set, and correlation analysis was performed according to the number of the independent variable. The estimated SM was verified with observed SM using the coefficient of determination (R2) and the root mean square error (RMSE). As a result of SM modeling using only BSC in the grass area, R2 was 0.13 and RMSE was 4.83%. When 5 days of antecedent precipitation data was used, R2 was 0.37 and RMSE was 4.11%. With the use of dry days and seasonal regression equation to reflect the decrease pattern and seasonal variability of SM, the correlation increased significantly with R2 of 0.69 and RMSE of 2.88%.

Application of diversity of recommender system accordingtouserpreferencechange (사용자 선호도 변화에 따른 추천시스템의 다양성 적용)

  • Na, Hyeyeon;Nam, Kihwan
    • Journal of Intelligence and Information Systems
    • /
    • v.26 no.4
    • /
    • pp.67-86
    • /
    • 2020
  • Recommender Systems have been huge influence users and business more and more. Recently the importance of E-commerce has been reached rapid growth greatly in world-wide COVID-19 pandemic. Recommender system is the center of E-commerce lively. Top ranked E-commerce managers mentioned that recommender systems have a major influence on customer's purchase such as about 50% of Netflix, Amazon sales from their recommender systems. Most algorithms have been focused on improving accuracy of recommender system regardless of novelty, diversity, serendipity etc. Recommender systems with only high accuracy cannot satisfy business long-term profit because of generating sales polarization. In addition, customers do not experience enjoyment of shopping from only focusing accuracy recommender system because customer's preference is changed constantly. Therefore, recommender systems with various values need to be developed for user's high satisfaction. Reranking is the most useful methodology to realize diversity of recommender system. In this paper, diversity of recommender system is represented through constructing high similarity with users who have different preference using each user's purchased item's category algorithm. It is distinguished from past research approach which is changing the algorithm of recommender system without user's diversity preference level. We tried to discover user's diversity preference level and observed the results how the effect was different according to user's diversity preference level. In addition, graph-based recommender system was used to show diversity through user's network, not collaborative filtering. In this paper, Amazon Grocery and Gourmet Food data was used because the low-involvement product, such as habitual product, foods, low-priced goods etc., had high probability to show customer's diversity. First, a bipartite graph with users and items simultaneously is constructed to make graph-based recommender system. However, each users and items unipartite graph also need to be established to show diversity of recommender system. The weight of each unipartite graph has played crucial role changing Jaccard Distance of item's category. We can observe two important results from the user's unipartite network. First, the user's diversity preference level is observed from the network and second, dissimilar users can be discovered in the user's network. Through the research process, diversity of recommender system is presented highly with small accuracy loss and optimalization for higher accuracy is possible controlling diversity ratio. This paper has three important theoretical points. First, this research expands recommender system research for user's satisfaction with various values. Second, the graph-based recommender system is developed newly. Third, the evaluation indicator of diversity is made for diversity. In addition, recommender systems are useful for corporate profit practically and this paper has contribution on business closely. Above all, business long-term profit can be improved using recommender system with diversity and the recommender system can provide right service according to user's diversity level. Lastly, the corporate selling low-involvement products have great effect based on the results.

Establishment of A WebGIS-based Information System for Continuous Observation during Ocean Research Vessel Operation (WebGIS 기반 해양 연구선 상시관측 정보 체계 구축)

  • HAN, Hyeon-Gyeong;LEE, Cholyoung;KIM, Tae-Hoon;HAN, Jae-Rim;CHOI, Hyun-Woo
    • Journal of the Korean Association of Geographic Information Studies
    • /
    • v.24 no.1
    • /
    • pp.40-53
    • /
    • 2021
  • Research vessels(R/Vs) used for ocean research move to the planned research area and perform ocean observations suitable for the research purpose. The five research vessels of the Korea Institute of Ocean Science & Technology(KIOST) are equipped with global positioning system(GPS), water depth, weather, sea surface layer temperature and salinity measurement equipment that can be observed at all times during cruise. An information platform is required to systematically manage and utilize the data produced through such continuous observation equipment. Therefore, the data flow was defined through a series of business analysis ranging from the research vessel operation plan to observation during the operation of the research vessel, data collection, data processing, data storage, display and service. After creating a functional design for each stage of the business process, KIOST Underway Meteorological & Oceanographic Information System(KUMOS), a Web-Geographic information system (Web-GIS) based information platform, was built. Since the data produced during the cruise of the R/Vs have characteristics of temporal and spatial variability, a quality management system was developed that considered these variabilities. For the systematic management and service of data, the KUMOS integrated Database(DB) was established, and functions such as R/V tracking, data display, search and provision were implemented. The dataset provided by KUMOS consists of cruise report, raw data, Quality Control(QC) flagged data, filtered data, cruise track line data, and data report for each cruise of the R/V. The business processing procedure and system of KUMOS for each function developed through this study are expected to serve as a benchmark for domestic ocean-related institutions and universities that have research vessels capable of continuous observations during cruise.

An Exploration of MIS Quarterly Research Trends: Applying Topic Modeling and Keyword Network Analysis (MIS Quarterly 연구동향 탐색: 토픽모델링 및 키워드 네트워크 분석 활용)

  • Kang, Eunkyung;Jung, Yeonsik;Yang, Seonuk;Kwon, Jiyoon;Yang, Sung-Byung
    • Journal of Intelligence and Information Systems
    • /
    • v.28 no.2
    • /
    • pp.207-235
    • /
    • 2022
  • In a knowledge-based society where knowledge and information industries are the main pillars of the economy, knowledge sharing and diffusion and its systematic management are recognized as essential strategies for improving national competitiveness and sustainable social development. In the field of Information Systems (IS) research, where the convergence of information technology and management takes place in various ways, the evolution of knowledge occurs only when researchers cooperate in turning old knowledge into new knowledge from the perspective of the scientific knowledge network. In particular, it is possible to derive new insights by identifying topics of interest in the relevant research field, applied methodologies, and research trends through network-based interdisciplinary graftings such as citations, co-authorships, and keywords. In previous studies, various attempts have been made to understand the structure of the knowledge system and the research trends of the relevant community by revealing the relationship between research topics, methodologies, and co-authors. However, most studies have compared two or more journals and been limited to a certain period; hence, there is a lack of research that looked at research trends covering the entire history of IS research. Therefore, this study was conducted in the following order for all the papers (from its first issue in 1977 to the first quarter of 2022) published in the MIS Quarterly (MISQ) Journal, which plays a leading role in revealing knowledge in the IS research field: (1) After extracting keywords, (2) classifying the extracted keywords into research topics, methodologies, and theories, and (3) using topic modeling and keyword network analysis in order to identify the changes from the beginning to the present of the IS research in a chronological manner. Through this study, it is expected that by examining the changes in IS research published in MISQ, the developing patterns of IS research can be revealed, and a new research direction can be presented to IS researchers, nurturing the sustainability of future research.

A Study of Fluoride Adsorption in Aqueous Solution Using Iron Sludge based Adsorbent at Mine Drainage Treatment Facility (광산배수 정화시설 철 슬러지 기반 흡착제를 활용한 수용액상 불소 흡착에 관한 연구)

  • Lee, Joon Hak;Kim, Sun Joon
    • Economic and Environmental Geology
    • /
    • v.54 no.6
    • /
    • pp.709-716
    • /
    • 2021
  • In this study, an adsorbent prepared by natural drying of iron hydroxide-based sludge collected from settling basin at a mine drainage treatment facility located in Gangneung, Gangwon-do was used to remove fluoride in an artificial fluoride solution and mine drainage, and the adsorption characteristics of the adsorbent were investigated. As a result of analyzing the chemical composition, mineralogical properties, and specific surface area of the adsorbent used in the experiment, iron oxide (Fe2O3) occupies 79.2 wt.% as the main constituent, and a peak related to calcite (CaCO3) in the crystal structure analysis was analyzed. It was also identified that an irregular surface and a specific surface area of 216.78 m2·g-1. In the indoor batch-type experiment, the effect of changes in reaction time, pH, initial fluoride concentration and temperature on the change in adsorption amount was analyzed. The adsorption of fluoride showed an adsorption amount of 3.85 mg·g-1 16 hours after the start of the reaction, and the increase rate of the adsorption amount gradually decreased. Also, as the pH increased, the amount of fluoride adsorption decreased, and in particular, the amount of fluoride adsorption decreased rapidly around pH 5.5, the point of zero charge at which the surface charge of the adsorbent changes. Meanwhile, the results of the isotherm adsorption experiment were applied to the Langmuir and Freundlich isotherm adsorption models to infer the fluoride adsorption mechanism of the used adsorbent. To understand the thermodynamic properties of the adsorbent using the Van't Hoff equation, thermodynamic constants 𝚫H° and 𝚫G° were calculated using the adsorption amount information obtained by increasing the temperature from 25℃ to 65℃ to determine the adsorption characteristics of the adsorbent. Finally, the adsorbent was applied to the mine drainage having a fluoride concentration of about 12.8 mg·L-1, and the fluoride removal rate was about 50%.

A Development of Facility Web Program for Small and Medium-Sized PSM Workplaces (중·소규모 공정안전관리 사업장의 웹 전산시스템 개발)

  • Kim, Young Suk;Park, Dal Jae
    • Korean Chemical Engineering Research
    • /
    • v.60 no.3
    • /
    • pp.334-346
    • /
    • 2022
  • There is a lack of knowledge and information on the understanding and application of the Process Safety Management (PSM) system, recognized as a major cause of industrial accidents in small-and medium-sized workplaces. Hence, it is necessary to prepare a protocol to secure the practical and continuous levels of implementation for PSM and eliminate human errors through tracking management. However, insufficient research has been conducted on this. Therefore, this study investigated and analyzed the various violations in the administrative measures, based on the regulations announced by the Ministry of Employment and Labor, in approximately 200 small-and medium-sized PSM workplaces with fewer than 300 employees across in korea. This study intended to contribute to the prevention of major industrial accidents by developing a facility maintenance web program that removed human errors in small-and medium-sized workplaces. The major results are summarized as follows. First, It accessed the web via a QR code on a smart device to check the equipment's specification search function, cause of failure, and photos for the convenience of accessing the program, which made it possible to make requests for the it inspection and maintenance in real time. Second, it linked the identification of the targets to be changed, risk assessment, worker training, and pre-operation inspection with the program, which allowed the administrator to track all the procedures from start to finish. Third, it made it possible to predict the life of the equipment and verify its reliability based on the data accumulated through the registration of the pictures for improvements, repairs, time required, cost, etc. after the work was completed. It is suggested that these research results will be helpful in the practical and systematic operation of small-and medium-sized PSM workplaces. In addition, it can be utilized in a useful manner for the development and dissemination of a facility maintenance web program when establishing future smart factories in small-and medium-sized PSM workplaces under the direction of the government.

Image based Experience Goods, Text-based Search Goods: Cognitive Fit between Product Information Composition and Product Type depending on Regulatory Focus (이미지 기반의 경험재, 텍스트 기반의 탐색재: 조절초점에 따른 제품 정보 구성 방식과 제품 유형의 일치 효과)

  • Park, Kyung-Hee;Seo, Bong-Goon;Park, Do-Hyung
    • Journal of Intelligence and Information Systems
    • /
    • v.28 no.2
    • /
    • pp.75-100
    • /
    • 2022
  • Untact mobile commerce shows a rapid growth due to the prolonged COVID-19 pandemic. And companies have a lot of tough competition in this trend. However, the detail pages of products which play an important role in purchase decision have been provided mostly for consumers in a form of stereotyped information composition. This study has found that the form of (image-centered vs. text-centered) information composition of detailed descriptions of products in the detail pages of mobile products has an effect on product attitude and purchase intention as consumers' information appeal methods vary depending on product types (search goods vs. experience goods). That is, search goods whose information search is easy and whose quality is predictable could be found that product attitude and purchase intention have a more positive effect on the form of image-centered information composition. And experience goods whose quality is unpredictable could be found that product attitude and purchase intention have a more positive effect on the form of text-centered information composition. And effects of congruence between product types based on Higgins' regulatory focus theory and the form of information composition have found to vary depending on consumers' chronic regulatory focus. Promotion focus seeking consumers showed effects of congruence between product types and the form of information composition and prevention focus seeking consumers did not show effects of congruence between them. That is, promotion focus seeking consumers have found to have more positive product attitude and purchase intention in the form of image-centered information composition of experience goods and text-centered information composition of search goods. And prevention focus seeking consumers have found to be unable to have an effect on product attitude and purchase intention even though the form of image or text-centered information composition of search and experience goods is presented. The study implies that the form of information composition should be designed, produced, and provided for consumers by considering product types and consumer propensity when designing it in the detail pages of mobile products.

A Study on the Development Direction of Medical Image Information System Using Big Data and AI (빅데이터와 AI를 활용한 의료영상 정보 시스템 발전 방향에 대한 연구)

  • Yoo, Se Jong;Han, Seong Soo;Jeon, Mi-Hyang;Han, Man Seok
    • KIPS Transactions on Computer and Communication Systems
    • /
    • v.11 no.9
    • /
    • pp.317-322
    • /
    • 2022
  • The rapid development of information technology is also bringing about many changes in the medical environment. In particular, it is leading the rapid change of medical image information systems using big data and artificial intelligence (AI). The prescription delivery system (OCS), which consists of an electronic medical record (EMR) and a medical image storage and transmission system (PACS), has rapidly changed the medical environment from analog to digital. When combined with multiple solutions, PACS represents a new direction for advancement in security, interoperability, efficiency and automation. Among them, the combination with artificial intelligence (AI) using big data that can improve the quality of images is actively progressing. In particular, AI PACS, a system that can assist in reading medical images using deep learning technology, was developed in cooperation with universities and industries and is being used in hospitals. As such, in line with the rapid changes in the medical image information system in the medical environment, structural changes in the medical market and changes in medical policies to cope with them are also necessary. On the other hand, medical image information is based on a digital medical image transmission device (DICOM) format method, and is divided into a tomographic volume image, a volume image, and a cross-sectional image, a two-dimensional image, according to a generation method. In addition, recently, many medical institutions are rushing to introduce the next-generation integrated medical information system by promoting smart hospital services. The next-generation integrated medical information system is built as a solution that integrates EMR, electronic consent, big data, AI, precision medicine, and interworking with external institutions. It aims to realize research. Korea's medical image information system is at a world-class level thanks to advanced IT technology and government policies. In particular, the PACS solution is the only field exporting medical information technology to the world. In this study, along with the analysis of the medical image information system using big data, the current trend was grasped based on the historical background of the introduction of the medical image information system in Korea, and the future development direction was predicted. In the future, based on DICOM big data accumulated over 20 years, we plan to conduct research that can increase the image read rate by using AI and deep learning algorithms.