• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.9
• /
• pp.3730-3744
• /
• 2020

This study proposes a deep learning-based evolutionary recommendation model for heterogeneous big data integration, for which collaborative filtering and a neural-network algorithm are employed. The proposed model is used to apply an individual's importance or sensory level to formulate a recommendation using the decision-making feedback. The evolutionary recommendation model is based on the Deep Neural Network (DNN), which is useful for analyzing and evaluating the feedback data among various neural-network algorithms, and the DNN is combined with collaborative filtering. The designed model is used to extract health information from data collected by the Korea National Health and Nutrition Examination Survey, and the collaborative filtering-based recommendation model was compared with the deep learning-based evolutionary recommendation model to evaluate its performance. The RMSE is used to evaluate the performance of the proposed model. According to the comparative analysis, the accuracy of the deep learning-based evolutionary recommendation model is superior to that of the collaborative filtering-based recommendation model.

• Journal of Family Resource Management and Policy Review
• /
• v.17 no.4
• /
• pp.85-100
• /
• 2013

The purposes of this study are to explore the effect of the network characteristics of Healthy Family Support Center on its performance, and also to investigate the mediating effect of the organizational properties on the performance. We used the data from 148 healthy family support centers in National Survey in Korea. The analytic sample for this study consists of 102 responses.(response rate=68.9%) Multivariate regression model estimated the effects of the network's structural, interactive and functional characteristics and the interaction between the network's characteristics and organizational properties on the performance The findings of this study demonstrate that healthy family support centers with higher closeness centrality and with better functional characteristics reported more performances. Moreover, Centers that are more independent in organizational properties showed higher performances. However, the findings did not show that the interaction between the network's characteristics and organizational properties mediates on the performance.

• Journal of Internet Computing and Services
• /
• v.25 no.1
• /
• pp.49-56
• /
• 2024

There have been emerging many use-cases applying recommendation systems especially in online platform. Although the performance of recommendation systems is affected by a variety of factors, selecting appropriate features is difficult since most of recommendation systems have sparse data. Conventional matrix factorization (MF) method is a basic way to handle with problems in the recommendation systems. However, the MF based scheme cannot reflect non-linearity characteristics well. As deep learning technology has been attracted widely, a deep neural network (DNN) framework based collaborative filtering (CF) was introduced to complement the non-linearity issue. However, there is still a problem related to feature embedding for use as input to the DNN. In this paper, we propose an effective method using singular value decomposition (SVD) based feature embedding for improving the DNN performance of recommendation algorithms. We evaluate the performance of recommendation systems using MovieLens dataset and show the proposed scheme outperforms the existing methods. Moreover, we analyze the performance according to the number of latent features in the proposed algorithm. We expect that the proposed scheme can be applied to the generalized recommendation systems.

• Journal of Broadcast Engineering
• /
• v.25 no.1
• /
• pp.1-12
• /
• 2020

In the medical field, numerical imbalance of data due to differences in disease prevalence is a common problem. It reduces the performance of a artificial intelligence network, leading to difficulties in learning a network with good performance. Recently, generative adversarial network (GAN) technology has been introduced as a way to address this problem, and its ability has been demonstrated by successful applications in various fields. However, it is still difficult to achieve good results in solving problems with performance degraded by numerical imbalances because the image resolution of the previous studies is not yet good enough and the structure in the image is modeled locally. In this paper, we propose a multi-scale conditional generative adversarial network based on attention mechanism, which can produce high resolution images to solve the numerical imbalance problem of chest X-ray image data. The network was able to produce images for various diseases by controlling condition variables with only one network. It's efficient and effective in that the network don't need to be learned independently for all disease classes and solves the problem of long distance dependency in image generation with self-attention mechanism.

• Proceedings of the Korean Nuclear Society Conference
• /
• 2004.10a
• /
• pp.1433-1434
• /
• 2004

• Food Science of Animal Resources
• /
• v.33 no.4
• /
• pp.463-473
• /
• 2013

Through the development of efficient data collecting technologies like RFID, and inter-enterprise collaboration platforms such as web services, companies which participate in supply chains can acquire visibility over the whole supply chain, and can make decisions to optimize the overall supply chain networks and processes, based on the extracted knowledge from historical data collected by the visibility system. Although not currently active, the MeatWatch system has been developed, and is used in part for this purpose, in the imported beef distribution network in Korea. However, the imported beef distribution network is too complicated to analyze its various aspects using ordinary process analysis approaches. In this paper, we suggest a novel approach, called RFID-based supply chain process mining, to automatically discover and analyze the overall supply chain processes from the distributed RFID event data, without any prior knowledge. The proposed approach was implemented and validated, by using a case study of the imported beef distribution network in Korea. Specifically we demonstrated that the proposed approach can be successfully applied to discover supply chain networks from the distributed event data, to simplify the supply chain networks, and to analyze anomaly of the distribution networks. Such novel process mining functionalities can reinforce the capability of traceability services like MeatWatch in the future.

• Journal of Nutrition and Health
• /
• v.46 no.3
• /
• pp.218-225
• /
• 2013

Although the functional ingredient has been evaluated by the Korea Food and Drug Administration (KFDA) based on scientific evidence, the levels of scientific evidence and consistency of the results might vary according to emerging data. Therefore, periodic re-evaluation may be needed for some functional ingredients. In this study, we re-evaluated scientific evidence for the antioxidant activity of coenzyme Q10 as a functional ingredient in health functional food. Literature searches were conducted using the Medline and Cochrane, KISS, and IBIDS databases for the years 1955-2010 with the search term of coenzyme Q10 in combination with antioxidant. The search was limited to human studies published in Korean, English, and Japanese. Using the KFDA's evidence based evaluation system for scientific evaluation of health claims, 33 human studies were identified and reviewed in order to evaluate the strength of the evidence supporting a relation between coenzyme Q10 and antioxidant activity. Among 33 studies, significant effects for antioxidant activities were reported in 22 studies and their daily intake amount was 60 to 300 mg. Based on this systematic review, we concluded that there was possible evidence to support a relation between coenzyme Q10 intake and antioxidant activities. However, because inconsistent results have recently been reported, future studies should be monitored.

• Journal of Korea Multimedia Society
• /
• v.8 no.6
• /
• pp.836-843
• /
• 2005

The Wireless Internet services widely spread out with the developments of CDMA(Code Division Multiple Access) networks and wireless units. In contrast to the telecommunication network, WPAN (Wireless Personal Area Network) enables to transmit data and voice in personal area. Although WPAN technologies are commercially utilized, the combined services with COMA network are not so poplar up to now. Various services can be provided using the combination between COMA and WPAN. This paper presents the practical and united model between COMA and WPAN. Specially, the main focus of this research lies on the design of the Middle-ware system of a handset which could be managing both COMA and WPAN. This system used Bluethooth by WPAN. For the devices with the proposed WPAN Middle-ware, service areas of the COMA network can be expanded to WPAN, various services can be realized by the transmission of data and voice, and consequently, the user computing environment could be improved.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.4 no.6
• /
• pp.1133-1151
• /
• 2010

Energy balanced consumption routing is based on assumption that the nodes consume energy both in transmitting and receiving. Lopsided energy consumption is an intrinsic problem in low-cost sensor networks characterized by multihop routing and in many traffic overhead pattern networks, and this irregular energy dissipation can significantly reduce network lifetime. In this paper, we study the problem of maximizing network lifetime through balancing energy consumption for uniformly deployed low-cost sensor networks. We formulate the energy consumption balancing problem as an optimal balancing data transmitting problem by combining the ideas of corona cluster based network division and optimized transmitting state routing strategy together with data transmission. We propose a localized cluster based routing scheme that guarantees balanced energy consumption among clusters within each corona. We develop a new energy cluster based routing protocol called "OECR". We design an offline centralized algorithm with time complexity O (log n) (n is the number of clusters) to solve the transmitting data distribution problem aimed at energy balancing consumption among nodes in different cluster. An approach for computing the optimal number of clusters to maximize the network lifetime is also presented. Based on the mathematical model, an optimized energy cluster routing (OECR) is designed and the solution for extending OEDR to low-cost sensor networks is also presented. Simulation results demonstrate that the proposed routing scheme significantly outperforms conventional energy routing schemes in terms of network lifetime.

• Journal of Environmental Impact Assessment
• /
• v.30 no.2
• /
• pp.75-88
• /
• 2021

Six locations in the automated monitoring network at the Geum River Basin were selected forthis study. The water quality characteristics at two of the locations in the water quality monitoring network that were identical, or nearby, were examined, and their correlations were evaluated through statistical analysis. The results of the water quality analysis were converted to the water quality index and expressed in grades for comparison. For the data necessary for the study, public data from four years, from 2016-2019 were used and the evaluation parameters were water temperature, pH, EC, DO, TOC, TN, and TP. Results of the analysis showed that the water quality concentrations measured in the automated monitoring network and the water quality monitoring network differed in some measured values, but they tended to register variation in a specified ratio in most of the locations in the network. The analysis of the correlations of the parameters between the two monitoring networks found that water temperature, EC, and DO showed high correlations between the two monitoring networks. The TOC, TN, and TP showed high correlations, with a 0.7 or higher (correlation coefficient r), with the exception of some of the monitoring networks, although their correlations were lower than those of the basic parameters. The water quality index analysis showed that the water quality index values of the automated monitoring network and the water quality monitoring network were similar. The water quality index decreased and the pollution degree increased in the downstream direction, in both networks.