• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.2
• /
• pp.242-247
• /
• 2009

Recently an intelligent system is developed for the service what users want not a passive system which just answered user's request. This intelligent system is used for personalized recommendation system and representative techniques are content-based and collaborative filtering. In this study, we propose a prediction system which is based on the techniques of recommendation system using a collaborative filtering and a fuzzy system to solve the collaborative filtering problems. In order to verify the prediction system, we used the data that is user's rating about movies. We predicted the user's rating using this data. The accuracy of this prediction system is determined by computing the RMSE(root mean square error) of the system's prediction against the actual rating about the each movie and is compared with the existing system. Thus, this prediction system can be applied to base technology of recommendation system and also recommendation of multimedia such as music and books.

• Journal of Digital Convergence
• /
• v.17 no.1
• /
• pp.123-130
• /
• 2019

One of the most commonly used methods of web recommendation techniques is collaborative filtering. Many studies on collaborative filtering have suggested ways to improve accuracy. This study proposes a method of movie recommendation using Word2Vec and an ensemble convolutional neural networks. First, in the user, movie, and rating information, construct the user sentences and movie sentences. It inputs user sentences and movie sentences into Word2Vec to obtain user vectors and movie vectors. User vectors are entered into user convolution model and movie vectors are input to movie convolution model. The user and the movie convolution models are linked to a fully connected neural network model. Finally, the output layer of the fully connected neural network outputs forecasts of user movie ratings. Experimentation results showed that the accuracy of the technique proposed in this study accuracy of conventional collaborative filtering techniques was improved compared to those of conventional collaborative filtering technique and the technique using Word2Vec and deep neural networks proposed in a similar study.

• Journal of Korean Medicine Rehabilitation
• /
• v.31 no.4
• /
• pp.105-116
• /
• 2021

Objectives Lumbar herniated intervertebral disc (L-HIVD) is common disease in which Western-Korean collaborative treatment is performed in Korea. This study aimed to analyze Western-Korean collaborative treatment utilization of Korean patients with L-HIVD using Health Insurance Review & Assessment Service's Patients Sample Data. Methods This study used the Health Insurance Review & Assessment Service-National Patient Sample (HIRA-NPS) in 2018. Claim data of L-HIVD patients were extracted. The claim data were rebuilt with the operational concept of 'episode of care' and divided into Korean medicine episode group (KM), Western medicine episode group (WM) and collaborative treatment episode group (CT). General characteristics, medical expenses and healthcare utilization were analyzed. In addition, the difference of average visit day and average medical expenses between non-collaborative group (KM plus WM) and CT were analyzed by the propensity score matching method. Results A Total of 64,333 patients and 365,745 claims were extracted. The number of episodes of WM, KM and CT was 69,383 (92.97%), 3,903 (5.23%), and 1,341 (1.80%) respectively. The frequency of collaborative treatment episode was higher in women and the age of 50s. The most frequently described treatment in CT was acupuncture therapy. As a result of the propensity score matching, the number of visit days and medical expenses in the collaborative treatment group was higher than in the non-collaborative group. Conclusions The analysis of healthcare utilization of Korean-Western collaborative treatment may be used as basic data for establishing medical policies and systematic collaborative treatment model in the future.

• Journal of the Korean Society for information Management
• /
• v.37 no.2
• /
• pp.71-93
• /
• 2020

Today, in order to more effectively cope with the emergence of various diseases and the rapidly-changing medical environment, several medical departments are conducting treatment collaborations within the university hospital. This collaborative care is very important and is already common in the medical field. Nevertheless, there is no research on this, especially how the departments are collaborating. Therefore, the purpose of this study is to investigate how the characteristics of the treatment collaboration networks vary by year and season by exploring the relationship between the medical departments within the university hospital. This study analyzed the collaboration networks of 29 medical departments of 'A' university in Korea by dividing the collaborative care by year and season. Directed networks were constructed in response to departments requesting and departments requested for collaborative care. Betweenness centrality, eigenvector centrality, closeness centrality analysis, ego network analysis, and faction analysis were also conducted. This study performed the first treatment collaboration network analysis among medical departments, and is expected to present new insights into the location and spatial composition of medical departments in consideration of the knowledge transfer paths within medical institutions.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.87-97
• /
• 2024

This study aims to develop a system that enables users employing PC and VR devices to collaboratively analyze data visualizations in a remote environment. The system provides a task-oriented node-link control interface to aid users in understanding the visualization analysis process and effectively distributing roles. Additionally, it offers a network environment where multiple users can collaborate and receive feedback on visualization analysis even when physically separated. To elucidate the collaborative analysis method implemented in the system, we designed a scenario. Furthermore, we conducted a pilot experiment to evaluate the system's usability with participants majoring in related fields. The experimental results confirmed that users can freely analyze data through easily comprehensible interface manipulations in an extended reality space, and efficiently conduct real-time collaborative analysis in a remote environment.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.9 no.6
• /
• pp.609-616
• /
• 2016

This paper is proposed a customized market analysis method using SVM and collaborative filtering. The proposed customized market analysis scheme is consists of DC(Data Classification) module, ICF(Improved Collaborative Filtering) module, and CMA(Customized Market Analysis) module. DC module classifies the characteristics of on-line and off-line shopping mall and traditional markets into price, quality, and quantity using SVM. ICF module calculates the similarity by adding age weight and job weight, and generates network using the similarity of purchased item each users, and makes a recommendation list of neighbor nodes. And CMA module provides the result of customized market analysis using the data classification result of DC module and the recommendation list of ICF module. As a result of comparing the proposed customized recommendation list with the existing user based recommendation list, the case of recommendation list using the existing collaborative filtering scheme, precision is 0.53, recall is 0.56, and F-measure is 0.57. But the case of proposed customized recommendation list, precision is 0.78, recall is 0.85, and F-measure is 0.81. That is, the proposed customized recommendation list shows more precision.

• Journal of Korean Academy of Nursing
• /
• v.51 no.6
• /
• pp.703-719
• /
• 2021

Purpose: We aimed to identify collaborative disaster governance through the demand and supply analysis of resources recognized by nurses during the COVID-19 pandemic. Methods: We used a descriptive study design with an online survey technique for data collection. The survey questions were developed based on focus group interviews with nurses responding to COVID-19 and expert validity testing. A 42-question online survey focusing on disaster governance was sent to nurses working in COVID-19 designated hospitals, public health offices, and schools. A total of 630 nurses participated in the survey. Demand and supply analysis was used to identify the specific components of disaster governance during a pandemic situation and analyze priority areas in disaster governance, as reported by nurses. Results: Demand and supply analysis showed that supplies procurement, cooperation, education, and environment factors clustered in the high demand and supply quadrant while labor condition, advocacy, emotional support, and workload adjustment factors clustered in the high demand but low supply quadrant, indicating a strong need in those areas of disaster governance among nurses. The nurses practicing at the public health offices and schools showed major components of disaster governance plotted in the second quadrant, indicating weak collaborative disaster governance. Conclusion: These findings show that there is an unbalanced distribution among nurses, resulting in major challenges in collaborative disaster governance during COVID-19. In the future and current pandemic, collaborative disaster governance, through improved distribution, will be useful for helping nurses to access more required resources and achieve effective pandemic response.

• Allergy, Asthma & Immunology Research
• /
• v.10 no.6
• /
• pp.628-647
• /
• 2018

Purpose: Obesity is associated with metabolic dysregulation, but the underlying metabolic signatures involving clinical and inflammatory profiles of obese asthma are largely unexplored. We aimed at identifying the metabolic signatures of obese asthma. Methods: Eligible subjects with obese (n = 11) and lean (n = 22) asthma underwent body composition and clinical assessment, sputum induction, and blood sampling. Sputum supernatant was assessed for interleukin $(IL)-1{\beta}$, -4, -5, -6, -13, and tumor necrosis factor $(TNF)-{\alpha}$, and serum was detected for leptin, adiponectin and C-reactive protein. Untargeted gas chromatography time-of-flight mass spectrometry (GC-TOF-MS)-based metabolic profiles in sputum, serum and peripheral blood monocular cells (PBMCs) were analyzed by orthogonal projections to latent structures-discriminate analysis (OPLS-DA) and pathway topology enrichment analysis. The differential metabolites were further validated by correlation analysis with body composition, and clinical and inflammatory profiles. Results: Body composition, asthma control, and the levels of $IL-1{\beta}$, -4, -13, leptin and adiponectin in obese asthmatics were significantly different from those in lean asthmatics. OPLS-DA analysis revealed 28 differential metabolites that distinguished obese from lean asthmatic subjects. The validation analysis identified 18 potential metabolic signatures (11 in sputum, 4 in serum and 2 in PBMCs) of obese asthmatics. Pathway topology enrichment analysis revealed that cyanoamino acid metabolism, caffeine metabolism, alanine, aspartate and glutamate metabolism, phenylalanine, tyrosine and tryptophan biosynthesis, pentose phosphate pathway in sputum, and glyoxylate and dicarboxylate metabolism, glycerolipid metabolism and pentose phosphate pathway in serum are suggested to be significant pathways related to obese asthma. Conclusions: GC-TOF-MS-based metabolomics indicates obese asthma is characterized by a metabolic profile different from lean asthma. The potential metabolic signatures indicated novel immune-metabolic mechanisms in obese asthma with providing more phenotypic and therapeutic implications, which needs further replication and validation.

• Journal of Information Technology Services
• /
• v.13 no.4
• /
• pp.93-107
• /
• 2014

Interests on collaborative research and academic relationship among researchers have been increased. Collaborative researchers can maximize productivity, time and cost savings, and reduce the risk of research. An empirical study on the research productivity of co-authors' network and review efficiency of the reviewer network was conducted based on co-author networks and reviewer networks in Korea Society of IT Service. This study aims to find the characteristics of the co-author and reviewer networks, and to analyze research productivity and review efficiency in order to draw some implications. The meaning of interactions among professional groups was analyzed. Research productivity index was calculated using 728 authors' papers submitted to the society. In order to verify the effects of indicators of social network analysis on research productivity and review efficiency, correlation and regression analyses were used. As a result, the indicators of network centrality did not affect the review efficiency, but affect the research productivity.

• Proceedings of the KSME Conference
• /
• 2000.11a
• /
• pp.818-823
• /
• 2000

In practical design studies, most of designers solve multidisciplinary problems with complex design structure. These multidisciplinary problems have hundreds of analysis and thousands of variables. The sequence of process to solve these problems affects the speed of total design cycle. Thus it is very important for designer to reorder original design processes to minimize total cost and time. This is accomplished by decomposing large multidisciplinary problem into several multidisciplinary analysis subsystem (MDASS) and processing it in parallel. This paper proposes new strategy for parallel decomposition of multidisciplinary problem to raise design efficiency by using genetic algorithm and shows the relationship between decomposition and multidisciplinary design optimization (MDO) methodology.