• Journal of Intelligence and Information Systems
• /
• v.27 no.4
• /
• pp.73-95
• /
• 2021

This study uses Node2vec graph embedding method and Light GBM link prediction to explore undeveloped export candidate countries in Korea's food and beverage industry. Node2vec is the method that improves the limit of the structural equivalence representation of the network, which is known to be relatively weak compared to the existing link prediction method based on the number of common neighbors of the network. Therefore, the method is known to show excellent performance in both community detection and structural equivalence of the network. The vector value obtained by embedding the network in this way operates under the condition of a constant length from an arbitrarily designated starting point node. Therefore, it has the advantage that it is easy to apply the sequence of nodes as an input value to the model for downstream tasks such as Logistic Regression, Support Vector Machine, and Random Forest. Based on these features of the Node2vec graph embedding method, this study applied the above method to the international trade information of the Korean food and beverage industry. Through this, we intend to contribute to creating the effect of extensive margin diversification in Korea in the global value chain relationship of the industry. The optimal predictive model derived from the results of this study recorded a precision of 0.95 and a recall of 0.79, and an F1 score of 0.86, showing excellent performance. This performance was shown to be superior to that of the binary classifier based on Logistic Regression set as the baseline model. In the baseline model, a precision of 0.95 and a recall of 0.73 were recorded, and an F1 score of 0.83 was recorded. In addition, the light GBM-based optimal prediction model derived from this study showed superior performance than the link prediction model of previous studies, which is set as a benchmarking model in this study. The predictive model of the previous study recorded only a recall rate of 0.75, but the proposed model of this study showed better performance which recall rate is 0.79. The difference in the performance of the prediction results between benchmarking model and this study model is due to the model learning strategy. In this study, groups were classified by the trade value scale, and prediction models were trained differently for these groups. Specific methods are (1) a method of randomly masking and learning a model for all trades without setting specific conditions for trade value, (2) arbitrarily masking a part of the trades with an average trade value or higher and using the model method, and (3) a method of arbitrarily masking some of the trades with the top 25% or higher trade value and learning the model. As a result of the experiment, it was confirmed that the performance of the model trained by randomly masking some of the trades with the above-average trade value in this method was the best and appeared stably. It was found that most of the results of potential export candidates for Korea derived through the above model appeared appropriate through additional investigation. Combining the above, this study could suggest the practical utility of the link prediction method applying Node2vec and Light GBM. In addition, useful implications could be derived for weight update strategies that can perform better link prediction while training the model. On the other hand, this study also has policy utility because it is applied to trade transactions that have not been performed much in the research related to link prediction based on graph embedding. The results of this study support a rapid response to changes in the global value chain such as the recent US-China trade conflict or Japan's export regulations, and I think that it has sufficient usefulness as a tool for policy decision-making.

• The KIPS Transactions:PartC
• /
• v.10C no.5
• /
• pp.625-634
• /
• 2003

More than a decade after its initial proposal, deployment of IP Multicast has been limited due to the problem of traffic control in multicast routing, multicast address allocation in global internet, reliable multicast transport techniques etc. Lately, according to increase of multicast application service such as internet broadcast, real time security information service etc., overlay multicast is developed as a new internet multicast technology. In this paper, we describe an overlay multicast protocol and propose fast join mechanism that considers switching of the tree. To find a potential parent, an existing search algorithm descends the tree from the root by one level at a time, and it causes long joining latency. Also, it is try to select the nearest node as a potential parent. However, it can't select the nearest node by the degree limit of the node. As a result, the generated tree has low efficiency. To reduce long joining latency and improve the efficiency of the tree, we propose searching two levels of the tree at a time. This method forwards joining request message to own children node. So, at ordinary times, there is no overhead to keep the tree. But the joining request came, the increasing number of searching messages will reduce a long joining latency. Also searching more nodes will be helpful to construct more efficient trees. In order to evaluate the performance of our fast join mechanism, we measure the metrics such as the search latency and the number of searched node and the number of switching by the number of members and degree limit. The simulation results show that the performance of our mechanism is superior to that of the existing mechanism.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.19-38
• /
• 2017

Collaborative filtering (CF) algorithm has been popularly used for implementing recommender systems. Until now, there have been many prior studies to improve the accuracy of CF. Among them, some recent studies adopt 'hybrid recommendation approach', which enhances the performance of conventional CF by using additional information. In this research, we propose a new hybrid recommender system which fuses CF and the results from the social network analysis on trust and distrust relationship networks among users to enhance prediction accuracy. The proposed algorithm of our study is based on memory-based CF. But, when calculating the similarity between users in CF, our proposed algorithm considers not only the correlation of the users' numeric rating patterns, but also the users' in-degree centrality values derived from trust and distrust relationship networks. In specific, it is designed to amplify the similarity between a target user and his or her neighbor when the neighbor has higher in-degree centrality in the trust relationship network. Also, it attenuates the similarity between a target user and his or her neighbor when the neighbor has higher in-degree centrality in the distrust relationship network. Our proposed algorithm considers four (4) types of user relationships - direct trust, indirect trust, direct distrust, and indirect distrust - in total. And, it uses four adjusting coefficients, which adjusts the level of amplification / attenuation for in-degree centrality values derived from direct / indirect trust and distrust relationship networks. To determine optimal adjusting coefficients, genetic algorithms (GA) has been adopted. Under this background, we named our proposed algorithm as SNACF-GA (Social Network Analysis - based CF using GA). To validate the performance of the SNACF-GA, we used a real-world data set which is called 'Extended Epinions dataset' provided by 'trustlet.org'. It is the data set contains user responses (rating scores and reviews) after purchasing specific items (e.g. car, movie, music, book) as well as trust / distrust relationship information indicating whom to trust or distrust between users. The experimental system was basically developed using Microsoft Visual Basic for Applications (VBA), but we also used UCINET 6 for calculating the in-degree centrality of trust / distrust relationship networks. In addition, we used Palisade Software's Evolver, which is a commercial software implements genetic algorithm. To examine the effectiveness of our proposed system more precisely, we adopted two comparison models. The first comparison model is conventional CF. It only uses users' explicit numeric ratings when calculating the similarities between users. That is, it does not consider trust / distrust relationship between users at all. The second comparison model is SNACF (Social Network Analysis - based CF). SNACF differs from the proposed algorithm SNACF-GA in that it considers only direct trust / distrust relationships. It also does not use GA optimization. The performances of the proposed algorithm and comparison models were evaluated by using average MAE (mean absolute error). Experimental result showed that the optimal adjusting coefficients for direct trust, indirect trust, direct distrust, indirect distrust were 0, 1.4287, 1.5, 0.4615 each. This implies that distrust relationships between users are more important than trust ones in recommender systems. From the perspective of recommendation accuracy, SNACF-GA (Avg. MAE = 0.111943), the proposed algorithm which reflects both direct and indirect trust / distrust relationships information, was found to greatly outperform a conventional CF (Avg. MAE = 0.112638). Also, the algorithm showed better recommendation accuracy than the SNACF (Avg. MAE = 0.112209). To confirm whether these differences are statistically significant or not, we applied paired samples t-test. The results from the paired samples t-test presented that the difference between SNACF-GA and conventional CF was statistical significant at the 1% significance level, and the difference between SNACF-GA and SNACF was statistical significant at the 5%. Our study found that the trust/distrust relationship can be important information for improving performance of recommendation algorithms. Especially, distrust relationship information was found to have a greater impact on the performance improvement of CF. This implies that we need to have more attention on distrust (negative) relationships rather than trust (positive) ones when tracking and managing social relationships between users.

• Journal of Korea Spatial Information System Society
• /
• v.10 no.4
• /
• pp.77-88
• /
• 2008

There has been growing demands to manage the water quality of west coastal region due to the large scale urbanization along the coastal zone, the possibility of application of TMDL(Total Maximum Daily Loadings) to Han river, and the natural disaster such as oil spill incident in Taean, Chungnam. However, no system has been developed for such purposes. In this background, the demand of GIS based effective water quality management has been increased to monitor water quality environment and propose best management alternatives for Han river and Kyeonggi bay. This study mainly focused on the development of integrated water quality management system for Han river bas in and its estuary are a connected to Kyeonggi bay to support integrated water quality management and its plan. Integration was made based on GIS by spatial linking between water quality attributes and location information. A GIS DB was built to estimate the amount of generated and discharged water pollutants according to TMDL technical guide and it included input data to use two different water quality models--W ASP7 for Han river and EFDC for coastal area--to forecast water quality and to suggest BMP(Best management Practices). The results of BOD, TN, and TP from WASP7 were used as the input to run EFDC. Based on the study results, some critical areas which have relatively higher pollutant loadings were identified, and it was also identified that the locations discharging water pollutant loadings to river and seasonal factor affected water quality. And the relationship of water quality between river and its estuary area was quantitatively verified. The results showed that GIS based integrated system could be used as a tool for estimating status-quo of water quality and proposing economically effective BMPs to mitigate water pollution. Further studies need to be made for improving system's capabilities such as adding decision making function as well as cost-benefit analysis, etc. Also, the concrete methodology for water quality management using the system need to be developed.

• Journal of Aquaculture
• /
• v.8 no.4
• /
• pp.261-269
• /
• 1995

A practical control diet was prepared and compared with raw fish ($80\%$ frozen horse mackerel + $20\%$ commercial binder meal) and moist pellet ($50\%$ frozen horse mackerel + $50\%$commercial binder meal) diets to develop a practical diet formulation for Korean rockfish (Sebastes schlegeli). Korean rockfish averaging 68.5g were fed with the three experimental diets for 11 months. Final average body weight was approximately 330g and showed no significant difference between fish groups (P>0.05). Feed efficiency of fish from control diet was significantly lower than those of fish from raw fish and moist pellet diets (P<0.05). Protein and lipid retention efficiency of fish ranged $26.9-28.8\%$ and $86.5-110.2\%$, respectively, without any significant difference between the different diets. At the end of the experiment, chemical composition for the various parts of fish body and flesh quality of the raw fish were examined. The data showed that there was no significant difference between fish from the different diet groups for moisture, protein and lipid contents of whole body, liver, and dorsal muscle. Also, thirty three panelists did not find any difference in color, smell, texture, and taste of the raw fish flesh. These results suggest that Korean rockfish can be cultured with a laboratory practical feed without any negative effects on growth, nutrient utilization, chemical composition of fish, and quality of raw fish. Therefore, the next step in developing practical feed is to modify the control diet for improving fish performance and reducing feed cost.

• Journal of Internet Computing and Services
• /
• v.17 no.1
• /
• pp.101-107
• /
• 2016

Due to the recent advancement in digital imaging technology, development of intervention equipment has become generalize. Video arbitration procedure is a process to insert a tiny catheter and a guide wire in the body, so in order to enhance the effectiveness and safety of this treatment, the high-quality of x-ray of image should be used. However, the increasing of radiation has become the problem. Therefore, the studies to improve the performance of x-ray detectors are being actively processed. Moreover, this intervention is based on the reference of the angiographic imaging and 3D medical image processing. In this paper, we propose a guidance system to support this intervention. Through this intervention, it can solve the problem of the existing 2D medical images based vessel that has a formation of cerebrovascular disease, and guide the real-time tracking and optimal route to the target lesion by intervention catheter and guide wire tool. As a result, the system was completely composed for medical image acquisition unit and image processing unit as well as a display device. The experimental environment, guide services which are provided by the proposed system Brain Phantom (complete intracranial model with aneurysms, ref H+N-S-A-010) was taken with x-ray and testing. To generate a reference image based on the Laplacian algorithm for the image processing which derived from the cerebral blood vessel model was applied to DICOM by Volume ray casting technique. $A^*$ algorithm was used to provide the catheter with a guide wire tracking path. Finally, the result does show the location of the catheter and guide wire providing in the proposed system especially, it is expected to provide a useful guide for future intervention service.

• Journal of the Mineralogical Society of Korea
• /
• v.16 no.3
• /
• pp.201-213
• /
• 2003

The adsorption property and ability of domestic zeolites for some heavy metal ions (Ag, Pb, Cr, Cu, Zn, Mn), which may cause a serious environmental problem in industrial wastewater, were evaluated on ore unit through a series of adsorption experiments together with careful examinations of mineral composition and properties of the zeolites. Though the adsorption behavior basically took place in the form of a cation exchange reaction, the higher CEC value does not necessarily to imply the higher adsorption capacity for a specific heavy metal. A general trend of the adsorption selectivity for heavy metals in the zeolites is determined to be as follow: $Ag\geq$Pb>Cr,Cu$\geq$Zn>Mn, but the adsorption properties of heavy metal ions somewhat depend on the species and composition of zeolite. Clinoptilolite tends to adsorb selectively Cu in case of Cr and Cu, whereas heulandite prefers Cr to Cu. A dominant adsorption selectivity of the zeolite ores for Ag and Pb is generally conspicuous regardless of their zeolite species and composition. The zeolite ores exhibit a preferential adsorption especially for $Ag^{+}$ so as not to regenerate when treated with $Na^{+}$ . In the adsorption capacity for heavy meta ions, the zeolites differ in great depending on their species: ferrierite>clinoptilolite>heulandite. Considering the CEC value of mordenite, the mordenite-rich ore appears to be similar to the clinoptilolite ore in the adsorption capacity. The adsorption capacity for heavy metals is not positively proportional to the CEC values of the zeolites measured by the exchange reaction with ammonium ion. In addition, the adsorption capacity roughly tends to depend on the zeolite contents, i.e., the grade of zeolite ore, but the trend is not consistent at all in some ores. These may be caused by the adsorption selectivity for some specific heavy metals, the presence of possible stacking micro-faults and natural cations such as K hardly to exchange in the zeolite. Considering the economic availability and functional effectiveness as natural zeolite resources, clinoptilolite ores could be applicable to utilize the domestic zeolites for the removal of heavy metals.

• Geophysics and Geophysical Exploration
• /
• v.13 no.3
• /
• pp.268-276
• /
• 2010

Earthquake Hazard Mitigation Law was activated into force on March 2009. By the law, the obligation to monitor the effect of earthquake on the facilities was extended to many organizations such as gas company and local governments. Based on the estimation of National Emergency Management Agency (NEMA), the number of free-surface acceleration stations would be expanded to more than 400. The advent of internet protocol and the more simplified operation have allowed the quick and easy installation of seismic stations. In addition, the dynamic range of seismic instruments has been continuously improved enough to evaluate damage intensity and to alert alarm directly for earthquake hazard mitigation. For direct visualization of damage intensity and area, Real Time Intensity COlor Mapping (RTICOM) is explained in detail. RTICOM would be used to retrieve the essential information for damage evaluation, Peak Ground Acceleration (PGA). Destructive earthquake damage is usually due to surface waves which just follow S wave. The peak amplitude of surface wave would be pre-estimated from the amplitude and frequency content of first arrival P wave. Earthquake Early Warning (EEW) system is conventionally defined to estimate local magnitude from P wave. The status of EEW is reviewed and the application of EEW to Odesan earthquake is exampled with ShakeMap in order to make clear its appearance. In the sense of rapidity, the earthquake announcement of Korea Meteorological Agency (KMA) might be dramatically improved by the adaption of EEW. In order to realize hazard mitigation, EEW should be applied to the local crucial facilities such as nuclear power plants and fragile semi-conduct plant. The distributed EEW is introduced with the application example of Uljin earthquake. Not only Nation-wide but also locally distributed EEW applications, all relevant information is needed to be shared in real time. The plan of extension of Korea Integrated Seismic System (KISS) is briefly explained in order to future cooperation of data sharing and utilization.

• Journal of IKEEE
• /
• v.15 no.2
• /
• pp.179-189
• /
• 2011

This paper presents an SVC based multi-channel transmission technique. Transmission of high definition multimedia and its service efficiency can be significantly improved by the proposed method. In this method, the HD stream is divided into the two layer streams, i.e., a base layer stream and an enhancement layer stream. The divided streams are transmitted through a primary channel and an auxiliary channel, respectively. The proposed technique provides a noble mode switching technique which enables a seamless service of HD multimedia even under the conditions of abrupt and intermittent deterioration of the auxiliary channel. When the enhancement layer stream is disrupted by the channel monitoring in the mode switching algorithm, the algorithm works further to maintain the spatial and time resolution of the HD multimedia by upsampling and interpolating the base layer stream, consequently serving for the non disrupted play of the media. Moreover, the adoption of an adaptive switching algorithm significantly reduces the frequency of channel disruption avoiding the unnecessary switching for the short period variations of the channel. The feasibility of the proposed technique is verified through the simulation study with an example application to the simultaneous utilization of both Ku and Ka bands for HD multimedia broadcasting service. The rainfall modeling and the analysis of the satellite channel attenuation characteristics are performed to simulate the quality of service performance of the proposed HD broadcasting method. The simulation results obtained under a relatively poor channel (weather) situations show that the average lasting period of enhancement layer service is extended from 9.48[min] to 23.12[min] and the average switching frequency is reduced from 3.84[times/hour] to 1.68[times/hour]. It is verified in the satellite example that the proposed SVC based transmission technique best utilizes the Ka band channel for the service of HD broadcasting, although it is characterized by its inherent weather related poor reliability causing severe limitations in its independent application.

• Korean Journal of Remote Sensing
• /
• v.34 no.3
• /
• pp.451-463
• /
• 2018

The empirical/statistical models to estimate the ground Particulate Matter ($PM_{2.5}$) concentration from Geostationary Ocean Color Imager (GOCI) Aerosol Optical Depth (AOD) product were developed and analyzed for the period of 2015 in Seoul, South Korea. In the model construction of AOD-$PM_{2.5}$, two vertical correction methods using the planetary boundary layer height and the vertical ratio of aerosol, and humidity correction method using the hygroscopic growth factor were applied to respective models. The vertical correction for AOD and humidity correction for $PM_{2.5}$ concentration played an important role in improving accuracy of overall estimation. The multiple linear regression (MLR) models with additional meteorological factors (wind speed, visibility, and air temperature) affecting AOD and $PM_{2.5}$ relationships were constructed for the whole year and each season. As a result, determination coefficients of MLR models were significantly increased, compared to those of empirical models. In this study, we analyzed the seasonal, monthly and diurnal characteristics of AOD-$PM_{2.5}$model. when the MLR model is seasonally constructed, underestimation tendency in high $PM_{2.5}$ cases for the whole year were improved. The monthly and diurnal patterns of observed $PM_{2.5}$ and estimated $PM_{2.5}$ were similar. The results of this study, which estimates surface $PM_{2.5}$ concentration using geostationary satellite AOD, are expected to be applicable to the future GK-2A and GK-2B.