• 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.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.47 no.7
• /
• pp.30-36
• /
• 2010

Due to the scaling of process parameters, the density on chips has been increasing. This trend increases not only the temperature on chips but also the gradient of the temperature depending on distances. In this paper, we propose the balanced skew tree generation technique for minimizing the clock skew that is affected by the temperature gradients on chips. We calculate the interconnect delay using Elmore delay equation, and find out the optimal balanced clock tree by modifying the clock trees that are generated through the DME(Deferred Merge Embedding) algorithm. We have implemented the proposed technique using C language for the performance evaluation. The experimental results show that the clock insertion point generated by the temperature gradient can be lowered below 54% and we confirm that the skew is remarkably decreased after applying the proposed technique.

• ETRI Journal
• /
• v.35 no.5
• /
• pp.880-888
• /
• 2013

The preexisting pairings ate, $ate_i$, R-ate, and optimal-ate use q-expansion, where q is the size of the defining field for the elliptic curves. Elliptic curves with small embedding degrees only allow a few of these pairings. In such cases, efficiently computable endomorphisms can be used, as in [11] and [12]. They used the endomorphisms that have characteristic polynomials with very small coefficients, which led to some restrictions in finding various pairing-friendly curves. To construct more pairing-friendly curves, we consider ${\mu}$-expansion using the Gallant-Lambert-Vanstone (GLV) decomposition method, where ${\mu}$ is an arbitrary integer. We illustrate some pairing-friendly curves that provide more efficient pairing from the ${\mu}$-expansion than from the ate pairing. The proposed method can achieve timing results at least 20% faster than the ate pairing.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.9
• /
• pp.846-851
• /
• 2010

In this paper, we newly propose a novel control strategy of a three joints-robot finger for the purpose of artificial hands. The robot finger is specifically modeled by using a 3D CAD program (CATIA), considering human fingers, and then the proposed control method is verified through the dynamic simulation tool (Simulink and Recurdyn R2). Each slider is individually controlled to be located at the optimal positions where the maximal joint torque can be generated. To prove the effectiveness of the proposed control method, we devise two cases for the reference position of sliders. By comparing the control performance of two cases, the validity of the proposed control method will be verified.

• ETRI Journal
• /
• v.32 no.5
• /
• pp.795-800
• /
• 2010

Embedding a large vocabulary speech recognition system in mobile devices requires a reduced acoustic model obtained by eliminating redundant model parameters. In conventional optimization methods based on the minimum description length (MDL) criterion, a binary Gaussian tree is built at each state of a hidden Markov model by iteratively finding and merging similar mixture components. An optimal subset of the tree nodes is then selected to generate a downsized acoustic model. To obtain a better binary Gaussian tree by improving the process of finding the most similar Gaussian components, this paper proposes a new distance measure that exploits the difference in likelihood values for cases before and after two components are combined. The mixture weight of Gaussian components is also introduced in the component merging step. Experimental results show that the proposed method outperforms MDL-based optimization using either a Kullback-Leibler (KL) divergence or weighted KL divergence measure. The proposed method could also reduce the acoustic model size by 50% with less than a 1.5% increase in error rate compared to a baseline system.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.11b
• /
• pp.301-305
• /
• 2002

Among many structural dynamics modification methods for plate and shell vibration problems, embedding an emboss to the surface is very efficient. But deciding an optimal position and shape using optimization algorithm needs defining geometry and remeshing the model for every iteration step to implement the method, which takes much numerical cost. An equivalent element produced here lessen the cost by representing the geometrical characteristics of an emboss using the element's material properties and thickness becoming a geometrically homogenous element of the base plate or shell. Some efficient factors which let the equivalent system have the same dynamical response as the original system embedded with emboss will be shown and the degree of equivalence will be tested in terms of natural frequency matching.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.24 no.6
• /
• pp.1068-1073
• /
• 1987

Traditional circuit partitioning algorithm using the cluster development method, which is suitable for such applications as single chip floor planning or multiple layer PCB system placement, where the clusters are formed so that inter-cluster nets are localized within the I/O connector pins, may not be appropriate for the functiona block placement in truly 3-D electronic modules. 3-D hybrid IC is one such example where the inter-layer routing as well as the intra-layer routing can be maximally incorporated to reduce the overall circuit size, cooling requirements and to improve the speed performance. In this paper, we propose a new algorithm called MBE(Minimum Box Embedding) for the layer assignment of each functional block in 3-D hybrid IC design. The sequence of MBE is as follows` i) force-directed relaxation in 3-D space, ii) exhaustive search for the optimal orientation of the slicing plane and iii) layer assignment. The algorithm is first explaines for a 2-D reduced problem, and then extended for 3-D applications. An example result for a circuit consisting of 80 blocks has been shown.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.25 no.1
• /
• pp.67-84
• /
• 2000

In this paper, we address a network design problem including the decision of hub facility locatiions which is typically found in a communicatio and a transportation network design studies. Due to the administrative and the geographical restrictions, it is common to assume that each user should be assigned to only one hub facility. To construct such a network, three types of network costs should be considered: the fixed costs of establishing the hubs and the arcs in the network, and the variable costs associated with transversing the network. The complex problem is formulated as a mixed IP embedding a multicommodity flow problem. Exploiting its special structure, a dual-based heuristic is then developed, which yields near-optimal design plans. The test results indicate that the heuristic is an effective way to solve this computationally complex problem.

• Journal of the Korea Society for Simulation
• /
• v.6 no.2
• /
• pp.89-104
• /
• 1997

Performance bottleneck of parallel computer systems has mostly been I/O devices because of disparity between processor speed and I/O speed. Therefore I/O node placement strategy is required such that it can minimize the number of I/O nodes, I/O access time and I/O traffic in an interconnection network. In this paper, we propose an optimal distance-k embedding algorithm, and analyze its effect on system performance when this algorithm is applied to n x n torus architecture. We prove this algorithm is an efficient I/O node placement using software simulation. I/O node placement using the proposed algorithm shows the highest performance among other I/O node placements in all cases. It is because locations of I/O nodes are uniformly distributed in the whole network, resulting in reduced traffic in the intE'rconnection network.

• Proceedings of the IEEK Conference
• /
• 2002.06d
• /
• pp.121-124
• /
• 2002

This paper presents an adaptive digital image watermarking scheme that uses successive subband quantization (SSQ) and perceptual modeling. Our approach performs a multiwavelet transform to determine the local image properties optimal and the watermark embedding location. The multiwavelet used in this paper is the DGHM multiwavelet with approximation order 2 to reduce artifacts in the reconstructed image. A watermark is embedded into the perceptually significant coefficients (PSC) of the image in each subband. The PSCs in high frequency subbands are selected by setting the thresholds to one half of the largest coefficient in each subband. After the PSCs in each subband are selected, a perceptual model is combined with a stochastic approach based on the noise visibility function to produce the final watermark.